subject:(Random forest)

Texas A&M University

1. Ku, Nian-Wei. Integration of Lidar Remote Sensing from Multiple Platforms to Assess Vegetation Biophysical Parameters.

Degree: PhD, Ecosystem Science and Management, 2018, Texas A&M University

URL: http://hdl.handle.net/1969.1/173611

► This research concentrates on using multiple platforms of lidar remote sensing for assessing vegetation biophysical parameters. Airborne and spaceborne light detection and ranging (lidar) (i.e.,… (more)

Subjects/Keywords: Lidar; Forest; Biomass; Random forests

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Ku, N. (2018). Integration of Lidar Remote Sensing from Multiple Platforms to Assess Vegetation Biophysical Parameters. (Doctoral Dissertation). Texas A&M University. Retrieved from http://hdl.handle.net/1969.1/173611

Chicago Manual of Style (16^th Edition):

Ku, Nian-Wei. “Integration of Lidar Remote Sensing from Multiple Platforms to Assess Vegetation Biophysical Parameters.” 2018. Doctoral Dissertation, Texas A&M University. Accessed January 18, 2021. http://hdl.handle.net/1969.1/173611.

MLA Handbook (7^th Edition):

Ku, Nian-Wei. “Integration of Lidar Remote Sensing from Multiple Platforms to Assess Vegetation Biophysical Parameters.” 2018. Web. 18 Jan 2021.

Vancouver:

Ku N. Integration of Lidar Remote Sensing from Multiple Platforms to Assess Vegetation Biophysical Parameters. [Internet] [Doctoral dissertation]. Texas A&M University; 2018. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/1969.1/173611.

Council of Science Editors:

Ku N. Integration of Lidar Remote Sensing from Multiple Platforms to Assess Vegetation Biophysical Parameters. [Doctoral Dissertation]. Texas A&M University; 2018. Available from: http://hdl.handle.net/1969.1/173611

2. Thureborn, Oscar. AI på spårbilbana - Maskinen mot människan .

Degree: Chalmers tekniska högskola / Institutionen för data och informationsteknik, 2020, Chalmers University of Technology

URL: http://hdl.handle.net/20.500.12380/301928

► Artificiell Intelligens blir allt vanligare för att övervaka prestanda hos system. Ofta skickas data från flera system till en molntjänst som sedan behandlar den. Desto… (more)

▼ Artificiell Intelligens blir allt vanligare för att övervaka prestanda hos system. Ofta skickas data från flera system till en molntjänst som sedan behandlar den. Desto fler system som kopplas upp, desto mer data skickas. För att undvika att överbelasta uppkopplingar hos system kan istället datan behandlas direkt på plats. Ekkono har utvecklat ett koncept som de kallar ”AI on the edge”. Detta innebär att maskininlärning sker direkt hos det system som ska tränas istället för att behöva skicka data till en molntjänst eller liknande. Cybercom, som är ett IT-konsultbolag, vill lära sig mer om hur Ekkonos SDK (Software Development Kit) fungerar. Studenterna kom tillsammans med Cybercom och Ekkono fram till idén om skapa ett sk. ”showcase” som kan användas för att öka intresset för deras koncept. Detta realiserades genom att modifiera en bil från en spårbilbana till att bli maskinstyrd och med hjälp av Ekkonos SDK ta bättre och/eller snabbare beslut än människan. Det huvudsakliga syftet med projektet var således att undersöka om den maskinstyrda bilen kunde köra runt en bana snabbare än en bil styrd av en människa. Bilen utrustades med ett accelerometer- och motorstyrningskort samt en Raspberry Pi Zero W, en liten 1GHz enkortsdator som kör ett linuxbaserat operativsystem. På Raspberry Pi Zero W installerades sedan Ekkonos SDK som användes med accelerometern för att prediktera de krafter som skulle komma att påverka bilen och därefter bestämma hur mycket gaspådrag bilen skulle få i nästa steg. Bilen lyckades köra runt banan med hjälp av Ekkonos AI men inte snabbare än vad en människa kunde göra. Detta berodde i stor del på tidsbegränsningar. Konstruktionen av bilen tog mer tid än väntat vilket resulterade i att den tid som kunde läggas ner på att implementera en väl fungerande AI-modell inte räckte till. Dessutom så finns det mycket att önska hos beslutsfattningsprocessen, den processen som tar det predikterade värdet och fattar ett beslut baserat på det. En större utmaning än väntat var också att inte designa programmet på ett sådant sätt att det blir väldigt skräddarsytt för en viss ban-design men inte fungerar på andra typer av banor. AI-modellen som användes var Random forest, vilket är en bra utgångspunkt då den är snabb att ställa upp utan att behöva vikta in-parametrarna. Hade det funnits mer tid till att implementera AI-modellen hade en Multilayer Perceptron modell valts att implementeras istället.

Subjects/Keywords: Artificiell Intelligens; Spårbilbana; Random Forest

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Thureborn, O. (2020). AI på spårbilbana - Maskinen mot människan . (Thesis). Chalmers University of Technology. Retrieved from http://hdl.handle.net/20.500.12380/301928

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Thureborn, Oscar. “AI på spårbilbana - Maskinen mot människan .” 2020. Thesis, Chalmers University of Technology. Accessed January 18, 2021. http://hdl.handle.net/20.500.12380/301928.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Thureborn, Oscar. “AI på spårbilbana - Maskinen mot människan .” 2020. Web. 18 Jan 2021.

Vancouver:

Thureborn O. AI på spårbilbana - Maskinen mot människan . [Internet] [Thesis]. Chalmers University of Technology; 2020. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/20.500.12380/301928.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Thureborn O. AI på spårbilbana - Maskinen mot människan . [Thesis]. Chalmers University of Technology; 2020. Available from: http://hdl.handle.net/20.500.12380/301928

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Waterloo

3. Jin, Jiao. A Random Forest Based Method for Urban Land Cover Classification using LiDAR Data and Aerial Imagery.

Degree: 2012, University of Waterloo

URL: http://hdl.handle.net/10012/6770

► Urban land cover classification has always been crucial due to its ability to link many elements of human and physical environments. Timely, accurate, and detailed… (more)

▼ Urban land cover classification has always been crucial due to its ability to link many elements of human and physical environments. Timely, accurate, and detailed knowledge of the urban land cover information derived from remote sensing data is increasingly required among a wide variety of communities. This surge of interest has been predominately driven by the recent innovations in data, technologies, and theories in urban remote sensing. The development of light detection and ranging (LiDAR) systems, especially incorporated with high-resolution camera component, has shown great potential for urban classification. However, the performance of traditional and widely used classification methods is limited in this context, due to image interpretation complexity. On the other hand, random forests (RF), a newly developed machine learning algorithm, is receiving considerable attention in the field of image classification and pattern recognition. Several studies have shown the advantages of RF in land cover classification. However, few have focused on urban areas by fusion of LiDAR data and aerial images. The performance of the RF based feature selection and classification methods for urban areas was explored and compared to other popular feature selection approach and classifiers. Evaluation was based on several criteria: classification accuracy, impact of different training sample size, and computational speed. LiDAR data and aerial imagery with 0.5-m resolution were used to classify four land categories in the study area located in the City of Niagara Falls (ON, Canada). The results clearly demonstrate that the use of RF improved the classification performance in terms of accuracy and speed. Support vector machines (SVM) based and RF based classifiers showed similar accuracies. However, RF based classifiers were much quicker than SVM based methods. Based on the results from this work, it can be concluded that the RF based method holds great potential for recent and future urban land cover classification problem with LiDAR data and aerial images.

Subjects/Keywords: Urban Land Cover; Random Forest

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Jin, J. (2012). A Random Forest Based Method for Urban Land Cover Classification using LiDAR Data and Aerial Imagery. (Thesis). University of Waterloo. Retrieved from http://hdl.handle.net/10012/6770

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Jin, Jiao. “A Random Forest Based Method for Urban Land Cover Classification using LiDAR Data and Aerial Imagery.” 2012. Thesis, University of Waterloo. Accessed January 18, 2021. http://hdl.handle.net/10012/6770.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Jin, Jiao. “A Random Forest Based Method for Urban Land Cover Classification using LiDAR Data and Aerial Imagery.” 2012. Web. 18 Jan 2021.

Vancouver:

Jin J. A Random Forest Based Method for Urban Land Cover Classification using LiDAR Data and Aerial Imagery. [Internet] [Thesis]. University of Waterloo; 2012. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/10012/6770.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Jin J. A Random Forest Based Method for Urban Land Cover Classification using LiDAR Data and Aerial Imagery. [Thesis]. University of Waterloo; 2012. Available from: http://hdl.handle.net/10012/6770

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Georgia

4. Ganesan, Sivanesan. Regression Leaf Forest.

Degree: 2014, University of Georgia

URL: http://hdl.handle.net/10724/27128

► There are a number of learning methods that provide solutions to classification and regression problems, including Linear Regression, Decision Trees, KNN, and SVMs. These methods… (more)

Subjects/Keywords: Random Forest; Linear Regression

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Ganesan, S. (2014). Regression Leaf Forest. (Thesis). University of Georgia. Retrieved from http://hdl.handle.net/10724/27128

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Ganesan, Sivanesan. “Regression Leaf Forest.” 2014. Thesis, University of Georgia. Accessed January 18, 2021. http://hdl.handle.net/10724/27128.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Ganesan, Sivanesan. “Regression Leaf Forest.” 2014. Web. 18 Jan 2021.

Vancouver:

Ganesan S. Regression Leaf Forest. [Internet] [Thesis]. University of Georgia; 2014. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/10724/27128.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Ganesan S. Regression Leaf Forest. [Thesis]. University of Georgia; 2014. Available from: http://hdl.handle.net/10724/27128

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Melbourne

5. FEDRIGO, MELISSA. Where is the forest carbon?: Characterising and modelling the structure and extent of south-eastern Australian temperate forests for improved estimation of carbon stocks.

