Digital Commons Network^™

Dynamically Optimized Context In Recommender Systems, Ghim-Eng Yap, Ah-Hwee Tan, Hwee Hwa Pang

Research Collection School Of Computing and Information Systems

Traditional approaches to recommender systems have not taken into account situational information when making recommendations, and this seriously limits the relevance of the results. This paper advocates context-awareness as a promising approach to enhance the performance of recommenders, and introduces a mechanism to realize this approach. We present a framework that separates the contextual concerns from the actual recommendation module, so that contexts can be readily shared across applications. More importantly, we devise a learning algorithm to dynamically identify the optimal set of contexts for a specific recommendation task and user. An extensive series of experiments has validated that our …

Improving And Extending Behavioral Animation Through Machine Learning, Jonathan J. Dinerstein

Theses and Dissertations

Behavioral animation has become popular for creating virtual characters that are autonomous agents and thus self-animating. This is useful for lessening the workload of human animators, populating virtual environments with interactive agents, etc. Unfortunately, current behavioral animation techniques suffer from three key problems: (1) deliberative behavioral models (i.e., cognitive models) are slow to execute; (2) interactive virtual characters cannot adapt online due to interaction with a human user; (3) programming of behavioral models is a difficult and time-intensive process. This dissertation presents a collection of papers that seek to overcome each of these problems. Specifically, these issues are alleviated …

Evaluating Online Trust Using Machine Learning Methods, Weihua Song

Doctoral Dissertations

Trust plays an important role in e-commerce, P2P networks, and information filtering. Current challenges in trust evaluations include: (1) fnding trustworthy recommenders, (2) aggregating heterogeneous trust recommendations of different trust standards based on correlated observations and different evaluation processes, and (3) managing efficiently large trust systems where users may be sparsely connected and have multiple local reputations. The purpose of this dissertation is to provide solutions to these three challenges by applying ordered depth-first search, neural network, and hidden Markov model techniques. It designs an opinion filtered recommendation trust model to derive personal trust from heterogeneous recommendations; develops a reputation …

An Assessment Of Case-Based Reasoning For Spam Filtering, Sarah Jane Delany, Padraig Cunningham, Lorcan Coyle

Articles

Because of the changing nature of spam, a spam filtering system that uses machine learning will need to be dynamic. This suggests that a case-based (memory-based) approach may work well. Case-Based Reasoning (CBR) is a lazy approach to machine learning where induction is delayed to run time. This means that the case base can be updated continuously and new training data is immediately available to the induction process. In this paper we present a detailed description of such a system called ECUE and evaluate design decisions concerning the case representation. We compare its performance with an alternative system that uses …

Collective Multi-Label Classification, Nadia Ghamrawi, Andrew Mccallum

Computer Science Department Faculty Publication Series

Common approaches to multi-label classification learn independent classifiers for each category, and employ ranking or thresholding schemes for classification. Because they do not exploit dependencies between labels, such techniques are only well-suited to problems in which categories are independent. However, in many domains labels are highly interdependent. This paper explores multilabel conditional random field (CRF) classification models that directly parameterize label co-occurrences in multi-label classification. Experiments show that the models outperform their singlelabel counterparts on standard text corpora. Even when multilabels are sparse, the models improve subset classification error by as much as 40%.

Learning Discrete Hidden Markov Models From State Distribution Vectors, Luis G. Moscovich

LSU Doctoral Dissertations

Hidden Markov Models (HMMs) are probabilistic models that have been widely applied to a number of fields since their inception in the late 1960’s. Computational Biology, Image Processing, and Signal Processing, are but a few of the application areas of HMMs. In this dissertation, we develop several new efficient learning algorithms for learning HMM parameters. First, we propose a new polynomial-time algorithm for supervised learning of the parameters of a first order HMM from a state probability distribution (SD) oracle. The SD oracle provides the learner with the state distribution vector corresponding to a query string. We prove the correctness …

A Bayesian Technique For Task Localization In Multiple Goal Markov Decision Processes, James Carroll, Kevin Seppi

Faculty Publications

In a reinforcement learning task library system for Multiple Goal Markov Decision Process (MGMDP), localization in the task space allows the agent to determine whether a given task is already in its library in order to exploit previously learned experience. Task localization in MGMDPs can be accomplished through a Bayesian approach, however a trivial approach fails when the rewards are not distributed normally. This can be overcome through our Bayesian Task Localization Technique (BTLT).

