+publisher:"Dalhousie University" +contributor:("Dr. Malcolm Heywood")

Dalhousie University

1. Marath, Sathi. Large-Scale Web Page Classification.

Degree: PhD, Faculty of Computer Science, 2010, Dalhousie University

► Web page classification is the process of assigning predefined categories to web pages. Empirical evaluations of classifiers such as Support Vector Machines (SVMs), k-Nearest Neighbor… (more)

▼ Web page classification is the process of assigning predefined categories to web pages. Empirical evaluations of classifiers such as Support Vector Machines (SVMs), k-Nearest Neighbor (k-NN), and Naïve Bayes (NB), have shown that these algorithms are effective in classifying small segments of web directories. The effectiveness of these algorithms, however, has not been thoroughly investigated on large-scale web page classification of such popular web directories as Yahoo! and LookSmart. Such web directories have hundreds of thousands of categories, deep hierarchies, spindle category and document distributions over the hierarchies, and skewed category distribution over the documents. These statistical properties indicate class imbalance and rarity within the dataset. In hierarchical datasets similar to web directories, expanding the content of each category using the web pages of the child categories helps to decrease the degree of rarity. This process, however, results in the localized overabundance of positive instances especially in the upper level categories of the hierarchy. The class imbalance, rarity and the localized overabundance of positive instances make applying classification algorithms to web directories very difficult and the problem has not been thoroughly studied. To our knowledge, the maximum number of categories ever previously classified on web taxonomies is 246,279 categories of Yahoo! directory using hierarchical SVMs leading to a Macro-F1 of 12% only. We designed a unified framework for the content based classification of imbalanced hierarchical datasets. The complete Yahoo! web directory of 639,671 categories and 4,140,629 web pages is used to setup the experiments. In a hierarchical dataset, the prior probability distribution of the subcategories indicates the presence or absence of class imbalance, rarity and the overabundance of positive instances within the dataset. Based on the prior probability distribution and associated machine learning issues, we partitioned the subcategories of Yahoo! web directory into five mutually exclusive groups. The effectiveness of different data level, algorithmic and architectural solutions to the associated machine learning issues is explored. Later, the best performing classification technologies for a particular prior probability distribution have been identified and integrated into the Yahoo! Web directory classification model. The methodology is evaluated using a DMOZ subset of 17,217 categories and 130,594 web pages and we statistically proved that the methodology of this research works equally well on large and small dataset. The average classifier performance in terms of macro-averaged F1-Measure achieved in this research for Yahoo! web directory and DMOZ subset is 81.02% and 84.85% respectively. Advisors/Committee Members: n/a (external-examiner), Dr. Malcolm Heywood (graduate-coordinator), Dr. Evangelos E. Milios (thesis-reader), Dr. Malcolm Heywood (thesis-reader), Dr. Michael Shepherd (thesis-supervisor), Not Applicable (ethics-approval), Not Applicable (manuscripts), Not Applicable (copyright-release).

Subjects/Keywords: Web page classification; class imbalance; rarity

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Marath, S. (2010). Large-Scale Web Page Classification. (Doctoral Dissertation). Dalhousie University. Retrieved from http://hdl.handle.net/10222/13130

Chicago Manual of Style (16^th Edition):

Marath, Sathi. “Large-Scale Web Page Classification.” 2010. Doctoral Dissertation, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/13130.

MLA Handbook (7^th Edition):

Marath, Sathi. “Large-Scale Web Page Classification.” 2010. Web. 09 Mar 2021.

Vancouver:

Marath S. Large-Scale Web Page Classification. [Internet] [Doctoral dissertation]. Dalhousie University; 2010. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/13130.

Council of Science Editors:

Marath S. Large-Scale Web Page Classification. [Doctoral Dissertation]. Dalhousie University; 2010. Available from: http://hdl.handle.net/10222/13130

Dalhousie University

2. Kalra, Love. Activities of Daily Living Detection Using Markov Models.

Degree: Master of Computer Science, Faculty of Computer Science, 2011, Dalhousie University

URL: http://hdl.handle.net/10222/14399

► The healthcare systems are experiencing heavy workload and high cost caused by ageing population. The assisted monitoring systems for the elderly persons, and persons with… (more)

Subjects/Keywords: ADL; Markov Models

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Kalra, L. (2011). Activities of Daily Living Detection Using Markov Models. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/14399

Chicago Manual of Style (16^th Edition):

Kalra, Love. “Activities of Daily Living Detection Using Markov Models.” 2011. Masters Thesis, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/14399.

MLA Handbook (7^th Edition):

Kalra, Love. “Activities of Daily Living Detection Using Markov Models.” 2011. Web. 09 Mar 2021.

Vancouver:

Kalra L. Activities of Daily Living Detection Using Markov Models. [Internet] [Masters thesis]. Dalhousie University; 2011. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/14399.

Council of Science Editors:

Kalra L. Activities of Daily Living Detection Using Markov Models. [Masters Thesis]. Dalhousie University; 2011. Available from: http://hdl.handle.net/10222/14399

Dalhousie University

3. Geta, Gemechu. A HYBRID FUZZY/GENETIC ALGORITHM FOR INTRUSION DETECTION IN RFID SYSTEMS.

Degree: Master of Computer Science, Faculty of Computer Science, 2012, Dalhousie University

URL: http://hdl.handle.net/10222/14416

► Various established and emerging applications of RFID technology have been and are being implemented by companies in different parts of the world. However, RFID technology… (more)

▼ Various established and emerging applications of RFID technology have been and are being implemented by companies in different parts of the world. However, RFID technology is susceptible to a variety of security and privacy concerns, as it is prone to attacks such as eavesdropping, denial of service, tag cloning and user tracking. This is mainly because RFID tags, specifically low-cost tags, have low computational capability to support complex cryptographic algorithms. Tag cloning is a key problem to be considered since it leads to severe economic losses. One of the possible approaches to address tag cloning is using an intrusion detection system. Intrusion detection systems in RFID networks, on top of the existing lightweight cryptographic algorithms, provide an additional layer of protection where other security mechanisms may fail. This thesis presents an intrusion detection mechanism that detects anomalies caused by one or more cloned RFID tags in the system. We make use of a Hybrid Fuzzy Genetics-Based Machine Learning algorithm to design an intrusion detection model from RFID system-generated event logs. For the purpose of training and evaluation of our proposed approach, part of the RFID system-generated dataset provided by the University of Tasmania’s School of Computing and Information Systems was used, in addition to simulated datasets. The results of our experiments show that the model can achieve high detection rates and low false positive rates when identifying anomalies caused by one or more cloned tags. In addition, the model yields linguistically interpretable rules that can be used to support decision making during the detection of anomaly caused by the cloned tags. Advisors/Committee Members: Dr. Malcolm Heywood (external-examiner), Dr. Stephen Brooks (graduate-coordinator), Dr. Malcolm Heywood (thesis-reader), Dr. Srinivas Sampalli, Dr. Denis Riordan (thesis-supervisor), Not Applicable (ethics-approval), Not Applicable (manuscripts), Not Applicable (copyright-release).

