You searched for subject:(feature extraction)
.
Showing records 1 – 30 of
669 total matches.
◁ [1] [2] [3] [4] [5] … [23] ▶

University of Waterloo
1.
Amelard, Robert.
High-Level Intuitive Features (HLIFs) for Melanoma Detection.
Degree: 2013, University of Waterloo
URL: http://hdl.handle.net/10012/7761
► Feature extraction of segmented skin lesions is a pivotal step for implementing accurate decision support systems. Existing feature sets combine many ad-hoc calculations and are…
(more)
▼ Feature extraction of segmented skin lesions is a pivotal step for implementing accurate decision support systems. Existing feature sets combine many ad-hoc calculations and are unable to easily provide intuitive diagnostic reasoning. This thesis presents the design and evaluation of a set of features for objectively detecting melanoma in an intuitive and accurate manner. We call these "high-level intuitive features" (HLIFs).
The current clinical standard for detecting melanoma, the deadliest form of skin cancer, is visual inspection of the skin's surface. A widely adopted rule for detecting melanoma is the "ABCD" rule, whereby the doctor identifies the presence of Asymmetry, Border irregularity, Colour patterns, and Diameter. The adoption of specialized medical devices for this cause is extremely slow due to the added temporal and financial burden. Therefore, recent research efforts have focused on detection support systems that analyse images acquired with standard consumer-grade camera images of skin lesions. The central benefit of these systems is the provision of technology with low barriers to adoption. Recently proposed skin lesion feature sets have been large sets of low-level features attempting to model the widely adopted ABCD criteria of melanoma. These result in high-dimensional feature spaces, which are computationally expensive and sparse due to the lack of available clinical data. It is difficult to convey diagnostic rationale using these feature sets due to their inherent ad-hoc mathematical nature.
This thesis presents and applies a generic framework for designing HLIFs for decision support systems relying on intuitive observations. By definition, a HLIF is designed explicitly to model a human-observable characteristic such that the feature score can be intuited by the user. Thus, along with the classification label, visual rationale can be provided to further support the prediction. This thesis applies the HLIF framework to design 10 HLIFs for skin cancer detection, following the ABCD rule. That is, HLIFs modeling asymmetry, border irregularity, and colour patterns are presented.
This thesis evaluates the effectiveness of HLIFs in a standard classification setting. Using publicly-available images obtained in unconstrained environments, the set of HLIFs is compared with and against a recently published low-level feature set. Since the focus is on evaluating the features, illumination correction and manually-defined segmentations are used, along with a linear classification scheme. The promising results indicate that HLIFs capture more relevant information than low-level features, and that concatenating the HLIFs to the low-level feature set results in improved accuracy metrics. Visual intuitive information is provided to indicate the ability of providing intuitive diagnostic reasoning to the user.
Subjects/Keywords: feature extraction; melanoma
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Amelard, R. (2013). High-Level Intuitive Features (HLIFs) for Melanoma Detection. (Thesis). University of Waterloo. Retrieved from http://hdl.handle.net/10012/7761
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Amelard, Robert. “High-Level Intuitive Features (HLIFs) for Melanoma Detection.” 2013. Thesis, University of Waterloo. Accessed February 27, 2021.
http://hdl.handle.net/10012/7761.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Amelard, Robert. “High-Level Intuitive Features (HLIFs) for Melanoma Detection.” 2013. Web. 27 Feb 2021.
Vancouver:
Amelard R. High-Level Intuitive Features (HLIFs) for Melanoma Detection. [Internet] [Thesis]. University of Waterloo; 2013. [cited 2021 Feb 27].
Available from: http://hdl.handle.net/10012/7761.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Amelard R. High-Level Intuitive Features (HLIFs) for Melanoma Detection. [Thesis]. University of Waterloo; 2013. Available from: http://hdl.handle.net/10012/7761
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Universitat de Valencia
2.
López Iñesta, Emilia.
Aprendizaje de similitudes entre pares de objetos mediante clasificación supervisada
.
Degree: 2017, Universitat de Valencia
URL: http://hdl.handle.net/10550/61001
► El uso de medidas de similitud, distancias o métricas se encuentra en la base del funcionamiento de numerosas técnicas estándar de clasificación, resultando además, una…
(more)
▼ El uso de medidas de similitud, distancias o métricas se encuentra en la base del funcionamiento de numerosas técnicas estándar de clasificación, resultando además, una tarea fundamental e importante en las áreas de estudio del Aprendizaje Automático (Machine Learning) y el Reconocimiento de Patrones (Pattern Recognition). Dado que el cálculo de la similitud entre dos objetos puede ser muy diferente en función del contexto, la construcción inteligente de estas medidas a partir de los datos disponibles, puede ayudar en la obtención de clasificadores más robustos y mejorar los resultados en la tarea específica que se propone resolver.
En los últimos años, el aprendizaje de métricas (Metric Learning) y medidas de similitud (Similarity Learning) ha recibido un creciente interés de la comunidad científica. Dada la información disponible en forma de ejemplos etiquetados con una categoría o clase, el objetivo del aprendizaje de métricas es aprender una distancia métrica de acuerdo al siguiente principio: las distancias entre pares similares (es decir, de la misma clase) han de ser pequeñas, mientras que las distancias entre pares diferentes (es decir, de diferentes clases) han de ser mayores. De la misma manera, el aprendizaje de similitud intenta aprender una función de similitud que asocie grandes puntuaciones (scores) a pares similares y pequeñas puntuaciones a pares diferentes. Un caso particular del aprendizaje de similitudes consiste en el empleo de métodos de clasificación para el aprendizaje de medidas de similitud (Classification-based Similarity Learning). En todos estos métodos, el rendimiento depende en gran medida de la representación de las características de los datos disponibles.Así, en esta Tesis se presenta un método de clasificación enriquecido que sigue un enfoque híbrido que combina la extracción de características (
Feature Extraction) y la ampliación de las mismas (
Feature Expansion). En particular, se propone una transformación de datos y el uso de un conjunto de distancias métricas y no métricas para complementar y enriquecer la información proporcionada por los vectores de características de los ejemplos de entrenamiento. Si bien es cierto que esto aumenta la dimensión del problema en cuestión, también supone una inyección de conocimiento adicional debido a que el uso de las medidas de distancias supone un emparejamiento implícito entre los vectores de características de dos objetos. Además, se analiza si la nueva información añadida compensa el aumento de dimensión que ello implica, así como la influencia de los diferentes formatos de datos de entrada y el tamaño de entrenamiento sobre el rendimiento del clasificador.
La propuesta se compara con métodos de aprendizaje de métricas y los resultados obtenidos muestran rendimientos comparables en favor del método propuesto en distintos contextos y empleando diferentes bases de datos.
Advisors/Committee Members: Arevalillo Herráez, Miguel (advisor).
Subjects/Keywords: distances;
feature extraction;
feature expansion;
classification
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
López Iñesta, E. (2017). Aprendizaje de similitudes entre pares de objetos mediante clasificación supervisada
. (Doctoral Dissertation). Universitat de Valencia. Retrieved from http://hdl.handle.net/10550/61001
Chicago Manual of Style (16th Edition):
López Iñesta, Emilia. “Aprendizaje de similitudes entre pares de objetos mediante clasificación supervisada
.” 2017. Doctoral Dissertation, Universitat de Valencia. Accessed February 27, 2021.
http://hdl.handle.net/10550/61001.
MLA Handbook (7th Edition):
López Iñesta, Emilia. “Aprendizaje de similitudes entre pares de objetos mediante clasificación supervisada
.” 2017. Web. 27 Feb 2021.
Vancouver:
López Iñesta E. Aprendizaje de similitudes entre pares de objetos mediante clasificación supervisada
. [Internet] [Doctoral dissertation]. Universitat de Valencia; 2017. [cited 2021 Feb 27].
Available from: http://hdl.handle.net/10550/61001.
Council of Science Editors:
López Iñesta E. Aprendizaje de similitudes entre pares de objetos mediante clasificación supervisada
. [Doctoral Dissertation]. Universitat de Valencia; 2017. Available from: http://hdl.handle.net/10550/61001