Degree: 2015, University of Melbourne

URL: http://hdl.handle.net/11343/57411

► Forests play a vital role in the global carbon cycle as both a source and sink of carbon. Increasingly, remote sensing data is being used… (more)

▼ Forests play a vital role in the global carbon cycle as both a source and sink of carbon. Increasingly, remote sensing data is being used to facilitate the identification, quantification, and management of forest carbon and associated resources at a variety of spatial scales. Efforts to extrapolate carbon estimates from site-specific observations and laboratory experiments to landscape scales require baseline estimates of forest distribution and structure. Model-data synthesis approaches are continually being improved to allow for field observations and remote sensing data to scale carbon estimates from the plot to the landscape scale. In the Central Highlands region of south-eastern Australia, recently suggested as the most carbon dense forests in the world (Keith et al., 2009), carbon stock estimates span wide ranges based on spatially limited field campaigns that have been scaled to the landscape using coarse resolution distribution maps of forest types and homogenising assumptions of forest structure. This study aimed to improve the resolution and accuracy of past studies by characterising and modelling the structure and extent of south-eastern Australian temperate forests for improved estimation of carbon stocks. Plot level uncertainties in carbon estimates were reduced by assessing carbon stocks in multiple above- and belowground forest components, including the first estimates of two dominant tree fern species that occur in the region. Utilising three-dimensional structural information from light detection and ranging (lidar) remote sensing data, hyperspectral remote sensing techniques were used to analyse the lidar data in a novel approach to map forest structure and distribution for these forests. A predictive ecosystem map (PEM) was generated to incorporate species distributions with lidar-measured forest structure to spatially identify the likely distribution of key rainforest and eucalypt stand types in the Central Highlands. Using detailed plot carbon estimates by stand types and the distribution map generated by the PEM, a model-data synthesis approach was used to predict forest carbon at 20 m spatial resolution for the study area. Carbon estimates for all stand types generated by the model were between regional and continental scale carbon predictions for the study area. The important outcomes of this research is a series of new approaches to characterising and modelling the structure and extent of forest ecosystems through the use of both detailed field assessments and remote sensing data. High spatial resolution map outputs of forest stand type distribution, structure, and estimates of carbon can be used by local management authorities as a baseline for informed decision making on managing and reporting the contribution of south-eastern Australian temperate forests to global carbon cycles.

Subjects/Keywords: lidar; remote sensing; forest carbon; forest structure; random forest

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

FEDRIGO, M. (2015). Where is the forest carbon?: Characterising and modelling the structure and extent of south-eastern Australian temperate forests for improved estimation of carbon stocks. (Doctoral Dissertation). University of Melbourne. Retrieved from http://hdl.handle.net/11343/57411

Chicago Manual of Style (16^th Edition):

FEDRIGO, MELISSA. “Where is the forest carbon?: Characterising and modelling the structure and extent of south-eastern Australian temperate forests for improved estimation of carbon stocks.” 2015. Doctoral Dissertation, University of Melbourne. Accessed January 18, 2021. http://hdl.handle.net/11343/57411.

MLA Handbook (7^th Edition):

FEDRIGO, MELISSA. “Where is the forest carbon?: Characterising and modelling the structure and extent of south-eastern Australian temperate forests for improved estimation of carbon stocks.” 2015. Web. 18 Jan 2021.

Vancouver:

FEDRIGO M. Where is the forest carbon?: Characterising and modelling the structure and extent of south-eastern Australian temperate forests for improved estimation of carbon stocks. [Internet] [Doctoral dissertation]. University of Melbourne; 2015. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/11343/57411.

Council of Science Editors:

FEDRIGO M. Where is the forest carbon?: Characterising and modelling the structure and extent of south-eastern Australian temperate forests for improved estimation of carbon stocks. [Doctoral Dissertation]. University of Melbourne; 2015. Available from: http://hdl.handle.net/11343/57411

University of Alberta

6. Zhou,Yi. Persistent Homology on Time series.

Degree: MS, Department of Mathematical and Statistical Sciences, 2016, University of Alberta

URL: https://era.library.ualberta.ca/files/cvx021f40p

► Topology is a useful tool of mathematics studying how objects are related to one another by investigating their qualitative structural properties, such as connectivity and… (more)

Subjects/Keywords: Persistent Homology; Time Series; Random Forest

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Zhou,Yi. (2016). Persistent Homology on Time series. (Masters Thesis). University of Alberta. Retrieved from https://era.library.ualberta.ca/files/cvx021f40p

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Chicago Manual of Style (16^th Edition):

Zhou,Yi. “Persistent Homology on Time series.” 2016. Masters Thesis, University of Alberta. Accessed January 18, 2021. https://era.library.ualberta.ca/files/cvx021f40p.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

MLA Handbook (7^th Edition):

Zhou,Yi. “Persistent Homology on Time series.” 2016. Web. 18 Jan 2021.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Vancouver:

Zhou,Yi. Persistent Homology on Time series. [Internet] [Masters thesis]. University of Alberta; 2016. [cited 2021 Jan 18]. Available from: https://era.library.ualberta.ca/files/cvx021f40p.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Council of Science Editors:

Zhou,Yi. Persistent Homology on Time series. [Masters Thesis]. University of Alberta; 2016. Available from: https://era.library.ualberta.ca/files/cvx021f40p

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Vanderbilt University

7. Knorr, David Christopher. Using Machine Learning to Identify and Predict Gentrification in Nashville, Tennessee.

Degree: MS, Earth and Environmental Sciences, 2019, Vanderbilt University

URL: http://hdl.handle.net/1803/13285

► Gentrification is a polarizing and elusive type of neighborhood change that disproportionately threatens our community’s most vulnerable populations. The lived consequences of gentrification have merited… (more)

▼ Gentrification is a polarizing and elusive type of neighborhood change that disproportionately threatens our community’s most vulnerable populations. The lived consequences of gentrification have merited a substantial amount of academic focus over the course of more than five decades. This paper takes a critical examination of the prescriptive frameworks that previous researchers have used to distinguish gentrification, identifying errors of inclusion, exclusion, as well as major methodological inconsistencies. We advance a k-means clustering approach of six change variables to identify four dominant trajectories of neighborhood change in Nashville, TN (Davidson County) between 2000 and 2016. One specific typology indicated the tell-tale patterns of gentrification and evidence for residential displacement in 13% of inner-city census tracts. A significant join-count statistic revealed that these change typologies were clustered spatially; the observed spatial phenomena gives promise to the potential to predict gentrification as a rational process. We used these outcomes to train a random forest binary classification model to predict susceptibility to gentrification based on starting housing, demographic, transportation, amenity, and locational characteristics. The mapped predictions of gentrification reveal continuing gentrification in south and east Nashville as well as possible expansion beyond previously identified areas, predominantly along highway corridors to the north and southeast where the majority of the affordable housing stock remains. This research contributes to the quantitative efforts to identify gentrification by advancing a more holistic and less biased alternative. This work also contributes to the forward-looking literature on gentrification. It is designed to serve communities as well as policymakers to optimize intervention strategies in an effort to increase equitable development and socially just cities. Advisors/Committee Members: Jonathan Gilligan (committee member), Janey Camp (committee member).

Subjects/Keywords: machine learning; random forest; spatial analysis; Gentrification

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Knorr, D. C. (2019). Using Machine Learning to Identify and Predict Gentrification in Nashville, Tennessee. (Thesis). Vanderbilt University. Retrieved from http://hdl.handle.net/1803/13285

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Knorr, David Christopher. “Using Machine Learning to Identify and Predict Gentrification in Nashville, Tennessee.” 2019. Thesis, Vanderbilt University. Accessed January 18, 2021. http://hdl.handle.net/1803/13285.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Knorr, David Christopher. “Using Machine Learning to Identify and Predict Gentrification in Nashville, Tennessee.” 2019. Web. 18 Jan 2021.

Vancouver:

Knorr DC. Using Machine Learning to Identify and Predict Gentrification in Nashville, Tennessee. [Internet] [Thesis]. Vanderbilt University; 2019. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/1803/13285.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Knorr DC. Using Machine Learning to Identify and Predict Gentrification in Nashville, Tennessee. [Thesis]. Vanderbilt University; 2019. Available from: http://hdl.handle.net/1803/13285

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

8. Sieben, Wiebke. Datengestützte Regelgenerierung für die Alarmgebung im Online-Monitoring von Intensivpatienten.

Degree: 2009, Technische Universität Dortmund

URL: http://hdl.handle.net/2003/26009

► In dieser Dissertation wird die Eignung datengestützt generierter Alarmregeln für die Überwachung von Patienten auf der Intensivstation untersucht. Hierfür wird ein bekantes Klassifikationsverfahren modifiziert, so… (more)

▼ In dieser Dissertation wird die Eignung datengestützt generierter Alarmregeln für die Überwachung von Patienten auf der Intensivstation untersucht. Hierfür wird ein bekantes Klassifikationsverfahren modifiziert, so dass es Alarmregeln mit einer wählbar hohen Sensitivität erzeugt. Dieses neue Verfahren wird online an Patientenmonitoring-Daten getestet. Die Reduktion von Fehlalarmen im Patientenmonitoring auf der Intensivstation ist aufgrund von Fehlalarmraten von bis zu 90% notwendig. Eine einfache Schwellwertüberwachung der Vitalparameter ist jedoch trotz wissenschaftlicher Fortschritte gegenwärtiger Stand der Technik. In einer Anforderungsanalyse werden Bedingungen für die überführbarkeit neuer Verfahren in die Praxis ermittelt, unter deren Berücksichtigung ein Klassifikationsverfahren zur Alarmregelgenerierung gewählt wird. Mit dessen Hilfe können die Alarme des Standard-Patientenmonitors validiert, d.h. unterdrückt oder ausgegeben werden. Hier bilden umfangreiche Aufzeichnungen von Daten eines Standard-Patientenmonitors sowie klinische Annotationen die benötigte Datengrundlage. In der Datenvorverarbeitung werden, entsprechend der Vorgehensweise von ärzten, Charakteristika konstruiert, die den gesundheitlichen Verlauf eines Patienten kurz vor Auslösung eines Alarms wiedergeben. Sie werden zum einen aus lokalen linearen Regressionen und zum anderen aus Wavelet-Zerlegungen abgeleitet. Übliche Klassifikationsverfahren eignen sich nicht, um Alarmregeln mit einer wählbaren und kontrollierbaren Zielsensitivität zu generieren. Aus diesem Grund wird das häufig genutzte Klassifikationsverfahren "Random Forest" gemäß dem Neyman-Pearson-Prinzip modifiziert, um die Konstruktion von Alarmregeln mit einer vorgegebenen Sensitivität zu ermöglichen. Die Eignung dieses Verfahrens wird für Zielsensitivitäten von 95% und 98% gezeigt. Die vorgegebenen Sensitivitäten werden in den betrachteten Fällen im arithmetischen Mittel und Median bei geringer Variabilität in den Ergebnissen erreicht. Gleichzeitig können die Fehlalarme um bis zu 55% im Median reduziert werden. Charakteristika des gesundheitlichen Verlaufs können diese Ergebnisse nicht weiter steigern. Die Allgemeingültigkeit der erzeugten Alarmregeln wird anhand einer nach Patienten stratifizierten Stichprobe überprüft. In diesem Fall bleibt die Reduktion der Fehlalarme bei hohen Sensitivitäten deutlich hinter den bisherigen Ergebnissen zurück. Dies deutet darauf hin, dass die vorliegenden Daten nicht ausreichen, um allgemein gültige Regeln zu generieren. Das im Rahmen dieser Arbeit entwickelte Verfahren kann bei Erhebung weiterer Daten zur Alarmregelgenerierung für die Patientenüberwachung genutzt werden. Das vorgeschlagene Konzept, die Klassifikations-Entscheidung eines gebaggten Ensembles von Klassifizierern analog zu einem Neyman-Pearson-Test zu bilden, ist auf neue Fragestellungen leicht übertragbar und daher in vielen Anwendungsgebieten von Interesse. Advisors/Committee Members: Gather, Ursula.

