Computer Sciences Commons^™

Weight-Based Boosting Model For Cross-Domain Relevance Ranking Adaptation, Peng Cai, Wei Gao, Kam-Fai Wong, Aoying Zhou

Research Collection School Of Computing and Information Systems

Adaptation techniques based on importance weighting were shown effective for RankSVM and RankNet, viz., each training instance is assigned a target weight denoting its importance to the target domain and incorporated into loss functions. In this work, we extend RankBoost using importance weighting framework for ranking adaptation. We find it non-trivial to incorporate the target weight into the boosting-based ranking algorithms because it plays a contradictory role against the innate weight of boosting, namely source weight that focuses on adjusting source-domain ranking accuracy. Our experiments show that among three variants, the additive weight-based RankBoost, which dynamically balances the two types …

Semantic Relevance Analysis Of Subject-Predicate-Object (Spo) Triples, Ranjana Kumar

Student Work

The goal of this thesis is to explore and integrate several existing measurements for ranking the relevance of a set of subject-predicate-object (SPO) triples to a given concept. As we are inundated with information from multiple sources on the World-Wide-Web, SPO similarity measures play a progressively important role in information extraction, information retrieval, document clustering and ontology learning. This thesis is applied in the Cyber Security Domain for identifying and understanding the factors and elements of sociopolitical events relevant to cyberattacks. Our efforts are towards developing an algorithm that begins with an analysis of news articles by taking into account …

Dynamic Reconfiguration In Modular Self-Reconfigurable Robots Using Multi-Agent Coalition Games, Zachary Ramaekers

Student Work

In this thesis, we consider the problem of autonomous self-reconfiguration by modular self-reconfigurable robots (MSRs). MSRs are composed of small units or modules that can be dynamically configured to form different structures, such as a lattice or a chain. The main problem in maneuvering MSRs is to enable them to autonomously reconfigure their structure depending on the operational conditions in the environment. We first discuss limitations of previous approaches to solve the MSR self-reconfiguration problem. We will then present a novel framework that uses a layered architecture comprising a conventional gait table-based maneuver to move the robot in a fixed …

Predicting Item Adoption Using Social Correlation, Freddy Chong-Tat Chua, Hady W. Lauw, Ee Peng Lim

Research Collection School Of Computing and Information Systems

Users face a dazzling array of choices on the Web when it comes to choosing which product to buy, which video to watch, etc. The trend of social information processing means users increasingly rely not only on their own preferences, but also on friends when making various adoption decisions. In this paper, we investigate the effects of social correlation on users’ adoption of items. Given a user-user social graph and an item-user adoption graph, we seek to answer the following questions: 1) whether the items adopted by a user correlate to items adopted by her friends, and 2) how to …

Mkboost: A Framework Of Multiple Kernel Boosting, Hao Xia, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Multiple kernel learning (MKL) has been shown as a promising machine learning technique for data mining tasks by integrating with multiple diverse kernel functions. Traditional MKL methods often formulate the problem as an optimization task of learning both optimal combination of kernels and classifiers, and attempt to resolve the challenging optimization task by various techniques. Unlike the existing MKL methods, in this paper, we investigate a boosting framework of exploring multiple kernel learning for classification tasks. In particular, we present a novel framework of Multiple Kernel Boosting (MKBoost), which applies boosting techniques for learning kernel-based classifiers with multiple kernels. Based …

Peercast: Improving Link Layer Multicast Through Cooperative Relaying, Jie Xiong, Romit Roy Choudhury

Research Collection School Of Computing and Information Systems

Wireless multicast applications, such as MobiTV, web telecast, and multimedia classrooms, are gaining rapid popularity. The broadcast nature of the wireless channel is amenable to such multicasts because a single packet transmission can be received by all clients. Unfortunately, the rate of this transmission is bottlenecked by data rate of the weakest client, degrading system performance. Attempts to increase the data rate results in lower reliability and higher unfairness. This paper presents PeerCast, a wireless multicast protocol that engages clients in cooperative relaying. The main idea is simple. Instead of multicasting at the bottleneck rate, the access point transmits at …