University of KwaZulu-Natal
3.
Adebanjo, Hannah Morenike.
Investigation of feature extraction algorithms and techniques for hyperspectral images.
Degree: 2017, University of KwaZulu-Natal
URL: https://researchspace.ukzn.ac.za/handle/10413/16758
► Hyperspectral images (HSIs) are remote-sensed images that are characterized by very high spatial and spectral dimensions and nd applications, for example, in land cover classi…
(more)
▼ Hyperspectral images (HSIs) are remote-sensed images that are characterized
by very high spatial and spectral dimensions and nd applications, for example,
in land cover classi cation, urban planning and management, security and food
processing. Unlike conventional three bands RGB images, their high
dimensional data space creates a challenge for traditional image processing
techniques which are usually based on the assumption that there exists
su cient training samples in order to increase the likelihood of high
classi cation accuracy. However, the high cost and di culty of obtaining
ground truth of hyperspectral data sets makes this assumption unrealistic and
necessitates the introduction of alternative methods for their processing.
Several techniques have been developed in the exploration of the rich spectral
and spatial information in HSIs. Speci cally,
feature extraction (FE)
techniques are introduced in the processing of HSIs as a necessary step before
classi cation. They are aimed at transforming the high dimensional data of the
HSI into one of a lower dimension while retaining as much spatial and/or
spectral information as possible. In this research, we develop semi-supervised
FE techniques which combine features of supervised and unsupervised
techniques into a single framework for the processing of HSIs. Firstly, we
developed a
feature extraction algorithm known as Semi-Supervised Linear
Embedding (SSLE) for the
extraction of features in HSI. The algorithm
combines supervised Linear Discriminant Analysis (LDA) and unsupervised
Local Linear Embedding (LLE) to enhance class discrimination while also
preserving the properties of classes of interest. The technique was developed
based on the fact that LDA extracts features from HSIs by discriminating
between classes of interest and it can only extract C 1 features provided there
are C classes in the image by extracting features that are equivalent to the
number of classes in the HSI. Experiments show that the SSLE algorithm
overcomes the limitation of LDA and extracts features that are equivalent to
ii
iii
the number of classes in HSIs. Secondly, a graphical manifold dimension
reduction (DR) algorithm known as Graph Clustered Discriminant Analysis
(GCDA) is developed. The algorithm is developed to dynamically select labeled
samples from the pool of available unlabeled samples in order to complement
the few available label samples in HSIs. The selection is achieved by entwining
K-means clustering with a semi-supervised manifold discriminant analysis.
Using two HSI data sets, experimental results show that GCDA extracts
features that are equivalent to the number of classes with high classi cation
accuracy when compared with other state-of-the-art techniques. Furthermore,
we develop a window-based partitioning approach to preserve the spatial
properties of HSIs when their features are being extracted. In this approach,
the HSI is partitioned along its spatial dimension into n windows and the
covariance matrices of each…
Advisors/Committee Members: Tapamo, Jules-Raymond. (advisor).
Subjects/Keywords: Hyperspectral images.; Feature extraction algorithms.
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Adebanjo, H. M. (2017). Investigation of feature extraction algorithms and techniques for hyperspectral images. (Thesis). University of KwaZulu-Natal. Retrieved from https://researchspace.ukzn.ac.za/handle/10413/16758
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Adebanjo, Hannah Morenike. “Investigation of feature extraction algorithms and techniques for hyperspectral images.” 2017. Thesis, University of KwaZulu-Natal. Accessed February 27, 2021.
https://researchspace.ukzn.ac.za/handle/10413/16758.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Adebanjo, Hannah Morenike. “Investigation of feature extraction algorithms and techniques for hyperspectral images.” 2017. Web. 27 Feb 2021.
Vancouver:
Adebanjo HM. Investigation of feature extraction algorithms and techniques for hyperspectral images. [Internet] [Thesis]. University of KwaZulu-Natal; 2017. [cited 2021 Feb 27].
Available from: https://researchspace.ukzn.ac.za/handle/10413/16758.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Adebanjo HM. Investigation of feature extraction algorithms and techniques for hyperspectral images. [Thesis]. University of KwaZulu-Natal; 2017. Available from: https://researchspace.ukzn.ac.za/handle/10413/16758
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Adelaide
4.
Baseri Huddin, Aqilah.
An investigation of automatic feature extraction for clustered microcalcifications on digital mammograms.
Degree: 2015, University of Adelaide
URL: http://hdl.handle.net/2440/97912
► Mammography is a common imaging modality used for breast screening. The limitations in reading mammogram images manually by radiologists have motivated an interest to the…
(more)
▼ Mammography is a common imaging modality used for breast screening. The limitations in reading mammogram images manually by radiologists have motivated an interest to the use of computerised systems to aid the process. Computer-aided diagnosis (CAD) systems have been widely used to assist radiologists in making decision; either for detection, CADe, or for diagnosis, CADx, of the anomalies in mammograms. This thesis aims to improve the sensitivity of the CADx system by proposing novel
feature extraction techniques. Previous works have shown that multiple resolution images provide useful information for classification. The wavelet transform is one of the techniques that is commonly used to produce multiple resolution images, and is used to extract features from the produced sub-images for classification of microcalcification clusters in mammograms. However, the fixed directionality produced by the transform limit the opportunity to extract further useful features that may contain information associated with the malignancy of the clusters. This has driven the thesis to experiment on multiple orientation and multiple resolution images for providing features for microcalcification classification purposes. Extensive and original experiments are conducted to seek whether the multiple orientation and multiple resolution analysis of microcalcification clusters features are useful for classification. Results show that the proposed method achieves an accuracy of 78.3%, and outperforms the conventional wavelet transform, which achieves an accuracy of 64.9%. A
feature selection step using Principal Component Analysis (PCA) is employed to reduce the number of the features as well as the complexity of the system. The overall result shows that the accuracy of the system when 2-features from steerable pyramid filtering are used as input achieved 85.5% as opposed to 2-features from conventional wavelet transform, which achieves an accuracy of 69.9%. In addition, the effectiveness of the diagnosis system also depends on the classifier. Deep belief networks have demonstrated to be able to extract high-level of input representations. The ability of greedy learning in deep networks provide a highly non-linear mapping of the input and the output. The advantage of DBN in being able to analyse complex patterns, in this thesis, is exploited for classification of microcalcification clusters into benign or malignant sets. An extensive research experiment is conducted to use DBN in extracting features for microcalcification classification. The experiment of using DBN solely as a
feature extractor and classifier of raw pixel microcalcification images shows no significant improvement. Therefore, a novel technique using filtered images is proposed, so that a DBN will extract features from the filtered images. The analysis result shows an improvement in accuracy from 47.9% to 60.8% when the technique is applied. With these new findings, it may contribute to the identification of the microcalcification clusters in mammograms.
Advisors/Committee Members: Ng, Brian Walter (advisor), Abbott, Derek (advisor), School of Electrical and Electronic Engineering (school).
Subjects/Keywords: microcalcifications; mammograms; feature extraction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Baseri Huddin, A. (2015). An investigation of automatic feature extraction for clustered microcalcifications on digital mammograms. (Thesis). University of Adelaide. Retrieved from http://hdl.handle.net/2440/97912
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Baseri Huddin, Aqilah. “An investigation of automatic feature extraction for clustered microcalcifications on digital mammograms.” 2015. Thesis, University of Adelaide. Accessed February 27, 2021.
http://hdl.handle.net/2440/97912.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Baseri Huddin, Aqilah. “An investigation of automatic feature extraction for clustered microcalcifications on digital mammograms.” 2015. Web. 27 Feb 2021.
Vancouver:
Baseri Huddin A. An investigation of automatic feature extraction for clustered microcalcifications on digital mammograms. [Internet] [Thesis]. University of Adelaide; 2015. [cited 2021 Feb 27].
Available from: http://hdl.handle.net/2440/97912.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Baseri Huddin A. An investigation of automatic feature extraction for clustered microcalcifications on digital mammograms. [Thesis]. University of Adelaide; 2015. Available from: http://hdl.handle.net/2440/97912
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Halmstad University
5.
Mühlfellner, Peter.
Selection, Analysis and Implementationof Image-based Feature Extraction Approaches for a Heterogenous, Modular and FPGA-based Architecture for Camera-based Driver Assistance Systems.
Degree: Intelligent systems (IS-lab), 2011, Halmstad University
URL: http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-16377
► We propose a scalable and fexible hardware architecture for the extraction of image features, used in conjunction with an attentional cascade classifier for appearance-based…
(more)
▼ We propose a scalable and fexible hardware architecture for the extraction of image features, used in conjunction with an attentional cascade classifier for appearance-based object detection. Individual feature processors calculate feature-values in parallel, using parameter-sets and image data that is distributed via BRAM buffers. This approach can provide high utilization- and throughput-rates for a cascade classifier. Unlike previous hardware implementations, we are able to flexibly assign feature processors to either work on a single- or multiple image windows in parallel, depending on the complexity of the current cascade stage. The core of the architecture was implemented in the form of a streaming based FPGA design, and validated in simulation, synthesis, as well as via the use of a Logic Analyser for the verification of the on-chip functionality. For the given implementation, we focused on the design of Haar-like feature processors, but feature processors for a variety of heterogenous feature types, such as Gabor-like features, can also be accomodated by the proposed hardware architecture.
Subjects/Keywords: Object Detection; Feature Extraction; FPGA
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Mühlfellner, P. (2011). Selection, Analysis and Implementationof Image-based Feature Extraction Approaches for a Heterogenous, Modular and FPGA-based Architecture for Camera-based Driver Assistance Systems. (Thesis). Halmstad University. Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-16377
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Mühlfellner, Peter. “Selection, Analysis and Implementationof Image-based Feature Extraction Approaches for a Heterogenous, Modular and FPGA-based Architecture for Camera-based Driver Assistance Systems.” 2011. Thesis, Halmstad University. Accessed February 27, 2021.
http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-16377.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Mühlfellner, Peter. “Selection, Analysis and Implementationof Image-based Feature Extraction Approaches for a Heterogenous, Modular and FPGA-based Architecture for Camera-based Driver Assistance Systems.” 2011. Web. 27 Feb 2021.
Vancouver:
Mühlfellner P. Selection, Analysis and Implementationof Image-based Feature Extraction Approaches for a Heterogenous, Modular and FPGA-based Architecture for Camera-based Driver Assistance Systems. [Internet] [Thesis]. Halmstad University; 2011. [cited 2021 Feb 27].
Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-16377.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Mühlfellner P. Selection, Analysis and Implementationof Image-based Feature Extraction Approaches for a Heterogenous, Modular and FPGA-based Architecture for Camera-based Driver Assistance Systems. [Thesis]. Halmstad University; 2011. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-16377
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Georgia Tech
6.
Kong, Tae Woon.
Assessing self-similarity in redundant complex and quaternion wavelet domains: Theory and applications.
Degree: PhD, Industrial and Systems Engineering, 2019, Georgia Tech
URL: http://hdl.handle.net/1853/61244
► Theoretical self-similar processes have been an essential tool for modeling a wide range of real-world signals or images that describe phenomena in engineering, physics, medicine,…
(more)
▼ Theoretical self-similar processes have been an essential tool for modeling a wide range of real-world signals or images that describe phenomena in engineering, physics, medicine, biology, economics, geology, chemistry, and so on. However, it is often difficult for general modeling methods to quantify a self-similarity due to irregularities in the signals or images. Wavelet-based spectral tools have become standard solutions for such problems in signal and image processing and achieved outstanding performances in real applications. This thesis proposes three novel wavelet-based spectral tools to improve the assessment of self-similarity. First, we propose spectral tools based on non-decimated complex wavelet transforms implemented by their matrix formulation. A structural redundancy in non-decimated wavelets and a componential redundancy in complex wavelets act in a synergy when extracting wavelet-based informative descriptors. Next, we step into the quaternion domain and propose a matrix-formulation for non-decimated quaternion wavelet transforms and define spectral tools for use in machine learning tasks. We define non-decimated quaternion wavelet spectra based on the modulus and three phase-dependent statistics as low-dimensional summaries for 1-D signals or 2-D images. Finally, we suggest a dual wavelet spectra based on non-decimated wavelet transform in real, complex, and quaternion domains. This spectra is derived from a new perspective that draws on the link of energies of the signal with the temporal or spatial scales in the multiscale representations.
Advisors/Committee Members: Vidakovic, Brani (advisor), Mei, Yajun (committee member), Paynabar, Kamran (committee member), Kang, Sung Ha (committee member), Lee, Kichun (committee member).
Subjects/Keywords: Wavelets; Classification; Feature extraction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Kong, T. W. (2019). Assessing self-similarity in redundant complex and quaternion wavelet domains: Theory and applications. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/61244
Chicago Manual of Style (16th Edition):
Kong, Tae Woon. “Assessing self-similarity in redundant complex and quaternion wavelet domains: Theory and applications.” 2019. Doctoral Dissertation, Georgia Tech. Accessed February 27, 2021.
http://hdl.handle.net/1853/61244.
MLA Handbook (7th Edition):
Kong, Tae Woon. “Assessing self-similarity in redundant complex and quaternion wavelet domains: Theory and applications.” 2019. Web. 27 Feb 2021.
Vancouver:
Kong TW. Assessing self-similarity in redundant complex and quaternion wavelet domains: Theory and applications. [Internet] [Doctoral dissertation]. Georgia Tech; 2019. [cited 2021 Feb 27].
Available from: http://hdl.handle.net/1853/61244.
Council of Science Editors:
Kong TW. Assessing self-similarity in redundant complex and quaternion wavelet domains: Theory and applications. [Doctoral Dissertation]. Georgia Tech; 2019. Available from: http://hdl.handle.net/1853/61244
7.
Cho, Sungjoon.
Dermal Radiomics: a new approach for computer-aided melanoma screening system.
Degree: 2016, University of Waterloo
URL: http://hdl.handle.net/10012/10657
► Skin cancer is the most common form of cancer in North America, and melanoma is the most dangerous type of skin cancer. Melanoma originates from…
(more)
▼ Skin cancer is the most common form of cancer in North America, and melanoma is the most dangerous type of skin cancer. Melanoma originates from melanocytes in the epidermis and has a high tendency to develop away from the skin surface and cause metastasis through the bloodstream. Early diagnosis is known to help improve survival rates. Under the current diagnosis, the initial examination of the potential melanoma patient is done via naked eye screening or standard photographic images of the lesion. From this, the accuracy of diagnosis varies depending on the expertise of the clinician.
Radiomics is a recent cancer diagnostic tool that centers around the high throughput extraction of quantitative and mineable imaging features from medical images to identify tumor phenotypes. Radiomics focuses on optimizing a large number of features through computational approaches to develop a decision support system for improving individualized treatment selection and monitoring. While radiomics has shown great promise for screening and analyzing di erent forms of cancer such as lung cancer and prostate cancer, to the best of our knowledge, radiomics has not been previously adopted for skin cancer,
especially melanoma.
This work presents a dermal radiomics framework, which is a novel computer-aided melanoma diagnosis. While most computer-aided melanoma screening systems follow the conventional diagnostic scheme, the proposed work utilizes the physiological biomarker information. To extract physiological biomarkers, non-linear random forest inverse light-skin interaction model is proposed. The construction of dermal radiomics sequence is followed using the extracted physiological biomarkers, and the dermal radiomics framework for melanoma is completed by constructing diagnostic decision system based on random
forest classi cation algorithm.
Subjects/Keywords: classification; melanoma; feature extraction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Cho, S. (2016). Dermal Radiomics: a new approach for computer-aided melanoma screening system. (Thesis). University of Waterloo. Retrieved from http://hdl.handle.net/10012/10657
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Cho, Sungjoon. “Dermal Radiomics: a new approach for computer-aided melanoma screening system.” 2016. Thesis, University of Waterloo. Accessed February 27, 2021.
http://hdl.handle.net/10012/10657.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Cho, Sungjoon. “Dermal Radiomics: a new approach for computer-aided melanoma screening system.” 2016. Web. 27 Feb 2021.
Vancouver:
Cho S. Dermal Radiomics: a new approach for computer-aided melanoma screening system. [Internet] [Thesis]. University of Waterloo; 2016. [cited 2021 Feb 27].
Available from: http://hdl.handle.net/10012/10657.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Cho S. Dermal Radiomics: a new approach for computer-aided melanoma screening system. [Thesis]. University of Waterloo; 2016. Available from: http://hdl.handle.net/10012/10657
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

