Computer Sciences Commons^™

Quantification Of Artistic Style Through Sparse Coding Analysis In The Drawings Of Pieter Bruegel The Elder, James M. Hughes, Daniel J. Graham, Daniel N. Rockmore

Dartmouth Scholarship

Recently, statistical techniques have been used to assist art historians in the analysis of works of art. We present a novel technique for the quantification of artistic style that utilizes a sparse coding model. Originally developed in vision research, sparse coding models can be trained to represent any image space by maximizing the kurtosis of a representation of an arbitrarily selected image from that space. We apply such an analysis to successfully distinguish a set of authentic drawings by Pieter Bruegel the Elder from another set of well-known Bruegel imitations. We show that our approach, which involves a direct comparison …

Vowel Recognition From Continuous Articulatory Movements For Speaker-Dependent Applications, Jun Wang, Jordan R. Green, Ashok Samal, Tom D. Carrell

Department of Special Education and Communication Disorders: Faculty Publications

A novel approach was developed to recognize vowels from continuous tongue and lip movements. Vowels were classified based on movement patterns (rather than on derived articulatory features, e.g., lip opening) using a machine learning approach. Recognition accuracy on a single-speaker dataset was 94.02% with a very short latency. Recognition accuracy was better for high vowels than for low vowels. This finding parallels previous empirical findings on tongue movements during vowels. The recognition algorithm was then used to drive an articulation-to-acoustics synthesizer. The synthesizer recognizes vowels from continuous input stream of tongue and lip movements and plays the corresponding sound samples …

A Boosting Framework For Visuality-Preserving Distance Metric Learning And Its Application To Medical Image Retrieval, Yang Liu, Rong Jin, Lily Mummert, Rahul Sukthankar, Adam Goode, Bin Zheng, Steven C. H. Hoi, Mahadev Satyanarayanan

Research Collection School Of Computing and Information Systems

Similarity measurement is a critical component in content-based image retrieval systems, and learning a good distance metric can significantly improve retrieval performance. However, despite extensive study, there are several major shortcomings with the existing approaches for distance metric learning that can significantly affect their application to medical image retrieval. In particular, "similarity" can mean very different things in image retrieval: resemblance in visual appearance (e.g., two images that look like one another) or similarity in semantic annotation (e.g., two images of tumors that look quite different yet are both malignant). Current approaches for distance metric learning typically address only one …

Prediction Of Brain Tumor Progression Using A Machine Learning Technique, Yuzhong Shen, Debrup Banerjee, Jiang Li, Adam Chandler, Yufei Shen, Frederic D. Mckenzie, Jihong Wang, Nico Karssemeijer (Ed.), Ronald M. Summers (Ed.)

Electrical & Computer Engineering Faculty Publications

A machine learning technique is presented for assessing brain tumor progression by exploring six patients' complete MRI records scanned during their visits in the past two years. There are ten MRI series, including diffusion tensor image (DTI), for each visit. After registering all series to the corresponding DTI scan at the first visit, annotated normal and tumor regions were overlaid. Intensity value of each pixel inside the annotated regions were then extracted across all of the ten MRI series to compose a 10 dimensional vector. Each feature vector falls into one of three categories:normal, tumor, and normal but progressed to …

Predicting Flavonoid Ugt Regioselectivity With Graphical Residue Models And Machine Learning., Arthur Rhydon Jackson

Electronic Theses and Dissertations

Machine learning is applied to a challenging and biologically significant protein classification problem: the prediction of flavonoid UGT acceptor regioselectivity from primary protein sequence. Novel indices characterizing graphical models of protein residues are introduced. The indices are compared with existing amino acid indices and found to cluster residues appropriately. A variety of models employing the indices are then investigated by examining their performance when analyzed using nearest neighbor, support vector machine, and Bayesian neural network classifiers. Improvements over nearest neighbor classifications relying on standard alignment similarity scores are reported.