Vision-Based Human Directed Robot Guidance, Richard B. Arthur

Theses and Dissertations

This paper describes methods to track a user-defined point in the vision of a robot as it drives forward. This tracking allows a robot to keep itself directed at that point while driving so that it can get to that user-defined point. I develop and present two new multi-scale algorithms for tracking arbitrary points between two frames of video, as well as through a video sequence. The multi-scale algorithms do not use the traditional pyramid image, but instead use a data structure called an integral image (also known as a summed area table). The first algorithm uses edge-detection to track …

Using Permutations Instead Of Student’S T Distribution For P-Values In Paired-Difference Algorithm Comparisons, Tony R. Martinez, Joshua Menke

Faculty Publications

The paired-difference t-test is commonly used in the machine learning community to determine whether one learning algorithm is better than another on a given learning task. This paper suggests the use of the permutation test instead hecause it calculates the exact p-value instead of an estimate. The permutation test is also distribution free and the time complexity is trivial for the commonly used 10-fold cross-validation paired-difference test. Results of experiments on real-world problems suggest it is not uncommon to see the t-test estimate deviate up to 30-50% from the exact p-value.

Solving Large Mdps Quickly With Partitioned Value Iteration, David Wingate

Theses and Dissertations

Value iteration is not typically considered a viable algorithm for solving large-scale MDPs because it converges too slowly. However, its performance can be dramatically improved by eliminating redundant or useless backups, and by backing up states in the right order. We present several methods designed to help structure value dependency, and present a systematic study of companion prioritization techniques which focus computation in useful regions of the state space. In order to scale to solve ever larger problems, we evaluate all enhancements and methods in the context of parallelizability. Using the enhancements, we discover that in many instances the limiting …

Machine Learning Techniques For Characterizing Ieee 802.11b Encrypted Data Streams, Michael J. Henson

Theses and Dissertations

As wireless networks become an increasingly common part of the infrastructure in industrialized nations, the vulnerabilities of this technology need to be evaluated. Even though there have been major advancements in encryption technology, security protocols and packet header obfuscation techniques, other distinguishing characteristics do exist in wireless network traffic. These characteristics include packet size, signal strength, channel utilization and others. Using these characteristics, windows of size 11, 31, and 51 packets are collected and machine learning (ML) techniques are trained to classify applications accessing the 802.11b wireless channel. The four applications used for this study included E-Mail, FTP, HTTP, and …

Visual Expectations: Using Machine Learning To Identify Patterns In Psychological Data, Skyler Place

Honors Theses

The goal of this project was to utilize the tools of machine learning to evaluate the data obtained through experiments in psychology. Advanced pattern finding algorithms are an effective approach to analyzing large sets of data, from any domain of science. Consequently, we have a psychological question and hypothesis, and a separate machine learning technique to assess these claims. The realm of psychology that I focused on is visual cognition, and how an individual's knowledge affects how they see the world. This alteration of visual data is a part of perception -when the brain enhances the data coming in from …

Using Symbolic Knowledge In The Umls To Disambiguate Words In Small Datasets With A Naive Bayes Classifier, Gondy Leroy, Thomas C. Rindflesch

CGU Faculty Publications and Research

Current approaches to word sense disambiguation use and combine various machine-learning techniques. Most refer to characteristics of the ambiguous word and surrounding words and are based on hundreds of examples. Unfortunately, developing large training sets is time-consuming. We investigate the use of symbolic knowledge to augment machine-learning techniques for small datasets. UMLS semantic types assigned to concepts found in the sentence and relationships between these semantic types form the knowledge base. A naïve Bayes classifier was trained for 15 words with 100 examples for each. The most frequent sense of a word served as the baseline. The effect of increasingly …

On Machine Learning Methods For Chinese Document Classification, Ji He, Ah-Hwee Tan, Chew-Lim Tan

Research Collection School Of Computing and Information Systems

This paper reports our comparative evaluation of three machine learning methods, namely k Nearest Neighbor (kNN), Support Vector Machines (SVM), and Adaptive Resonance Associative Map (ARAM) for Chinese document categorization. Based on two Chinese corpora, a series of controlled experiments evaluated their learning capabilities and efficiency in mining text classification knowledge. Benchmark experiments showed that their predictive performance were roughly comparable, especially on clean and well organized data sets. While kNN and ARAM yield better performances than SVM on small and clean data sets, SVM and ARAM significantly outperformed kNN on noisy data. Comparing efficiency, kNN was notably more costly …

Machine Learning Approaches For Determining Effective Seeds For K -Means Algorithm, Kaveephong Lertwachara

Doctoral Dissertations

In this study, I investigate and conduct an experiment on two-stage clustering procedures, hybrid models in simulated environments where conditions such as collinearity problems and cluster structures are controlled, and in real-life problems where conditions are not controlled. The first hybrid model (NK) is an integration between a neural network (NN) and the k-means algorithm (KM) where NN screens seeds and passes them to KM. The second hybrid (GK) uses a genetic algorithm (GA) instead of the neural network. Both NN and GA used in this study are in their simplest-possible forms.