California State University – Sacramento
8.
Balasubramanian, Sinduja.
Text mining on Amazon reviews to extract feature based feedback.
Degree: MS, Computer Science, 2017, California State University – Sacramento
URL: http://hdl.handle.net/10211.3/198628
► Analyzing the feedback on a product or a service helps to improve the quality of the product or service. That way, reviews from online shopping…
(more)
▼ Analyzing the feedback on a product or a service helps to improve the quality of the product or service. That way, reviews from online shopping sites (such as Amazon) not only help a consumer to buy a product but also can help a manufacturer or seller to know the pros and cons of their product. Amazon star ratings alone is not enough for this. One should go through the text reviews to know specifically which
feature of the product is lacking customer satisfaction. But a product may have thousands of reviews and it???s hard for a person to go through all the reviews. Hence, we need a system which can give a statistical report on the number of reviewers not satisfied with a specific
feature of a product. This project enables the user to view
feature based review for a selected category of Amazon products. For a particular product the percentage of dissatisfied reviewers for each major
feature of the product can be viewed. The dataset which includes product details and customer reviews for each product are collected from Amazon.com. The implementation of this system is achieved by using MongoDB and R. The statistical results that are generated by the system are visualized with the help of Tableau software. The Amazon reviews undergo Natural Language Processing and text mining to identify major features of the product. Then a deep sentiment analysis is made to identify the polarity (positive or negative) of each review. This project can be further developed to a user interactive web or mobile application where user can choose categories and products and have better visualization of results. Implementation required integrating both data mining and artificial intelligence techniques.
Advisors/Committee Members: Gordon, V. Scott.
Subjects/Keywords: NLP; Text mining; Feature extraction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Balasubramanian, S. (2017). Text mining on Amazon reviews to extract feature based feedback. (Masters Thesis). California State University – Sacramento. Retrieved from http://hdl.handle.net/10211.3/198628
Chicago Manual of Style (16th Edition):
Balasubramanian, Sinduja. “Text mining on Amazon reviews to extract feature based feedback.” 2017. Masters Thesis, California State University – Sacramento. Accessed February 27, 2021.
http://hdl.handle.net/10211.3/198628.
MLA Handbook (7th Edition):
Balasubramanian, Sinduja. “Text mining on Amazon reviews to extract feature based feedback.” 2017. Web. 27 Feb 2021.
Vancouver:
Balasubramanian S. Text mining on Amazon reviews to extract feature based feedback. [Internet] [Masters thesis]. California State University – Sacramento; 2017. [cited 2021 Feb 27].
Available from: http://hdl.handle.net/10211.3/198628.
Council of Science Editors:
Balasubramanian S. Text mining on Amazon reviews to extract feature based feedback. [Masters Thesis]. California State University – Sacramento; 2017. Available from: http://hdl.handle.net/10211.3/198628

Penn State University
9.
Xia, Wentao.
VEHICULAR FSO COMMUNICATION SYSTEM APPLYING REAL-TIME RECOGNITION AND TRACKING.
Degree: 2018, Penn State University
URL: https://submit-etda.libraries.psu.edu/catalog/15350wzx12
► In self-driving vehicles, vehicle-to-vehicle communication is a key to solving traffic jams, avoiding accidents, choosing a perfect routine to destination and many other problems. In…
(more)
▼ In self-driving vehicles, vehicle-to-vehicle communication is a key to solving
traffic jams, avoiding accidents, choosing a perfect routine to destination and many
other problems. In vehicle-to-vehicle scenarios, people usually use microwave
communication which works well but is
subject to times of low SNR in cluttered
radio frequency(RF) environment and cost is high, so optical communication can be
used to improve SNR. While laser transmission has direction restriction. Tracking
techniques can be deployed to narrow the transmitting angle of the laser, enhancing
the intensity level at receiver.If the transmitter can be tracked under vehicular
environments, the performance of free space optical(FSO) communication will be
enhanced to a large extent. According to frames caught by camera on car, we try
using
feature identifying and
extraction techniques to locate the positions of multiple
markers on other cars from caught frame and using object tracking algorithm to
predict the moving of markers to guide the direction of laser’s transmitting.
Advisors/Committee Members: Tim Kane, Thesis Advisor/Co-Advisor, Julio Urbina, Committee Member.
Subjects/Keywords: self-driving; feature extraction; ORB feature; contour extraction; object tracking
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Xia, W. (2018). VEHICULAR FSO COMMUNICATION SYSTEM APPLYING REAL-TIME RECOGNITION AND TRACKING. (Thesis). Penn State University. Retrieved from https://submit-etda.libraries.psu.edu/catalog/15350wzx12
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Xia, Wentao. “VEHICULAR FSO COMMUNICATION SYSTEM APPLYING REAL-TIME RECOGNITION AND TRACKING.” 2018. Thesis, Penn State University. Accessed February 27, 2021.
https://submit-etda.libraries.psu.edu/catalog/15350wzx12.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Xia, Wentao. “VEHICULAR FSO COMMUNICATION SYSTEM APPLYING REAL-TIME RECOGNITION AND TRACKING.” 2018. Web. 27 Feb 2021.
Vancouver:
Xia W. VEHICULAR FSO COMMUNICATION SYSTEM APPLYING REAL-TIME RECOGNITION AND TRACKING. [Internet] [Thesis]. Penn State University; 2018. [cited 2021 Feb 27].
Available from: https://submit-etda.libraries.psu.edu/catalog/15350wzx12.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Xia W. VEHICULAR FSO COMMUNICATION SYSTEM APPLYING REAL-TIME RECOGNITION AND TRACKING. [Thesis]. Penn State University; 2018. Available from: https://submit-etda.libraries.psu.edu/catalog/15350wzx12
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Penn State University
10.
Ahn, Eun Yeong Yeong.
Evolutionary-based Feature Extraction for Gesture Recognition Using a Motion Camera.
Degree: 2012, Penn State University
URL: https://submit-etda.libraries.psu.edu/catalog/14735
► Gesture recognition systems have garnered increasing interest for their potential to support more natural human-computer interactions. However, compared to other human-computer interaction technologies such as…
(more)
▼ Gesture recognition systems have garnered increasing interest for their potential to support more natural human-computer interactions. However, compared to other human-computer interaction technologies such as speech recognition, gesture recognition has not been actively applied to personal devices such as mobile phones or laptops due to the spatial requirements when performing gestures as well as sensitivity to background noise. My research first devises a problem of recognizing speed sensitive finger gestures using a novel camera called Dynamic Vision Sensor camera, which detects the temporal luminance difference for each pixel at microsecond-level granularity and outputs a stream of on-events (brighter) and off-events (darker) to the hardware. As with other machine learning problems, the performance of a gesture classification task depends on how well the representative features are extracted. Thus the
feature extraction process must consider device-specific data properties to maximize the
feature recognition abilities while minimizing computational cost. My research studies two
feature extraction methods, namely local and global
feature extractions, which are designed to maximize the performance of the DVS camera-based gesture recognition system.
First, the local
feature extraction method aims to extract a smaller number of representative features from a long sequence of the raw gesture events detected by the DVS camera using segmentation. This approach is called the local
feature extraction, since the features are extracted by considering neighboring events only. Specifically, I propose bottom-up segmentation methods, where the sequence of events are first divided into segments having the same time interval, called the time-based, or the same number of events, called the event-based, and the segments are repeatedly augmented based on the event distributions of the neighboring segments. The experimental results show that the event-based initial segmentation outperforms the time-based across different classifiers, and is more robust to noise. I also found that Bayesian network classifier is more accurate than hidden Markov model when features are well extracted using the event-based segmentation.
Second, the global
feature extraction method aims to construct higher level compound features by transforming the locally extracted features. Specifically, an evolutionary algorithm is employed to find a good set of simple and compound features. This is a challenging task due to the large search space and the risks of overfitting. I define problem-specific representation, genetic operators, and evaluation methods, and analyze how the specified mutation and crossover operator controls the individual’s search space. The experimental results show that the proposed EA can extract a good set of compound features that can enhance the performance accuracy with a smaller number of features. Finally, I show how my evolutionary-based
feature extraction approach can serve as a knowledge discovery process in the context of gesture…
Advisors/Committee Members: John Yen, Dissertation Advisor/Co-Advisor, John Yen, Committee Chair/Co-Chair, Dinghao Wu, Committee Member, Dongwon Lee, Committee Member, Patrick M Reed, Committee Member, Tracy Mullen, Special Member.
Subjects/Keywords: Global Feature Extraction; Local Feature Extraction; DVS camera; Evolutionary Algorithm; Segmentation
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Ahn, E. Y. Y. (2012). Evolutionary-based Feature Extraction for Gesture Recognition Using a Motion Camera. (Thesis). Penn State University. Retrieved from https://submit-etda.libraries.psu.edu/catalog/14735
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Ahn, Eun Yeong Yeong. “Evolutionary-based Feature Extraction for Gesture Recognition Using a Motion Camera.” 2012. Thesis, Penn State University. Accessed February 27, 2021.
https://submit-etda.libraries.psu.edu/catalog/14735.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Ahn, Eun Yeong Yeong. “Evolutionary-based Feature Extraction for Gesture Recognition Using a Motion Camera.” 2012. Web. 27 Feb 2021.
Vancouver:
Ahn EYY. Evolutionary-based Feature Extraction for Gesture Recognition Using a Motion Camera. [Internet] [Thesis]. Penn State University; 2012. [cited 2021 Feb 27].
Available from: https://submit-etda.libraries.psu.edu/catalog/14735.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Ahn EYY. Evolutionary-based Feature Extraction for Gesture Recognition Using a Motion Camera. [Thesis]. Penn State University; 2012. Available from: https://submit-etda.libraries.psu.edu/catalog/14735
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Penn State University
11.
Callahan-Flintoft, Chloe.
Understanding the role of visual transients and the temporal autocorrelation of features in extending and closing the attentional window.
Degree: 2019, Penn State University
URL: https://submit-etda.libraries.psu.edu/catalog/16263czc213
► Reflexive attention allows the visual system to rapidly select and prioritize important visual information. As our environments are often changing, it is important to understand…
(more)
▼ Reflexive attention allows the visual system to rapidly select and prioritize important visual information. As our environments are often changing, it is important to understand how this selection process occurs in time. To this end, previous literature finds conflicting results. Discrete display paradigms such as Rapid Serial Visual Presentation (RSVP) find that attention is able to select information presented simultaneously with a cue (Goodbourn & Holcombe, 2015) whereas smoothly changing displays show evidence that attention lags in
extraction, selecting information presented over 100 ms after a cue (Carlson, Hogendoorn & Verstraten, 2006). The attentional drag theory, a conceptual model of attention proposed in this dissertation, accounts for this difference by attributing the latency in selecting information not to a difference in the latency of attentional onset, as has been previously hypothesized, but rather to a difference in the duration of attentional engagement. The model proposes that the temporal autocorrelation of a
feature (i.e. when features are perceived as smoothly changing) maintains attentional engagement longer, extending the attentional window in time, which results in a later
feature selection. Conversely, a visual transient, such as a salient change in the
feature of an object, closes the attentional window, allowing for fewer
feature values to receive attentional amplification, and, consequently, an earlier selection.
The aim of this dissertation is to test the underlying assumptions of the attentional drag theory. Firstly, the effect is demonstrated in a second
feature dimension (orientation) and it is shown that the temporal autocorrelation presented after the onset of attention, rather than before, produces the selection latency increase. In examining the influence of a visual transient on attentional engagement, results showed that a transient presented in a task-irrelevant
feature can trigger the disengagement of attention. However, this transient needs to be presented at the attended location in order to have such an effect. This influence of one feature’s transient on another’s sampling did not prove to be reciprocal though. When two features were extracted from the same object it was found that a transient in orientation reduced the selection latency of color but a transient in color did not have an effect on the selection latency of orientation. Finally, exploratory analyses were performed on EEG data collected during
feature information
extraction, but no neural correlates for the varied duration of the attentional window were found. Together the results outline how visual transients and the temporal autocorrelation of a
feature affect attentional sampling and could shed important insights into how the brain parses information in time to construct coherent object representations.
Advisors/Committee Members: Bradley Paul Wyble, Dissertation Advisor/Co-Advisor, Bradley Paul Wyble, Committee Chair/Co-Chair, Richard Alan Carlson, Committee Member, Frank Gerard Hillary, Committee Member, John Collins, Outside Member.
Subjects/Keywords: Attentional drag theory; attention; feature extraction; N2pc
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Callahan-Flintoft, C. (2019). Understanding the role of visual transients and the temporal autocorrelation of features in extending and closing the attentional window. (Thesis). Penn State University. Retrieved from https://submit-etda.libraries.psu.edu/catalog/16263czc213
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Callahan-Flintoft, Chloe. “Understanding the role of visual transients and the temporal autocorrelation of features in extending and closing the attentional window.” 2019. Thesis, Penn State University. Accessed February 27, 2021.
https://submit-etda.libraries.psu.edu/catalog/16263czc213.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Callahan-Flintoft, Chloe. “Understanding the role of visual transients and the temporal autocorrelation of features in extending and closing the attentional window.” 2019. Web. 27 Feb 2021.
Vancouver:
Callahan-Flintoft C. Understanding the role of visual transients and the temporal autocorrelation of features in extending and closing the attentional window. [Internet] [Thesis]. Penn State University; 2019. [cited 2021 Feb 27].
Available from: https://submit-etda.libraries.psu.edu/catalog/16263czc213.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Callahan-Flintoft C. Understanding the role of visual transients and the temporal autocorrelation of features in extending and closing the attentional window. [Thesis]. Penn State University; 2019. Available from: https://submit-etda.libraries.psu.edu/catalog/16263czc213
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of North Texas
12.
Florescu, Corina Andreea.
SurfKE: A Graph-Based Feature Learning Framework for Keyphrase Extraction.
Degree: 2019, University of North Texas
URL: https://digital.library.unt.edu/ark:/67531/metadc1538730/
► Current unsupervised approaches for keyphrase extraction compute a single importance score for each candidate word by considering the number and quality of its associated words…
(more)
▼ Current unsupervised approaches for keyphrase
extraction compute a single importance score for each candidate word by considering the number and quality of its associated words in the graph and they are not flexible enough to incorporate multiple types of information. For instance, nodes in a network may exhibit diverse connectivity patterns which are not captured by the graph-based ranking methods. To address this, we present a new approach to keyphrase
extraction that represents the document as a word graph and exploits its structure in order to reveal underlying explanatory factors hidden in the data that may distinguish keyphrases from non-keyphrases. Experimental results show that our model, which uses phrase graph representations in a supervised probabilistic framework, obtains remarkable improvements in performance over previous supervised and unsupervised keyphrase
extraction systems.
Advisors/Committee Members: Jin, Wei, Nielsen, Rodney, Huang, Yan, Fu, Song, Blanco, Eduardo.
Subjects/Keywords: keyphrase extraction; graph representation learning; feature learning
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share