Subjects/Keywords: Klassifikation; Patienten-Monitoring; Random Forest; 310

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Sieben, W. (2009). Datengestützte Regelgenerierung für die Alarmgebung im Online-Monitoring von Intensivpatienten. (Thesis). Technische Universität Dortmund. Retrieved from http://hdl.handle.net/2003/26009

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Sieben, Wiebke. “Datengestützte Regelgenerierung für die Alarmgebung im Online-Monitoring von Intensivpatienten.” 2009. Thesis, Technische Universität Dortmund. Accessed January 18, 2021. http://hdl.handle.net/2003/26009.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Sieben, Wiebke. “Datengestützte Regelgenerierung für die Alarmgebung im Online-Monitoring von Intensivpatienten.” 2009. Web. 18 Jan 2021.

Vancouver:

Sieben W. Datengestützte Regelgenerierung für die Alarmgebung im Online-Monitoring von Intensivpatienten. [Internet] [Thesis]. Technische Universität Dortmund; 2009. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/2003/26009.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Sieben W. Datengestützte Regelgenerierung für die Alarmgebung im Online-Monitoring von Intensivpatienten. [Thesis]. Technische Universität Dortmund; 2009. Available from: http://hdl.handle.net/2003/26009

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

9. Voigt, Tobias. Threshold optimization and variable construction for classification in the MAGIC and FACT experiments.

Degree: 2014, Technische Universität Dortmund

URL: http://dx.doi.org/10.17877/DE290R-14114

► In the MAGIC and FACT experiments, random forests are usually used for a classification of a gamma ray signal and hadronic background. Random forests use… (more)

Subjects/Keywords: Classification; Astronomy; Random forest; 310; 570

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Voigt, T. (2014). Threshold optimization and variable construction for classification in the MAGIC and FACT experiments. (Doctoral Dissertation). Technische Universität Dortmund. Retrieved from http://dx.doi.org/10.17877/DE290R-14114

Chicago Manual of Style (16^th Edition):

Voigt, Tobias. “Threshold optimization and variable construction for classification in the MAGIC and FACT experiments.” 2014. Doctoral Dissertation, Technische Universität Dortmund. Accessed January 18, 2021. http://dx.doi.org/10.17877/DE290R-14114.

MLA Handbook (7^th Edition):

Voigt, Tobias. “Threshold optimization and variable construction for classification in the MAGIC and FACT experiments.” 2014. Web. 18 Jan 2021.

Vancouver:

Voigt T. Threshold optimization and variable construction for classification in the MAGIC and FACT experiments. [Internet] [Doctoral dissertation]. Technische Universität Dortmund; 2014. [cited 2021 Jan 18]. Available from: http://dx.doi.org/10.17877/DE290R-14114.

Council of Science Editors:

Voigt T. Threshold optimization and variable construction for classification in the MAGIC and FACT experiments. [Doctoral Dissertation]. Technische Universität Dortmund; 2014. Available from: http://dx.doi.org/10.17877/DE290R-14114

10. Barroso, João António Araújo. Modelo preditivo para o risco de readmissão hospitalar .

Degree: 2017, Universidade de Aveiro

URL: http://hdl.handle.net/10773/25092

► O desenvolvimento deste projeto passou por 4 fases: duas pesquisas preliminares em momentos distintos; construção e avaliação de modelos preditivos; desenvolvimento de uma aplicação web… (more)

▼ O desenvolvimento deste projeto passou por 4 fases: duas pesquisas preliminares em momentos distintos; construção e avaliação de modelos preditivos; desenvolvimento de uma aplicação web com a solução de um desses modelos. A primeira fase do projeto consistiu numa pesquisa em que o objetivo foi a recolha de um grande número de artigos relacionados com problemáticas no meio hospitalar. Para esta fase dedicou-se cerca de um mês de trabalho. Desta primeira etapa, determinou-se o objetivo do projeto: o desenvolvimento de um modelo preditivo para o risco de readmissão hospitalar. A segunda fase do projeto foi sem dúvida a que mais tempo se despendeu, onde se dedicaram mais de dois meses de trabalho. Para esta fase foi disponibilizada uma base de dados hospitalar real (de vários hospitais) com cerca de um milhão de observações e centenas de variáveis. Esta fase pode ser dividida em várias etapas: numa etapa inicial procurou-se compreender e resolver incoerências através de modificações e transformações da base de dados original; na segunda fase efetuaram-se modificações ao formato de algumas variáveis e criaram-se outras novas variáveis com recurso às variáveis já existentes; na terceira etapa, após finalizadas as transformações à base de dados, selecionaram-se alguns conjuntos de variáveis por ordem de significância; na última fase construiram-se e testaram-se vários modelos random forest com os conjuntos de treino selecionados na etapa anterior. Na a terceira fase, o objetivo englobava selecionar uma tecnologia Machine Learning (ML) para posterior desenvolvimento de uma aplicação web. Assim, procedeu-se a uma nova pesquisa sobre tecnologias ML, nomeadamente o Apache Spark, o H2O, o H2O Sparkling Water, o Microsoft Azure ML e o OpenCPU. Para esta fase, foi dedicado cerca de um mês de trabalho. Após a pesquisa e decisão da tecnologia a utilizar, desenvolveu-se uma aplicação web. Mais uma vez, foi dedicado cerca de um mês de trabalho para se finalizar esta fase. As fases de trabalho do estágio seguiram a ordem temporal acima descrita, contudo foram desenvolvidos outros trabalhos complementares, como por exemplo, a criação de dashboards usando o software Microsoft Power BI. Para além do que foi mencionado, sempre que existiu oportunidade, discutiuse informalmente com trabalhadores desta área (maioritariamente médicos) acerca do tema, de forma a compreender melhor o problema e descobrir a melhor forma de o abordar. Advisors/Committee Members: Silva, Luís Miguel Almeida da (advisor), Marques, Bernardo (advisor).

Subjects/Keywords: Random forest; Readmissão hospitalar; OpenCPU; Modelo preditivo

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Barroso, J. A. A. (2017). Modelo preditivo para o risco de readmissão hospitalar . (Thesis). Universidade de Aveiro. Retrieved from http://hdl.handle.net/10773/25092

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Barroso, João António Araújo. “Modelo preditivo para o risco de readmissão hospitalar .” 2017. Thesis, Universidade de Aveiro. Accessed January 18, 2021. http://hdl.handle.net/10773/25092.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Barroso, João António Araújo. “Modelo preditivo para o risco de readmissão hospitalar .” 2017. Web. 18 Jan 2021.

Vancouver:

Barroso JAA. Modelo preditivo para o risco de readmissão hospitalar . [Internet] [Thesis]. Universidade de Aveiro; 2017. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/10773/25092.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Barroso JAA. Modelo preditivo para o risco de readmissão hospitalar . [Thesis]. Universidade de Aveiro; 2017. Available from: http://hdl.handle.net/10773/25092

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

KTH

11. Röhss, Josefine. A Statistical Framework for Classification of Tumor Type from microRNA Data.

Degree: Mathematical Statistics, 2016, KTH

URL: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-191990

►

Hepatocellular carcinoma (HCC) is a type of liver cancer with low survival rate, not least due to the difficulty of diagnosing it in an… (more)

▼

Hepatocellular carcinoma (HCC) is a type of liver cancer with low survival rate, not least due to the difficulty of diagnosing it in an early stage. The objective of this thesis is to build a random forest classification method based on microRNA (and messenger RNA) expression profiles from patients with HCC. The main purpose is to be able to distinguish between tumor samples and normal samples by measuring the miRNA expression. If successful, this method can be used to detect HCC at an earlier stage and to design new therapeutics. The microRNAs and messenger RNAs which have a significant difference in expression between tumor samples and normal samples are selected for building random forest classification models. These models are then tested on paired samples of tumor and surrounding normal tissue from patients with HCC. The results show that the classification models built for classifying tumor and normal samples have high prediction accuracy and hence show high potential for using microRNA and messenger RNA expression levels for diagnosis of HCC.

Hepatocellulär cancer (HCC) är en typ av levercancer med mycket låg överlevnadsgrad, inte minst på grund av svårigheten att diagnosticera i ett tidigt skede. Syftet med det här projektet är att bygga en klassificeringsmodell med random forest, baserad på uttrycksprofiler av mikroRNA (och budbärar-RNA) från patienter med HCC. Målet är att kunna skilja mellan tumörprover och normala prover genom att mäta uttrycket av mikroRNA. Om detta mål uppnås kan metoden användas för att upptäcka HCC i ett tidigare skede och för att utveckla nya läkemedel. De mikroRNA och budbärar-RNA som har en signifikant skillnad i uttryck mellan prover från tumörvävnad och intilliggande normal vävnad väljs ut för att bygga klassificaringsmodeller med random forest. Dessa modeller testas sedan på parade prover av tumörvävnad och intilliggande vävnad från patienter med HCC. Resultaten visar att modeller som byggs med denna metod kan klassificera tumörprover och normala prover med hög noggrannhet. Det finns således stor potential för att använda uttrycksprofiler från mikroRNA och budbärar-RNA för att diagnosticera HCC.

