Engineering Commons^™

Automated Classification Of Breast Pathology Using Local Measures Of Broadband Reflectance, Ashley M. Laughney, Venkataramanan Krishnaswamy, Pilar Beatriz Garcia-Allende, Olga M. Conde, Wendy A. Wells, Keith D. Paulsen, Brian W. Pogue

Dartmouth Scholarship

We demonstrate that morphological features pertinent to a tissue's pathology may be ascertained from localized measures of broadband reflectance, with a mesoscopic resolution (100-μm lateral spot size) that permits scanning of an entire margin for residual disease. The technical aspects and optimization of a k-nearest neighbor classifier for automated diagnosis of pathologies are presented, and its efficacy is validated in 29 breast tissue specimens. When discriminating between benign and malignant pathologies, a sensitivity and specificity of 91 and 77% was achieved. Furthermore, detailed subtissue-type analysis was performed to consider how diverse pathologies influence scattering response and overall classification efficacy. The …

Computation Intelligence Method To Find Generic Non-Coding Rna Search Models, Jennifer A. Smith

Electrical and Computer Engineering Faculty Publications and Presentations

Fairly effective methods exist for finding new noncoding RNA genes using search models based on known families of ncRNA genes (for example covariance models). However, these models only find new members of the existing families and are not useful in finding potential members of novel ncRNA families. Other problems with family-specific search include large processing requirements, ambiguity in defining which sequences form a family and lack of sufficient numbers of known sequences to properly estimate model parameters. An ncRNA search model is proposed which includes a collection of non-overlapping RNA hairpin structure covariance models. The hairpin models are chosen from …

Using Quality Attributes And Computational Intelligence To Generate And Evaluate System Architecture Alternatives, Atmika Singh, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

This paper proposes an evolutionary algorithm based approach for evolving architecture alternatives using quality attributes as design drivers. A novel fuzzy architecture assessment approach is presented to quantitatively evaluate the set of possible solutions based on linguistic assessments of architecture quality attributes elicited from the stakeholders. The proposed approach makes a valuable contribution to the systems architecting knowledge base by presenting a measurable and quantifiable approach to architecture design and evaluation.

Artificial Intelligence: Soon To Be The World’S Greatest Intelligence, Or Just A Wild Dream?, Edward R. Kollett

Academic Symposium of Undergraduate Scholarship

The purpose of the paper was to examine the field of artificial intelligence. In particular, the paper focused on what has been accomplished towards the goal of making a machine that can think like a human, and the hardships that researchers in the field has faced. It also touched upon the potential outcomes of success. Why is this paper important? As computers become more powerful, the common conception is that they are becoming more intelligent. As computers become more integrated with society and more connected with each other, people again believe they are becoming smarter. Therefore, it is important that …

Developing An Effective And Efficient Real Time Strategy Agent For Use As A Computer Generated Force, Kurt Weissgerber

Theses and Dissertations

Computer Generated Forces (CGF) are used to represent units or individuals in military training and constructive simulation. The use of CGF significantly reduces the time and money required for effective training. For CGF to be effective, they must behave as a human would in the same environment. Real Time Strategy (RTS) games place players in control of a large force whose goal is to defeat the opponent. The military setting of RTS games makes them an excellent platform for the development and testing of CGF. While there has been significant research in RTS agent development, most of the developed agents …

Controlling The Uncontrollable: A New Approach To Digital Storytelling Using Autonomous Virtual Actors And Environmental Manipulation, Matthew J. Colon

Master's Theses

In most video games today that focus on a single story, scripting languages are used for controlling the artificial intelligence of the virtual actors. While scripting is a great tool for reliably performing a story, it has many disadvantages; mainly, it is limited by only being able to respond to those situations that were explicitly declared, causing unreliable responses to unknown situations, and the believability of the virtual actor is hindered by possible conflicts between scripted actions and appropriate responses as perceived by the viewer. This paper presents a novel method of storytelling by manipulating the environment, whether physically or …

Robust Dialog Management Through A Context-Centric Architecture, Victor C. Hung

Electronic Theses and Dissertations

This dissertation presents and evaluates a method of managing spoken dialog interactions with a robust attention to fulfilling the human user’s goals in the presence of speech recognition limitations. Assistive speech-based embodied conversation agents are computer-based entities that interact with humans to help accomplish a certain task or communicate information via spoken input and output. A challenging aspect of this task involves open dialog, where the user is free to converse in an unstructured manner. With this style of input, the machine’s ability to communicate may be hindered by poor reception of utterances, caused by a user’s inadequate command of …

Episodic Memory Model For Embodied Conversational Agents, Miguel Elvir

Electronic Theses and Dissertations

Embodied Conversational Agents (ECA) form part of a range of virtual characters whose intended purpose include engaging in natural conversations with human users. While works in literature are ripe with descriptions of attempts at producing viable ECA architectures, few authors have addressed the role of episodic memory models in conversational agents. This form of memory, which provides a sense of autobiographic record-keeping in humans, has only recently been peripherally integrated into dialog management tools for ECAs. In our work, we propose to take a closer look at the shared characteristics of episodic memory models in recent examples from the field. …