NSYSU
13.
Yang, Cheng-Ju.
Image classification via successive core tensor selection procedure.
Degree: Master, Applied Mathematics, 2018, NSYSU
URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0606118-151922
► In the field of artificial intelligence, high-order tensor data have been studied and analyzed, such as the automated optical inspection and MRI. Therefore, tensor decompositions…
(more)
▼ In the field of artificial intelligence, high-order tensor data have been studied and analyzed, such as the automated optical inspection and MRI. Therefore, tensor decompositions and classification algorithms have become an important research topic.
In a traditional neural network or machine learning method, the classification algorithm inputs training data in the form of vectors, and the trained model can identify and classify the testing data. In order to conform the input constraints, high-order tensor data are often expanded into high-dimensional vectors. However, it also leads to the loss of spatially related information adjacent to different orders, thus damages the performance of the classification.
This thesis proposes a classification model combining non-negative Tucker decomposition and high-order tensors principal component analysis, and extracts
feature core tensors successively to improve the accuracy of classification. Comparing with to neural network classifiers, we replace affine transformations with tensor transformations, which optimizes tensor projections to avoid missing information representing the spatial relationships in different orders, so that it extracts more complete features. For signal processing and medical image fields, data will lose its physical significance at negative values. So many non-negative decomposition and analysis methods have also become important research issues. The non-negative Tucker decomposition referred in this paper is one of them, and it is also one of the classic high-order extensions of non-negative matrix factorization. In the classification model, non-negative Tucker decomposition can not only maintain the non-negative physical meaning, but also can ignore the difference between same class, which makes the classification accuracy increase.
This study explores the computational time cost and classification accuracy of the model. In the experiment of image recognition, the training time of the high-order tensor principal component analysis was reduced to half after combining non-negative Tucker decomposition. In terms of accuracy, the smaller the number of training data, the more pronounced the lead of our model is.
Advisors/Committee Members: Yueh-Cheng Kuo (chair), Tzon-Tzer Lu (chair), Chieh-Sen Huang (chair), Tsung-Lin Lee (committee member).
Subjects/Keywords: data feature extraction; image classification; tensor decomposition
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Yang, C. (2018). Image classification via successive core tensor selection procedure. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0606118-151922
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Yang, Cheng-Ju. “Image classification via successive core tensor selection procedure.” 2018. Thesis, NSYSU. Accessed February 27, 2021.
http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0606118-151922.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Yang, Cheng-Ju. “Image classification via successive core tensor selection procedure.” 2018. Web. 27 Feb 2021.
Vancouver:
Yang C. Image classification via successive core tensor selection procedure. [Internet] [Thesis]. NSYSU; 2018. [cited 2021 Feb 27].
Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0606118-151922.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Yang C. Image classification via successive core tensor selection procedure. [Thesis]. NSYSU; 2018. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0606118-151922
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
14.
Eroğlu, Hulisi.
Tek mikrofon ile ses kaynağı uzaklığı tahmini: Audio source distance estimation via single microphone.
Degree: Dil ve Tarih-Coğrafya Fakültesi, 2018, University of Ankara
URL: http://hdl.handle.net/20.500.12575/68858
► Bu tez çalışmasında, geleneksel yöntemler (öznitelik çıkarımı ve sınıflandırma) ve derin ağlar ile öğrenme olmak üzere iki ayrı yöntem, tek mikrofon ile ses kaynağı mesafesi…
(more)
▼ Bu tez çalışmasında, geleneksel yöntemler (öznitelik çıkarımı ve sınıflandırma) ve derin ağlar ile öğrenme olmak üzere iki ayrı yöntem, tek mikrofon ile ses kaynağı mesafesi tahmini problemine çözüm olarak sunulmuştur. Veri seti olarak kullanılmak üzere öncelikle 1 metre, 2 metre, 3 metre ve 4 metrelik uzaklıklardan ses kayıtları toplanmıştır. Problem ilk olarak geleneksel yöntemler ile üç adımda çözülmüştür. İlk adımda ses aktivatörü kullanılarak sadece konuşma içeren ses sinyali alınmıştır ve Hanning pencereleme uygulanmıştır. İkinci adımda ise bu sinyalden öznitelikler çıkartılmıştır. Son adımda ise çıkartılan bu öznitelikler k-nn (k-nearest neighbour, k-en yakın komşuluk) sınıflandırıcı ile sınıflandırılıp mesafeye karar verilmiştir. İkinci yöntem olarak ise derin sinir ağları kullanılarak mesafeye karar verilmiştir. Derin sinir ağ yapısı, 1 giriş, 7 konvolüsyönel katman ve 1 çıkış katmanından oluşturulmuştur. Geleneksel yönteme göre derin sinir ağları ile elde edilen başarımda % 14'lük bir artış gözlenmiştir.
In this thesis, traditional methods (
feature extraction and classification) and deep neural networks, are presented as a solution to the sound source distance estimation problem via single microphone. As dataset, 1 meter, 2 meter, 3 meter and 4 meter recordings were used. The problem is solved in three steps by conventional methods. In the first step, a VAD (voice activity detector) and Hanning windowing are applied to speech signal. In the second step, features are extracted from this signal. In the last step, these extracted features are classified with k-nn (k-nearest neighborhood) classifier. As a second method, it has been decided to use deep neural networks. The deep network structure is composed of 1 input, 7 convolutional layers and 1 output layer. Compared with the conventional method, deep networks increased the performance of the overall system by 14 %.
Advisors/Committee Members: İlk, Hakkı Gökhan (advisor).
Subjects/Keywords: Sınıflandırma; Öznitelik çıkarımı; Classification; Feature extraction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Eroğlu, H. (2018). Tek mikrofon ile ses kaynağı uzaklığı tahmini: Audio source distance estimation via single microphone. (Masters Thesis). University of Ankara. Retrieved from http://hdl.handle.net/20.500.12575/68858
Chicago Manual of Style (16th Edition):
Eroğlu, Hulisi. “Tek mikrofon ile ses kaynağı uzaklığı tahmini: Audio source distance estimation via single microphone.” 2018. Masters Thesis, University of Ankara. Accessed February 27, 2021.
http://hdl.handle.net/20.500.12575/68858.
MLA Handbook (7th Edition):
Eroğlu, Hulisi. “Tek mikrofon ile ses kaynağı uzaklığı tahmini: Audio source distance estimation via single microphone.” 2018. Web. 27 Feb 2021.
Vancouver:
Eroğlu H. Tek mikrofon ile ses kaynağı uzaklığı tahmini: Audio source distance estimation via single microphone. [Internet] [Masters thesis]. University of Ankara; 2018. [cited 2021 Feb 27].
Available from: http://hdl.handle.net/20.500.12575/68858.
Council of Science Editors:
Eroğlu H. Tek mikrofon ile ses kaynağı uzaklığı tahmini: Audio source distance estimation via single microphone. [Masters Thesis]. University of Ankara; 2018. Available from: http://hdl.handle.net/20.500.12575/68858
15.
Pham, Thanh Van.
Detection of plant characteristics and a comparison of effectiveness between 2d and 3d data visualization in supporting human perception of plant characteristics
.
Degree: 2018, Texas A&M University – Corpus Christi
URL: https://tamucc-ir.tdl.org/handle/1969.6/87018
► Efficient agriculture requires the assessment of plant characteristics. A higher crop yield can be achieved with good quality plant characteristic data. In this research, a…
(more)
▼ Efficient agriculture requires the assessment of plant characteristics. A higher crop yield can be achieved with good quality plant characteristic data. In this research, a system was developed using the algorithms presented here to automatically extract plant characteristics. The automatically extracted values were compared with ground-truth data to evaluate the accuracy of the system. As well, the effectiveness of using 2 or 3-dimensional data visualization for determining these characteristics is studied. An experiment was conducted to investigate how effective plant characteristics are evaluated when using 2D or 3D data visualizations. Participants were presented with either plant pictures (2D) or 3D plant models and tasked with identifying plant height and the number of leaves. Task completion times and accuracy rates were gathered for performance analysis.
Advisors/Committee Members: King, Scott A (advisor), Lee, Byung Cheol (committeeMember), Sheta, Alaa (committeeMember).
Subjects/Keywords: Agriculture;
Characteristic;
Data Visualization;
Feature extraction;
Plant
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Pham, T. V. (2018). Detection of plant characteristics and a comparison of effectiveness between 2d and 3d data visualization in supporting human perception of plant characteristics
. (Thesis). Texas A&M University – Corpus Christi. Retrieved from https://tamucc-ir.tdl.org/handle/1969.6/87018
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Pham, Thanh Van. “Detection of plant characteristics and a comparison of effectiveness between 2d and 3d data visualization in supporting human perception of plant characteristics
.” 2018. Thesis, Texas A&M University – Corpus Christi. Accessed February 27, 2021.
https://tamucc-ir.tdl.org/handle/1969.6/87018.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Pham, Thanh Van. “Detection of plant characteristics and a comparison of effectiveness between 2d and 3d data visualization in supporting human perception of plant characteristics
.” 2018. Web. 27 Feb 2021.
Vancouver:
Pham TV. Detection of plant characteristics and a comparison of effectiveness between 2d and 3d data visualization in supporting human perception of plant characteristics
. [Internet] [Thesis]. Texas A&M University – Corpus Christi; 2018. [cited 2021 Feb 27].
Available from: https://tamucc-ir.tdl.org/handle/1969.6/87018.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Pham TV. Detection of plant characteristics and a comparison of effectiveness between 2d and 3d data visualization in supporting human perception of plant characteristics
. [Thesis]. Texas A&M University – Corpus Christi; 2018. Available from: https://tamucc-ir.tdl.org/handle/1969.6/87018
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
16.
Tate, Anne Rosemary.
Pattern recognition analysis of in vivo magnetic resonance spectra.
Degree: PhD, 1996, University of Sussex
URL: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.307732
Subjects/Keywords: 621.3994; Feature extraction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Tate, A. R. (1996). Pattern recognition analysis of in vivo magnetic resonance spectra. (Doctoral Dissertation). University of Sussex. Retrieved from https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.307732
Chicago Manual of Style (16th Edition):
Tate, Anne Rosemary. “Pattern recognition analysis of in vivo magnetic resonance spectra.” 1996. Doctoral Dissertation, University of Sussex. Accessed February 27, 2021.
https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.307732.
MLA Handbook (7th Edition):
Tate, Anne Rosemary. “Pattern recognition analysis of in vivo magnetic resonance spectra.” 1996. Web. 27 Feb 2021.
Vancouver:
Tate AR. Pattern recognition analysis of in vivo magnetic resonance spectra. [Internet] [Doctoral dissertation]. University of Sussex; 1996. [cited 2021 Feb 27].
Available from: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.307732.
Council of Science Editors:
Tate AR. Pattern recognition analysis of in vivo magnetic resonance spectra. [Doctoral Dissertation]. University of Sussex; 1996. Available from: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.307732