Subjects/Keywords: RFID Systems; Cloning Detection; Hybrid Genetic Fuzzy Systems; Fuzzy Logic; Fuzzy Systems; Soft Computing; Genetic Algorithms

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Geta, G. (2012). A HYBRID FUZZY/GENETIC ALGORITHM FOR INTRUSION DETECTION IN RFID SYSTEMS. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/14416

Chicago Manual of Style (16^th Edition):

Geta, Gemechu. “A HYBRID FUZZY/GENETIC ALGORITHM FOR INTRUSION DETECTION IN RFID SYSTEMS.” 2012. Masters Thesis, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/14416.

MLA Handbook (7^th Edition):

Geta, Gemechu. “A HYBRID FUZZY/GENETIC ALGORITHM FOR INTRUSION DETECTION IN RFID SYSTEMS.” 2012. Web. 09 Mar 2021.

Vancouver:

Geta G. A HYBRID FUZZY/GENETIC ALGORITHM FOR INTRUSION DETECTION IN RFID SYSTEMS. [Internet] [Masters thesis]. Dalhousie University; 2012. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/14416.

Council of Science Editors:

Geta G. A HYBRID FUZZY/GENETIC ALGORITHM FOR INTRUSION DETECTION IN RFID SYSTEMS. [Masters Thesis]. Dalhousie University; 2012. Available from: http://hdl.handle.net/10222/14416

Dalhousie University

4. Lichodzijewski, Peter. A Symbiotic Bid-Based Framework for Problem Decomposition using Genetic Programming.

Degree: PhD, Faculty of Computer Science, 2011, Dalhousie University

URL: http://hdl.handle.net/10222/13260

► This thesis investigates the use of symbiosis as an evolutionary metaphor for problem decomposition using Genetic Programming. It begins by drawing a connection between lateral… (more)

▼ This thesis investigates the use of symbiosis as an evolutionary metaphor for problem decomposition using Genetic Programming. It begins by drawing a connection between lateral problem decomposition, in which peers with similar capabilities coordinate their actions, and vertical problem decomposition, whereby solution subcomponents are organized into increasingly complex units of organization. Furthermore, the two types of problem decomposition are associated respectively with context learning and layered learning. The thesis then proposes the Symbiotic Bid-Based framework modeled after a three-staged process of symbiosis abstracted from biological evolution. As such, it is argued, the approach has the capacity for both types of problem decomposition. Three principles capture the essence of the proposed framework. First, a bid-based approach to context learning is used to separate the issues of `what to do' and `when to do it'. Whereas the former issue refers to the problem-specific actions, e.g., class label predictions, the latter refers to a bidding behaviour that identifies a set of problem conditions. In this work, Genetic Programming is used to evolve the bids casting the method in a non-traditional role as programs no longer represent complete solutions. Second, the proposed framework relies on symbiosis as the primary mechanism of inheritance driving evolution, where this is in contrast to the crossover operator often encountered in Evolutionary Computation. Under this evolutionary metaphor, a set of symbionts, each representing a solution subcomponent in terms of a bid-action pair, is compartmentalized inside a host. Communication between symbionts is realized through their collective bidding behaviour, thus, their cooperation is directly supported by the bid-based approach to context learning. Third, assuming that challenging tasks where problem decomposition is likely to play a key role will often involve large state spaces, the proposed framework includes a dynamic evaluation function that explicitly models the interaction between candidate solutions and training cases. As such, the computational overhead incurred during training under the proposed framework does not depend on the size of the problem state space. An approach to model building, the Symbiotic Bid-Based framework is first evaluated on a set of real-world classification problems which include problems with multi-class labels, unbalanced distributions, and large attribute counts. The evaluation includes a comparison against Support Vector Machines and AdaBoost. Under temporal sequence learning, the proposed framework is evaluated on the truck reversal and Rubik's Cube tasks, and in the former case, it is compared with the Neuroevolution of Augmenting Topologies algorithm. Under both problems, it is demonstrated that the increased capacity for problem decomposition under the proposed approach results in improved performance, with solutions employing vertical problem decomposition under temporal sequence learning proving to be especially… Advisors/Committee Members: Dr. Terence Soule (external-examiner), Dr. Malcolm Heywood (graduate-coordinator), Heywood%22%29&pagesize-30">Dr. Nur Zincir-Heywood (thesis-reader), Dr. Dirk Arnold (thesis-reader), Dr. Malcolm Heywood (thesis-supervisor), Not Applicable (ethics-approval), Not Applicable (manuscripts), Not Applicable (copyright-release).

Subjects/Keywords: Genetic Programming; Problem Decomposition; Symbiosis; Coevolution; Machine Learning

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Lichodzijewski, P. (2011). A Symbiotic Bid-Based Framework for Problem Decomposition using Genetic Programming. (Doctoral Dissertation). Dalhousie University. Retrieved from http://hdl.handle.net/10222/13260

Chicago Manual of Style (16^th Edition):

Lichodzijewski, Peter. “A Symbiotic Bid-Based Framework for Problem Decomposition using Genetic Programming.” 2011. Doctoral Dissertation, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/13260.

MLA Handbook (7^th Edition):

Lichodzijewski, Peter. “A Symbiotic Bid-Based Framework for Problem Decomposition using Genetic Programming.” 2011. Web. 09 Mar 2021.

Vancouver:

Lichodzijewski P. A Symbiotic Bid-Based Framework for Problem Decomposition using Genetic Programming. [Internet] [Doctoral dissertation]. Dalhousie University; 2011. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/13260.

Council of Science Editors:

Lichodzijewski P. A Symbiotic Bid-Based Framework for Problem Decomposition using Genetic Programming. [Doctoral Dissertation]. Dalhousie University; 2011. Available from: http://hdl.handle.net/10222/13260

Dalhousie University

5. Shah, Jignasa. Cloning Prevention Protocol for RFID.

Degree: Master of Computer Science, Faculty of Computer Science, 2010, Dalhousie University

URL: http://hdl.handle.net/10222/13140

► Radio Frequency Identification (RFID) is an emerging area under ubiquitous computing. RFID benefits include multiple read/write, longer read range and no requirement for line of… (more)

Subjects/Keywords: RFID; radio frequency identification; RFID security; cloning

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Shah, J. (2010). Cloning Prevention Protocol for RFID. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/13140

Chicago Manual of Style (16^th Edition):

Shah, Jignasa. “Cloning Prevention Protocol for RFID.” 2010. Masters Thesis, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/13140.