Subjects/Keywords: miRNA; mRNA; random forest; classification; HCC; diagnosis

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Röhss, J. (2016). A Statistical Framework for Classification of Tumor Type from microRNA Data. (Thesis). KTH. Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-191990

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Röhss, Josefine. “A Statistical Framework for Classification of Tumor Type from microRNA Data.” 2016. Thesis, KTH. Accessed January 18, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-191990.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Röhss, Josefine. “A Statistical Framework for Classification of Tumor Type from microRNA Data.” 2016. Web. 18 Jan 2021.

Vancouver:

Röhss J. A Statistical Framework for Classification of Tumor Type from microRNA Data. [Internet] [Thesis]. KTH; 2016. [cited 2021 Jan 18]. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-191990.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Röhss J. A Statistical Framework for Classification of Tumor Type from microRNA Data. [Thesis]. KTH; 2016. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-191990

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Delft University of Technology

12. Kaandorp, Mikael (author). Machine Learning for Data-Driven RANS Turbulence Modelling.

Degree: 2018, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:f833e151-7c0f-414c-8217-5af783c88474

►

The application of machine learning algorithms as data-driven turbulence modelling tools for Reynolds Averaged Navier-Stokes (RANS) simulations is presented. A novel machine learning algorithm, called… (more)

Subjects/Keywords: machine learning; RANS; Random Forest; Turbulence

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Kaandorp, M. (. (2018). Machine Learning for Data-Driven RANS Turbulence Modelling. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:f833e151-7c0f-414c-8217-5af783c88474

Chicago Manual of Style (16^th Edition):

Kaandorp, Mikael (author). “Machine Learning for Data-Driven RANS Turbulence Modelling.” 2018. Masters Thesis, Delft University of Technology. Accessed January 18, 2021. http://resolver.tudelft.nl/uuid:f833e151-7c0f-414c-8217-5af783c88474.

MLA Handbook (7^th Edition):

Kaandorp, Mikael (author). “Machine Learning for Data-Driven RANS Turbulence Modelling.” 2018. Web. 18 Jan 2021.

Vancouver:

Kaandorp M(. Machine Learning for Data-Driven RANS Turbulence Modelling. [Internet] [Masters thesis]. Delft University of Technology; 2018. [cited 2021 Jan 18]. Available from: http://resolver.tudelft.nl/uuid:f833e151-7c0f-414c-8217-5af783c88474.

Council of Science Editors:

Kaandorp M(. Machine Learning for Data-Driven RANS Turbulence Modelling. [Masters Thesis]. Delft University of Technology; 2018. Available from: http://resolver.tudelft.nl/uuid:f833e151-7c0f-414c-8217-5af783c88474

University of Southern California

13. Zhu, Xun. Identifying important microRNAs in progression of breast cancer.

Degree: MS, Applied Mathematics, 2014, University of Southern California

URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/435497/rec/3334

► Stefan Wuchty et. al. from PLOS summarized a workflow to identify important miRs of pathways for a type of tumor, which uses GSEA to measure… (more)

Subjects/Keywords: microRNA; GSEA; random‐forest; p‐value

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Zhu, X. (2014). Identifying important microRNAs in progression of breast cancer. (Masters Thesis). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/435497/rec/3334

Chicago Manual of Style (16^th Edition):

Zhu, Xun. “Identifying important microRNAs in progression of breast cancer.” 2014. Masters Thesis, University of Southern California. Accessed January 18, 2021. http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/435497/rec/3334.

MLA Handbook (7^th Edition):

Zhu, Xun. “Identifying important microRNAs in progression of breast cancer.” 2014. Web. 18 Jan 2021.

Vancouver:

Zhu X. Identifying important microRNAs in progression of breast cancer. [Internet] [Masters thesis]. University of Southern California; 2014. [cited 2021 Jan 18]. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/435497/rec/3334.

Council of Science Editors:

Zhu X. Identifying important microRNAs in progression of breast cancer. [Masters Thesis]. University of Southern California; 2014. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/435497/rec/3334

University of Cambridge

14. Bland, Matthew Paul. Targeting domestic abuse by mining police records.

Degree: PhD, 2020, University of Cambridge

URL: https://doi.org/10.17863/CAM.46479 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.793089

► This dissertation presents findings from analyses of three large datasets of domestic abuse records sourced from multiple police forces in England and Wales. It seeks… (more)

▼ This dissertation presents findings from analyses of three large datasets of domestic abuse records sourced from multiple police forces in England and Wales. It seeks to address research questions in relation to the extent of repeat and serial abuse, concentration and escalation of harm, and the forecasting of future serious crimes. Using a variety of statistics, it shows that most victims and offenders report domestic abuse to the police forces just once in a multi-year period. Among these cases however, are many of the individuals who comprise very small 'power few' groups that account for most of total crime harm. Using the Cambridge Crime Harm Index as the instrument of measurement, analysis shows that 80% of cumulative harm is attributable to fewer than 3% of victims and offenders, and almost half of these most harmed victims or harmful offenders have only one record of domestic abuse in police databases. Police forces are therefore presented with a substantial challenge when it comes to preventing serious harm from domestic abuse, because in more than 40% of the most harmful cases they have not dealt with the victims or offenders of domestic abuse before. Furthermore, among the victims and offenders who are linked to multiple records of domestic abuse, analysis detects no pattern of escalating severity. In fact, the first crime reported is, on average, the most harmful domestic crime reported to the police. This runs contrary to popular theories of escalation and further illustrates the forecasting challenge facing police agencies. Contemporary harm reduction strategies have placed some emphasis on the management of serial perpetrators of abuse, but analysis shows that these do not offer a complete solution for harm reduction either. These analyses show that serial offenders account for only between 10% and 15% of all domestic offenders and contribute no more to the 'power few' than repeat offenders who have just one victim. However, analysis of the non-domestic crime records of domestic offenders does show that serial perpetrators are less specialised in domestic abuse than repeat or single-time offenders - they commit more non-domestic types of crime and account for more total crime harm overall. Serial and repeat offenders with the greatest generalist tendencies were shown to be attributed to the most domestic abuse harm of any domestic offender types, indicating potential relevance to non-domestic offending records in the pursuit of predicting serious domestic crimes. How then, might police agencies seek to identify the most harmful cases before they occur? This research explores a large bank of records relating to arrests for any type of crime, using a statistical model created by a supervised machine learning algorithm. This model processes each arrestee every time they enter custody and using predictors from 35 pieces of information primarily concerning the prior offending history of the arrestee, generates a forecast of future arrest for a domestic crime within two years. The forecast has three…

Subjects/Keywords: Domestic Abuse; Police Data; Random Forest

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Bland, M. P. (2020). Targeting domestic abuse by mining police records. (Doctoral Dissertation). University of Cambridge. Retrieved from https://doi.org/10.17863/CAM.46479 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.793089

Chicago Manual of Style (16^th Edition):

Bland, Matthew Paul. “Targeting domestic abuse by mining police records.” 2020. Doctoral Dissertation, University of Cambridge. Accessed January 18, 2021. https://doi.org/10.17863/CAM.46479 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.793089.

MLA Handbook (7^th Edition):

Bland, Matthew Paul. “Targeting domestic abuse by mining police records.” 2020. Web. 18 Jan 2021.

Vancouver:

Bland MP. Targeting domestic abuse by mining police records. [Internet] [Doctoral dissertation]. University of Cambridge; 2020. [cited 2021 Jan 18]. Available from: https://doi.org/10.17863/CAM.46479 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.793089.

Council of Science Editors:

Bland MP. Targeting domestic abuse by mining police records. [Doctoral Dissertation]. University of Cambridge; 2020. Available from: https://doi.org/10.17863/CAM.46479 ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.793089

University of Montana

15. Elmore, Nathan J. CLASSIFYING EMOTION USING STREAMING OF PHYSIOLOGICAL CORRELATES OF EMOTION.

Degree: MS, 2012, University of Montana

URL: https://scholarworks.umt.edu/etd/199

► The ability for a computer to recognize emotions would have many uses. In the field of human-computer interaction, it would be useful if computers could… (more)

Subjects/Keywords: emotion; machine learning; random forest; streaming

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Elmore, N. J. (2012). CLASSIFYING EMOTION USING STREAMING OF PHYSIOLOGICAL CORRELATES OF EMOTION. (Masters Thesis). University of Montana. Retrieved from https://scholarworks.umt.edu/etd/199

Chicago Manual of Style (16^th Edition):

Elmore, Nathan J. “CLASSIFYING EMOTION USING STREAMING OF PHYSIOLOGICAL CORRELATES OF EMOTION.” 2012. Masters Thesis, University of Montana. Accessed January 18, 2021. https://scholarworks.umt.edu/etd/199.

MLA Handbook (7^th Edition):

Elmore, Nathan J. “CLASSIFYING EMOTION USING STREAMING OF PHYSIOLOGICAL CORRELATES OF EMOTION.” 2012. Web. 18 Jan 2021.

Vancouver:

Elmore NJ. CLASSIFYING EMOTION USING STREAMING OF PHYSIOLOGICAL CORRELATES OF EMOTION. [Internet] [Masters thesis]. University of Montana; 2012. [cited 2021 Jan 18]. Available from: https://scholarworks.umt.edu/etd/199.