Linköping University
17.
Wasell, Richard.
Automatisk detektering av diken i LiDAR-data.
Degree: Computer Vision, 2011, Linköping University
URL: http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-72066
► Den här rapporten har utrett möjligheten att automatiskt identifiera diken frånflygburet insamlat LiDAR-data. Den metod för identifiering som har valts harförst skapat en höjdbild…
(more)
▼ Den här rapporten har utrett möjligheten att automatiskt identifiera diken frånflygburet insamlat LiDAR-data. Den metod för identifiering som har valts harförst skapat en höjdbild från LiDAR-data. Därefter har den tagit fram kandidatertill diken genom att vektorisera resultatet från en linjedetektering. Egenskaper-na för dikeskandidaterna har sedan beräknats genom en analys av höjdprofilerför varje enskild kandidat, där höjdprofilerna skapats utifrån ursprungliga data.Genom att filtrera kandidaterna efter deras egenskaper kan dikeskartor med an-vändarspecificerade mått på diken presenteras i ett vektorformat som underlättarvidare användning. Rapporten beskriver hur algoritmen har implementerats ochpresenterar också exempel på resultat. Efter en analys av algoritmen samt förslagpå förbättringar presenteras den viktigaste behållningen av rapporten; Att det ärmöjligt med automatisk detektering av diken.
This Master’s thesis is investigating the possibility of automatically identifyingditches in airborne collected LiDAR data. The chosen approach to identificationcommences by creating an elevation picture from the LiDAR data. Then it usesthe result of a line detection to exhibit candidates for ditches. The properties forthe various candidates are calculated through an analysis of the elevation profile forthe candidates, where the elevation profiles are created from the original data. Byfiltering the candidates according to their calculated properties, maps with ditchesconforming to user-specified limits are created and presented in vector format.This thesis describes how the algorithm is implemented and gives examples ofresults. After an analysis of the algorithm and a proposal for improvements, itis suggested that automatic detection of ditches in LiDAR collected data is anachievable objective.
Subjects/Keywords: linear feature extraction; line detection; LiDAR; ditches
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Wasell, R. (2011). Automatisk detektering av diken i LiDAR-data. (Thesis). Linköping University. Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-72066
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Wasell, Richard. “Automatisk detektering av diken i LiDAR-data.” 2011. Thesis, Linköping University. Accessed February 27, 2021.
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-72066.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Wasell, Richard. “Automatisk detektering av diken i LiDAR-data.” 2011. Web. 27 Feb 2021.
Vancouver:
Wasell R. Automatisk detektering av diken i LiDAR-data. [Internet] [Thesis]. Linköping University; 2011. [cited 2021 Feb 27].
Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-72066.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Wasell R. Automatisk detektering av diken i LiDAR-data. [Thesis]. Linköping University; 2011. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-72066
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Delft University of Technology
18.
Kreuk, Laura (author).
Sentiment Analysis: a comparison of feature sets for social data and reviews.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:eca6e7b5-a846-424b-ba44-84c060c29d97
► Consumers share their experiences or opinion about products or brands in various channels nowadays, for example on review websites or social media. Sentiment analysis is…
(more)
▼ Consumers share their experiences or opinion about products or brands in various channels nowadays, for example on review websites or social media. Sentiment analysis is used to predict the sentiment of text from consumers about these products or brands in order to understand the tone of customers towards these products or brands. This thesis addresses sentiment analysis in the product domain on sentence level. In this thesis three data types are used which are collected by Unilever, review data which is text that contains the opinion of a customer towards a specific product. Social data, which can be tweets, Facebook messages, Instagram messages etc. and phone data which is a summary of a phone call of a customer about a specific product. When conducting sentiment analysis one solution is to extract features from the data which can be given to a machine learning algorithm together with sentiment labels given by human annotators. The machine learning algorithm will generate a classifier which can predict a label for sentences. In sentiment analysis literature it is often not clear why certain features are chosen or for which data type certain features will work well. In this research we compare the differences when using several feature sets for the different data types. We propose three feature sets for review data and three feature sets for social data. We focus on two aspects, comparing the different feature sets and comparing the data types. In our results we do not find significant differences in performance between the feature sets. The results suggest there might be feature sets which can improve sentiment analysis specifically for the data type, but a general feature set with standard features can be comparable to that result.
Computer Science | Data Science and Technology | Information Architecture
Advisors/Committee Members: Tintarev, Nava (mentor), Houben, Geert-Jan (graduation committee), Urbano Merino, Julian (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Sentiment Analysis; feature extraction; reviews; social data
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Kreuk, L. (. (2018). Sentiment Analysis: a comparison of feature sets for social data and reviews. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:eca6e7b5-a846-424b-ba44-84c060c29d97
Chicago Manual of Style (16th Edition):
Kreuk, Laura (author). “Sentiment Analysis: a comparison of feature sets for social data and reviews.” 2018. Masters Thesis, Delft University of Technology. Accessed February 27, 2021.
http://resolver.tudelft.nl/uuid:eca6e7b5-a846-424b-ba44-84c060c29d97.
MLA Handbook (7th Edition):
Kreuk, Laura (author). “Sentiment Analysis: a comparison of feature sets for social data and reviews.” 2018. Web. 27 Feb 2021.
Vancouver:
Kreuk L(. Sentiment Analysis: a comparison of feature sets for social data and reviews. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Feb 27].
Available from: http://resolver.tudelft.nl/uuid:eca6e7b5-a846-424b-ba44-84c060c29d97.
Council of Science Editors:
Kreuk L(. Sentiment Analysis: a comparison of feature sets for social data and reviews. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:eca6e7b5-a846-424b-ba44-84c060c29d97