MLA Handbook (7^th Edition):

Shah, Jignasa. “Cloning Prevention Protocol for RFID.” 2010. Web. 09 Mar 2021.

Vancouver:

Shah J. Cloning Prevention Protocol for RFID. [Internet] [Masters thesis]. Dalhousie University; 2010. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/13140.

Council of Science Editors:

Shah J. Cloning Prevention Protocol for RFID. [Masters Thesis]. Dalhousie University; 2010. Available from: http://hdl.handle.net/10222/13140

Dalhousie University

6. Author Not Available. An Ontology-Based Electronic Medical Record for Chronic Disease Management.

Degree: Master of Computer Science, Faculty of Computer Science, 2011, Dalhousie University

URL: http://hdl.handle.net/10222/13263

► Effective chronic disease management ensures better treatment and reduces medical costs. Representing knowledge through building an ontology for Electronic Medical Records (EMRs) is important to… (more)

Subjects/Keywords: EMR; EHR; Ontology; HL7

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Available, A. N. (2011). An Ontology-Based Electronic Medical Record for Chronic Disease Management. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/13263

Chicago Manual of Style (16^th Edition):

Available, Author Not. “An Ontology-Based Electronic Medical Record for Chronic Disease Management.” 2011. Masters Thesis, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/13263.

MLA Handbook (7^th Edition):

Available, Author Not. “An Ontology-Based Electronic Medical Record for Chronic Disease Management.” 2011. Web. 09 Mar 2021.

Vancouver:

Available AN. An Ontology-Based Electronic Medical Record for Chronic Disease Management. [Internet] [Masters thesis]. Dalhousie University; 2011. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/13263.

Council of Science Editors:

Available AN. An Ontology-Based Electronic Medical Record for Chronic Disease Management. [Masters Thesis]. Dalhousie University; 2011. Available from: http://hdl.handle.net/10222/13263

Dalhousie University

7. Paek, Jaehyun. Privacy-Enhanced Public Name-Authority System for Building Research Communities.

Degree: Master of Computer Science, Faculty of Computer Science, 2011, Dalhousie University

URL: http://hdl.handle.net/10222/13301

► Today, the Internet has become an important source of information about academic researchers and their research activities.Â Â The types of information one can obtain from… (more)

▼ Today, the Internet has become an important source of information about academic researchers and their research activities.Â Â The types of information one can obtain from the Internet include contact information, publication information, biographical information, photographs, and other miscellaneous information.Â Some of this information is generated by professional societies and academic institutions, while other information is generated by individuals and independent enterprises. As the quantity of academic material on the web grows, finding and processing information about a researcher's work is increasingly difficult. For example, it is often hard to discern whether authors of different papers in tangentially-related areas are the same person, based solely on a name. Even if one can determine this information, it is often difficult to assess the accuracy of information obtained, especially if it was generated either by an individual or by community of users. In this thesis, we propose a novel community-based and web-accessible repository of information about academic researchers and their research activities. First, we introduce a web-application called \emph{Federated World Directory of Mathematicians}(FWDM), which retrieves personal information from a variety of disparate data-sets, and which inspired the solutions proposed in this thesis. We then propose a \emph{public name-authority system}, as a means to provide high quality disambiguated information on researchers. The proposed system helps to ensure the quality of information by obtaining only the information approved by the research community. We introduce and describe two approaches to the design of public name-authority systems - the data-filtered and the user-filtered name authority systems - in order to explore their benefits and drawbacks. Advisors/Committee Members: - (external-examiner), Dr. Malcolm Heywood (graduate-coordinator), Dr. Alex Brodsky (thesis-reader), Dr. Christian Blouin (thesis-reader), Dr. Andrew Rau-Chaplin (thesis-supervisor), Not Applicable (ethics-approval), Not Applicable (manuscripts), Not Applicable (copyright-release).

Subjects/Keywords: Subject Not Available

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Paek, J. (2011). Privacy-Enhanced Public Name-Authority System for Building Research Communities. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/13301

Chicago Manual of Style (16^th Edition):

Paek, Jaehyun. “Privacy-Enhanced Public Name-Authority System for Building Research Communities.” 2011. Masters Thesis, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/13301.

MLA Handbook (7^th Edition):

Paek, Jaehyun. “Privacy-Enhanced Public Name-Authority System for Building Research Communities.” 2011. Web. 09 Mar 2021.

Vancouver:

Paek J. Privacy-Enhanced Public Name-Authority System for Building Research Communities. [Internet] [Masters thesis]. Dalhousie University; 2011. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/13301.

Council of Science Editors:

Paek J. Privacy-Enhanced Public Name-Authority System for Building Research Communities. [Masters Thesis]. Dalhousie University; 2011. Available from: http://hdl.handle.net/10222/13301

Dalhousie University

8. Mostafi, Maswood Hasan. Visualizing Geospatial Uncertainty in Marine Animal Tracks.

Degree: Master of Computer Science, Faculty of Computer Science, 2011, Dalhousie University

URL: http://hdl.handle.net/10222/13500

►

Marine animal movement is a fundamental yet poorly understood process. One of the reasons is because our understanding of movement is affected by the measurement… (more)

▼

Marine animal movement is a fundamental yet poorly understood process. One of the reasons is because our understanding of movement is affected by the measurement error during the observation and process noise. Differentiating real movement behavior from observation error in data remains difficult and challenging. Methods that acknowledge uncertainty in movement pathways when estimating constantly changing animal movement have been lacking until this time. However with the arrival of state-space models, this problem is partially solved as SSMs acknowledge this problem by allowing unobservable true states to be estimated from data observed with errors which arise from imprecise observations. State-space models use Markov Chain Monte Carlo methods which generate samples from a distribution by constructing a Markov Chain where the current state only depends on the immediately preceding state. The task of fitting SSMs to data is challenging and requires large computational effort and expertise in statistics. With the arrival of the WinBUGs software, this formidable task becomes relatively easy. Though using the WinBUGs software researchers try to visualize the tracks and behaviors, new problems appear. One of the problems is that when marine animals come back to certain places or animals' tracks cross each other several times, the tracks become cluttered and users are not able to understand the direction. Another problem of visualizing the confidence intervals generated using SSMs is that images generated using other systems are static in nature and therefore lack interactivity. Information becomes cluttered when too much data appear. Users are not able to differentiate tracks, confidence intervals or the information they would like to visualize. Acknowledging these, we have designed and implemented an interactive visualization system, MarineVis, where these problems are overcome. Using our system the confidence intervals generated using the SSMs, can be visualized more clearly and the direction of the turtle tracks can be understood easily. Our system does not occlude the underlying terrain as much because the glyphs are localized at the sample points rather than being spread out around the entire path. Our system encodes both direction and position rather than just position. Users can interactively limit the view of data points as a subset of available data points on a path, in clustered regions, to reduce congestion, and can animate the progression of the animal along its trajectory which is absent in existing approaches. All these results are visualized over NASA World Wind maps that facilitates the understanding of the tracks.

