Digital Commons Network^™

Reinforcement Learning-Based Output Feedback Control Of Nonlinear Systems With Input Constraints, Pingan He, Jagannathan Sarangapani

Electrical and Computer Engineering Faculty Research & Creative Works

A novel neural network (NN) -based output feedback controller with magnitude constraints is designed to deliver a desired tracking performance for a class of multi-input-multi-output (MIMO) discrete-time strict feedback nonlinear systems. Reinforcement learning in discrete time is proposed for the output feedback controller, which uses three NN: 1) a NN observer to estimate the system states with the input-output data; 2) a critic NN to approximate certain strategic utility function; and 3) an action NN to minimize both the strategic utility function and the unknown dynamics estimation errors. The magnitude constraints are manifested as saturation nonlinearities in the output feedback …

On Some Generalized Transforms For Signal Decomposition And Reconstruction., Yumnam Singh Dr.

Doctoral Theses

In this thesis, we propose two new subband transforms entitled ISITRA and YKSK transforms and their possible applications in image compression and encryption. Both these transforms are developed based on a common model of multiplication known as Bino’s model of multiplication. ISITRA is a convolution based transforms i.e., that both forward and inverse transform of ISITRA is based on convolution as in DWT or 2-channel filter bank. However, it is much more general than the existing DWT or 2-channel filter bank scheme in the sense that it we can get different kinds of filters in addition to the filters specified …

Automatic Hydraulic Fracturing Design For Low Permeability Reservoirs Using Artificial Intelligence, Andrei Sergiu Popa

Graduate Theses, Dissertations, and Problem Reports (ETD)

The hydraulic fracturing technique is one of the major developments in petroleum engineering in the last two decades. Today, nearly all the wells completed in low permeability gas reservoirs require a hydraulic fracturing treatment in order to produce at an economical level. This study presents a new methodology, applicable to tight gas reservoirs, for designing hydraulic fractures.;This study is intended to develop an automatic hydraulic fracture design tool to help users design fracture jobs without being an expert in the art and science of hydraulic fracturing. This process is composed entirely of an integration of several artificial intelligence techniques.;The methodology …

Effects Of Artificial Neural Network Speed-Based Inputs On Heavy-Duty Vehicle Emissions Prediction, Nastaran Hashemi

Graduate Theses, Dissertations, and Problem Reports (ETD)

The PM split study was performed in Southern California on thirty-four heavy-duty diesel vehicles using the West Virginia University Transportable Heavy-Duty Vehicle Emissions Testing Laboratories to gather emissions data of these vehicles. The data obtained from six vehicles in the 1985--2001 model year and 33,000--80,000 lb weight range exercised through three different cycles were selected in this thesis. To predict the instantaneous levels of oxides of nitrogen (NOx), carbon dioxide (CO2), hydrocarbons (HC) and carbon monoxide (CO), an Artificial Neural Network (ANN) was used. Axle speed, torque, their rates of change over different time periods and two other variables as …

The Evolution Of Intelligent Computer Software And The Semantic Web, Jens G. Pohl

Collaborative Agent Design (CAD) Research Center

The purpose of this paper is to trace the evolution of intelligent software from data-centric applications that essentially encapsulate their data environment to ontology-based applications with automated reasoning capabilities. The author draws a distinction between human intelligence and component capabilities within a more general definition of intelligence, which may be embedded in computer software. The primary vehicle in the quest for intelligent software has been the gradual recognition of the central role played by data and information, rather than the logic and functionality of the application. The three milestones in this evolution have been: the separation of data management from …

Circadian Patterns Recognition In Ecosystems By Wavelet Filtering And Fuzzy Clustering, Stefano Marsili-Libelli, Simone Arrigucci

International Congress on Environmental Modelling and Software

This paper presents a method for extracting representative patterns from a set of data representing circadian cycles. The analysis is based on a combination of wavelet filtering and fuzzy clustering. The data are first processed with a discrete wavelet decomposition in order to filter out the noise and isolate the relevant circadian cycle. It is shown that the second level decomposition yields the best cycle approximation, filtering out measurement noise and other artefacts and preserving the main cycle features. From the filtered data the following discriminating features are extracted: minimum and maximum daily values, and the slope of the line …

Computer-Assisted Music Composition In The 32-Bar Jazz Standard Form, Chad Hogg

Computer Science Honors Papers

The goal of this research project was to explore the potential for teaching a computer to compose jazz music. Specifically, the hope was to develop a method in which every decision could be made based on information about the entire system. If this problem were solved, the ancillary goal of allowing the user to set any arbitrary constraints that have global effects would be a trivial addition.