University of Illinois – Urbana-Champaign
19.
Jain, Shubham.
Landmarks for clothing retrieval.
Degree: MS, Computer Science, 2019, University of Illinois – Urbana-Champaign
URL: http://hdl.handle.net/2142/104891
► Clothing Retrieval is a task that is increasingly becoming popular with the rise of online shopping and social media’s popularity. We propose to solve the…
(more)
▼ Clothing Retrieval is a task that is increasingly becoming popular with the rise of online shopping and social media’s popularity. We propose to solve the clothing retrieval problem using landmarks based on the clothing type and features surrounding the landmarks to get a more ingrained view of the design. We compare this method with other models most of which use the whole image as inputs and show the superiority of the model which gives importance to the crucial parts of the images. For the blouses sub-set from of the Deep Fashion dataset[1], we get an 16% increase in the accuracy for the top 3, 14% in top 5 and 11% top 10 retrieval results using the keypoints
extraction methods combined with whole images compared to whole images as inputs. We also observe that the clothes retrieved are more similar in terms or design as well as high level properties like sleeve sizes, folded v/s non-folded sleeves etc.
Advisors/Committee Members: Lazebnik, Svetlana (advisor).
Subjects/Keywords: clothing; retrieval; landmarks; keypoints; feature extraction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Jain, S. (2019). Landmarks for clothing retrieval. (Thesis). University of Illinois – Urbana-Champaign. Retrieved from http://hdl.handle.net/2142/104891
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Jain, Shubham. “Landmarks for clothing retrieval.” 2019. Thesis, University of Illinois – Urbana-Champaign. Accessed February 27, 2021.
http://hdl.handle.net/2142/104891.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Jain, Shubham. “Landmarks for clothing retrieval.” 2019. Web. 27 Feb 2021.
Vancouver:
Jain S. Landmarks for clothing retrieval. [Internet] [Thesis]. University of Illinois – Urbana-Champaign; 2019. [cited 2021 Feb 27].
Available from: http://hdl.handle.net/2142/104891.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Jain S. Landmarks for clothing retrieval. [Thesis]. University of Illinois – Urbana-Champaign; 2019. Available from: http://hdl.handle.net/2142/104891
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Waterloo
20.
Li, Fan.
Automated Remote Sensing Image Interpretation with Limited Labeled Training Data.
Degree: 2015, University of Waterloo
URL: http://hdl.handle.net/10012/9571
► Automated remote sensing image interpretation has been investigated for more than a decade. In early years, most work was based on the assumption that there…
(more)
▼ Automated remote sensing image interpretation has been investigated for more than a decade. In early years, most work was based on the assumption that there are sufficient labeled samples to be used for training. However, ground-truth collection is a very tedious and time-consuming task and sometimes very expensive, especially in the field of remote sensing that usually relies on field surveys to collect ground truth. In recent years, as the development of advanced machine learning techniques, remote sensing image interpretation with limited ground-truth has caught the attention of researchers in the fields of both remote sensing and computer science.
Three approaches that focus on different aspects of the interpretation process, i.e., feature extraction, classification, and segmentation, are proposed to deal with the limited ground truth problem. First, feature extraction techniques, which usually serve as a pre-processing step for remote sensing image classification are explored. Instead of only focusing on feature extraction, a joint feature extraction and classification framework is proposed based on ensemble local manifold learning. Second, classifiers in the case of limited labeled training data are investigated, and an enhanced ensemble learning method that outperforms state-of-the-art classification methods is proposed. Third, image segmentation techniques are investigated, with the aid of unlabeled samples and spatial information. A semi-supervised self-training method is proposed, which is capable of expanding the number of training samples by its own and hence improving classification performance iteratively. Experiments show that the proposed approaches outperform state-of-the-art techniques in terms of classification accuracy on benchmark remote sensing datasets.
Subjects/Keywords: remote sensing; classification; segmentation; feature extraction.
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Li, F. (2015). Automated Remote Sensing Image Interpretation with Limited Labeled Training Data. (Thesis). University of Waterloo. Retrieved from http://hdl.handle.net/10012/9571
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Li, Fan. “Automated Remote Sensing Image Interpretation with Limited Labeled Training Data.” 2015. Thesis, University of Waterloo. Accessed February 27, 2021.
http://hdl.handle.net/10012/9571.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Li, Fan. “Automated Remote Sensing Image Interpretation with Limited Labeled Training Data.” 2015. Web. 27 Feb 2021.
Vancouver:
Li F. Automated Remote Sensing Image Interpretation with Limited Labeled Training Data. [Internet] [Thesis]. University of Waterloo; 2015. [cited 2021 Feb 27].
Available from: http://hdl.handle.net/10012/9571.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Li F. Automated Remote Sensing Image Interpretation with Limited Labeled Training Data. [Thesis]. University of Waterloo; 2015. Available from: http://hdl.handle.net/10012/9571
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Louisiana State University
21.
Chen, Jing.
Vocal Fold Analysis From High Speed Videoendoscopic Data.
Degree: PhD, Electrical and Computer Engineering, 2014, Louisiana State University
URL: etd-05152014-135123
;
https://digitalcommons.lsu.edu/gradschool_dissertations/664
► High speed videoendoscopy (HSV) of the larynx far surpasses the limits of videostroboscopy in evaluating the vocal fold vibratory behavior by providing much higher frame…
(more)
▼ High speed videoendoscopy (HSV) of the larynx far surpasses the limits of videostroboscopy in evaluating the vocal fold vibratory behavior by providing much higher frame rate. HSV enables the visualization of vocal fold vibratory pattern within an actual glottic cycle. This very detailed infor-mation on vocal fold vibratory characteristics could provide valuable information for the assessment of vocal fold vibratory function in disordered voices and the treatments effects of the behavioral, medical and surgical treatment procedures. In this work, we aim at addressing the problem of classi-fying voice disorders with varying etiology by following four steps described shortly. Our method-ology starts with glottis segmentation. Given a HSV data, the contour of the glottal opening area in each frame should be acquired. These contours record the vibration track of the vocal fold. After this, we obtain a reliable glottal axis that is necessary for getting certain vibratory features. The third step is the feature extraction on HSV data. In the last step, we complete the classification based on the features obtained from step 3. In this study, we first propose a novel glottis segmentation method based on simplified dynam-ic programming, which proves to be efficient and accurate. In addition, we introduce a new ap-proach for calculating the glottal axis. By comparing the proposed glottal axis determination meth-ods (modified linear regression) against state-of-the-art techniques, we demonstrate that our tech-nique is more reliable. After that, the concentration shifts to feature extraction and classification schemes. Eighteen different features are extracted and their discrimination is evaluated based on principal component analysis. Support vector machine and neural network are implemented to achieve the classification among three different types of vocal folds(normal vocal fold, unilateral vocal fold polyp, and unilateral vocal fold paralysis). The result demonstrates that the classification rates of four different tasks are all above 80%.
Subjects/Keywords: vocal fold; segmentaion; glottal axis; feature extraction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Chen, J. (2014). Vocal Fold Analysis From High Speed Videoendoscopic Data. (Doctoral Dissertation). Louisiana State University. Retrieved from etd-05152014-135123 ; https://digitalcommons.lsu.edu/gradschool_dissertations/664
Chicago Manual of Style (16th Edition):
Chen, Jing. “Vocal Fold Analysis From High Speed Videoendoscopic Data.” 2014. Doctoral Dissertation, Louisiana State University. Accessed February 27, 2021.
etd-05152014-135123 ; https://digitalcommons.lsu.edu/gradschool_dissertations/664.
MLA Handbook (7th Edition):
Chen, Jing. “Vocal Fold Analysis From High Speed Videoendoscopic Data.” 2014. Web. 27 Feb 2021.
Vancouver:
Chen J. Vocal Fold Analysis From High Speed Videoendoscopic Data. [Internet] [Doctoral dissertation]. Louisiana State University; 2014. [cited 2021 Feb 27].
Available from: etd-05152014-135123 ; https://digitalcommons.lsu.edu/gradschool_dissertations/664.
Council of Science Editors:
Chen J. Vocal Fold Analysis From High Speed Videoendoscopic Data. [Doctoral Dissertation]. Louisiana State University; 2014. Available from: etd-05152014-135123 ; https://digitalcommons.lsu.edu/gradschool_dissertations/664

University of New South Wales
22.
Li, Zelin.
Feature learning, selection and representation for object detection and recognition.
Degree: Computer Science & Engineering, 2017, University of New South Wales
URL: http://handle.unsw.edu.au/1959.4/58813
;
https://unsworks.unsw.edu.au/fapi/datastream/unsworks:47626/SOURCE02?view=true
► The recent years have seen the increasing popularity of a wide range of applications in Computer Vision. Object Recognition is critical in determining the success…
(more)
▼ The recent years have seen the increasing popularity of a wide range of applications in Computer Vision. Object Recognition is critical in determining the success of these applications. In general, object recognition consists of three major components: imagery acquisition,
feature extraction and classification. Imagery acquisition is the process by which hardware is used to obtain information from a scene.
Feature extraction is the process by which an object within the image is described either explicitly or implicitly. Finally, classification attempts to use the extracted features as an input to generate classifiers, thereby distinguishing different objects. Therefore,
feature extraction and its derived representations play a vital role in improving the accuracy of object recognition.In traditional hand-crafted
feature representation methods, such as Histogram of Gradient, the representative and discriminative capabilities of these methods are highly vulnerable to various factors, such as image noise. Therefore, in this study, novel
feature descriptors are proposed to tackle the issues arising from
feature representation in object recognition. Two kernel-based
feature descriptors are developed: Steering Kernel Regression Weight Matrix and Long-Axis of Local Adaptive Steering Kernel; both of which are derived from Steering Kernel Regression. The proposed
feature descriptors facilitate the ability of Steering Kernel Regression to capture the local structure around an object and tolerate the noise that occurs in the images. Subsequently covariance techniques are employed to form a robust
feature representation for an object. To alleviate the complexity arising from covariance, Long-Axis of Local Adaptive Steering Kernel
feature is proposed to simplify the computation required.Additionally, to further reduce computation complexity, a sparse representation based
feature descriptor is developed for object detection. Sparse representation has proven its superior capabilities in image classification, but not in object detection, i.e. isolating objects within a complicated environment. Therefore, in this study, the reconstruction error from sparse representation is utilised as a
feature, and a Bayesian model is applied to use learned atoms to reinforce the discriminative power of reconstruction error that may have been 'polluted' by noise.Computer Vision applications not only work with static images, but also with videos. A motion-based approach is developed to tackle the problem caused by appearance-based features in video-based Person Re-identification. Fine-grained displacement along dense trajectories is applied to describe a specific human motion. Such motion information encodes numerous distinctive biometric cues to discriminate between the walking styles of different people. Utilising Dissimilarity based Sparse Subset Learning, the proposed approach demonstrates increased robustness in long term Person Re-identification applications.
Advisors/Committee Members: Chen, Fang, Computer Science & Engineering, Faculty of Engineering, UNSW.
Subjects/Keywords: Feature Extraction; Computer Vision; Pattern Recognition
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Li, Z. (2017). Feature learning, selection and representation for object detection and recognition. (Doctoral Dissertation). University of New South Wales. Retrieved from http://handle.unsw.edu.au/1959.4/58813 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:47626/SOURCE02?view=true
Chicago Manual of Style (16th Edition):
Li, Zelin. “Feature learning, selection and representation for object detection and recognition.” 2017. Doctoral Dissertation, University of New South Wales. Accessed February 27, 2021.
http://handle.unsw.edu.au/1959.4/58813 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:47626/SOURCE02?view=true.
MLA Handbook (7th Edition):
Li, Zelin. “Feature learning, selection and representation for object detection and recognition.” 2017. Web. 27 Feb 2021.
Vancouver:
Li Z. Feature learning, selection and representation for object detection and recognition. [Internet] [Doctoral dissertation]. University of New South Wales; 2017. [cited 2021 Feb 27].
Available from: http://handle.unsw.edu.au/1959.4/58813 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:47626/SOURCE02?view=true.
Council of Science Editors:
Li Z. Feature learning, selection and representation for object detection and recognition. [Doctoral Dissertation]. University of New South Wales; 2017. Available from: http://handle.unsw.edu.au/1959.4/58813 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:47626/SOURCE02?view=true