Electronically collected animal movement data has been analyzed either statistically or visually using generic geographical information systems. The area of statistical analysis in this field has made progress over the last decade. However, visualizing the movement and behavior remains an open research problem. We have designed and implemented an interactive visualization system, MarineVis,…

Advisors/Committee Members: Not applicable (external-examiner), Dr. Malcolm Heywood (graduate-coordinator), Dr. Norman Scrimger (thesis-reader), Dr. Dirk Arnold, Dr. Stephen Brooks (thesis-supervisor), Not Applicable (ethics-approval), Not Applicable (manuscripts), Not Applicable (copyright-release).

Subjects/Keywords: Uncertainty; visualization; marine; marine animals; SSMs; MCMC; NASA World Wind; geospatial

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Mostafi, M. H. (2011). Visualizing Geospatial Uncertainty in Marine Animal Tracks. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/13500

Chicago Manual of Style (16^th Edition):

Mostafi, Maswood Hasan. “Visualizing Geospatial Uncertainty in Marine Animal Tracks.” 2011. Masters Thesis, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/13500.

MLA Handbook (7^th Edition):

Mostafi, Maswood Hasan. “Visualizing Geospatial Uncertainty in Marine Animal Tracks.” 2011. Web. 09 Mar 2021.

Vancouver:

Mostafi MH. Visualizing Geospatial Uncertainty in Marine Animal Tracks. [Internet] [Masters thesis]. Dalhousie University; 2011. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/13500.

Council of Science Editors:

Mostafi MH. Visualizing Geospatial Uncertainty in Marine Animal Tracks. [Masters Thesis]. Dalhousie University; 2011. Available from: http://hdl.handle.net/10222/13500

Dalhousie University

9. Arora, Rekha. Exceptions and Contingencies Handling in a SCADA System.

Degree: Master of Computer Science, Faculty of Computer Science, 2011, Dalhousie University

URL: http://hdl.handle.net/10222/13497

► The use of rollback is a fundamental flaw in some existing distributed control systems because the advance in time and in external world situations means… (more)

Subjects/Keywords: Exceptions; Contingencies; Resumption model; termination model; SCADA

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Arora, R. (2011). Exceptions and Contingencies Handling in a SCADA System. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/13497

Chicago Manual of Style (16^th Edition):

Arora, Rekha. “Exceptions and Contingencies Handling in a SCADA System.” 2011. Masters Thesis, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/13497.

MLA Handbook (7^th Edition):

Arora, Rekha. “Exceptions and Contingencies Handling in a SCADA System.” 2011. Web. 09 Mar 2021.

Vancouver:

Arora R. Exceptions and Contingencies Handling in a SCADA System. [Internet] [Masters thesis]. Dalhousie University; 2011. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/13497.

Council of Science Editors:

Arora R. Exceptions and Contingencies Handling in a SCADA System. [Masters Thesis]. Dalhousie University; 2011. Available from: http://hdl.handle.net/10222/13497

Dalhousie University

10. Mostafi, Maswood Hasan. Visualizing Geospatial Uncertainty in Marine Animal Tracks.

Degree: Master of Computer Science, Faculty of Computer Science, 2011, Dalhousie University

URL: http://hdl.handle.net/10222/13505

►

Marine animal movement is a fundamental yet poorly understood process. One of the reasons is because our understanding of movement is affected by the measurement… (more)

▼

Marine animal movement is a fundamental yet poorly understood process. One of the reasons is because our understanding of movement is affected by the measurement error during the observation and process noise. Differentiating real movement behavior from observation error in data remains difficult and challenging. Methods that acknowledge uncertainty in movement pathways when estimating constantly changing animal movement have been lacking until this time. However with the arrival of state-space models, this problem is partially solved as SSMs acknowledge this problem by allowing unobservable true states to be estimated from data observed with errors which arise from imprecise observations. State-space models use Markov Chain Monte Carlo methods which generate samples from a distribution by constructing a Markov Chain where the current state only depends on the immediately preceding state. The task of fitting SSMs to data is challenging and requires large computational effort and expertise in statistics. With the arrival of the WinBUGs software, this formidable task becomes relatively easy. Though using the WinBUGs software researchers try to visualize the tracks and behaviors, new problems appear. One of the problems is that when marine animals come back to certain places or animals' tracks cross each other several times, the tracks become cluttered and users are not able to understand the direction. Another problem of visualizing the confidence intervals generated using SSMs is that images generated using other systems are static in nature and therefore lack interactivity. Information becomes cluttered when too much data appear. Users are not able to differentiate tracks, confidence intervals or the information they would like to visualize. Acknowledging these, we have designed and implemented an interactive visualization system, MarineVis, where these problems are overcome. Using our system the confidence intervals generated using the SSMs, can be visualized more clearly and the direction of the turtle tracks can be understood easily. Our system does not occlude the underlying terrain as much because the glyphs are localized at the sample points rather than being spread out around the entire path. Our system encodes both direction and position rather than just position. Users can interactively limit the view of data points as a subset of available data points on a path, in clustered regions, to reduce congestion, and can animate the progression of the animal along its trajectory which is absent in existing approaches. All these results are visualized over NASA World Wind maps that facilitates the understanding of the tracks.

Electronically collected animal movement data has been analyzed either statistically or visually using generic geographical information systems. The area of statistical analysis in this field has made progress over the last decade. However, visualizing the movement and behavior remains an open research problem. We have designed and implemented an interactive visualization system, MarineVis,…

Advisors/Committee Members: Not Applicable (external-examiner), Dr. Malcolm Heywood (graduate-coordinator), Dr. Norman Scrimger (thesis-reader), Dr. Dirk Arnold, Dr. Stephen Brooks (thesis-supervisor), Not Applicable (ethics-approval), Not Applicable (manuscripts), Not Applicable (copyright-release).

Subjects/Keywords: SSM; uncertainty; marine animals

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Mostafi, M. H. (2011). Visualizing Geospatial Uncertainty in Marine Animal Tracks. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/13505

Chicago Manual of Style (16^th Edition):

Mostafi, Maswood Hasan. “Visualizing Geospatial Uncertainty in Marine Animal Tracks.” 2011. Masters Thesis, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/13505.

MLA Handbook (7^th Edition):

Mostafi, Maswood Hasan. “Visualizing Geospatial Uncertainty in Marine Animal Tracks.” 2011. Web. 09 Mar 2021.

Vancouver:

Mostafi MH. Visualizing Geospatial Uncertainty in Marine Animal Tracks. [Internet] [Masters thesis]. Dalhousie University; 2011. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/13505.