Council of Science Editors:

Elmore NJ. CLASSIFYING EMOTION USING STREAMING OF PHYSIOLOGICAL CORRELATES OF EMOTION. [Masters Thesis]. University of Montana; 2012. Available from: https://scholarworks.umt.edu/etd/199

Penn State University

16. Xia, Zhiyue. HARNESSING THE POWER OF GEOSPATIAL DATA WITH RANDOM FOREST TO FORECAST GYPSY MOTH OUTBREAK.

Degree: 2018, Penn State University

URL: https://submit-etda.libraries.psu.edu/catalog/15704zzx13

► The gypsy moth (Lymantria dispar) is a non-native forest pest that was introduced to the USA in 1869. Since then it has spread continuously across… (more)

▼ The gypsy moth (Lymantria dispar) is a non-native forest pest that was introduced to the USA in 1869. Since then it has spread continuously across most of the northeastern US. Larvae of this insect prefer feeding on oak species, although other species may also serve as host trees. During an outbreak, larvae defoliate forests across large regions and repeated defoliation can predispose the trees to attacks by secondary insect pests or fungal infections causing tree mortality. Gypsy moth outbreaks are episodic and are difficult to predict. Development of forecasting models remains a challenge despite their potential usefulness in effectively mobilizing resources to deal with the outbreaks. Previous studies indicate that vegetation attributes measured through remote sensing, terrain, and climate characteristics influence the likelihood of gypsy moth outbreaks. In addition, temporal and spatial variables describing the cyclic and spatial patterns of the outbreaks could be very valuable in forecasting outbreaks. In this thesis, a model is developed to forecast gypsy moth outbreaks using Pennsylvania as a case study. Systematic sampling was used to locate 5,042 sample pixels across forest areas of Pennsylvania and focus on defoliation episodes during the time period 2000-2016 to develop the model. For each pixel, a large suite of temporal and spatial predictor variables is derived from inventory data, climate, topography, and remote sensing measures of vegetation status, while the occurrence of defoliation is obtained from annual defoliation sketch maps. Machine learning modeling algorithm Random Forests was used in this study, which has a well-documented predictive ability and can deal with a large number of variables. The model performance is assessed by hindcasting defoliations in 1985, 1990 and 1995, and by cross validation leaving out one year of the fit dataset at a time. An accurate forecasting model is of critical importance for projecting the spatial extent of future defoliations and for forest management planning. Advisors/Committee Members: Douglas A Miller, Thesis Advisor/Co-Advisor, Laura P Leites, Thesis Advisor/Co-Advisor, Shelby Fleischer, Committee Member.

Subjects/Keywords: Gypsy moth; Random Forest; Random Forests; Forest disturbance; Spatial modeling; Ecological modeling

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Xia, Z. (2018). HARNESSING THE POWER OF GEOSPATIAL DATA WITH RANDOM FOREST TO FORECAST GYPSY MOTH OUTBREAK. (Thesis). Penn State University. Retrieved from https://submit-etda.libraries.psu.edu/catalog/15704zzx13

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Xia, Zhiyue. “HARNESSING THE POWER OF GEOSPATIAL DATA WITH RANDOM FOREST TO FORECAST GYPSY MOTH OUTBREAK.” 2018. Thesis, Penn State University. Accessed January 18, 2021. https://submit-etda.libraries.psu.edu/catalog/15704zzx13.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Xia, Zhiyue. “HARNESSING THE POWER OF GEOSPATIAL DATA WITH RANDOM FOREST TO FORECAST GYPSY MOTH OUTBREAK.” 2018. Web. 18 Jan 2021.

Vancouver:

Xia Z. HARNESSING THE POWER OF GEOSPATIAL DATA WITH RANDOM FOREST TO FORECAST GYPSY MOTH OUTBREAK. [Internet] [Thesis]. Penn State University; 2018. [cited 2021 Jan 18]. Available from: https://submit-etda.libraries.psu.edu/catalog/15704zzx13.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Xia Z. HARNESSING THE POWER OF GEOSPATIAL DATA WITH RANDOM FOREST TO FORECAST GYPSY MOTH OUTBREAK. [Thesis]. Penn State University; 2018. Available from: https://submit-etda.libraries.psu.edu/catalog/15704zzx13

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Brno University of Technology

17. Jurák, Martin. Detekce objektů na GPU: Object Detection on GPU.

Degree: 2019, Brno University of Technology

URL: http://hdl.handle.net/11012/52221

► This thesis is focused on the acceleration of Random Forest object detection in an image. Random Forest detector is an ensemble of independently evaluated random… (more)

Subjects/Keywords: Detekce objektů; GPGPU; GPU; OpenCL; Random Forest; Object detection; GPGPU; GPU; OpenCL; Random Forest

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Jurák, M. (2019). Detekce objektů na GPU: Object Detection on GPU. (Thesis). Brno University of Technology. Retrieved from http://hdl.handle.net/11012/52221

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Jurák, Martin. “Detekce objektů na GPU: Object Detection on GPU.” 2019. Thesis, Brno University of Technology. Accessed January 18, 2021. http://hdl.handle.net/11012/52221.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Jurák, Martin. “Detekce objektů na GPU: Object Detection on GPU.” 2019. Web. 18 Jan 2021.

Vancouver:

Jurák M. Detekce objektů na GPU: Object Detection on GPU. [Internet] [Thesis]. Brno University of Technology; 2019. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/11012/52221.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Jurák M. Detekce objektů na GPU: Object Detection on GPU. [Thesis]. Brno University of Technology; 2019. Available from: http://hdl.handle.net/11012/52221

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Delft University of Technology

18. van Schetsen, Anouk (author). Impact of graph-based features on Bitcoin prices.

Degree: 2019, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:363d443c-64f6-4c35-9671-4092aa334923

►

Predicting the trends in Bitcoin market prices is a very challenging task due to the many uncertainties and variables influencing the market value. The market… (more)

▼

Predicting the trends in Bitcoin market prices is a very challenging task due to the many uncertainties and variables influencing the market value. The market is susceptible to quick changes, causing seemingly random fluctuations in the Bitcoin price. Due to the chaotic and highly volatile nature of Bitcoin behavior, investments come with high risk. To minimize the risk involved, knowledge of the Bitcoin price movement in the future is desirable. Different studies have shown that Machine Learning algorithms can predict, to varying degrees, the price fluctuations of Bitcoin. However, most researches do not explore the relationship between the price and other features outside the transaction network, such as market capitalization, Bitcoin mining speed, or entity behavior. Also, most of the features are extracted from the network level, which means obtaining the number of transactions, users, Bitcoins mined, etc. In this research, we focus on additional features, such as features outside the transaction network and node-based features inside the transaction network, which could improve the price prediction of Bitcoin. The investigated features are the “fairness and goodness” measure and the “1-ARW-betweenness cen- trality” measure. Fairness and goodness are entity behavior measures. The goodness of a Bitcoin address captures how much this address is liked/trusted by other addresses, while the fairness of a Bitcoin address captures how fair the address is in rating other addresses’ likeability or trust level. The 1-ARW-betweenness centrality is a feature based on absorbing random walks. The feature captures the extent to which a Bitcoin address has control over the money flow between different addresses. A benchmark, based on the machine learning algorithm Random Forest with commonly used features, is used to test the impact of the additional features. The Random Forest tries to predict the sign (up-down movement) of the price per day, using data from the two previous days. Comparing this benchmark with a similar model, but then including the additional features, will gain more information about how these additional features influence the Bitcoin price.

Applied Mathematics | Financial Engineering

Advisors/Committee Members: Oosterlee, Kees (mentor), Delft University of Technology (degree granting institution).

Subjects/Keywords: Machine Learning; Random Forest; Bitcoin; random walk; graph analysis

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

van Schetsen, A. (. (2019). Impact of graph-based features on Bitcoin prices. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:363d443c-64f6-4c35-9671-4092aa334923

Chicago Manual of Style (16^th Edition):

van Schetsen, Anouk (author). “Impact of graph-based features on Bitcoin prices.” 2019. Masters Thesis, Delft University of Technology. Accessed January 18, 2021. http://resolver.tudelft.nl/uuid:363d443c-64f6-4c35-9671-4092aa334923.

MLA Handbook (7^th Edition):

van Schetsen, Anouk (author). “Impact of graph-based features on Bitcoin prices.” 2019. Web. 18 Jan 2021.

Vancouver:

van Schetsen A(. Impact of graph-based features on Bitcoin prices. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Jan 18]. Available from: http://resolver.tudelft.nl/uuid:363d443c-64f6-4c35-9671-4092aa334923.

Council of Science Editors:

van Schetsen A(. Impact of graph-based features on Bitcoin prices. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:363d443c-64f6-4c35-9671-4092aa334923

University of Edinburgh

19. Fedrigo, Melissa. Estimating Biomass in the Mountain Regions of Bwindi Impenetrable National Park, Uganda using Radar and Optical Remote Sensing.

Degree: 2009, University of Edinburgh

URL: http://hdl.handle.net/1842/3094

► Field measured estimates of aboveground biomass (AGB) for 15 transects in Bwindi Impenetrable National Park (BINP), Uganda were used to generate a number of prediction… (more)

Subjects/Keywords: biomass; remote sensing; random forest; tropical forest; carbon

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Fedrigo, M. (2009). Estimating Biomass in the Mountain Regions of Bwindi Impenetrable National Park, Uganda using Radar and Optical Remote Sensing. (Thesis). University of Edinburgh. Retrieved from http://hdl.handle.net/1842/3094

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Fedrigo, Melissa. “Estimating Biomass in the Mountain Regions of Bwindi Impenetrable National Park, Uganda using Radar and Optical Remote Sensing.” 2009. Thesis, University of Edinburgh. Accessed January 18, 2021. http://hdl.handle.net/1842/3094.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Fedrigo, Melissa. “Estimating Biomass in the Mountain Regions of Bwindi Impenetrable National Park, Uganda using Radar and Optical Remote Sensing.” 2009. Web. 18 Jan 2021.

Vancouver:

Fedrigo M. Estimating Biomass in the Mountain Regions of Bwindi Impenetrable National Park, Uganda using Radar and Optical Remote Sensing. [Internet] [Thesis]. University of Edinburgh; 2009. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/1842/3094.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Fedrigo M. Estimating Biomass in the Mountain Regions of Bwindi Impenetrable National Park, Uganda using Radar and Optical Remote Sensing. [Thesis]. University of Edinburgh; 2009. Available from: http://hdl.handle.net/1842/3094

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

NSYSU

20. Kuo, Bo-Wen. Interpretable representation learning based on Deep Rule Forests.

Degree: Master, Information Management, 2018, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727118-134901

► The spirit of tree-based methods is to learn rules. A large number of machine learning techniques are tree-based. More complicated tree learners may result in… (more)

Subjects/Keywords: Rule Learning; Random Forest; Representation Learning; Interpretability; Deep Rule Forest

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Kuo, B. (2018). Interpretable representation learning based on Deep Rule Forests. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727118-134901

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Kuo, Bo-Wen. “Interpretable representation learning based on Deep Rule Forests.” 2018. Thesis, NSYSU. Accessed January 18, 2021. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727118-134901.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Kuo, Bo-Wen. “Interpretable representation learning based on Deep Rule Forests.” 2018. Web. 18 Jan 2021.