Noninvasive Estimation Of Pulmonary Artery Pressure Using Heart Sound Analysis, Aaron W. Dennis

Theses and Dissertations

Right-heart catheterization is the most accurate method for estimating pulmonary artery pressure (PAP). Because it is an invasive procedure it is expensive, exposes patients to the risk of infection, and is not suited for long-term monitoring situations. Medical researchers have shown that PAP influences the characteristics of heart sounds. This suggests that heart sound analysis is a potential noninvasive solution to the PAP estimation problem. This thesis describes the development of a prototype system, called PAPEr, which estimates PAP noninvasively using heart sound analysis. PAPEr uses patient data with machine learning algorithms to build models of how PAP affects heart …

A Neural Network Approach To Border Gateway Protocol Peer Failure Detection And Prediction, Cory B. White

Master's Theses

The size and speed of computer networks continue to expand at a rapid pace, as do the corresponding errors, failures, and faults inherent within such extensive networks. This thesis introduces a novel approach to interface Border Gateway Protocol (BGP) computer networks with neural networks to learn the precursor connectivity patterns that emerge prior to a node failure. Details of the design and construction of a framework that utilizes neural networks to learn and monitor BGP connection states as a means of detecting and predicting BGP peer node failure are presented. Moreover, this framework is used to monitor a BGP network …

Dataset Threshold For The Performance Estimators In Supervised Machine Learning Experiments, Zanifa Omary, Fredrick Mtenzi

Conference papers

The establishment of dataset threshold is one among the first steps when comparing the performance of machine learning algorithms. It involves the use of different datasets with different sample sizes in relation to the number of attributes and the number of instances available in the dataset. Currently, there is no limit which has been set for those who are unfamiliar with machine learning experiments on the categorisation of these datasets, as either small or large, based on the two factors. In this paper we perform experiments in order to establish dataset threshold. The established dataset threshold will help unfamiliar supervised …

Automatic Red Tide Detection Using Modis Satellite Images, Wijian Cheng

USF Tampa Graduate Theses and Dissertations

Red tides pose a significant economic and environmental threat in the Gulf of Mexico. Detecting red tide is important for understanding this phenomenon. In this thesis, machine learning approaches based on Random Forests, Support Vector Machines and K-Nearest Neighbors have been evaluated for red tide detection from MODIS satellite images. Detection results using machine learning algorithms were compared to ship collected ground truth red tide data. This work has three major contributions. First, machine learning approaches outperformed two of the latest thresholding red tide detection algorithms based on bio-optical characterization by more than 10% in terms of F measure and …

Intentional Learning Agent Architecture, Budhitama Subagdja, Liz Sonenberg, Iyad Rahwan

Research Collection School Of Computing and Information Systems

Dealing with changing situations is a major issue in building agent systems. When the time is limited, knowledge is unreliable, and resources are scarce, the issue becomes more challenging. The BDI (Belief-Desire-Intention) agent architecture provides a model for building agents that addresses that issue. The model can be used to build intentional agents that are able to reason based on explicit mental attitudes, while behaving reactively in changing circumstances. However, despite the reactive and deliberative features, a classical BDI agent is not capable of learning. Plans as recipes that guide the activities of the agent are assumed to be static. …

Predictive Decoding Of Neural Data, Yaroslav O. Halchenko

Dissertations

In the last five decades the number of techniques available for non-invasive functional imaging has increased dramatically. Researchers today can choose from a variety of imaging modalities that include EEG, MEG, PET, SPECT, MRI, and fMRI.