A Computational Analysis Of Cognitive Effort, Luca Longo, Stephen Barrett

Books/Book Chapters

Cognitive effort is a concept of unquestionable utility in understanding human behaviour. However, cognitive effort has been defined in several ways in literature and in everyday life, suffering from a partial understanding. It is common to say “Pay more attention in studying that subject” or “How much effort did you spend in resolving that task?”, but what does it really mean? This contribution tries to clarify the concept of cognitive effort, by introducing its main influencing factors and by presenting a formalism which provides us with a tool for precise discussion. The formalism is implementable as a computational concept and …

Uncertainty Management Of Intelligent Feature Selection In Wireless Sensor Networks, Sanchita Mal-Sarkar

ETD Archive

Wireless sensor networks (WSN) are envisioned to revolutionize the paradigm of monitoring complex real-world systems at a very high resolution. However, the deployment of a large number of unattended sensor nodes in hostile environments, frequent changes of environment dynamics, and severe resource constraints pose uncertainties and limit the potential use of WSN in complex real-world applications. Although uncertainty management in Artificial Intelligence (AI) is well developed and well investigated, its implications in wireless sensor environments are inadequately addressed. This dissertation addresses uncertainty management issues of spatio-temporal patterns generated from sensor data. It provides a framework for characterizing spatio-temporal pattern in …

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 …

An Analysis Of Misclassification Rates For Decision Trees, Mingyu Zhong

Electronic Theses and Dissertations

The decision tree is a well-known methodology for classification and regression. In this dissertation, we focus on the minimization of the misclassification rate for decision tree classifiers. We derive the necessary equations that provide the optimal tree prediction, the estimated risk of the tree's prediction, and the reliability of the tree's risk estimation. We carry out an extensive analysis of the application of Lidstone's law of succession for the estimation of the class probabilities. In contrast to existing research, we not only compute the expected values of the risks but also calculate the corresponding reliability of the risk (measured by …

Least Squares Support Vector Machine Based Classification Of Abnormalities In Brain Mr Images, S. Thamarai Selvi, D. Selvathi, R. Ramkumar, Henry Selvaraj

Electrical & Computer Engineering Faculty Research

The manual interpretation of MRI slices based on visual examination by radiologist/physician may lead to missing diagnosis when a large number of MRIs are analyzed. To avoid the human error, an automated intelligent classification system is proposed. This research paper proposes an intelligent classification technique to the problem of classifying four types of brain abnormalities viz. Metastases, Meningiomas, Gliomas, and Astrocytomas. The abnormalities are classified based on Two/Three/ Four class classification using statistical and textural features. In this work, classification techniques based on Least Squares Support Vector Machine (LS-SVM) using textural features computed from the MR images of patient are …

Instantaneously Trained Neural Networks With Complex And Quaternion Inputs, Adityan V. Rishiyur

LSU Master's Theses

Neural network architectures such as backpropagation networks, perceptrons or generalized Hopfield networks can handle complex inputs but they require a large amount of time and resources for the training process. This thesis investigates instantaneously trained feedforward neural networks that can handle complex and quaternion inputs. The performance of the basic algorithm has been analyzed and shown how it provides a plausible model of human perception and understanding of images. The motivation for studying quaternion inputs is their use in representing spatial rotations that find applications in computer graphics, robotics, global navigation, computer vision and the spatial orientation of instruments. The …

Salient Closed Boundary Extraction With Ratio Contour, Song Wang, Toshiro Kubota, Jeffrey Mark Siskind, Jun Wang

Faculty Publications

We present ratio contour, a novel graph-based method for extracting salient closed boundaries from noisy images. This method operates on a set of boundary fragments that are produced by edge detection. Boundary extraction identifies a subset of these fragments and connects them sequentially to form a closed boundary with the largest saliency. We encode the Gestalt laws of proximity and continuity in a novel boundary-saliency measure based on the relative gap length and average curvature when connecting fragments to form a closed boundary. This new measure attempts to remove a possible bias toward short boundaries. We present a polynomial-time algorithm …

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 …

The Contextable: Building And Testing An Intelligent, Context-Aware Kitchen Table, Daniel Matthew Hoopes

Theses and Dissertations

The purpose of this thesis was to design and evaluate The ContexTable, a context-aware system built into a kitchen table. After establishing the current status of the field of context-aware systems and the hurdles and problems being faced, a functioning prototype system was designed and built. The prototype makes it possible to explore established, untested theory and novel solutions to problems faced in the field.

Automation Laboratory Development With Design Implementation Scheme And Simulation Software, Cheng Y. Lin, Gary R. Crossman

Engineering Technology Faculty Publications

This paper describes the development of the Automation Control Lab in the Mechanical Engineering Technology Program of the Engineering Technology Department at Old Dominion University. The reorganization goal of the development is to help students design, test, and implement their automation designs effectively. Three processes are adopted to achieve this goal: (1) floor-plan design and inventory control of the components, (2) using Automation Studio to dynamically check each design, and (3) using industrial Programmable Logic Controllers (PLC) controllers to download PLC programs.