Intelligent Query Answering Through Rule Learning And Generalization, James M. Carsten

Theses and Dissertations

The Department of Defense (DoD) relies heavily on information systems to complete a myriad of tasks, from day-to-day personnel actions to mission critical imagery retrieval, intelligence analysis, and mission planning. The astronomical growth in size and performance of data storage systems leads to problems in processing the amount of data returned on any given query. Typical relational database systems return a set of unordered records. This approach is acceptable in small information systems, but in large systems, such as military image retrieval systems with more than 1 million records, it requires considerable time (often hours to days) to sort through …

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 …

Expert System: Mushroom Species / Nur Fuhaizah Mohammad Fawzi, Mohammad Fawzi Nur Fuhaizah

Student Works (2000-2009)

Expert Systems are computer programs that use artificial intelligence to solve problems within a specialized domain that ordinarily requires human expertise. A very important aspect of helping mycologist with diagnosis of the mushroom health effects is the identification itself by using only the visible feature of the mushroom. Their identification, although very important, is often difficult. This thesis addresses this problem by providing an expert system that takes into consideration various factors about the mushroom, and presents identification as a possible solution. In order to achieve the purpose, the system uses Prolog, a logic programming. In this paper, chapter one …

Quantum-Implementable Selective Reconstruction Of High-Resolution Images, M. Peruå¡, H. Bischof, H.J. Caulfield, C.K. Loo

Research Publications (2000 to 2005)

This paper, written for interdisciplinary audience, presents computational image reconstruction implementable by quantum optics. The input-triggered selection of a high-resolution image among many stored ones, and its reconstruction if the input is occluded or noisy, has been successfully simulated. The original algorithm, based on the Hopfield associative neural net, was transformed in order to enable its quantum-wave implementation based on holography. The main limitations of the classical Hopfield net are much reduced with the simulated new quantum-optical implementation.

A Software-Based Knowledge Management System Using Narrative Texts, Thomas Rudy Mcdaniel

Electronic Theses and Dissertations

Technical and professional communicators have in recent research been challenged to make significant contributions to the field of knowledge management, and to learn or create the new technologies allowing them to do so. The purpose of this dissertation is to make such a combined theoretical and applied contribution from the context of the emerging discipline of Texts and Technology. This dissertation explores the field of knowledge management (KM), particularly its relationship to the related study of artificial intelligence (AI), and then recommends a KM software application based on the principles of narratology and narrative information exchange. The focus of knowledge …

On Textured Image Analysis Using Wavelets., Mausumi Acharyya Dr.

Doctoral Theses

In image processing and computer vision research, we aim to derive better tools that give us different perspectives on the same image, allowing us to understand not only its content, but also its meaning and significance. Image processing can not compete with the human eye in terms of accuracy but it can outperform the latter easily on observational consistency, and ability to carry out detailed mathematical estimations. With time, image processing research has broadened from the basic pixel-based low- level operations to high-level analysis, that now includes the use of artificially intelligent techniques for image interpretation and understanding. These new …

Effects Of Artificial Neural Networks Characterization On Prediction Of Diesel Engine Emissions, Azadeh Tehranian

Graduate Theses, Dissertations, and Problem Reports (ETD)

More than a century after its invention, diesel remains the fuel of choice for buses and freight trucks. Diesel exhaust contains three gases that are regulated by the United States Environmental Protection Agency (EPA), as well as particulate matter (PM). There is a societal need both to lower emissions and to predict or model emissions more accurately for inventory purposes. Engine modeling, and real time control are the most indispensable steps towards lowering engine emissions, and it is argued that this modeling can be achieved by implementation of Artificial Neural Networks (ANN). Effects of ANN design, architecture, and learning parameters …

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 …

Certain Pattern Recognition Tasks For Data Mining Problems., Pabitra Mitra Dr.