Identifying An Optimal Dining Plan System For The Entertainment Industry, Joseph Crimi

Doctoral Dissertations and Master's Theses

The Disney Dining Plan (DDP) is a pre-paid meal plan guests can purchase when they make their reservation at Walt Disney World (WDW). Under the current system, the information provided to guests explaining the program is unclear which leads to confusion for guests. For example, guests are not sure what food they can purchase using the DDP or at which dining locations they can use the DDP. Given these problems, the present study evaluated a new information system for the DDP. The independent variables in this study were symbol type, the symbols used in the current DDP and new symbols …

Ab Initio Protein Structure Prediction Algorithms, Maciej Kicinski

Master's Projects

Genes that encode novel proteins are constantly being discovered and added to databases, but the speed with which their structures are being determined is not keeping up with this rate of discovery. Currently, homology and threading methods perform the best for protein structure prediction, but they are not appropriate to use for all proteins. Still, the best way to determine a protein's structure is through biological experimentation. This research looks into possible methods and relations that pertain to ab initio protein structure prediction. The study includes the use of positional and transitional probabilities of amino acids obtained from a non-redundant …

Model-Controller Interfacing Using Struts-Based Web Application, Deepti Bhardwaj

Master's Projects

StrutsHib IDE is an IDE for interfacing the model and controller of a MVC architecture based applications. It is developed using Java-based technologies such as the Struts framework, Hibernate and jQuery. The StrutsHib IDE is a web application. This project implements the part of StrutsHib IDE that makes it easy to create model and controller components. Moreover, it automates the process of database creation for web applications which means the user does not have to be a database expert when dealing with databases. Finally, StrutsHib IDE takes all the advantages of a web-based application and provides lot of flexibility to …

Evaluation Of Classical Inter-Process Communication Problems In Parallel Programming Languages, Arunesh Joshi

Master's Projects

It is generally believed for the past several years that parallel programming is the future of computing technology due to its incredible speed and vastly superior performance as compared to classic linear programming. However, how sure are we that this is the case? Despite its aforesaid average superiority, usually parallel-program implementations run in single-processor machines, making the parallelism almost virtual. In this case, does parallel programming still remain superior?
The purpose of this document is to research and analyze the performance, in both storage and speed, of three parallel-programming language libraries: OpenMP, OpenMPI and PThreads, along with a few other …

Metamorphic Detection Via Emulation, Sushant Priyadarshi

Master's Projects

In parallel with improvements in anti-virus technologies, computer virus writers have developed innovative viruses that are challenging to detect. Metamorphic viruses change their appearance from one generation to another by using various code obfuscation techniques. Today, signature detection is the most common method used in anti-virus products, but well designed metamorphic viruses cannot be detected using signatures. Hence, there is a need for a more robust anti-virus technology.
To counter metamorphic virus, a very successful tool based on hidden Markov models (HMM) has been previously developed. This tool was able to detect all hacker produced metamorphic viruses on which it …

Dynamic Code Checksum Generator, Ashish Sharma

Master's Projects

A checksum (i.e., a cryptographic hash) of a file can be used as an integrity check, if an attacker tries to change the code in an executable file, a checksum can be used to detect the tampering. While it is easy to compute a checksum for any static file, it is possible for an attacker to tamper with an executable file as it is being loaded into memory, or after it has been loaded. Therefore, it would be more useful to checksum an executable file dynamically only after the file has been loaded into memory. However, checksumming dynamic code is …

Bittorrent Traffic Detection With Deep Packet Inspection And Deep Flow Inspection, Raymond Wong

Master's Projects

The peer-to-peer (P2P) technology has been well developed with the internet networking and BitTorrent (BT) is one of the very popular P2P sharing protocols widely used. BT network traffic detection has become very challenging in recent years due to smarter peer-to-peer applications. During my CS297 project, a new improved detection method based on Deep Packet Inspection (DPI) and Deep Flow Inspection (DFI) was proposed for detecting BT packets. The preliminary experiments show promising results in terms of detection rate. In my CS298 project, the proposed method is implemented in C and Matlab. In addition, the detection rate and performance of …