Council of Science Editors:

Mostafi MH. Visualizing Geospatial Uncertainty in Marine Animal Tracks. [Masters Thesis]. Dalhousie University; 2011. Available from: http://hdl.handle.net/10222/13505

Dalhousie University

11. Mankowski, Timothy. "Webscraps" – A Tool to Manage Web Information Gathering Tasks.

Degree: Master of Computer Science, Faculty of Computer Science, 2011, Dalhousie University

URL: http://hdl.handle.net/10222/13501

►

Dr. Keselj was the external to my supervision.

Online tasks that involve information gathering, those ranging from academic research to vacation planning, often present challenges… (more)

Subjects/Keywords: Information Gathering; WWW; Webscraps; Web tasks; Prototypes; User Study

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Mankowski, T. (2011). "Webscraps" – A Tool to Manage Web Information Gathering Tasks. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/13501

Chicago Manual of Style (16^th Edition):

Mankowski, Timothy. “"Webscraps" – A Tool to Manage Web Information Gathering Tasks.” 2011. Masters Thesis, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/13501.

MLA Handbook (7^th Edition):

Mankowski, Timothy. “"Webscraps" – A Tool to Manage Web Information Gathering Tasks.” 2011. Web. 09 Mar 2021.

Vancouver:

Mankowski T. "Webscraps" – A Tool to Manage Web Information Gathering Tasks. [Internet] [Masters thesis]. Dalhousie University; 2011. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/13501.

Council of Science Editors:

Mankowski T. "Webscraps" – A Tool to Manage Web Information Gathering Tasks. [Masters Thesis]. Dalhousie University; 2011. Available from: http://hdl.handle.net/10222/13501

Dalhousie University

12. Arndt, Daniel Joseph. An Investigation of Using Machine Learning with Distribution Based Flow Features for Classifying SSL Encrypted Network Traffic.

Degree: Master of Computer Science, Faculty of Computer Science, 2012, Dalhousie University

URL: http://hdl.handle.net/10222/15279

► Encrypted protocols, such as Secure Socket Layer (SSL), are becoming more prevalent because of the growing use of e-commerce, anonymity services, gaming and Peer-to-Peer (P2P)… (more)

Subjects/Keywords: encryption; network security; machine learning; SSL; secure socket layer

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Arndt, D. J. (2012). An Investigation of Using Machine Learning with Distribution Based Flow Features for Classifying SSL Encrypted Network Traffic. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/15279

Chicago Manual of Style (16^th Edition):

Arndt, Daniel Joseph. “An Investigation of Using Machine Learning with Distribution Based Flow Features for Classifying SSL Encrypted Network Traffic.” 2012. Masters Thesis, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/15279.

MLA Handbook (7^th Edition):

Arndt, Daniel Joseph. “An Investigation of Using Machine Learning with Distribution Based Flow Features for Classifying SSL Encrypted Network Traffic.” 2012. Web. 09 Mar 2021.

Vancouver:

Arndt DJ. An Investigation of Using Machine Learning with Distribution Based Flow Features for Classifying SSL Encrypted Network Traffic. [Internet] [Masters thesis]. Dalhousie University; 2012. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/15279.

Council of Science Editors:

Arndt DJ. An Investigation of Using Machine Learning with Distribution Based Flow Features for Classifying SSL Encrypted Network Traffic. [Masters Thesis]. Dalhousie University; 2012. Available from: http://hdl.handle.net/10222/15279

Dalhousie University

13. Atwater, Aaron. Towards Coevolutionary Genetic Programming with Pareto Archiving Under Streaming Data.

Degree: Master of Computer Science, Faculty of Computer Science, 2013, Dalhousie University

URL: http://hdl.handle.net/10222/35358

►

Hyperref'd copy available at: https://web.cs.dal.ca/~atwater/

Classification under streaming data constraints implies that training must be performed continuously, can only access individual exemplars for a short… (more)

Subjects/Keywords: computer science; genetic programming; machine learning; classification

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Atwater, A. (2013). Towards Coevolutionary Genetic Programming with Pareto Archiving Under Streaming Data. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/35358

Chicago Manual of Style (16^th Edition):

Atwater, Aaron. “Towards Coevolutionary Genetic Programming with Pareto Archiving Under Streaming Data.” 2013. Masters Thesis, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/35358.

MLA Handbook (7^th Edition):

Atwater, Aaron. “Towards Coevolutionary Genetic Programming with Pareto Archiving Under Streaming Data.” 2013. Web. 09 Mar 2021.

Vancouver:

Atwater A. Towards Coevolutionary Genetic Programming with Pareto Archiving Under Streaming Data. [Internet] [Masters thesis]. Dalhousie University; 2013. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/35358.

Council of Science Editors:

Atwater A. Towards Coevolutionary Genetic Programming with Pareto Archiving Under Streaming Data. [Masters Thesis]. Dalhousie University; 2013. Available from: http://hdl.handle.net/10222/35358

Dalhousie University

14. Mason, Jane E. An n-gram Based Approach to the Automatic Classification of Web Pages by Genre.

Degree: PhD, Faculty of Computer Science, 2009, Dalhousie University

URL: http://hdl.handle.net/10222/12351

► The extraordinary growth in both the size and popularity of the World Wide Web has generated a growing interest in the identification of Web page… (more)

▼ The extraordinary growth in both the size and popularity of the World Wide Web has generated a growing interest in the identification of Web page genres, and in the use of these genres to classify Web pages. Web page genre classification is a potentially powerful tool for filtering the results of online searches. Although most information retrieval searches are topic-based, users are typically looking for a specific type of information with regard to a particular query, and genre can provide a complementary dimension along which to categorize Web pages. Web page genre classification could also aid in the automated summarization and indexing of Web pages, and in improving the automatic extraction of metadata. The hypothesis of this thesis is that a byte n-gram representation of a Web page can be used effectively to classify the Web page by its genre(s). The goal of this thesis was to develop an approach to the problem of Web page genre classification that is effective not only on balanced, single-label corpora, but also on unbalanced and multi-label corpora, which better represent a real world environment. This thesis research develops n-gram representations for Web pages and Web page genres, and based on these representations, a new approach to the classification of Web pages by genre is developed. The research includes an exhaustive examination of the questions associated with developing the new classification model, including the length, number, and type of the n-grams with which each Web page and Web page genre is represented, the method of computing the distance (dissimilarity) between two n-gram representations, and the feature selection method with which to choose these n-grams. The effect of preprocessing the data is also studied. Techniques for setting genre thresholds in order to allow a Web page to belong to more than one genre, or to no genre at all are also investigated, and a comparison of the classification performance of the new classification model with that of the popular support vector machine approach is made. Experiments are also conducted on highly unbalanced corpora, both with and without the inclusion of noise Web pages. Advisors/Committee Members: Dr. Stan Matwin (external-examiner), Dr. Malcolm Heywood (graduate-coordinator), Dr. Jack Duffy (thesis-reader), Dr. Vlado Keselj (thesis-reader), Dr. Michael Shepherd, Dr. Evangelos Milios (thesis-supervisor).