University of New South Wales
23.
Wang, Yunqi.
Detection and Classification of Disturbances in Islanded Micro-grid.
Degree: Electrical Engineering & Telecommunications, 2018, University of New South Wales
URL: http://handle.unsw.edu.au/1959.4/61517
;
https://unsworks.unsw.edu.au/fapi/datastream/unsworks:56398/SOURCE02?view=true
► Micro-grids are envisaged as single plug-and-play electrical systems that can operate either in grid-connected or islanded modes. Their main sources of power are renewable and…
(more)
▼ Micro-grids are envisaged as single plug-and-play electrical systems that can operate either in grid-connected or islanded modes. Their main sources of power are renewable and are usually integrated through power electronic devices. These present new challenges to reliable operation of the system due to their inherent incapability to regulate the system. Power quality (PQ) disturbances in the micro-grid make it further vulnerable, especially when the micro-grid operates in an islanded mode. The PQ disturbances only occur for a few cycles and cannot be easily detected directly in the time domain.This thesis utilizes wavelet transformation (WT) method to detect and analyse the disturbance signals in the islanded micro-grid. The signals are collected from both simulation and experimental setup. The wavelet-based and time domain based
feature extraction algorithms are investigated and compared. Factors that can affect the performance of these methods are discussed. Furthermore, three different types of wavelet-based
feature extraction methods are also tested and two of them – normilized Renyi entropy with signal energy and normalized Renyi entropy with distribution volume, are algorithms which have not been applied into the power system before.The results show that the disturbances created by using simulated data are successfully identified using wavelet transformation. The variation of wavelet coefficients helps in identifying the time and duration of the disturbances. However, when data from the micro-grid laboratory setup is used, the performance of the WT is not satisfactory due to presence of noise and harmonics. Although, single disturbances such as voltage sag, swell and interruption can still be identified and classified, the WT is unable to detect and classify multiple disturbances, especially when non-linear loads are involved. The presence of non-linear loads in islanded micro-grids, increases the fluctuations of the WT coefficients, thus making the disturbance signals to be buried.To overcome this issue, the Renyi entropy is used to improve the performance of WT. A comparison is made between the time-domain Renyi and wavelet-based Renyi. The results show that the wavelet-based Renyi has improved efficiency. Two normalized Renyi entropies are also investigated and compared with the normal Renyi entropy, to overcome the problem whereby Renyi entropy fails to detect zero-mean cross-terms in some cases when odd is used, as well as to reduce the distribution to the unity signal energy case. These two algorithms are found to show higher accuracy and efficiency for classifying multiple disturbances in an islanded micro-grid.
Advisors/Committee Members: Ravishankar, Jayashri, Electrical Engineering & Telecommunications, Faculty of Engineering, UNSW, Phung, Toan, Electrical Engineering & Telecommunications, Faculty of Engineering, UNSW.
Subjects/Keywords: Feature extraction; Power quality; Micro-grid
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Wang, Y. (2018). Detection and Classification of Disturbances in Islanded Micro-grid. (Doctoral Dissertation). University of New South Wales. Retrieved from http://handle.unsw.edu.au/1959.4/61517 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:56398/SOURCE02?view=true
Chicago Manual of Style (16th Edition):
Wang, Yunqi. “Detection and Classification of Disturbances in Islanded Micro-grid.” 2018. Doctoral Dissertation, University of New South Wales. Accessed February 27, 2021.
http://handle.unsw.edu.au/1959.4/61517 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:56398/SOURCE02?view=true.
MLA Handbook (7th Edition):
Wang, Yunqi. “Detection and Classification of Disturbances in Islanded Micro-grid.” 2018. Web. 27 Feb 2021.
Vancouver:
Wang Y. Detection and Classification of Disturbances in Islanded Micro-grid. [Internet] [Doctoral dissertation]. University of New South Wales; 2018. [cited 2021 Feb 27].
Available from: http://handle.unsw.edu.au/1959.4/61517 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:56398/SOURCE02?view=true.
Council of Science Editors:
Wang Y. Detection and Classification of Disturbances in Islanded Micro-grid. [Doctoral Dissertation]. University of New South Wales; 2018. Available from: http://handle.unsw.edu.au/1959.4/61517 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:56398/SOURCE02?view=true
24.
Wan, Huan.
Cluster-based supervised classification.
Degree: PhD, 2020, Ulster University
URL: https://pure.ulster.ac.uk/en/studentTheses/7e984d07-2ce4-4959-8063-32f8ba233958
;
https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.821060
► Supervised classification is one of our fundamental approaches to understanding the world, and is studied in many research areas. Feature extraction and classification learning are…
(more)
▼ Supervised classification is one of our fundamental approaches to understanding the world, and is studied in many research areas. Feature extraction and classification learning are two key processes, which significantly influence the performance of supervised classification. Although impressive progress has been made in supervised classification due to the development of feature extraction methods and classifiers, there are still unsolved problems in supervised classification, such as the class imbalance problem and the few-shot classification problem. In this thesis, we focus on the complex boundary problem — it is hard to obtain high classification accuracy for problems with complex decision boundaries due to the existence of subclass structures. We propose a cluster-based approach to supervised classification and develop cluster-based feature extraction methods and cluster-based classification learning methods. For feature extraction, to find out the importance of considering within-class multimodality for feature extraction, we conduct a study on within-class multimodal data distribution and classification under such a distribution. This study is guided by five important questions about within-class multimodal data. Systematic experiments using a variety of artificial and real data are conducted to answer the five questions, which further lead to some useful findings. In the second study, a new feature extraction method is proposed, called global subclass discriminant analysis (GSDA). To extract discriminative features, GSDA first obtains clusters in a global way by clustering the whole data set and derives class-specific clusters based on these global clusters. Then it seeks to maximise interclass distance and minimise intraclass distance based on these class-specific clusters. GSDA is extensively evaluated on a wide range of data through comparison with the closely related and state-of-the-art feature extraction methods. Experimental results demonstrate GSDA’s superiority in terms of accuracy and run time. For classification learning, in the third study, we propose a cluster-based data relabelling (CBDR) method for improving the classification performance of existing classifiers on nonlinear data. CBDR aims to impel classifiers to find cluster-based decision boundaries rather than class-based decision boundaries. Extensive experimentations demonstrate that CBDR dramatically boosts the classification performance of classifiers on nonlinear data, especially for linear classifiers. In the final study, a novel Gaussian mixture model (GMM) classifier is proposed, called separability criterion based GMM (SC-GMM) classifier. In SC-GMM, the separability criterion is employed to find the optimal number of Gaussian components for GMM. Experiments have been carried out on various classification tasks. Experimental results demonstrate the superiority of the SC-GMM classifier.
Subjects/Keywords: Clustering; Classification; LDA; Feature extraction; Subclass
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Wan, H. (2020). Cluster-based supervised classification. (Doctoral Dissertation). Ulster University. Retrieved from https://pure.ulster.ac.uk/en/studentTheses/7e984d07-2ce4-4959-8063-32f8ba233958 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.821060
Chicago Manual of Style (16th Edition):
Wan, Huan. “Cluster-based supervised classification.” 2020. Doctoral Dissertation, Ulster University. Accessed February 27, 2021.
https://pure.ulster.ac.uk/en/studentTheses/7e984d07-2ce4-4959-8063-32f8ba233958 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.821060.
MLA Handbook (7th Edition):
Wan, Huan. “Cluster-based supervised classification.” 2020. Web. 27 Feb 2021.
Vancouver:
Wan H. Cluster-based supervised classification. [Internet] [Doctoral dissertation]. Ulster University; 2020. [cited 2021 Feb 27].
Available from: https://pure.ulster.ac.uk/en/studentTheses/7e984d07-2ce4-4959-8063-32f8ba233958 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.821060.
Council of Science Editors:
Wan H. Cluster-based supervised classification. [Doctoral Dissertation]. Ulster University; 2020. Available from: https://pure.ulster.ac.uk/en/studentTheses/7e984d07-2ce4-4959-8063-32f8ba233958 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.821060

Queensland University of Technology
25.
Dong, Xueyan.
Content-based birdcall retrieval from environmental audio.
Degree: 2016, Queensland University of Technology
URL: http://eprints.qut.edu.au/94402/
► This research investigates techniques to analyse long duration acoustic recordings to help ecologists monitor birdcall activities. It designs a generalized algorithm to identify a broad…
(more)
▼ This research investigates techniques to analyse long duration acoustic recordings to help ecologists monitor birdcall activities. It designs a generalized algorithm to identify a broad range of bird species. It allows ecologists to search for arbitrary birdcalls of interest, rather than restricting them to just a very limited number of species on which the recogniser is trained. The algorithm can help ecologists find sounds of interest more efficiently by filtering out large volumes of unwanted sounds and only focusing on birdcalls.
Subjects/Keywords: birdcall retrieval; feature extraction; spectral ridge feature; event representation; environmental recording
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Dong, X. (2016). Content-based birdcall retrieval from environmental audio. (Thesis). Queensland University of Technology. Retrieved from http://eprints.qut.edu.au/94402/
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Dong, Xueyan. “Content-based birdcall retrieval from environmental audio.” 2016. Thesis, Queensland University of Technology. Accessed February 27, 2021.
http://eprints.qut.edu.au/94402/.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Dong, Xueyan. “Content-based birdcall retrieval from environmental audio.” 2016. Web. 27 Feb 2021.
Vancouver:
Dong X. Content-based birdcall retrieval from environmental audio. [Internet] [Thesis]. Queensland University of Technology; 2016. [cited 2021 Feb 27].
Available from: http://eprints.qut.edu.au/94402/.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Dong X. Content-based birdcall retrieval from environmental audio. [Thesis]. Queensland University of Technology; 2016. Available from: http://eprints.qut.edu.au/94402/
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Delft University of Technology
26.
Wang, Yuyang (author).
An automated ECG signal quality assessment method with supervised learning algorithm.
Degree: 2018, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:41eab0f1-05a5-440c-a43b-f2f12b15a8aa
► Wearable health has become a striking area in our daily life. Electrocardiogram (ECG) is one of the biomedical signals collected by the wearable or portable…
(more)
▼ Wearable health has become a striking area in our daily life. Electrocardiogram (ECG) is one of the biomedical signals collected by the wearable or portable devices, which is widely used in heart rate monitoring and cardiac diagnosis. However, automatic ECG signal analysis is difficult in real application because the signals are easy to be contaminated by the noise and artifacts. Thus, the quality of ECG signals is essential for the accurate analysis. The objective of this project is to design a reliable automated ECG signal quality indicator based on the supervised learning algorithm, which intends to estimate the quality of the signals and distinguish them. The methodology of this project is creating a classification model to indicate the quality of ECG signals based on the machine learning algorithm. The model is trained by the extracted features based on the Fourier transform, Wavelet transform, Autocorrelation function and Principal component analysis of ECG signals. Subsequently, the
feature selection techniques are proposed to remove the irrelevant and redundant features and then the selected features are fed to classification algorithms. The classifier was then trained and tested on the expert-labeled data from the collected ECG signals. Particularly, we focus on the performance of classifier and use the best training model to predict the quality of new ECG signals.
Advisors/Committee Members: Hendriks, Richard (mentor), Heusdens, Richard (graduation committee), Tax, David (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: ECG signal; quality assessment; Supervised Learning; Feature extraction; Feature selection
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Wang, Y. (. (2018). An automated ECG signal quality assessment method with supervised learning algorithm. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:41eab0f1-05a5-440c-a43b-f2f12b15a8aa
Chicago Manual of Style (16th Edition):
Wang, Yuyang (author). “An automated ECG signal quality assessment method with supervised learning algorithm.” 2018. Masters Thesis, Delft University of Technology. Accessed February 27, 2021.
http://resolver.tudelft.nl/uuid:41eab0f1-05a5-440c-a43b-f2f12b15a8aa.
MLA Handbook (7th Edition):
Wang, Yuyang (author). “An automated ECG signal quality assessment method with supervised learning algorithm.” 2018. Web. 27 Feb 2021.
Vancouver:
Wang Y(. An automated ECG signal quality assessment method with supervised learning algorithm. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Feb 27].
Available from: http://resolver.tudelft.nl/uuid:41eab0f1-05a5-440c-a43b-f2f12b15a8aa.
Council of Science Editors:
Wang Y(. An automated ECG signal quality assessment method with supervised learning algorithm. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:41eab0f1-05a5-440c-a43b-f2f12b15a8aa