Vancouver:

Kuo B. Interpretable representation learning based on Deep Rule Forests. [Internet] [Thesis]. NSYSU; 2018. [cited 2021 Jan 18]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727118-134901.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Kuo B. Interpretable representation learning based on Deep Rule Forests. [Thesis]. NSYSU; 2018. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727118-134901

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Missouri – Columbia

21. Serna, Erica. Quantifying error in vegetation mapping.

Degree: 2011, University of Missouri – Columbia

URL: http://hdl.handle.net/10355/11508

► Understanding the current distribution and structure of forest vegetation is important for designing forest management plans and prioritizing restoration at landscape scales. This project provides… (more)

Subjects/Keywords: random forest; Vegetation mapping; Forest management; Forest restoration; Regression analysis; Trees (Graph theory)

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Serna, E. (2011). Quantifying error in vegetation mapping. (Thesis). University of Missouri – Columbia. Retrieved from http://hdl.handle.net/10355/11508

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Serna, Erica. “Quantifying error in vegetation mapping.” 2011. Thesis, University of Missouri – Columbia. Accessed January 18, 2021. http://hdl.handle.net/10355/11508.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Serna, Erica. “Quantifying error in vegetation mapping.” 2011. Web. 18 Jan 2021.

Vancouver:

Serna E. Quantifying error in vegetation mapping. [Internet] [Thesis]. University of Missouri – Columbia; 2011. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/10355/11508.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Serna E. Quantifying error in vegetation mapping. [Thesis]. University of Missouri – Columbia; 2011. Available from: http://hdl.handle.net/10355/11508

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Michigan Technological University

22. Cleaver, Megan. USING RANDOM FOREST MODELING TO PREDICT EARTHWORM DISTRIBUTION IN THE OTTAWA NATIONAL FOREST.

Degree: MS, College of Forest Resources and Environmental Science, 2018, Michigan Technological University

URL: https://digitalcommons.mtu.edu/etdr/716

► Our study applies the machine learning method, Random Forest (RF), to understand distribution patterns and predictive powers of environmental variables determining earthworm occurrence in… (more)

Subjects/Keywords: Earthworms; Distribution; Predictive Modeling; Random Forest; GIS; Ottawa National Forest; Ecology and Evolutionary Biology; Forest Management; Forest Sciences

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Cleaver, M. (2018). USING RANDOM FOREST MODELING TO PREDICT EARTHWORM DISTRIBUTION IN THE OTTAWA NATIONAL FOREST. (Masters Thesis). Michigan Technological University. Retrieved from https://digitalcommons.mtu.edu/etdr/716

Chicago Manual of Style (16^th Edition):

Cleaver, Megan. “USING RANDOM FOREST MODELING TO PREDICT EARTHWORM DISTRIBUTION IN THE OTTAWA NATIONAL FOREST.” 2018. Masters Thesis, Michigan Technological University. Accessed January 18, 2021. https://digitalcommons.mtu.edu/etdr/716.

MLA Handbook (7^th Edition):

Cleaver, Megan. “USING RANDOM FOREST MODELING TO PREDICT EARTHWORM DISTRIBUTION IN THE OTTAWA NATIONAL FOREST.” 2018. Web. 18 Jan 2021.

Vancouver:

Cleaver M. USING RANDOM FOREST MODELING TO PREDICT EARTHWORM DISTRIBUTION IN THE OTTAWA NATIONAL FOREST. [Internet] [Masters thesis]. Michigan Technological University; 2018. [cited 2021 Jan 18]. Available from: https://digitalcommons.mtu.edu/etdr/716.

Council of Science Editors:

Cleaver M. USING RANDOM FOREST MODELING TO PREDICT EARTHWORM DISTRIBUTION IN THE OTTAWA NATIONAL FOREST. [Masters Thesis]. Michigan Technological University; 2018. Available from: https://digitalcommons.mtu.edu/etdr/716

23. Oshiro, Thais Mayumi. Uma abordagem para a construção de uma única árvore a partir de uma Random Forest para classificação de bases de expressão gênica.

Degree: Mestrado, Bioinformática, 2013, University of São Paulo

URL: http://www.teses.usp.br/teses/disponiveis/95/95131/tde-15102013-183234/ ;

►

Random Forest é uma técnica computacionalmente eciente que pode operar rapida-mente sobre grandes bases de dados. Ela tem sido usada em muitos projetos de pesquisa… (more)

▼

Random Forest é uma técnica computacionalmente eciente que pode operar rapida-mente sobre grandes bases de dados. Ela tem sido usada em muitos projetos de pesquisa recentes e aplicações do mundo real em diversos domínios, entre eles a bioinformática uma vez que a Random Forest consegue lidar com bases que apresentam muitos atributos e poucos exemplos. Porém, ela é de difícil compreensão para especialistas humanos de diversas áreas. A pesquisa de mestrado aqui relatada tem como objetivo criar um modelo simbólico, ou seja, uma única árvore a partir da Random Forest para a classicação de bases de dados de expressão gênica. Almeja-se assim, aumentar a compreensão por parte dos especialistas humanos sobre o processo que classica os exemplos no mundo real tentando manter um bom desempenho. Os resultados iniciais obtidos com o algoritmo aqui proposto são pro-missores, uma vez que ela apresenta, em alguns casos, desempenho melhor do que outro algoritmo amplamente utilizado (J48) e um pouco inferior à Random Forest. Além disso, a árvore criada apresenta, no geral, tamanho menor do que a árvore criada pelo algoritmo J48.

Random Forest is a computationally ecient technique which can operate quickly over large datasets. It has been used in many research projects and recent real-world applications in several elds, including bioinformatics since Random Forest can handle datasets having many attributes, and few examples. However, it is dicult for human experts to understand it. The research reported here aims to create a symbolic model, i.e. a single tree from a Random Forest for the classication of gene expression datasets. Thus, we hope to increase the understanding by human experts on the process that classies the examples in the real world trying to keep a good performance. Initial results obtained from the proposed algorithm are promising since it presents in some cases performance better than other widely used algorithm (J48) and a slightly lower than a Random Forest. Furthermore, the induced tree presents, in general, a smaller size than the tree built by the algorithm J48.

Advisors/Committee Members: Baranauskas, José Augusto.

Subjects/Keywords: Aprendizado de Máquina; Classicador Simbólico.; Expressão Gênica; Gene Expression; Machine Learning; Random Forest; Random Forest; Symbolic Classier.

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Oshiro, T. M. (2013). Uma abordagem para a construção de uma única árvore a partir de uma Random Forest para classificação de bases de expressão gênica. (Masters Thesis). University of São Paulo. Retrieved from http://www.teses.usp.br/teses/disponiveis/95/95131/tde-15102013-183234/ ;

Chicago Manual of Style (16^th Edition):

Oshiro, Thais Mayumi. “Uma abordagem para a construção de uma única árvore a partir de uma Random Forest para classificação de bases de expressão gênica.” 2013. Masters Thesis, University of São Paulo. Accessed January 18, 2021. http://www.teses.usp.br/teses/disponiveis/95/95131/tde-15102013-183234/ ;.

MLA Handbook (7^th Edition):

Oshiro, Thais Mayumi. “Uma abordagem para a construção de uma única árvore a partir de uma Random Forest para classificação de bases de expressão gênica.” 2013. Web. 18 Jan 2021.

Vancouver:

Oshiro TM. Uma abordagem para a construção de uma única árvore a partir de uma Random Forest para classificação de bases de expressão gênica. [Internet] [Masters thesis]. University of São Paulo; 2013. [cited 2021 Jan 18]. Available from: http://www.teses.usp.br/teses/disponiveis/95/95131/tde-15102013-183234/ ;.

Council of Science Editors:

Oshiro TM. Uma abordagem para a construção de uma única árvore a partir de uma Random Forest para classificação de bases de expressão gênica. [Masters Thesis]. University of São Paulo; 2013. Available from: http://www.teses.usp.br/teses/disponiveis/95/95131/tde-15102013-183234/ ;

24. Tran khac, Viet. Le rôle des facteurs environnementaux sur la concentration des métaux-tracesdans les lacs urbains -Lac de Pampulha, Lac de Créteil et 49 lacs péri-urbains d’Ile de France : The role of environmental factors on trace-metalconcentrations in urban lakes - Lake Pampulha, Lake Créteil and 49 lakes in the Ile-de-France region.

Degree: Docteur es, Sciences et Techniques de l'Environnement, 2016, Université Paris-Est

URL: http://www.theses.fr/2016PESC1160

► Les lacs jouent un rôle particulier dans le cycle de l’eau dans les bassins versants urbains. La stratification thermique et le temps de séjour de… (more)

▼ Les lacs jouent un rôle particulier dans le cycle de l’eau dans les bassins versants urbains. La stratification thermique et le temps de séjour de l’eau élevé favorisent le développement phytoplanctonique. La plupart des métaux sont naturellement présents dans l’environnement à l’état de traces. Ils sont essentiels pour les organismes vivants. Néanmoins, certains métaux sont connus pour leurs effets toxiques sur les animaux et les humains. La concentration totale des métaux ne reflète pas leur toxicité. Elle dépend de leurs propriétés et de leur spéciation (fractions particulaires, dissoutes: labiles ou biodisponibles et inertes). Dans les systèmes aquatiques, les métaux peuvent être absorbés par des ligands organiques ou minéraux. Leur capacité à se complexer avec la matière organique dissoute (MOD), particulièrement les substances humiques, a été largement étudiée. Dans les lacs, le développement phytoplanctonique peut produire de la MOD non-humique, connue pour sa capacité complexante des métaux. Pourtant, peu de recherche sur la spéciation des métaux dans la colonne d’eau des lacs urbains a été réalisée jusqu’à présent.Les objectifs principaux de cette thèse sont (1) d’obtenir une base de données fiables des concentrations en métaux traces dans la colonne d’eau de lacs urbains représentatifs; (2) d’évaluer leur biodisponibilité via une technique de spéciation adéquate ; (3) d’analyser leur évolution saisonnière et spatiale et leur spéciation; (4) d’étudier l’impact des variables environnementales, en particulier de la MOD autochtone sur leur biodisponibilité; (5) de lier la concentration des métaux au mode d’occupation du sol du bassin versant.Notre méthodologie est basée sur un suivi in-situ des lacs en complément d’analyses spécifiques en laboratoire. L’étude a été conduite sur trois sites: le lac de Créteil (France), le lac de Pampulha (Brésil) et 49 lacs péri-urbains (Ile de France). Sur le lac de Créteil, plusieurs dispositifs de mesure en continu nous ont fourni une partie de la base de données limnologiques. Dans le bassin versant du lac de Pampulha, la pression anthropique est très importante. Le climat et le régime hydrologique des 2 lacs sont très différents. Les 49 lacs de la région d’Ile de France ont été échantillonnés une fois pendant trois étés successifs (2011-2013). Ces lacs nous ont fourni une base de données synoptique, représentative de la contamination métallique à l’échelle d’une région fortement anthropisée.Afin d’expliquer le rôle des variables environnementales sur la concentration métallique, le modèle Random Forest a été appliqué sur les bases de données du lac de Pampulha et des 49 lacs urbains avec 2 objectifs spécifiques: (1) dans le lac de Pampulha, comprendre le rôle des variables environnementales sur la fraction labile des métaux traces, potentiellement biodisponible et (2) dans les 49 lacs, comprendre la relation des variables environnementales, particulièrement au niveau du bassin versant, sur la concentration dissoute des métaux. L’analyse des relations entre métaux et… Advisors/Committee Members: Vinçon-Leite, Brigitte (thesis director), De Oliveira Nascimento, Nilo (thesis director), Varrault, Gilles (thesis director).