Subjects/Keywords: Web page classification; Web page genre; information retrieval

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Mason, J. E. (2009). An n-gram Based Approach to the Automatic Classification of Web Pages by Genre. (Doctoral Dissertation). Dalhousie University. Retrieved from http://hdl.handle.net/10222/12351

Chicago Manual of Style (16^th Edition):

Mason, Jane E. “An n-gram Based Approach to the Automatic Classification of Web Pages by Genre.” 2009. Doctoral Dissertation, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/12351.

MLA Handbook (7^th Edition):

Mason, Jane E. “An n-gram Based Approach to the Automatic Classification of Web Pages by Genre.” 2009. Web. 09 Mar 2021.

Vancouver:

Mason JE. An n-gram Based Approach to the Automatic Classification of Web Pages by Genre. [Internet] [Doctoral dissertation]. Dalhousie University; 2009. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/12351.

Council of Science Editors:

Mason JE. An n-gram Based Approach to the Automatic Classification of Web Pages by Genre. [Doctoral Dissertation]. Dalhousie University; 2009. Available from: http://hdl.handle.net/10222/12351

Dalhousie University

15. Tanta-ngai, Hathai. SHRACK: A SELF-ORGANIZING PEER-TO-PEER SYSTEM FOR DOCUMENT SHARING AND TRACKING.

Degree: PhD, Faculty of Computer Science, 2010, Dalhousie University

URL: http://hdl.handle.net/10222/12814

► Given a set of peers with overlapping interests where each peer wishes to keep track of new documents that are relevant to their interests, we… (more)

▼ Given a set of peers with overlapping interests where each peer wishes to keep track of new documents that are relevant to their interests, we propose Shrack-a self-organizing peer-to-peer (P2P) system for document sharing and tracking. The goal of a document-tracking system is to disseminate new documents as they are published. We present a framework of Shrack and propose a gossip-like pull-only information dissemination protocol. We explore and develop mechanisms to enable a self-organizing network, based on common interest of document sets among peers. Shrack peers collaboratively share new documents of interest with other peers. Interests of peers are modeled using relevant document sets and are represented as peer profiles. There is no explicit pro file exchange between peers and no global information available. We describe how peers create their user pro files, discover the existence of other peers, locally learn about interest of other peers, and finally form a self-organizing overlay network of peers with common interests. Unlike most existing P2P file sharing systems which serve their users by finding relevant documents based on an instant query, Shrack is designed to help users that have long-term interests to keep track of relevant documents that are newly available in the system. The framework can be used as an infrastructure for any kind of documents and data, but in this thesis, we focus on research publications. We built an event-driven simulation to evaluate the performance and behaviour of Shrack. We model simulated users associated with peers after a subset of authors in the ACM digital library metadata collection. The experimental results demonstrate that the Shrack dissemination protocol is scalable as the network size increases. In addition, self-organizing overlay networks, where connections between peers are based on common interests as captured by their associated document sets, can help improve the relevance of documents received by peers in terms of F-score over random peer networks. Moreover, the resulting self-organizing networks have the characteristics of social networks. Advisors/Committee Members: Dr. Jimmy Huang (external-examiner), Dr. Malcolm Heywood (graduate-coordinator), Dr. Nick Cercone (thesis-reader), Heywood%22%29&pagesize-30">Dr. Nur Zincir-Heywood (thesis-reader), Dr. Evangelos E. Milios and Dr. Vlado Keselj (thesis-supervisor), Not Applicable (ethics-approval), Not Applicable (manuscripts), Not Applicable (copyright-release).

Subjects/Keywords: peer-to-peer systems; document tracking; self-organizing networks; recommendation

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Tanta-ngai, H. (2010). SHRACK: A SELF-ORGANIZING PEER-TO-PEER SYSTEM FOR DOCUMENT SHARING AND TRACKING. (Doctoral Dissertation). Dalhousie University. Retrieved from http://hdl.handle.net/10222/12814

Chicago Manual of Style (16^th Edition):

Tanta-ngai, Hathai. “SHRACK: A SELF-ORGANIZING PEER-TO-PEER SYSTEM FOR DOCUMENT SHARING AND TRACKING.” 2010. Doctoral Dissertation, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/12814.

MLA Handbook (7^th Edition):

Tanta-ngai, Hathai. “SHRACK: A SELF-ORGANIZING PEER-TO-PEER SYSTEM FOR DOCUMENT SHARING AND TRACKING.” 2010. Web. 09 Mar 2021.

Vancouver:

Tanta-ngai H. SHRACK: A SELF-ORGANIZING PEER-TO-PEER SYSTEM FOR DOCUMENT SHARING AND TRACKING. [Internet] [Doctoral dissertation]. Dalhousie University; 2010. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/12814.

Council of Science Editors:

Tanta-ngai H. SHRACK: A SELF-ORGANIZING PEER-TO-PEER SYSTEM FOR DOCUMENT SHARING AND TRACKING. [Doctoral Dissertation]. Dalhousie University; 2010. Available from: http://hdl.handle.net/10222/12814

Dalhousie University

16. Bacquet, Carlos. An Investigation of a Multi-Objective Genetic Algorithm applied to Encrypted Traffic Identification.

Degree: Master of Computer Science, Faculty of Computer Science, 2010, Dalhousie University

URL: http://hdl.handle.net/10222/13016

► This work explores the use of a Multi-Objective Genetic Algorithm (MOGA) for both, feature selection and cluster count optimization, for an unsupervised machine learning technique,… (more)

Subjects/Keywords: Network Traffic Identification; Encrypted Traffic

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Bacquet, C. (2010). An Investigation of a Multi-Objective Genetic Algorithm applied to Encrypted Traffic Identification. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/13016

Chicago Manual of Style (16^th Edition):

Bacquet, Carlos. “An Investigation of a Multi-Objective Genetic Algorithm applied to Encrypted Traffic Identification.” 2010. Masters Thesis, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/13016.

MLA Handbook (7^th Edition):

Bacquet, Carlos. “An Investigation of a Multi-Objective Genetic Algorithm applied to Encrypted Traffic Identification.” 2010. Web. 09 Mar 2021.

Vancouver:

Bacquet C. An Investigation of a Multi-Objective Genetic Algorithm applied to Encrypted Traffic Identification. [Internet] [Masters thesis]. Dalhousie University; 2010. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/13016.