Computational Complexity Of Approximate And Precise Data With Constraint Automaton, Dipty Singh

School of Computing: Dissertations, Theses, and Student Research

The DNA molecules packaged in structures called chromosomes within the cells of living organisms encode hereditary information that is passed on to their offspring. Using transcription and translation, the genes within these DNA molecules help in protein synthesis. Thus chromosomal DNA serves as a blueprint for the chemical processes of life.

In order to analyze a DNA sequence by currently available technology, we have to cut it into small fragments, e.g. by using restriction enzymes. The application of different restriction enzymes to the multiple copies of the same DNA sequence generates many overlapping fragments. In order to construct the original …

Rethinking The Patch Test For Phase Measuring Bathymetric Sonars, Janice Eisenberg, Michael Davidson, Jonathan Beaudoin, Steve Brodet

Center for Coastal and Ocean Mapping

While conducting hydrographic survey operations in the Florida Keys, NOAA Ship Thomas Jefferson served as a test platform for the initial operational implementation of an L-3 Klein HydroChart 5000 Swath Bathymetry Sonar System1 , a hull-mounted phase measuring bathymetric sonar (PMBS). During the project it became apparent that the traditional patch test typically utilized for multibeam echosounder (MBES) systems was poorly suited to the HydroChart – and perhaps other PMBS systems as well. These systems have several inherent characteristics that make it difficult to isolate and subsequently solve for biases under the traditional patch test paradigm: presence of a nadir …

Heterogeneous Signcryption With Key Privacy, Qiong Huang, Duncan S. Wong, Guomin Yang

Research Collection School Of Computing and Information Systems

A signcryption scheme allows a sender to produce a ciphertext for a receiver so that both confidentiality and non-repudiation can be ensured. It is built to be more efficient and secure, for example, supporting insider security, when compared with the conventional sign-then-encrypt approach. In this paper, we propose a new notion called heterogeneous signcryption in which the sender has an identity-based secret key while the receiver is holding a certificate-based public key pair. Heterogeneous signcryption is suitable for practical scenarios where an identity-based user, who does not have a personal certificate or a public key, wants to communicate securely with …

Confidence Weighted Mean Reversion Strategy For On-Line Portfolio Selection, Bin Li, Steven C. H. Hoi, Peilin Zhao, Vivek Gopalkrishnan

Research Collection School Of Computing and Information Systems

On-line portfolio selection has been attracting increasing attention from the data mining and machine learning communities. All existing on-line portfolio selection strategies focus on the first order information of a portfolio vector, though the second order information may also be beneficial to a strategy. Moreover, empirical evidences show that the stock price relatives may follow the mean reversion property, which has not been fully exploited by existing strategies. This article proposes a novel on-line portfolio selection strategy named ``Confidence Weighted Mean Reversion'' (CWMR). Inspired by the mean reversion principle in finance and confidence weighted online learning technique in machine learning, …

Random Keys Genetic Algorithms Scheduling And Rescheduling Systems For Common Production Systems, Elkin Rodriguez-Velasquez

Engineering Management & Systems Engineering Theses & Dissertations

The majority of scheduling research deals with problems in specific production environments with specific objective functions. However, in many cases, more than one problem type and/or objective function exists, resulting in the need for a more generic and flexible system to generate schedules. Furthermore, most of the published scheduling research focuses on creating an optimal or near optimal initial schedule during the planning phase. However, after production processes start, circumstances like machine breakdowns, urgent jobs, and other unplanned events may render the schedule suboptimal, obsolete or even infeasible resulting in a "rescheduling" problem, which is typically also addressed for a …

Learning Feature Dependencies For Noise Correction In Biomedical Prediction, Ghim-Eng Yap, Ah-Hwee Tan, Hwee Hwa Pang