University of Tennessee – Knoxville
27.
Luo, Jiajia.
Feature Extraction and Recognition for Human Action Recognition.
Degree: 2014, University of Tennessee – Knoxville
URL: https://trace.tennessee.edu/utk_graddiss/2710
► How to automatically label videos containing human motions is the task of human action recognition. Traditional human action recognition algorithms use the RGB videos as…
(more)
▼ How to automatically label videos containing human motions is the task of human action recognition. Traditional human action recognition algorithms use the RGB videos as input, and it is a challenging task because of the large intra-class variations of actions, cluttered background, possible camera movement, and illumination variations. Recently, the introduction of cost-effective depth cameras provides a new possibility to address difficult issues. However, it also brings new challenges such as noisy depth maps and time alignment. In this dissertation, effective and computationally efficient feature extraction and recognition algorithms are proposed for human action recognition.
At the feature extraction step, two novel spatial-temporal feature descriptors are proposed which can be combined with local feature detectors. The first proposed descriptor is the Shape and Motion Local Ternary Pattern (SMltp) descriptor which can dramatically reduced the number of features generated by dense sampling without sacrificing the accuracy. In addition, the Center-Symmetric Motion Local Ternary Pattern (CS-Mltp) descriptor is proposed, which describes the spatial and temporal gradients-like features. Both descriptors (SMltp and CS-Mltp) take advantage of the Local Binary Pattern (LBP) texture operator in terms of tolerance to illumination change, robustness in homogeneous region and computational efficiency.
For better feature representation, this dissertation presents a new Dictionary Learning (DL) method to learn an overcomplete set of representative vectors (atoms) so that any input feature can be approximated by a linear combination of these atoms with minimum reconstruction error. Instead of simultaneously learning one overcomplete dictionary for all classes, we learn class-specific sub-dictionaries to increase the discrimination. In addition, the group sparsity and the geometry constraint are added to the learning process to further increase the discriminative power, so that features are well reconstructed by atoms from the same class and features from the same class with high similarity will be forced to have similar coefficients.
To evaluate the proposed algorithms, three applications including single view action recognition, distributed multi-view action recognition, and RGB-D action recognition have been explored. Experimental results on benchmark datasets and comparative analyses with the state-of-the-art methods show the effectiveness and merits of the proposed algorithms.
Subjects/Keywords: feature extraction; feature representation; dictionary learning; sparse coding; Other Computer Engineering
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Luo, J. (2014). Feature Extraction and Recognition for Human Action Recognition. (Doctoral Dissertation). University of Tennessee – Knoxville. Retrieved from https://trace.tennessee.edu/utk_graddiss/2710
Chicago Manual of Style (16th Edition):
Luo, Jiajia. “Feature Extraction and Recognition for Human Action Recognition.” 2014. Doctoral Dissertation, University of Tennessee – Knoxville. Accessed February 27, 2021.
https://trace.tennessee.edu/utk_graddiss/2710.
MLA Handbook (7th Edition):
Luo, Jiajia. “Feature Extraction and Recognition for Human Action Recognition.” 2014. Web. 27 Feb 2021.
Vancouver:
Luo J. Feature Extraction and Recognition for Human Action Recognition. [Internet] [Doctoral dissertation]. University of Tennessee – Knoxville; 2014. [cited 2021 Feb 27].
Available from: https://trace.tennessee.edu/utk_graddiss/2710.
Council of Science Editors:
Luo J. Feature Extraction and Recognition for Human Action Recognition. [Doctoral Dissertation]. University of Tennessee – Knoxville; 2014. Available from: https://trace.tennessee.edu/utk_graddiss/2710

Arizona State University
28.
Yamak, Didem.
Characterization of Coronary Atherosclerotic Plaques by Dual
Energy Computed Tomography.
Degree: PhD, Bioengineering, 2013, Arizona State University
URL: http://repository.asu.edu/items/18027
► Coronary heart disease (CHD) is the most prevalent cause of death worldwide. Atherosclerosis which is the condition of plaque buildup on the inside of the…
(more)
▼ Coronary heart disease (CHD) is the most prevalent
cause of death worldwide. Atherosclerosis which is the condition of
plaque buildup on the inside of the coronary artery wall is the
main cause of CHD. Rupture of unstable atherosclerotic coronary
plaque is known to be the cause of acute coronary syndrome. The
composition of plaque is important for detection of plaque
vulnerability. Due to prognostic importance of early stage
identification, non-invasive assessment of plaque characterization
is necessary. Computed tomography (CT) has emerged as a
non-invasive alternative to coronary angiography. Recently, dual
energy CT (DECT) coronary angiography has been performed
clinically. DECT scanners use two different X-ray energies in order
to determine the energy dependency of tissue attenuation values for
each voxel. They generate virtual monochromatic energy images, as
well as material basis pair images. The characterization of plaque
components by DECT is still an active research topic since overlap
between the CT attenuations measured in plaque components and
contrast material shows that the single mean density might not be
an appropriate measure for characterization. This dissertation
proposes feature extraction, feature selection and learning
strategies for supervised characterization of coronary
atherosclerotic plaques. In my first study, I proposed an approach
for calcium quantification in contrast-enhanced examinations of the
coronary arteries, potentially eliminating the need for an extra
non-contrast X-ray acquisition. The ambiguity of separation of
calcium from contrast material was solved by using virtual
non-contrast images. Additional attenuation data provided by DECT
provides valuable information for separation of lipid from fibrous
plaque since the change of their attenuation as the energy level
changes is different. My second study proposed these as the input
to supervised learners for a more precise classification of lipid
and fibrous plaques. My last study aimed at automatic segmentation
of coronary arteries characterizing plaque components and lumen on
contrast enhanced monochromatic X-ray images. This required
extraction of features from regions of interests. This study
proposed feature extraction strategies and selection of important
ones. The results show that supervised learning on the proposed
features provides promising results for automatic characterization
of coronary atherosclerotic plaques by DECT.
Subjects/Keywords: Biomedical engineering; Atherosclerosis; Dual Energy Computed Tomography; feature extraction; feature selection
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Yamak, D. (2013). Characterization of Coronary Atherosclerotic Plaques by Dual
Energy Computed Tomography. (Doctoral Dissertation). Arizona State University. Retrieved from http://repository.asu.edu/items/18027
Chicago Manual of Style (16th Edition):
Yamak, Didem. “Characterization of Coronary Atherosclerotic Plaques by Dual
Energy Computed Tomography.” 2013. Doctoral Dissertation, Arizona State University. Accessed February 27, 2021.
http://repository.asu.edu/items/18027.
MLA Handbook (7th Edition):
Yamak, Didem. “Characterization of Coronary Atherosclerotic Plaques by Dual
Energy Computed Tomography.” 2013. Web. 27 Feb 2021.
Vancouver:
Yamak D. Characterization of Coronary Atherosclerotic Plaques by Dual
Energy Computed Tomography. [Internet] [Doctoral dissertation]. Arizona State University; 2013. [cited 2021 Feb 27].
Available from: http://repository.asu.edu/items/18027.
Council of Science Editors:
Yamak D. Characterization of Coronary Atherosclerotic Plaques by Dual
Energy Computed Tomography. [Doctoral Dissertation]. Arizona State University; 2013. Available from: http://repository.asu.edu/items/18027

NSYSU
29.
Liu, Ren-jia.
A Self-Constructing Fuzzy Feature Clustering for Text Categorization.
Degree: Master, Electrical Engineering, 2009, NSYSU
URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0826109-151344
► Feature clustering is a powerful method to reduce the dimensionality of feature vectors for text classification. In this paper, we propose a fuzzy similarity-based self-constructing…
(more)
▼ Feature clustering is a powerful method to reduce the dimensionality of
feature vectors for text classification. In this paper, we propose a fuzzy similarity-based self-constructing algorithm for
feature clustering. The words in the
feature vector of a document set are grouped into clusters based on similarity test. Words that are similar to each other are grouped into the same cluster. Each cluster is characterized by a membership function with statistical mean and deviation. When all the words have been fed in, a desired number of clusters are formed automatically. We then have one extracted
feature for each cluster. The extracted
feature corresponding to a cluster is a weighted combination of the words contained in the cluster.
By this algorithm, the derived membership functions match closely with and describe properly the real distribution of the training data. Besides, the user need not specify the number of extracted features in advance, and trial-and-error for determining the appropriate number of extracted features can then be avoided. 20 Newsgroups data set and Cade 12 web directory are introduced to be our experimental data. We adopt the support vector machine to classify the documents. Experimental results show that our method can run faster and obtain better extracted features than other methods.
Advisors/Committee Members: Chaur-Heh Hsieh (chair), Wen-Yang Lin (chair), Shie-Jue Lee (committee member), Chung-Ming Kuo (chair), Tzung-Pei Hong (chair).
Subjects/Keywords: text classification; feature reduction; feature clustering; feature extraction; fuzzy clustering; fuzzy similarity
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Liu, R. (2009). A Self-Constructing Fuzzy Feature Clustering for Text Categorization. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0826109-151344
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Liu, Ren-jia. “A Self-Constructing Fuzzy Feature Clustering for Text Categorization.” 2009. Thesis, NSYSU. Accessed February 27, 2021.
http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0826109-151344.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Liu, Ren-jia. “A Self-Constructing Fuzzy Feature Clustering for Text Categorization.” 2009. Web. 27 Feb 2021.
Vancouver:
Liu R. A Self-Constructing Fuzzy Feature Clustering for Text Categorization. [Internet] [Thesis]. NSYSU; 2009. [cited 2021 Feb 27].
Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0826109-151344.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Liu R. A Self-Constructing Fuzzy Feature Clustering for Text Categorization. [Thesis]. NSYSU; 2009. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0826109-151344
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

NSYSU
30.
Wu, Bo-sheng.
Acceleration of Image Feature Extraction Algorithms.
Degree: Master, Computer Science and Engineering, 2014, NSYSU
URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0810114-020324
► The description of local features of images has been successfully applied to many areas, including wide baseline matching, object recognition, texture recognition, image retrieval, robot…
(more)
▼ The description of local features of images has been successfully applied to many areas, including wide baseline matching, object recognition, texture recognition, image retrieval, robot localization, video data mining, etc. However, pure software implementations usually cannot achieve the requirement of real-time processing. In this thesis, we present software acceleration of general-purpose computing on graphics processing units (GPGPU) for two popular image
feature extraction/description algorithms, Shift-Invariant
Feature Transform (SIFT) and Speeded-Up Robust
Feature (SURF). Furthermore, several versions of hardware SURF accelerators are also implemented. The four major parts of SIFT are scale-space extrema detection, keypoint localization, orientation assignment, and keypoint description where scale-space extrema detection and keypoint description, the most critical parts, take most of the total execution time. SURF is composed of four major steps: integral image calculation, fast Hessian detection, orientation assignment, and keypoint description. In terms of software implementation, the computation complexity of SURF is significantly reduced compared with that of SIFT. However, hardware acceleration of SURF is still required for real time processing requirement. In this thesis, we slightly modify the original SURF algorithms in order to significantly reduce the hardware complexity for the implementations of fast Hessian detection and keypoint description without sacrificing too much in speed performance. Experimental results of both software and hardware acceleration are also given and compared.
Advisors/Committee Members: Shiann-Rong Kuang (chair), Jih-Ching Chiu (chair), Chuen-Yau Chen (chair), Shen-Fu Hsiao (committee member), Ming-Chih Chen (chair).
Subjects/Keywords: scale-invariant feature transform; Speeded-Up Robust Feature; hardware acceleration; image feature extraction; OpenCL; GPGPU
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share





❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Wu, B. (2014). Acceleration of Image Feature Extraction Algorithms. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0810114-020324
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Wu, Bo-sheng. “Acceleration of Image Feature Extraction Algorithms.” 2014. Thesis, NSYSU. Accessed February 27, 2021.
http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0810114-020324.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Wu, Bo-sheng. “Acceleration of Image Feature Extraction Algorithms.” 2014. Web. 27 Feb 2021.
Vancouver:
Wu B. Acceleration of Image Feature Extraction Algorithms. [Internet] [Thesis]. NSYSU; 2014. [cited 2021 Feb 27].
Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0810114-020324.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Wu B. Acceleration of Image Feature Extraction Algorithms. [Thesis]. NSYSU; 2014. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0810114-020324
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
◁ [1] [2] [3] [4] [5] … [23] ▶
.