Council of Science Editors:

Bacquet C. An Investigation of a Multi-Objective Genetic Algorithm applied to Encrypted Traffic Identification. [Masters Thesis]. Dalhousie University; 2010. Available from: http://hdl.handle.net/10222/13016

Dalhousie University

17. Hamilton, Christopher. Range Searching Data Structures with Cache Locality.

Degree: PhD, Faculty of Computer Science, 2011, Dalhousie University

URL: http://hdl.handle.net/10222/13363

► This thesis focuses on range searching data structures, an elementary problem in computational geometry with research spanning decades. These problems often involve very large data… (more)

▼ This thesis focuses on range searching data structures, an elementary problem in computational geometry with research spanning decades. These problems often involve very large data sets. Processor speeds increase faster than memory speeds, thus the gap between the rate at which CPUs can process data and the rate at which it can be retrieved is increasing. To bridge this gap, various levels of cache are used. Since cache misses are costly, algorithms should be cache-friendly. The input-output (I/O) model was the first model for constructing cache-efficient algorithms, focusing on a two-level memory hierarchy. Algorithms for this model require manual tuning to determine optimal values for hardware dependent parameters, and are only optimal at a single level of a memory hierarchy. Cache-oblivious (CO) algorithms are built without knowledge of the hierarchy, allowing them to be optimal across all levels at once. There exist strong theoretical and practical results for I/O-efficient range searching. Recently, the CO model has received attention, but range searching remains poorly understood. This thesis explores data structures for CO range counting and reporting. It presents the first space and worst-case query-time optimal approximate range counting structure for a family of related problems, and associated O(N log N)-space query-optimal reporting structures. The approximate counting structure is the first of its kind in internal memory, I/O and CO models. Researchers have been trying to create linear-space query-optimal CO reporting structures. This thesis shows that for a variety of problems, linear space is in fact impossible. Heuristics are also used for building cache-friendly algorithms. Space-filling curves are continuous functions mapping multi-dimensional sets into one-dimensional ones. They are used to build search structures in the hopes that objects that were close in the original space remain close in the resulting ordering. This results in queries incurring fewer page swaps when traversing the structure. The Hilbert curve is notably good at this, but often imposes a space or time penalty. This thesis introduces compact Hilbert indices, which remove the ineffiency inherent for input point sets with bounding boxes smaller than their bounding hypercubes. Advisors/Committee Members: Dr. Pat Morin (external-examiner), Dr. Malcolm Heywood (graduate-coordinator), Dr. Andrew Rau-Chaplin (thesis-reader), Dr. Alex Brodsky (thesis-reader), Dr. Norbert Zeh (thesis-supervisor), Not Applicable (ethics-approval), Not Applicable (manuscripts), Not Applicable (copyright-release).

Subjects/Keywords: computational geometry; range searching; range counting; approximate range counting; external memory; cache oblivious; data structures; algorithms; space-filling curves; Hilbert curve; orthogonal range searching; halfspace range searching; shallow cuttings; lower bounds

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Hamilton, C. (2011). Range Searching Data Structures with Cache Locality. (Doctoral Dissertation). Dalhousie University. Retrieved from http://hdl.handle.net/10222/13363

Chicago Manual of Style (16^th Edition):

Hamilton, Christopher. “Range Searching Data Structures with Cache Locality.” 2011. Doctoral Dissertation, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/13363.

MLA Handbook (7^th Edition):

Hamilton, Christopher. “Range Searching Data Structures with Cache Locality.” 2011. Web. 09 Mar 2021.

Vancouver:

Hamilton C. Range Searching Data Structures with Cache Locality. [Internet] [Doctoral dissertation]. Dalhousie University; 2011. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/13363.

Council of Science Editors:

Hamilton C. Range Searching Data Structures with Cache Locality. [Doctoral Dissertation]. Dalhousie University; 2011. Available from: http://hdl.handle.net/10222/13363

Dalhousie University

18. Alshammari, Riyad. Automatically Generating Robust Signatures Using a Machine Learning Approach to Unveil Encrypted VoIP Traffic Without Using Port Numbers, IP Addresses and Payload Inspection.

Degree: PhD, Faculty of Computer Science, 2012, Dalhousie University

URL: http://hdl.handle.net/10222/14872

► The identification of encrypted network traffic represents an important issue for network management tasks including quality of service, firewall enforcement and security. Traffic identification becomes… (more)

▼ The identification of encrypted network traffic represents an important issue for network management tasks including quality of service, firewall enforcement and security. Traffic identification becomes more and more challenging as the traditional techniques such as port numbers or deep packet inspection are becoming ineffective against applications such as the Peer-to-Peer (P2P) Voice over Internet Protocol (VoIP), which uses non-standard ports and encryption. Thus, different approaches such as machine learning (ML) are explored in the literature for traffic classification. However, traffic classification represents a particularly challenging application domain for ML. Ideally, solutions should be both simple (hence efficient to deploy) and accurate. Recent advances in ML provide the opportunity to decompose the original problem into a subset of classifiers with non-overlapping behaviours, in effect providing further insight into the problem domain and increasing the throughput of solutions. Thus, this thesis presents a novel approach for generating robust signatures to classify P2P VoIP traffic using a ML-based approach, specifically with the C5.0, GP and AdaBoost classification algorithms. In this research, simple packet header feature sets and statistical flow feature sets are explored without using the IP addresses, source/destination ports and payload information to unveil the encrypted VoIP application in network traffic. In this context, what is meant by robust signatures are those which have been learned by training on one network are still valid when they are applied to traffic coming from different time periods, different networks (locations) as well as under evasion attacks that are designed to bypass such a classifier. Results show that the performance of the automatically generated signatures does not degrade significantly when evaluated against the robustness criteria. These results demonstrate that flow-based statistical features (temporal information) with the use of a ML-based approach can achieve high classification accuracy and produce robust signatures. Furthermore, the results on the evasion experiments demonstrate that the performance of the signatures is very promising if a malicious user tries to alter the characteristics of VoIP (specifically, Skype) traffic to evade the classifier. Advisors/Committee Members: Dr. Mourad Debbabi (external-examiner), Dr. Qigang Gao (graduate-coordinator), Dr. Malcolm Heywood (thesis-reader), Dr. Srinivas Sampalli (thesis-reader), Heywood%22%29&pagesize-30">Dr. A. Nur Zincir-Heywood (thesis-supervisor), Not Applicable (ethics-approval), Not Applicable (manuscripts), Not Applicable (copyright-release).

Subjects/Keywords: Subject Not Available

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Alshammari, R. (2012). Automatically Generating Robust Signatures Using a Machine Learning Approach to Unveil Encrypted VoIP Traffic Without Using Port Numbers, IP Addresses and Payload Inspection. (Doctoral Dissertation). Dalhousie University. Retrieved from http://hdl.handle.net/10222/14872

Chicago Manual of Style (16^th Edition):

Alshammari, Riyad. “Automatically Generating Robust Signatures Using a Machine Learning Approach to Unveil Encrypted VoIP Traffic Without Using Port Numbers, IP Addresses and Payload Inspection.” 2012. Doctoral Dissertation, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/14872.