Subjects/Keywords: Lacs urbains; Métaux traces; Spéciation; Biodisponibilité; Random Forest model; Urban lakes; Trace metal; Speciation; Bioavailability; Landuse; Random Forest model

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Tran khac, V. (2016). Le rôle des facteurs environnementaux sur la concentration des métaux-tracesdans les lacs urbains -Lac de Pampulha, Lac de Créteil et 49 lacs péri-urbains d’Ile de France : The role of environmental factors on trace-metalconcentrations in urban lakes - Lake Pampulha, Lake Créteil and 49 lakes in the Ile-de-France region. (Doctoral Dissertation). Université Paris-Est. Retrieved from http://www.theses.fr/2016PESC1160

Chicago Manual of Style (16^th Edition):

Tran khac, Viet. “Le rôle des facteurs environnementaux sur la concentration des métaux-tracesdans les lacs urbains -Lac de Pampulha, Lac de Créteil et 49 lacs péri-urbains d’Ile de France : The role of environmental factors on trace-metalconcentrations in urban lakes - Lake Pampulha, Lake Créteil and 49 lakes in the Ile-de-France region.” 2016. Doctoral Dissertation, Université Paris-Est. Accessed January 18, 2021. http://www.theses.fr/2016PESC1160.

MLA Handbook (7^th Edition):

Tran khac, Viet. “Le rôle des facteurs environnementaux sur la concentration des métaux-tracesdans les lacs urbains -Lac de Pampulha, Lac de Créteil et 49 lacs péri-urbains d’Ile de France : The role of environmental factors on trace-metalconcentrations in urban lakes - Lake Pampulha, Lake Créteil and 49 lakes in the Ile-de-France region.” 2016. Web. 18 Jan 2021.

Vancouver:

Tran khac V. Le rôle des facteurs environnementaux sur la concentration des métaux-tracesdans les lacs urbains -Lac de Pampulha, Lac de Créteil et 49 lacs péri-urbains d’Ile de France : The role of environmental factors on trace-metalconcentrations in urban lakes - Lake Pampulha, Lake Créteil and 49 lakes in the Ile-de-France region. [Internet] [Doctoral dissertation]. Université Paris-Est; 2016. [cited 2021 Jan 18]. Available from: http://www.theses.fr/2016PESC1160.

Council of Science Editors:

Tran khac V. Le rôle des facteurs environnementaux sur la concentration des métaux-tracesdans les lacs urbains -Lac de Pampulha, Lac de Créteil et 49 lacs péri-urbains d’Ile de France : The role of environmental factors on trace-metalconcentrations in urban lakes - Lake Pampulha, Lake Créteil and 49 lakes in the Ile-de-France region. [Doctoral Dissertation]. Université Paris-Est; 2016. Available from: http://www.theses.fr/2016PESC1160

25. FLORÊNCIO, João Carlos Procópio. Análise e predição de bilheterias de filmes .

Degree: 2016, Universidade Federal de Pernambuco

URL: http://repositorio.ufpe.br/handle/123456789/17639

► Prever o sucesso de um filme e, por consequência, seu sucesso nas bilheterias tem uma grande importância na indústria cinematográfica, desde a fase de pré-produção… (more)

▼ Prever o sucesso de um filme e, por consequência, seu sucesso nas bilheterias tem uma grande importância na indústria cinematográfica, desde a fase de pré-produção do filme, quando os investidores querem saber quais serão os filmes mais promissores, até nas semanas seguintes ao seu lançamento, quando se deseja prever as bilheterias das semanas restantes de exibição. Por conta disso, essa área tem sido alvo de muitos estudos que tem usado diferentes abordagens de predição, seja na seleção das características dos filmes como nas técnicas de aprendizagem, para atingir uma maior capacidade de prever o sucesso dos filmes. Neste trabalho de mestrado, foi feita uma investigação sobre o comportamento das principais características dos filmes (gênero, classificação etária, orçamento de produção, etc), com maior foco nos resultados das bilheterias e sua relação com as características dos filmes, de forma a obter uma visão mais clara de como as caracaterísticas dos filmes podem influenciar no seu sucesso, seja ele interpretado como lucro ou volume de bilheterias. Em seguida, em posse de uma base de filmes extraída do Box-Office Mojo e do IMDb, foi proposto um novo modelo de predição de box office utilizando os dados disponíveis dessa base, que é composta de: meta-dados dos filmes, palavras-chaves, e dados de bilheterias. Algumas dessas características são hibridizadas com o objetivo evidenciar as combinações de características mais importantes. É aplicado também um processo de seleção de características para excluir aquelas que não são relevantes ao modelo. O modelo utiliza Random Forest como máquina de aprendizagem. Os resultados obtidos com a técnica proposta sugerem, além de uma maior simplificação do modelo em relação a estudos anteriores, que o método consegue obter taxas de acerto superior 90% quando a classificação é medida com a métrica 1-away (quando a amostra é classificada com até 1 classe de distância), e consegue melhorar a qualidade da predição em relação a estudos anteriores quando testado com os dados da base disponível. Advisors/Committee Members: REN, Tsang Ing (advisor), http://lattes.cnpq.br/3084134533707587 (advisor).

Subjects/Keywords: Predição de bilheteria; Recomendação; Box-Office; Filmes; Random Forest; Box Office Prediction; Recommendation; Box-Office; Movies; Random Forest

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

FLORÊNCIO, J. C. P. (2016). Análise e predição de bilheterias de filmes . (Thesis). Universidade Federal de Pernambuco. Retrieved from http://repositorio.ufpe.br/handle/123456789/17639

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

FLORÊNCIO, João Carlos Procópio. “Análise e predição de bilheterias de filmes .” 2016. Thesis, Universidade Federal de Pernambuco. Accessed January 18, 2021. http://repositorio.ufpe.br/handle/123456789/17639.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

FLORÊNCIO, João Carlos Procópio. “Análise e predição de bilheterias de filmes .” 2016. Web. 18 Jan 2021.

Vancouver:

FLORÊNCIO JCP. Análise e predição de bilheterias de filmes . [Internet] [Thesis]. Universidade Federal de Pernambuco; 2016. [cited 2021 Jan 18]. Available from: http://repositorio.ufpe.br/handle/123456789/17639.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

FLORÊNCIO JCP. Análise e predição de bilheterias de filmes . [Thesis]. Universidade Federal de Pernambuco; 2016. Available from: http://repositorio.ufpe.br/handle/123456789/17639

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

26. ARAÚJO, Gilderlanio Santana de. Uso de random forests e redes biológicas na associação de poliformismos à doença de Alzheimer .

Degree: 2013, Universidade Federal de Pernambuco

URL: https://repositorio.ufpe.br/handle/123456789/18012

► O desenvolvimento de técnicas de genotipagem de baixo custo (SNP arrays) e as anotações de milhares de polimorfismos de nucleotídeo único (SNPs) em bancos de… (more)

Subjects/Keywords: GWAS. Random Forest. SNPs. Neuropsiquiatria. Fatores genéticos de risco.; GWAS. Random Forest. SNPs. Alzheimer’s Disease. Genetic Risk Factors.

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

ARAÚJO, G. S. d. (2013). Uso de random forests e redes biológicas na associação de poliformismos à doença de Alzheimer . (Thesis). Universidade Federal de Pernambuco. Retrieved from https://repositorio.ufpe.br/handle/123456789/18012

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

ARAÚJO, Gilderlanio Santana de. “Uso de random forests e redes biológicas na associação de poliformismos à doença de Alzheimer .” 2013. Thesis, Universidade Federal de Pernambuco. Accessed January 18, 2021. https://repositorio.ufpe.br/handle/123456789/18012.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

ARAÚJO, Gilderlanio Santana de. “Uso de random forests e redes biológicas na associação de poliformismos à doença de Alzheimer .” 2013. Web. 18 Jan 2021.

Vancouver:

ARAÚJO GSd. Uso de random forests e redes biológicas na associação de poliformismos à doença de Alzheimer . [Internet] [Thesis]. Universidade Federal de Pernambuco; 2013. [cited 2021 Jan 18]. Available from: https://repositorio.ufpe.br/handle/123456789/18012.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

ARAÚJO GSd. Uso de random forests e redes biológicas na associação de poliformismos à doença de Alzheimer . [Thesis]. Universidade Federal de Pernambuco; 2013. Available from: https://repositorio.ufpe.br/handle/123456789/18012

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Brno University of Technology

27. Grolig, Lukáš. Implementace algoritmů založených na rozhodovacích stromech v jazyce C#: Implementation of Algorithms Based on Decision Trees in C#.

Degree: 2020, Brno University of Technology

URL: http://hdl.handle.net/11012/189709

► This bachelor thesis is focused on selection of data mining algorithms based on decision trees for an analytical system developed under the project System for… (more)

Subjects/Keywords: Dolování z dat; dolovací algoritmy; klasifikace; rozhodovací stromy; random forest; sprint; Data mining; mining algorithms; classification; decision trees; random forest; sprint

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Grolig, L. (2020). Implementace algoritmů založených na rozhodovacích stromech v jazyce C#: Implementation of Algorithms Based on Decision Trees in C#. (Thesis). Brno University of Technology. Retrieved from http://hdl.handle.net/11012/189709

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Grolig, Lukáš. “Implementace algoritmů založených na rozhodovacích stromech v jazyce C#: Implementation of Algorithms Based on Decision Trees in C#.” 2020. Thesis, Brno University of Technology. Accessed January 18, 2021. http://hdl.handle.net/11012/189709.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Grolig, Lukáš. “Implementace algoritmů založených na rozhodovacích stromech v jazyce C#: Implementation of Algorithms Based on Decision Trees in C#.” 2020. Web. 18 Jan 2021.