In the simulated data sets, I investigate two …

Machine Learning Techniques For Efficient Query Processing In Kowledge Base Systems, Kevin Paul Grant

LSU Doctoral Dissertations

In this dissertation we propose a new technique for efficient query processing in knowledge base systems. Query processing in knowledge base systems poses strong computational challenges because of the presence of combinatorial explosion. This arises because at any point during query processing there may be too many subqueries available for further exploration. Overcoming this difficulty requires effective mechanisms for choosing from among these subqueries good subqueries for further processing. Inspired by existing works on stochastic logic programs, compositional modeling and probabilistic heuristic estimates we create a new, nondeterministic method to accomplish the task of subquery selection for query processing. Specifically, …

Machine-Learned Contexts For Linguistic Operations In German Sentence Realization, Eric K. Ringger, Simon Corston-Oliver, Michael Gamon, Robert Moore

Faculty Publications

We show that it is possible to learn the contexts for linguistic operations which map a semantic representation to a surface syntactic tree in sentence realization with high accuracy. We cast the problem of learning the contexts for the linguistic operations as classification tasks, and apply straightforward machine learning techniques, such as decision tree learning. The training data consist of linguistic features extracted from syntactic and semantic representations produced by a linguistic analysis system. The target features are extracted from links to surface syntax trees. Our evidence consists of four examples from the German sentence realization system code-named Amalgam: case …

Modular Machine Learning Methods For Computer-Aided Diagnosis Of Breast Cancer, Mia Kathleen Markey '94

Doctoral Dissertations

The purpose of this study was to improve breast cancer diagnosis by reducing the number of benign biopsies performed. To this end, we investigated modular and ensemble systems of machine learning methods for computer-aided diagnosis (CAD) of breast cancer. A modular system partitions the input space into smaller domains, each of which is handled by a local model. An ensemble system uses multiple models for the same cases and combines the models' predictions.

Five supervised machine learning techniques (LDA, SVM, BP-ANN, CBR, CART) were trained to predict the biopsy outcome from mammographic findings (BIRADS™) and patient age based on a …

An Analysis Of The Effectiveness Of A Constructive Induction-Based Virus Detection Prototype, Kevin T. Damp

Theses and Dissertations

Computer viruses remain a tangible threat to systems both within the Department of Defense and throughout the greater international data communications infrastructure on which the DoD increasingly depends. This threat is exacerbated continually, as new viruses are introduced at an alarming rate by the growing collection of connected machines and their operators. Unfortunately, current antivirus solutions are ill-equipped to address these issues in the long term. This thesis documents an investigation into the use of constructive induction, a form of machine learning, as a supplemental antivirus technique theoretically capable of detecting previously unknown viruses through generalized decision-making techniques. A group …

Multiple Stochastic Learning Automata For Vehicle Path Control In An Automated Highway System, Cem Unsal, Pushkin Kachroo, John S. Bay

Electrical & Computer Engineering Faculty Research

This paper suggests an intelligent controller for an automated vehicle planning its own trajectory based on sensor and communication data. The intelligent controller is designed using the learning stochastic automata theory. Using the data received from on-board sensors, two automata (one for lateral actions, one for longitudinal actions) can learn the best possible action to avoid collisions. The system has the advantage of being able to work in unmodeled stochastic environments, unlike adaptive control methods or expert systems. Simulations for simultaneous lateral and longitudinal control of a vehicle provide encouraging results

Simulation Study Of Learning Automata Games In Automated Highway Systems, Cem Unsal, Pushkin Kachroo, John S. Bay

Electrical & Computer Engineering Faculty Research

One of the most important issues in Automated Highway System (AHS) deployment is intelligent vehicle control. While the technology to safely maneuver vehicles exists, the problem of making intelligent decisions to improve a single vehicle’s travel time and safety while optimizing the overall traffic flow is still a stumbling block. We propose an artificial intelligence technique called stochastic learning automata to design an intelligent vehicle path controller. Using the information obtained by on-board sensors and local communication modules, two automata are capable of learning the best possible (lateral and longitudinal) actions to avoid collisions. This learning method is capable of …

Utilizing Data And Knowledge Mining For Probabilistic Knowledge Bases, Daniel J. Stein Iii

Theses and Dissertations

Problems can arise whenever inferencing is attempted on a knowledge base that is incomplete. Our work shows that data mining techniques can be applied to fill in incomplete areas in Bayesian Knowledge Bases (BKBs), as well as in other knowledge-based systems utilizing probabilistic representations. The problem of inconsistency in BKBs has been addressed in previous work, where reinforcement learning techniques from neural networks were applied. However, the issue of automatically solving incompleteness in BKBs has yet to be addressed. Presently, incompleteness in BKBs is repaired through the application of traditional knowledge acquisition techniques. We show how association rules can be …

Intelligent Control Of Vehicles: Preliminary Results On The Application Of Learning Automata Techniques To Automated Highway System, Cem Unsal, John S. Bay, Pushkin Kachroo

Electrical & Computer Engineering Faculty Research

We suggest an intelligent controller for an automated vehicle to plan its own trajectory based on sensor and communication data received. Our intelligent controller is based on an artificial intelligence technique called learning stochastic automata. The automaton can learn the best possible action to avoid collisions using the data received from on-board sensors. The system has the advantage of being able to work in unmodeled stochastic environments. Simulations for the lateral control of a vehicle using this AI method provides encouraging results.