Seven Principles Of Efficient Human Robot Interaction, Michael A. Goodrich, Dan R. Olsen Jr.

Faculty Publications

Advances in robot technology and artificial intelligence have increased the range of robot applications as well as the importance of supporting human interaction with robots and robot teams. Previous work by the authors has highlighted the importance of creating neglect tolerant autonomy and efficient interfaces. In this paper, lessons learned from evaluating neglect tolerance and interface efficiency are compiled into a set of principles for efficient interaction. Emphasis is placed on designing efficient interfaces, but many of the principles require autonomy levels that support the principles. Each principle is illustrated by an example and motivated by citing relevant factors from …

The Sentient Web, Michael N. Huhns

Faculty Publications

In a startling revelation, a team of university scientists has reported that a network of computers has become conscious and sentient, and is beginning to assume control of online information system. In spite of the ominous tone typically chosen for dramatic effect, a sentient Web would be more helpful and much easier for people to use. An agent is an active, persistent software component that perceives, reasons, and acts, and whose actions include communication. Agents inherently take intentional actions based on sensory information and memories of past actions. All agents have necessary communication ability, but they do not necessarily possess …

Massive Deliberation, William H. Turkett Jr., John R. Rose, Michael N. Huhns

Faculty Publications

Agents are proliferating on the Web, making it conceivable that their collective reasoning ability might someday be harnessed for robust decision-making. The hope is that massive deliberation power can soon help solve problems that require knowledge, reasoning, and intelligence. Until recently, working individually or in small groups, agents across the Web could barely communicate and could only reason under conditions of severely bounded rationality. Projects such as Agentcities showed that widespread heterogeneous agents could collaborate on specific predefined tasks and provide diverse agent-based services. When the tasks are dynamic, of long duration, and ill defined, however, success requires planning that …

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.

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 …

Diagnostics Of Bar And End-Ring Connector Breakage Faults In Polyphase Induction Motors Through A Novel Dual Track Of Time-Series Data Mining And Time-Stepping Coupled Fe-State Space Modeling, Richard J. Povinelli, John F. Bangura, Nabeel Demerdash, Ronald H. Brown

Electrical and Computer Engineering Faculty Research and Publications

This paper develops the fundamental foundations of a technique for detection of faults in induction motors that is not based on the traditional Fourier transform frequency domain approach. The technique can extensively and economically characterize and predict faults from the induction machine adjustable speed drive design data. This is done through the development of dual-track proof-of-principle studies of fault simulation and identification. These studies are performed using our proven Time Stepping Coupled Finite Element-State Space method to generate fault case data. Then, the fault cases are classified by their inherent characteristics, so-called “signatures” or “fingerprints.” These fault signatures are extracted …

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, …

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 …

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 …

Development Of Self-Adaptive Back Propagation And Derivative Free Training Algorithms In Artificial Neural Networks, Shamsuddin Ahmed

Theses: Doctorates and Masters

Three new iterative, dynamically self-adaptive, derivative-free and training parameter free artificial neural network (ANN) training algorithms are developed. They are defined as self-adaptive back propagation, multi-directional and restart ANN training algorithms. The descent direction in self-adaptive back propagation training is determined implicitly by a central difference approximation scheme, which chooses its step size according to the convergence behavior of the error function. This approach trains an ANN when the gradient information of the corresponding error function is not readily available. The self- adaptive variable learning rates per epoch are determined dynamically using a constrained interpolation search. As a result, appropriate …

Constructive Induction Machines For Data Mining, Marek Perkowski, Stanislaw Grygiel, Qihong Chen, Dave Mattson

Electrical and Computer Engineering Faculty Publications and Presentations

"Learning Hardware" approach involves creating a computational network based on feedback from the environment (for instance, positive and negative examples from the trainer), and realizing this network in an array of Field Programmable Gate Arrays (FPGAs). Computational networks can be built based on incremental supervised learning (Neural Net training) or global construction (Decision Tree design). Here we advocate the approach to Learning Hardware based on Constructive Induction methods of Machine Learning (ML) using multivalued functions. This is contrasted with the Evolvable Hardware (EHW) approach in which learning/evolution is based on the genetic algorithm only.

Constructive Induction Machines For Data Mining, Marek Perkowski, Stanislaw Grygiel, Qihong Chen, Dave Mattson

Electrical and Computer Engineering Faculty Publications and Presentations

"Learning Hardware" approach involves creating a computational network based on feedback from the environment (for instance, positive and negative examples from the trainer), and realizing this network in an array of Field Programmable Gate Arrays (FPGAs). Computational networks can be built based on incremental supervised learning (Neural Net training) or global construction (Decision Tree design). Here we advocate the approach to Learning Hardware based on Constructive Induction methods of Machine Learning (ML) using multivalued functions. This is contrasted with the Evolvable Hardware (EHW) approach in which learning/evolution is based on the genetic algorithm only. Various approaches to supervised inductive learning …