Research Collection School Of Computing and Information Systems

The presence of noise or errors in the stated feature values of biomedical data can lead to incorrect prediction. We introduce a Bayesian Network-based Noise Correction framework named BN-NC. After data preprocessing, a Bayesian Network (BN) is learned to capture the feature dependencies. Using the BN to predict each feature in turn, BN-NC estimates a feature's error rate as the deviation between its predicted and stated values in the training data, and allocates the appropriate uncertainty to its subsequent findings during prediction. BN-NC automatically generates a probabilistic rule to explain BN prediction on the class variable using the feature values …

Corn: Correlation-Driven Nonparametric Learning Approach For Portfolio Selection, Bin Li, Steven C. H. Hoi, Vivekanand Gopalkrishnan

Research Collection School Of Computing and Information Systems

Machine learning techniques have been adopted to select portfolios from financial markets in some emerging intelligent business applications. In this article, we propose a novel learning-to-trade algorithm termed CO Relation-driven Nonparametric learning strategy (CORN) for actively trading stocks. CORN effectively exploits statistical relations between stock market windows via a nonparametric learning approach. We evaluate the empirical performance of our algorithm extensively on several large historical and latest real stock markets, and show that it can easily beat both the market index and the best stock in the market substantially (without or with small transaction costs), and also surpass a variety …

Abstracting Events For Data Mining, David Lo, Ganesan Ramalingam, Venkatesh-Prasad Ranganath, Kapil Vaswani

Research Collection School Of Computing and Information Systems

An event is described herein as being representable by a quantified abstraction of the event. The event includes at least one predicate, and the at least one predicate has at least one constant symbol corresponding thereto. An instance of the constant symbol corresponding to the event is identified, and the instance of the constant symbol is replaced by a free variable to obtain an abstracted predicate. Thus, a quantified abstraction of the event is composed as a pair: the abstracted predicate and a mapping between the free variable and an instance of the constant symbol that corresponds to the predicate. …

Fusing Heterogeneous Modalities For Video And Image Re-Ranking, Hung-Khoon Tan, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Multimedia documents in popular image and video sharing websites such as Flickr and Youtube are heterogeneous documents with diverse ways of representations and rich user-supplied information. In this paper, we investigate how the agreement among heterogeneous modalities can be exploited to guide data fusion. The problem of fusion is cast as the simultaneous mining of agreement from different modalities and adaptation of fusion weights to construct a fused graph from these modalities. An iterative framework based on agreement-fusion optimization is thus proposed. We plug in two well-known algorithms: random walk and semi-supervised learning to this framework to illustrate the idea …

Ir-Tree: An Efficient Index For Geographic Document Search, Zhisheng Li, Ken C. K. Lee, Baihua Zheng, Wang-Chien Lee, Dik Lun Lee, Xufa Wang

Research Collection School Of Computing and Information Systems

Given a geographic query that is composed of query keywords and a location, a geographic search engine retrieves documents that are the most textually and spatially relevant to the query keywords and the location, respectively, and ranks the retrieved documents according to their joint textual and spatial relevances to the query. The lack of an efficient index that can simultaneously handle both the textual and spatial aspects of the documents makes existing geographic search engines inefficient in answering geographic queries. In this paper, we propose an efficient index, called IR-tree, that together with a top-k document search algorithm facilitates four …

Utility-Oriented K-Anonymization On Social Networks, Yazhe Wang, Long Xie, Baihua Zheng, Ken C. K. Lee

Research Collection School Of Computing and Information Systems

"Identity disclosure" problem on publishing social network data has gained intensive focus from academia. Existing k-anonymization algorithms on social network may result in nontrivial utility loss. The reason is that the number of the edges modified when anonymizing the social network is the only metric to evaluate utility loss, not considering the fact that different edge modifications have different impact on the network structure. To tackle this issue, we propose a novel utility-oriented social network anonymization scheme to achieve privacy protection with relatively low utility loss. First, a proper utility evaluation model is proposed. It focuses on the changes on …