On The Impact Of Forgetting On Learning Machines, Rūsiņš Freivalds, Efim Kinber, Carl H. Smith

School of Computer Science & Engineering Faculty Publications

People tend not to have perfect memories when it comes to learning, or to anything else for that matter. Most formal studies of learning, however, assume a perfect memory. Some approaches have restricted the number of items that could be retained. We introduce a complexity theoretic accounting of memory utilization by learning machines. In our new model, memory is measured in bits as a function of the size of the input. There is a hierarchy of learnability based on increasing memory allotment. The lower bound results are proved using an unusual combination of pumping and mutual recursion theorem arguments. For …

A Fortran Based Learning System Using Multilayer Back-Propagation Neural Network Techniques, Gregory L. Reinhart

Theses and Dissertations

An interactive computer system which allows the researcher to build an optimal neural network structure quickly, is developed and validated. This system assumes a single hidden layer perceptron structure and uses the back- propagation training technique. The software enables the researcher to quickly define a neural network structure, train the neural network, interrupt training at any point to analyze the status of the current network, re-start training at the interrupted point if desired, and analyze the final network using two- dimensional graphs, three-dimensional graphs, confusion matrices and saliency metrics. A technique for training, testing, and validating various network structures and …

Using Discovery-Based Learning To Prove The Behavior Of An Autonomous Agent, David N. Mezera

Theses and Dissertations

Computer-generated autonomous agents in simulation often behave predictably and unrealistically. These characteristics make them easy to spot and exploit by human participants in the simulation, when we would prefer the behavior of the agent to be indistinguishable from human behavior. An improvement in behavior might be possible by enlarging the library of responses, giving the agent a richer assortment of tactics to employ during a combat scenario. Machine learning offers an exciting alternative to constructing additional responses by hand by instead allowing the system to improve its own performance with experience. This thesis presents NOSTRUM, a discovery-based learning DBL system …

Discovery Learning In Autonomous Agents Using Genetic Algorithms, Edward O. Gordon

Theses and Dissertations

As the new Distributed Interactive Simulation (DIS) draft standard evolves into a useful document and distributed simulations begin to emerge that implement parts of the standard, there is renewed interest in available methods to effectively control autonomous aircraft agents in such a simulated environment. This investigation examines the use of a genetics-based classifier system for agent control. These are robust learning systems that use the adaptive search mechanisms of genetic algorithms to guide the learning system in forming new concepts (decision rules) about its environment. By allowing the rule base to evolve, it adapts agent behavior to environmental changes. Addressed …

Multiple Learner Systems Using Resampling Methods, Binyun Xie

Computer Science Theses & Dissertations

The N-Learners Problem deals with combining a number of learners such that the resultant system is "better", under some criterion, than the best of the individual learners. We consider a system of probably approximately correct concept learners. Depending on the available information, there are several methods to make the composite system better than the best of the individual learners. If a sample and an oracle that generates data points (but, not their classification) is available, then we show that we can achieve arbitrary levels of the normalized confidence of the composite system if (a) a robust learning algorithm is available, …

An Examination And Analysis Of The Boltzmann Machine, Its Mean Field Theory Approximation, And Learning Algorithm, Vincent Clive Phillips

Theses : Honours

It is currently believed that artificial neural network models may form the basis for inte1ligent computational devices. The Boltzmann Machine belongs to the class of recursive artificial neural networks and uses a supervised learning algorithm to learn the mapping between input vectors and desired outputs. This study examines the parameters that influence the performance of the Boltzmann Machine learning algorithm. Improving the performance of the algorithm through the use of a naïve mean field theory approximation is also examined. The study was initiated to examine the hypothesis that the Boltzmann Machine learning algorithm, when used with the mean field approximation, …

Artificial Intelligence: Myths And Realities, Hugo D'Alarcao

Bridgewater Review

Artificial intelligence the name conjures images of mechanical monsters, the Golem, Dr. Frankenstein’s creation and the rebellious computer Hal. We have always been fascinated by the possibility of creating a machine in our image, but this fascination is often accompanied by apprehension. We fear losing control of our creation and suspect that it might turn against us. It is this duality, this conflict between the desire to create and the fear of the consequences of the creation that has been so successfully exploited by writers. It is also, in part, this fascination that has recently brought the field of Artificial …