Doctoral Theses

Pattern recognition (PR) is an activity that we humans normally excel in. We do it almost all the time, and without conscious effort. We receive information via our various sensory organs, which is processed instantaneously by our brain so that, almost immediately, we are able to identify the source of the information, without having made any perceptible effort. What is even more impressive is the accuracy with which we can perform recognition tasks even under non-ideal conditions, for instance, when the information that needs to be processed is vague, imprecise or even incomplete. In fact, most of our day-to-day activities …

Intelligent Tutoring System Using Natural Language Dialogues / Harvinderjit Singh Gornam Singh, Gornam Singh Harvinderjit Singh

Student Works (2000-2009)

Intelligent tutoring system, ITS is a system that provides individualized tutoring or instruction. The intelligent systems, agents or tutoring systems act as virtual tutors and learning companions that help learners in learning. The notion of intelligent machines for teaching purposes can be traced back to 1926 when Sidney L. Pressey built a machine with multiple choice questions and answers. This machine delivered questions and provided immediate feedback to the user. With rapid technology changes, the Malaysian educational system is challenged with providing increased educational opportunities to every student. Many educational institutions are answering this challenge by developing distance teaching programs. …

A Trusted Environment For Mpi Programs, German Florez-Larrahondo

Theses and Dissertations

Several algorithms have been proposed to implement intrusion detection systems (IDS) based on the idea that anomalies in the behavior of a system might be produced by a set of actions of an intruder or by a system fault. Almost no previous research has been conducted in the area of anomaly detection for high performance clusters. The research reported in this thesis demonstrates that the analysis of sequences of function calls issued by one or more processes can be used to verify the correct execution of parallel programs written in C/C++ with the Message Passing Interface (MPI) in a cluster …

A New Approach To Robot’S Imitation Of Behaviors By Decomposition Of Multiple-Valued Relations, Uland Wong, Marek Perkowski

Electrical and Computer Engineering Faculty Publications and Presentations

Relation decomposition has been used for FPGA mapping, layout optimization, and data mining. Decision trees are very popular in data mining and robotics. We present relation decomposition as a new general-purpose machine learning method which generalizes the methods of inducing decision trees, decision diagrams and other structures. Relation decomposition can be used in robotics also in place of classical learning methods such as Reinforcement Learning or Artificial Neural Networks. This paper presents an approach to imitation learning based on decomposition. A Head/Hand robot learns simple behaviors using features extracted from computer vision, speech recognition and sensors.

Monitoring Process And Assessing Uncertainty For Anfis Time Series Forecasting, Yan K. Cathey Deng

Graduate Theses, Dissertations, and Problem Reports (ETD)

Although intelligent tools such as neural network, fuzzy logic and neuro-fuzzy methods have been applied in time series forecasting for some time, problems of monitoring forecasting processes and assessing uncertainty for the forecasts represent a major challenge that need to be fully investigated. In this research, we use statistical methods to analyze nonstationary time series forecasting where forecasts are accrued from a neuro-fuzzy ANFIS model. The main focus is to monitor the process and assess the uncertainty of the forecasts.;Single-step-ahead forecasts and multiple-step-ahead forecasts have been investigated by using three nonstationary time series data sets. It is shown that the …

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 …

Information Domain Modeling Of Emergent Phenomena, Ron Fulbright

Theses and Dissertations

Study in fields such as distributed artificial intelligence (DAI), decentralized artificial intelligence (DzAI), parallel artificial intelligence (PAl), multiagent systems (MAS), computer supported cooperative work (CSCW), artificial life (AL), and complex adaptive systems (CAS) is concerned with the cooperation, coordination, communication, and coherence of multiple agents working together to achieve a common goal. The notion that the ability of a collective can exceed the sum of the individuals is a fundamental concept and a generally accepted truth. However, no general theoretical explanation exists as to why this could or should be the case. This dissertation explores such an explanation by considering …

A Variable Response Time Lag Module For Car Following Models Using Fuzzy Set Theory, Yilmaz Hatipkarasulu

LSU Doctoral Dissertations

Since the 1950s, car following phenomena have been studied and analyzed, resulting in various models and algorithms. In general, the car following process has been defined as a stimulus-response relationship in which the driver of the following vehicle reacts to the actions of the lead vehicle after a time lag. One of the fundamental assumptions that underlie car following theory is that the driver response time lag is always a constant value for the driver at all times, regardless of level of detail of the model. Assumption of a constant time lag value introduces a number of broad assumptions however, …

A Review Of Data Mining Techniques, Sang Jun Lee, Keng Siau

Research Collection School Of Computing and Information Systems

Terabytes of data are generated everyday in many organizations. To extract hidden predictive information from large volumes of data, data mining (DM) techniques are needed. Organizations are starting to realize the importance of data mining in their strategic planning and successful application of DM techniques can be an enormous payoff for the organizations. This paper discusses the requirements and challenges of DM, and describes major DM techniques such as statistics, artificial intelligence, decision tree approach, genetic algorithm, and visualization.