Vancouver:

Grolig L. Implementace algoritmů založených na rozhodovacích stromech v jazyce C#: Implementation of Algorithms Based on Decision Trees in C#. [Internet] [Thesis]. Brno University of Technology; 2020. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/11012/189709.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Grolig L. Implementace algoritmů založených na rozhodovacích stromech v jazyce C#: Implementation of Algorithms Based on Decision Trees in C#. [Thesis]. Brno University of Technology; 2020. Available from: http://hdl.handle.net/11012/189709

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Helsinki

28. Roivainen, Hege. Document classification based on library catalogue metadata.

Degree: Department of Modern Languages; Helsingfors universitet, Humanistiska fakulteten, Institutionen för moderna språk, 2017, University of Helsinki

URL: http://hdl.handle.net/10138/229702

► Kansalliskirjastojen metadataluettelot ovat hyviä informaatiolähteitä, sillä ne sisältävät tiedon lähes kaikesta tiettynä aikana ja tietyllä alueella julkaistusta aineistosta. Yleensä ne ovat kattavasti kuvailtuja, joten niitä… (more)

Subjects/Keywords: random forest; machine learning; genre classification; library catalogues; kieliteknologia; Language Technology; Språkteknologi; random forest; machine learning; genre classification; library catalogues

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Roivainen, H. (2017). Document classification based on library catalogue metadata. (Masters Thesis). University of Helsinki. Retrieved from http://hdl.handle.net/10138/229702

Chicago Manual of Style (16^th Edition):

Roivainen, Hege. “Document classification based on library catalogue metadata.” 2017. Masters Thesis, University of Helsinki. Accessed January 18, 2021. http://hdl.handle.net/10138/229702.

MLA Handbook (7^th Edition):

Roivainen, Hege. “Document classification based on library catalogue metadata.” 2017. Web. 18 Jan 2021.

Vancouver:

Roivainen H. Document classification based on library catalogue metadata. [Internet] [Masters thesis]. University of Helsinki; 2017. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/10138/229702.

Council of Science Editors:

Roivainen H. Document classification based on library catalogue metadata. [Masters Thesis]. University of Helsinki; 2017. Available from: http://hdl.handle.net/10138/229702

Brno University of Technology

29. Grolig, Lukáš. Implementace algoritmů založených na rozhodovacích stromech v jazyce C#: Implementation of Algorithms Based on Decision Trees in C#.

Degree: 2020, Brno University of Technology

URL: http://hdl.handle.net/11012/188334

► This bachelor thesis is focused on selection of data mining algorithms based on decision trees for an analytical system developed under the project System for… (more)

Subjects/Keywords: Dolování z dat; dolovací algoritmy; klasifikace; rozhodovací stromy; random forest; sprint; Data mining; mining algorithms; classification; decision trees; random forest; sprint

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Grolig, L. (2020). Implementace algoritmů založených na rozhodovacích stromech v jazyce C#: Implementation of Algorithms Based on Decision Trees in C#. (Thesis). Brno University of Technology. Retrieved from http://hdl.handle.net/11012/188334

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Grolig, Lukáš. “Implementace algoritmů založených na rozhodovacích stromech v jazyce C#: Implementation of Algorithms Based on Decision Trees in C#.” 2020. Thesis, Brno University of Technology. Accessed January 18, 2021. http://hdl.handle.net/11012/188334.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Grolig, Lukáš. “Implementace algoritmů založených na rozhodovacích stromech v jazyce C#: Implementation of Algorithms Based on Decision Trees in C#.” 2020. Web. 18 Jan 2021.

Vancouver:

Grolig L. Implementace algoritmů založených na rozhodovacích stromech v jazyce C#: Implementation of Algorithms Based on Decision Trees in C#. [Internet] [Thesis]. Brno University of Technology; 2020. [cited 2021 Jan 18]. Available from: http://hdl.handle.net/11012/188334.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Grolig L. Implementace algoritmů založených na rozhodovacích stromech v jazyce C#: Implementation of Algorithms Based on Decision Trees in C#. [Thesis]. Brno University of Technology; 2020. Available from: http://hdl.handle.net/11012/188334

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

30. Ebrahimi, Shahin. Contribution to automatic adjustments of vertebrae landmarks on x-ray images for 3D reconstruction and quantification of clinical indices : Contribution aux ajustements automatiques de points anatomiques des vertèbres pour la reconstruction 3D et la quantification d’indices cliniques.

Degree: Docteur es, Informatique-traitement du signal, 2017, Paris, ENSAM

URL: http://www.theses.fr/2017ENAM0050

►

L’exploitation de données radiographiques, en particulier pour la reconstruction 3D du rachis de patients scoliotiques, est un prérequis à la modélisation personnalisée. Les méthodes actuelles,… (more)

▼

L’exploitation de données radiographiques, en particulier pour la reconstruction 3D du rachis de patients scoliotiques, est un prérequis à la modélisation personnalisée. Les méthodes actuelles, bien qu’assez robustes pour la routine clinique, reposent sur des ajustements manuels fastidieux. Dans ce contexte, ce travail de thèse vise à la détection automatisée de points anatomiques spécifiques des vertèbres, permettant ainsi des ajustements automatisés. Nous avons développé premièrement une méthode originale de localisation de coins de vertèbres cervicales et lombaires sur les radiographies sagittales. L’évaluation rigoureuse de cette méthode suggère sa robustesse et sa précision. Nous avons ensuite développé un algorithme pour le problème pertinent cliniquement de localisation des pédicules sur les radiographies coronales. Cet algorithme se compare favorablement aux méthodes similaires dans la littérature, qui nécessitent une saisie manuelle. Enfin, nous avons soulevé les problèmes, relativement peu étudiés, de détection, identification et segmentation des apophyses épineuses du rachis cervical dans les radiographies sagittales. Toutes les tâches mentionnées ont été réalisées grâce à une combinaison originale de descripteurs visuels et une classification multi-classe par Random Forest, menant à une nouvelle et puissante approche de localisation et de segmentation. Les méthodes proposées dans cette thèse suggèrent un grand potentiel pour être intégré à la reconstruction 3D du rachis, utilisée quotidiennement en routine clinique.

Exploitation of spine radiographs, in particular for 3D spine shape reconstruction of scoliotic patients, is a prerequisite for personalized modelling. Current methods, even though robust enough to be used in clinical routine, still rely on tedious manual adjustments. In this context, this PhD thesis aims toward automated detection of specific vertebrae landmarks in spine radiographs, enabling automated adjustments. In the first part, we developed an original Random Forest based framework for vertebrae corner localization that was applied on sagittal radiographs of both cervical and lumbar spine regions. A rigorous evaluation of the method confirms robustness and high accuracy of the proposed method. In the second part, we developed an algorithm for the clinically-important task of pedicle localization in the thoracolumbar region on frontal radiographs. The proposed algorithm compares favourably to similar methods from the literature while relying on less manual supervision. The last part of this PhD tackled the scarcely-studied task of joint detection, identification and segmentation of spinous processes of cervical vertebrae in sagittal radiographs, with again high precision performance. All three algorithmic solutions were designed around a generic framework exploiting dedicated visual feature descriptors and multi-class Random Forest classifiers, proposing a novel solution with computational and manual supervision burdens aiming for translation into clinical use. Overall, the presented…

Advisors/Committee Members: Skalli, Wafa (thesis director), Angelini, Elsa (thesis director), Gajny, Laurent (thesis director).

Subjects/Keywords: Rachis; Radiographies; Vertèbres; Random forest; Descripteurs visuels; Descripteurs contextuels; Spine; X-Ray; Vertebrae landmarks; Random Forest; Visual features; Contextuel Features

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Ebrahimi, S. (2017). Contribution to automatic adjustments of vertebrae landmarks on x-ray images for 3D reconstruction and quantification of clinical indices : Contribution aux ajustements automatiques de points anatomiques des vertèbres pour la reconstruction 3D et la quantification d’indices cliniques. (Doctoral Dissertation). Paris, ENSAM. Retrieved from http://www.theses.fr/2017ENAM0050

Chicago Manual of Style (16^th Edition):

Ebrahimi, Shahin. “Contribution to automatic adjustments of vertebrae landmarks on x-ray images for 3D reconstruction and quantification of clinical indices : Contribution aux ajustements automatiques de points anatomiques des vertèbres pour la reconstruction 3D et la quantification d’indices cliniques.” 2017. Doctoral Dissertation, Paris, ENSAM. Accessed January 18, 2021. http://www.theses.fr/2017ENAM0050.

MLA Handbook (7^th Edition):

Ebrahimi, Shahin. “Contribution to automatic adjustments of vertebrae landmarks on x-ray images for 3D reconstruction and quantification of clinical indices : Contribution aux ajustements automatiques de points anatomiques des vertèbres pour la reconstruction 3D et la quantification d’indices cliniques.” 2017. Web. 18 Jan 2021.

Vancouver:

Ebrahimi S. Contribution to automatic adjustments of vertebrae landmarks on x-ray images for 3D reconstruction and quantification of clinical indices : Contribution aux ajustements automatiques de points anatomiques des vertèbres pour la reconstruction 3D et la quantification d’indices cliniques. [Internet] [Doctoral dissertation]. Paris, ENSAM; 2017. [cited 2021 Jan 18]. Available from: http://www.theses.fr/2017ENAM0050.

Council of Science Editors:

Ebrahimi S. Contribution to automatic adjustments of vertebrae landmarks on x-ray images for 3D reconstruction and quantification of clinical indices : Contribution aux ajustements automatiques de points anatomiques des vertèbres pour la reconstruction 3D et la quantification d’indices cliniques. [Doctoral Dissertation]. Paris, ENSAM; 2017. Available from: http://www.theses.fr/2017ENAM0050

		in
And / Or
		in
And / Or
		in
And / Or
		in

Open Access Theses and Dissertations