This doctoral dissertation offers a methodology for the reliable analysis of neural data at different levels of investigation. By using statistical learning algorithms the proposed approach allows single-trial analysis of various neural data by decoding them into variables of interest. Unbiased testing of the decoder on new samples of the data provides a generalization assessment of decoding performance reliability. Through consecutive analysis of the …

Bootstrapping Events And Relations From Text, Ting Liu

Legacy Theses & Dissertations (2009 - 2024)

Information Extraction (IE) is a technique for automatically extracting structured data from text documents. One of the key analytical tasks is extraction of important and relevant information from textual sources. While information is plentiful and readily available, from the Internet, news services, media, etc., extracting the critical nuggets that matter to business or to national security is a cognitively demanding and time consuming task. Intelligence and business analysts spend many hours poring over endless streams of text documents pulling out reference to entities of interest (people, locations, organizations) as well as their relationships as reported in text. Such extracted "information …

Machine Learned Melody Matching Using Strictly Relative Musical Abstractions, Michael Joseph Kolta

Legacy Theses & Dissertations (2009 - 2024)

We implement and evaluate a machine learning approach to improve systems for searching a database of music via melodic sample. We explore symbolic and aural input queries and test our prototypes with extensive user surveys. Our main contribution is to combine the following four elements. First is to create a unique musical abstraction that accounts for both pitch and rhythm in a relative manner. Second, our system allows for approximate matching of imperfect queries via the utilization of the Smith-Waterman algorithm that was originally designed for approximate matching of molecular subsequences, such as DNA samples. Third is to design our …

Concept Learning By Example Decomposition, Sameer Joshi

Electronic Theses and Dissertations

For efficient understanding and prediction in natural systems, even in artificially closed ones, we usually need to consider a number of factors that may combine in simple or complex ways. Additionally, many modern scientific disciplines face increasingly large datasets from which to extract knowledge (for example, genomics). Thus to learn all but the most trivial regularities in the natural world, we rely on different ways of simplifying the learning problem. One simplifying technique that is highly pervasive in nature is to break down a large learning problem into smaller ones; to learn the smaller, more manageable problems; and then to …

Real-Time Automatic Price Prediction For Ebay Online Trading, Ilya Igorevitch Raykhel

Theses and Dissertations

While Machine Learning is one of the most popular research areas in Computer Science, there are still only a few deployed applications intended for use by the general public. We have developed an exemplary application that can be directly applied to eBay trading. Our system predicts how much an item would sell for on eBay based on that item's attributes. We ran our experiments on the eBay laptop category, with prior trades used as training data. The system implements a feature-weighted k-Nearest Neighbor algorithm, using genetic algorithms to determine feature weights. Our results demonstrate an average prediction error of 16%; …

Development Of A Workflow For The Comparison Of Classification Techniques, Zanifa Omary

Masters

As the interest in machine learning and data mining springs up, the problem of how to assess learning algorithms and compare classifiers become more pressing. This has been associated with the lack of comprehensive and complete workflow depending on the project scale to provide guidance to its users. This means the success or failure of the project can be highly dependent on the person or team carrying it. The standard practice adopted by many researchers and experimenters has been to follow steps or phases from existing workflows such as CRISP-DM, KDD and SASSEMMA. However, as machine learning and data mining …

Scaling Ant Colony Optimization With Hierarchical Reinforcement Learning Partitioning, Erik J. Dries, Gilbert L. Peterson

Faculty Publications

This paper merges hierarchical reinforcement learning (HRL) with ant colony optimization (ACO) to produce a HRL ACO algorithm capable of generating solutions for large domains. This paper describes two specific implementations of the new algorithm: the first a modification to Dietterich’s MAXQ-Q HRL algorithm, the second a hierarchical ant colony system algorithm. These implementations generate faster results, with little to no significant change in the quality of solutions for the tested problem domains. The application of ACO to the MAXQ-Q algorithm replaces the reinforcement learning, Q-learning, with the modified ant colony optimization method, Ant-Q. This algorithm, MAXQ-AntQ, converges to solutions …

Assessing The Costs Of Sampling Methods In Active Learning For Annotation, James Carroll, Robbie Haertel, Peter Mcclanahan, Eric K. Ringger, Kevin Seppi

Faculty Publications

Traditional Active Learning (AL) techniques assume that the annotation of each datum costs the same. This is not the case when annotating sequences; some sequences will take longer than others. We show that the AL technique which performs best depends on how cost is measured. Applying an hourly cost model based on the results of an annotation user study, we approximate the amount of time necessary to annotate a given sentence. This model allows us to evaluate the effectiveness of AL sampling methods in terms of time spent in annotation. We acheive a 77% reduction in hours from a random …