Evolutionary Polymorphic Neural Networks In Chemical Engineering Modeling, Li Gao

Dissertations

Evolutionary Polymorphic Neural Network (EPNN) is a novel approach to modeling chemical, biochemical and physical processes. This approach has its basis in modern artificial intelligence, especially neural networks and evolutionary computing. EPNN can perform networked symbolic regressions for input-output data, while providing information about both the structure and complexity of a process during its own evolution.

In this work three different processes are modeled: 1. A dynamic neutralization process. 2. An aqueous two-phase system. 3. Reduction of a biodegradation model. In all three cases, EPNN shows better or at least equal performances over published data than traditional thermodynamics /transport or …

Restimulation Candidate Selection Using Virtual Intelligence, Khalid Y. Mohamad

Graduate Theses, Dissertations, and Problem Reports (ETD)

Due to the importance of well deliverability maintenance, a committee of specialists from Dominion East Ohio and other service companies meets every year to select the wells to be included in the deliverability maintenance plan. The application tool not only help in selecting the wells for deliverability maintenance plan but goes beyond that by designing the most optimum frac recipe.;The purpose of this study is to develop an engineering tool that will help petroleum engineers making a better decision for selecting well candidate and design well restimulation. The project focuses on a gas storage field and use data such as …

Improving The Simulation Of A Waterflooding Recovery Process Using Artificial Neural Networks, Edison Gil

Graduate Theses, Dissertations, and Problem Reports (ETD)

The waterflood performance of the dual five-spot pilot project in the Stringtown oil field, situated in West Virginia, has been studied. A numerical simulator, called BOAST98, was used for the simulation purposes, after developing a reservoir description.;The producing horizon in the field is the Upper Devonian Gordon sandstone, which is characterized by severe heterogeneity due to the depositional environment. Using available core and log data and geological analysis, a reservoir characterization study was done. A preliminary reservoir description based on log porosity-core permeability correlation was improved by developing Artificial Neural Networks (A.N.N.), which incorporates geophysical well log information. These A.N.N.'s …

On Some Self-Organizing Models And Their Applications., Amitava Dutta Dr.

Doctoral Theses

Abstract: Self-organizing neural network models constitute the main theme of this thesis. Some well-known self-organizing models are surveyed and their properties are discussed. The application areas on which the thesis focuses are briefly described.This thesis deals with Artificial Neural Network models, in particular, Self- organizing (unsupervisnd) models. We develop here a few self-organizing neural net- work models to solve certain problems which are well studied in the areas of Image Processing and Computationel Geometry and have wide applications in shape eztrac- tion and optimization.1.1 Artificial neural networkThe study of Biological Neural Networks originally comes under biological sciences. They deal with …

The Application And Performance Of A Generic Task Routine Decision Making Algorithm To Recipe Selection In Meal Planning, Michelle M. Cox

Theses and Dissertations - UTB/UTPA

A nutritional meal planning system was implemented to test the effectiveness of a previously developed routine decision making algorithm. The combinatorics involved in ordering recipes in all possible combinations to produce variability in a meal plan and provide sufficient nutrition is conceptually intensive. Meal planning involves selection of food to eat to fulfill a person's nutritional and personal preferences. This thesis demonstrates meal planning as a decision making problem and demonstrates the utility of the routine decision making algorithm by solving this problem. Generic Tasks, identified through artificial intelligence research, provides the basis for this algorithm. It uses user preferences …

Porosity Distribution Prediction Using Artificial Neural Networks, Fahad Abdullah Al-Qahtani

Graduate Theses, Dissertations, and Problem Reports (ETD)

Reservoir characterization plays a very important role in the petroleum industry, especially to the economic success of the reservoir development. Heterogeneity can complicate the evaluation of reservoir properties. Porosity is the primary key to a reliable reservoir model.;Several studies in the literature indicated that accurate evaluation of reservoir properties can be made by the analysis of electric logs. Stringtown oil field in Tyler and Wetzel counties in the northwestern part of West Virginia was selected to conduct this study.;Artificial Neural Networks (ANN) is one of the latest technologies available to the petroleum industry. The objective of this study was to …