Search Results (1 - 25 of 43 Results)

Sort By  
Sort Dir
 
Results per page  

O'Rell, James L.Smart Terrain using Multiple Needs
Master of Computing and Information Systems, Youngstown State University, 2012, Department of Computer Science and Information Systems
Gaming artificial intelligence must look intelligent, real intelligence is a near impossible goal to achieve because of the number of CPU cycles it requires. Using Multiple Need Smart Terrain, AI can look intelligent without requiring the large number of CPU cycles it requires for such intelligence. It can be used to manage a character's needs and direct them to which objectives are most profitable for them. Unlike normal smart terrain that only pays attention to one need at a time, this algorithm can look at any number of needs and check which objective would be best to meet that need. This way, the AI can have little actual intelligence, the terrain tells it where to go. With this technology, AI can appear intelligent and keep the cycles required to a minimum.

Committee:

John Sullins, PhD (Advisor); Bonita Sharif, PhD (Committee Member); Susan Harper, MS (Committee Member)

Subjects:

Computer Science

Keywords:

Smart Terrain; Gaming AI; Artificial Intelligence; AI; Gaming; Artificial Intelligence

Bonaventura, PatriziaInvariant patterns in articulatory movements
Doctor of Philosophy, The Ohio State University, 2003, Speech and Hearing Science
The purpose of the study is to discover an effective method of characterizing movement patterns of the crucial articulator as the function of an abstract syllable magnitude and the adjacent boundary, and at the same time to investigate effects of prosodic control on utterance organization. In particular, the speed of movement when a flesh-point on the tongue blade or the lower lip crosses a selected position relative to the occlusion plane is examined. The time of such crossing provides an effective measure of syllable timing and syllable duration according to previous work. In the present work, using a very limited vocabulary with only a few consonants and one vowel as the key speech materials, effects of contrastive emphasis on demisyllabic movement patterns were studied. The theoretical framework for this analysis is the C/D model of speech production in relation to the concept of an invariant part of selected articulatory movements. The results show evidence in favor of the existence of ‘iceberg’ patterns, but a linear dependence of slope on the total excursion of the demisyllabic movement, instead of the approximate constancy of the threshold crossing speed as suggested in the original proposal of the ‘iceberg’, has been found. Accordingly, a revision of the original concept of ‘iceberg’ seems necessary. This refinement is consistent with the C/D model assumption on ‘prominence control’ that the syllable magnitude determines the movement amplitude, accompanying directly related syllable duration change. In this assumption, the movement of a consonantal component should also be proportional to syllable magnitude. The results suggest, however, systematic outliers deviating from the linear dependence of movement speed on excursion. This deviation may be caused by the effect of the immediately following boundary, often referred to as phrase-final elongation.

Committee:

Osamu Fujimura (Advisor)

Keywords:

Speech science; speech production; speech production modeling; C/D model of speech production; phonetics; linguistics; artificial intelligence; articulatory movements; x-ray microbeam system

Jappinen, Harry JuhaniA perception-based developmental skill acquisition system /
Doctor of Philosophy, The Ohio State University, 1979, Graduate School

Committee:

Not Provided (Other)

Subjects:

Computer Science

Keywords:

Artificial intelligence

Mitchell, SophiaA Cascading Fuzzy Logic Approach for Decision Making in Dynamic Applications
MS, University of Cincinnati, 2016, Engineering and Applied Science: Aerospace Engineering
There is growing interest in the effectiveness of emulating human decision making and learning in modern aerospace applications. The following thesis is an examination of several applications in which cascading type 1 and 2 fuzzy logic has been utilized in artificial intelligence and machine learning problems to demonstrate its capabilities. In Fuzzy Logic Inferencing for PONG (FLIP), the effectiveness of cascading type 1 logic is examined as an optimal controller for players in the game of PONG. Robotic collaboration is also developed as the PONG game was expanded into a multi-player option. Precision Route Optimization using Fuzzy Intelligence (PROFIT) examines the use of fuzzy logic as an optimizer in a cascaded algorithmic solution to a modified Traveling Salesman Problem (TSP). The TSP is modified in a way to better mimic a real-life scenario where footprints must be visited instead of simply points, which gives an interesting complexity to the problem. Collaborative Learning using Fuzzy Inferencing (CLIFF) is an extension of the PONG game introduced in FLIP, however a type-2 fuzzy logic toolbox is developed for potential use in development of a robotic coach that could optimize its players to beat an opponent in an application of layered fuzzy learning. Considering the successes associated with these research endeavors, it can be concluded that cascading type 1 and 2 fuzzy logic are both interesting tools that can further the abilities of intelligent systems and machine learning algorithms.