Improving Liquid State Machines Through Iterative Refinement Of The Reservoir, R David Norton

Theses and Dissertations

Liquid State Machines (LSMs) exploit the power of recurrent spiking neural networks (SNNs) without training the SNN. Instead, a reservoir, or liquid, is randomly created which acts as a filter for a readout function. We develop three methods for iteratively refining a randomly generated liquid to create a more effective one. First, we apply Hebbian learning to LSMs by building the liquid with spike-time dependant plasticity (STDP) synapses. Second, we create an eligibility based reinforcement learning algorithm for synaptic development. Third, we apply principles of Hebbian learning and reinforcement learning to create a new algorithm called separation driven synaptic modification …

Learning Policies For Embodied Virtual Agents Through Demonstration, Jonathan Dinerstein, Parris K. Egbert, Dan A. Ventura

Faculty Publications

Although many powerful AI and machine learning techniques exist, it remains difficult to quickly create AI for embodied virtual agents that produces visually lifelike behavior. This is important for applications (e.g., games, simulators, interactive displays) where an agent must behave in a manner that appears human-like. We present a novel technique for learning reactive policies that mimic demonstrated human behavior. The user demonstrates the desired behavior by dictating the agent’s actions during an interactive animation. Later, when the agent is to behave autonomously, the recorded data is generalized to form a continuous state-to-action mapping. Combined with an appropriate animation algorithm …

A Direct Algorithm For The K-Nearest-Neighbor Classifier Via Local Warping Of The Distance Metric, Tohkoon Neo

Theses and Dissertations

The k-nearest neighbor (k-NN) pattern classifier is a simple yet effective learner. However, it has a few drawbacks, one of which is the large model size. There are a number of algorithms that are able to condense the model size of the k-NN classifier at the expense of accuracy. Boosting is therefore desirable for increasing the accuracy of these condensed models. Unfortunately, there does not exist a boosting algorithm that works well with k-NN directly. We present a direct boosting algorithm for the k-NN classifier that creates an ensemble of models with locally modified distance weighting. An empirical study conducted …

Learning Multiple Languages In Groups, Sanjay Jain, Efim Kinber

School of Computer Science & Engineering Faculty Publications

We consider a variant of Gold’s learning paradigm where a learner receives as input different languages (in the form of one text where all input languages are interleaved). Our goal is to explore the situation when a more “coarse” classification of input languages is possible, whereas more refined classification is not. More specifically, we answer the following question: under which conditions, a learner, being fed different languages, can produce grammars covering all input languages, but cannot produce grammars covering input languages for any . We also consider a variant of this task, where each of the output grammars may not …

Context-Aware Statistical Debugging: From Bug Predictors To Faulty Control Flow Paths, Lingxiao Jiang, Zhendong Su

Research Collection School Of Computing and Information Systems

Effective bug localization is important for realizing automated debugging. One attractive approach is to apply statistical techniques on a collection of evaluation profiles of program properties to help localize bugs. Previous research has proposed various specialized techniques to isolate certain program predicates as bug predictors. However, because many bugs may not be directly associated with these predicates, these techniques are often ineffective in localizing bugs. Relevant control flow paths that may contain bug locations are more informative than stand-alone predicates for discovering and understanding bugs. In this paper, we propose an approach to automatically generate such faulty control flow paths …

Heuristic Weighted Voting, Kristine Perry Monteith

Theses and Dissertations

Selecting an effective method for combining the votes of classifiers in an ensemble can have a significant impact on the overall classification accuracy an ensemble is able to achieve. With some methods, the ensemble cannot even achieve as high a classification accuracy as the most accurate individual classifying component. To address this issue, we present the strategy of Heuristic Weighted Voting, a technique that uses heuristics to determine the confidence that a classifier has in its predictions on an instance by instance basis. Using these heuristics to weight the votes in an ensemble results in an overall average increase in …

A Data-Dependent Distance Measure For Transductive Instance-Based Learning, Jared Lundell, Dan A. Ventura

Faculty Publications

We consider learning in a transductive setting using instance-based learning (k-NN) and present a method for constructing a data-dependent distance “metric” using both labeled training data as well as available unlabeled data (that is to be classified by the model). This new data-driven measure of distance is empirically studied in the context of various instance-based models and is shown to reduce error (compared to traditional models) under certain learning conditions. Generalizations and improvements are suggested.