MLA Handbook (7^th Edition):

Alshammari, Riyad. “Automatically Generating Robust Signatures Using a Machine Learning Approach to Unveil Encrypted VoIP Traffic Without Using Port Numbers, IP Addresses and Payload Inspection.” 2012. Web. 09 Mar 2021.

Vancouver:

Alshammari R. Automatically Generating Robust Signatures Using a Machine Learning Approach to Unveil Encrypted VoIP Traffic Without Using Port Numbers, IP Addresses and Payload Inspection. [Internet] [Doctoral dissertation]. Dalhousie University; 2012. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/14872.

Council of Science Editors:

Alshammari R. Automatically Generating Robust Signatures Using a Machine Learning Approach to Unveil Encrypted VoIP Traffic Without Using Port Numbers, IP Addresses and Payload Inspection. [Doctoral Dissertation]. Dalhousie University; 2012. Available from: http://hdl.handle.net/10222/14872

Dalhousie University

19. Rahimi, Sara. Label Free Change Detection on Streaming Data with Cooperative Multi-objective Genetic Programming.

Degree: Master of Computer Science, Faculty of Computer Science, 2013, Dalhousie University

URL: http://hdl.handle.net/10222/35420

► Classification under streaming data conditions requires that the machine learning approach operate interactively with the stream content. Thus, given some initial machine learning classification capability,… (more)

Subjects/Keywords: Change Detection; Streaming Data; Genetic Programming

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Rahimi, S. (2013). Label Free Change Detection on Streaming Data with Cooperative Multi-objective Genetic Programming. (Masters Thesis). Dalhousie University. Retrieved from http://hdl.handle.net/10222/35420

Chicago Manual of Style (16^th Edition):

Rahimi, Sara. “Label Free Change Detection on Streaming Data with Cooperative Multi-objective Genetic Programming.” 2013. Masters Thesis, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/35420.

MLA Handbook (7^th Edition):

Rahimi, Sara. “Label Free Change Detection on Streaming Data with Cooperative Multi-objective Genetic Programming.” 2013. Web. 09 Mar 2021.

Vancouver:

Rahimi S. Label Free Change Detection on Streaming Data with Cooperative Multi-objective Genetic Programming. [Internet] [Masters thesis]. Dalhousie University; 2013. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/35420.

Council of Science Editors:

Rahimi S. Label Free Change Detection on Streaming Data with Cooperative Multi-objective Genetic Programming. [Masters Thesis]. Dalhousie University; 2013. Available from: http://hdl.handle.net/10222/35420

20. Rahman, Musfiq. A Novel Scalable Key Management Protocol for Wireless Sensor Networks.

Degree: PhD, Faculty of Computer Science, 2013, Dalhousie University

URL: http://hdl.handle.net/10222/21683

► Wireless Sensor Networks (WSNs) are ad-hoc networks consisting of tiny battery- operated wireless sensors. The sensor nodes are lightweight in terms of memory, computation, energy… (more)

▼ Wireless Sensor Networks (WSNs) are ad-hoc networks consisting of tiny battery- operated wireless sensors. The sensor nodes are lightweight in terms of memory, computation, energy and communication. These networks are usually deployed in unsecured, open, and harsh environments, where it is difficult for humans to perform continuous monitoring. Consequently, it is very crucial to provide security mecha- nisms for authenticating data among sensor nodes. Key management is a pre-requisite for any security mechanism. Efficient distribution and management of keys in WSNs is a challenging task. Many standard key establishment techniques have been pro- posed using symmetric cryptosystems. Unfortunately, these systems often fail to pro- vide a good trade-off between memory and security and since WSNs are lightweight in nature, these cryptosystems are not feasible. On the other hand, public key in- frastructure (PKI) is infeasible in WSNs because of its continuous requirement of a trusted third party and heavy computational demands for certificate verification. Pairing-Based Cryptography (PBC) has paved the way for how parties can agree on keys without any interaction. It has relaxed the requirement of expensive certificate verification on PKI systems. In this thesis, we propose a new hybrid identity-based non-interactive key management protocol for WSNs, which leverages the benefits of both symmetric key based cryptosystems and pairing-based cryptosystems. The pro- posed protocol is scalable, suits many applications and can be deployed in multiple types of networks without modifications. We also provide mechanisms for key refresh when the network topology changes. A security analysis is presented to prove that the scheme is resilient to many types of attacks. To validate our scheme, we have implemented it on Crossbow TelosB motes running TinyOS and analyzed the perfor- mance in terms of memory, communication, computation and energy consumption. The results indicate that our scheme can be deployed efficiently to provide high level of security in a large-scale network without increasing memory, communication and energy overheads. Advisors/Committee Members: Dr. Sagar Naik (external-examiner), Dr. Malcolm Heywood (graduate-coordinator), Dr. Keith Johnson (thesis-reader), Heywood%22%29&pagesize-30">Dr. Nur Zincir-Heywood (thesis-reader), Dr. Vlado Keselj (thesis-reader), Dr.Srinivas Sampalli (thesis-supervisor), Not Applicable (ethics-approval), Not Applicable (manuscripts), Not Applicable (copyright-release).

Subjects/Keywords: Key Management; PBC; Security; Wireless Sensor Network; WSN; WSN Security

2 more images…

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Rahman, M. (2013). A Novel Scalable Key Management Protocol for Wireless Sensor Networks. (Doctoral Dissertation). Dalhousie University. Retrieved from http://hdl.handle.net/10222/21683

Chicago Manual of Style (16^th Edition):

Rahman, Musfiq. “A Novel Scalable Key Management Protocol for Wireless Sensor Networks.” 2013. Doctoral Dissertation, Dalhousie University. Accessed March 09, 2021. http://hdl.handle.net/10222/21683.

MLA Handbook (7^th Edition):

Rahman, Musfiq. “A Novel Scalable Key Management Protocol for Wireless Sensor Networks.” 2013. Web. 09 Mar 2021.

Vancouver:

Rahman M. A Novel Scalable Key Management Protocol for Wireless Sensor Networks. [Internet] [Doctoral dissertation]. Dalhousie University; 2013. [cited 2021 Mar 09]. Available from: http://hdl.handle.net/10222/21683.

Council of Science Editors:

Rahman M. A Novel Scalable Key Management Protocol for Wireless Sensor Networks. [Doctoral Dissertation]. Dalhousie University; 2013. Available from: http://hdl.handle.net/10222/21683

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

Open Access Theses and Dissertations