Solving The Vehicle Re-Identification Problem By Using Neural Networks, Tanweer Rashid

Computational Modeling & Simulation Engineering Theses & Dissertations

Vehicle re-identification is the process by which vehicle attributes measured at one point on a road network are compared to vehicle attributes measured at another point in an effort to match vehicles without using any unique identifiers such as license plate numbers. A match is made if the two measurements are estimated to belong to the same vehicle. Vehicle attributes can be sensor readings such as loop induction signatures, or they can also be actual vehicle characteristics such as length, weight, number of axles, etc. This research makes use of vehicle length, travel time, axle spacing and axle weights for …

Design And Demonstration Of A Miniature Lidar System For Rover Applications, Benjamin Robinson

Electrical & Computer Engineering Theses & Dissertations

Public awareness of harmful human environmental effects such as global warming has increased greatly in recent years and researchers have increased their efforts in gaining more knowledge about the Earth's atmosphere. Natural and man-made processes pose threats lo the environment and human life, so knowledge of all atmospheric processes is necessary. Ozone and aerosols are important factors in many atmospheric processes and active remote sensing techniques provide a way lo analyze their quantity and distribution.

A compact ground-based lidar system for a robotic platform meant for atmospheric aerosol measurements was designed, tested, and evaluated. The system will eventually be deployed …

Adding Executable Context To Executable Architectures: Enabling An Executable Context Simulation Framework (Ecsf), Johnny J. Garcia

Computational Modeling & Simulation Engineering Theses & Dissertations

A system that does not stand alone is represented by a complex entity of component combinations that interact with each other to execute a function. In today's interconnected world, systems integrate with other systems - called a system-of-systems infrastructure: a network of interrelated systems that can often exhibit both predictable and unpredictable behavior. The current state-of-the-art evaluation process of these system-of-systems and their community of practitioners in the academic community are limited to static methods focused on defining who is doing what and where. However, to answer the questions of why and how a system operates within complex systems-of-systems interrelationships, …

A Framework For Incident Detection And Notification In Vehicular Ad-Hoc Networks, Mahmoud Abuelela

Computer Science Theses & Dissertations

The US Department of Transportation (US-DOT) estimates that over half of all congestion events are caused by highway incidents rather than by rush-hour traffic in big cities. The US-DOT also notes that in a single year, congested highways due to traffic incidents cost over $75 billion in lost worker productivity and over 8.4 billion gallons of fuel. Further, the National Highway Traffic Safety Administration (NHTSA) indicates that congested roads are one of the leading causes of traffic accidents, and in 2005 an average of 119 persons died each day in motor vehicle accidents.

Recently, Vehicular Ad-hoc Networks (VANET) employing a …

Learning Local Features Using Boosted Trees For Face Recognition, Rajkiran Gottumukkal

Electrical & Computer Engineering Theses & Dissertations

Face recognition is fundamental to a number of significant applications that include but not limited to video surveillance and content based image retrieval. Some of the challenges which make this task difficult are variations in faces due to changes in pose, illumination and deformation. This dissertation proposes a face recognition system to overcome these difficulties. We propose methods for different stages of face recognition which will make the system more robust to these variations. We propose a novel method to perform skin segmentation which is fast and able to perform well under different illumination conditions. We also propose a method …

War Fighting In Cyberspace: Evolving Force Presentation And Command And Control, M. Bodine Birdwell, Robert F. Mills

Faculty Publications

The Department of Defense (DOD) is endeavoring to define war fighting in the global cyberspace domain. Creation of US Cyber Command (USCYBERCOM), a subunified functional combatant command (FCC) under US Strategic Command (USSTRATCOM), is a huge step in integrating and coordinating the defense, protection, and operation of DOD networks; however, this step does not mean that USCYBERCOM will perform or manage all cyberspace functions. In fact the vast majority of cyberspace functions conducted by the services and combatant commands (COCOM), although vital for maintaining access to the domain in support of their operations, are not of an active war-fighting nature. …