Limitations And Extensions Of The Wolf-Phc Algorithm, Philip R. Cook

Theses and Dissertations

Policy Hill Climbing (PHC) is a reinforcement learning algorithm that extends Q-learning to learn probabilistic policies for multi-agent games. WoLF-PHC extends PHC with the "win or learn fast" principle. A proof that PHC will diverge in self-play when playing Shapley's game is given, and WoLF-PHC is shown empirically to diverge as well. Various WoLF-PHC based modifications were created, evaluated, and compared in an attempt to obtain convergence to the single shot Nash equilibrium when playing Shapley's game in self-play without using more information than WoLF-PHC uses. Partial Commitment WoLF-PHC (PCWoLF-PHC), which performs best on Shapley's game, is tested on other …

Improving Neural Network Classification Training, Michael Edwin Rimer

Theses and Dissertations

The following work presents a new set of general methods for improving neural network accuracy on classification tasks, grouped under the label of classification-based methods. The central theme of these approaches is to provide problem representations and error functions that more directly improve classification accuracy than conventional learning and error functions. The CB1 algorithm attempts to maximize classification accuracy by selectively backpropagating error only on misclassified training patterns. CB2 incorporates a sliding error threshold to the CB1 algorithm, interpolating between the behavior of CB1 and standard error backpropagation as training progresses in order to avoid prematurely saturated network weights. CB3 …

Parallelization Of Ant Colony Optimization Via Area Of Expertise Learning, Adrian A. De Freitas

Theses and Dissertations

Ant colony optimization algorithms have long been touted as providing an effective and efficient means of generating high quality solutions to NP-hard optimization problems. Unfortunately, while the structure of the algorithm is easy to parallelize, the nature and amount of communication required for parallel execution has meant that parallel implementations developed suffer from decreased solution quality, slower runtime performance, or both. This thesis explores a new strategy for ant colony parallelization that involves Area of Expertise (AOE) learning. The AOE concept is based on the idea that individual agents tend to gain knowledge of different areas of the search space …

Solar Activity Detection And Prediction Using Image Processing And Machine Learning Techniques, Gang Fu

Dissertations

The objective of the research in this dissertation is to develop the methods for automatic detection and prediction of solar activities, including prominence eruptions, emerging flux regions and solar flares. Image processing and machine learning techniques are applied in this study. These methods can be used for automatic observation of solar activities and prediction of space weather that may have great influence on the near earth environment.

The research presented in this dissertation covers the following topics: i) automatic detection of prominence eruptions (PBs), ii) automatic detection of emerging flux regions (EFRs), and iii) automatic prediction of solar flares.

In …

Predicting Coronary Artery Disease With Medical Profile And Gene Polymorphisms Data, Qiongyu Chen, Guoliang Li, Tze-Yun Leong, Chew-Kiat Heng

Research Collection School Of Computing and Information Systems

Coronary artery disease (CAD) is a main cause of death in the world. Finding cost-effective methods to predict CAD is a major challenge in public health. In this paper, we investigate the combined effects of genetic polymorphisms and non-genetic factors on predicting the risk of CAD by applying well known classification methods, such as Bayesian networks, naïve Bayes, support vector machine, k-nearest neighbor, neural networks and decision trees. Our experiments show that all these classifiers are comparable in terms of accuracy, while Bayesian networks have the additional advantage of being able to provide insights into the relationships among the variables. …