Committee:

Kelly Cohen, Ph.D. (Committee Chair); Nicholas D. Ernest, Ph.D. (Committee Member); Manish Kumar, Ph.D. (Committee Member); Grant Schaffner, Ph.D. (Committee Member)

Subjects:

Aerospace Materials

Keywords:

Fuzzy Logic;Cascading;Intelligent Systems;Artificial Intelligence;Travelling Salesman Problem;Genetic Algorithm

IONESCU, MIRCEA MARIANADAPTIVE MEASURES OF SIMILARITY - FUZZY HAMMING DISTANCE - AND ITS APPLICATIONS TO PATTERN RECOGNITION PROBLEMS
PhD, University of Cincinnati, 2006, Engineering : Computer Science
Similarity measures are the basis of most of the machine learning and pattern recognition algorithms. The choice of the similarity determines the effectiveness of the algorithm in solving the specific problem. This is why finding a relevant similarity measure is an active area of research in machine learning and pattern recognition. Hamming distance is a simple and efficient similarity measure, but because it was designed to deal with binary vectors, it can not be applied to many problems that uses real-valued vectors. This thesis build upon and extends a generalization of the Hamming distance, Fuzzy Hamming distance, that can operate on real-valued vectors and maintain the same meaning as the Hamming distance: the number of different elements. To assess the effectiveness of this new measure, FHD is employed in several experiments as basis for a Content Image Retrieval system, a banknote validation system and into a conceptual spaces based, knowledge discovery system.

Committee:

Dr. Anca Ralescu (Advisor)

Subjects:

Computer Science; Mathematics

Keywords:

Fuzzy Hamming Distance; artificial intelligence; fuzzy; image retrieval system

SHERRON, CATHERINE ELIZABETHCRITICAL VALUES: FEMINIST PHILOSOPHY OF SCIENCE AND THE COMPUTING SCIENCES
PhD, University of Cincinnati, 2003, Arts and Sciences : Philosophy
My dissertation is an examination of the intersections between epistemology, philosophy of science, and feminist theory. Feminist philosophy of science creates new and valuable ways of looking at the sciences by using gender as a category of analysis, or a lens through which to critically assess and constructively build projects in science, as well as in the philosophy of science. I employ feminist philosophy of science and a gendered lens in particular to examine the computing sciences. Starting specifically from the underrepresentation of women in computing, the project creates a platform for exploring the dimensions and contributions of feminist philosophy of science. This is not merely a critique of philosophy of science or a feminist review of computing, but a positive project in its own right, examining the epistemological structure of scientific inquiry, including the nature of objectivity, epistemic agency and the composition of an epistemic community, the importance of those epistemic communities, and the role of values in science. A central tenet of the work is that objectivity in science does not require leaving personal and political commitments at the lab door, but that social, ethical, cultural, and other values play a foundational epistemological role in science. Using gender as a lens uncovers some of those values for critical evaluation. This is not to deny the importance of the natural, empirical world in science. I argue that a philosophical position must at minimum account for our actual relationships-emotional, embodied, social, etc.-in the world and their impact on our theorizing and that dismissing the embodied experience of scientists results in a diminished understanding of the world in addition to diminished epistemological theories.

Committee:

Dr. Chris J. Cuomo (Advisor)

Subjects:

Philosophy

Keywords:

feminist philosophy of science; computing and artificial intelligence; epistemology; feminist epistemology; philosophy of science

Eckroth, Joshua RyanAnomaly-Driven Belief Revision by Abductive Metareasoning
Doctor of Philosophy, The Ohio State University, 2014, Computer Science and Engineering
Abduction, or inference to the best explanation, is, plausibly, part of commonsense reasoning, and a means by which a cognitive system may arrive at estimates of its world from observational and other evidence. We take this "world estimate" to be the cognitive system's beliefs. Since such reasoning is fallible, and world estimates will sometimes contain errors, an abductive reasoning system might improve its performance if it has a way to engage in belief revision when new evidence, or further reasoning, indicates the existence of a problem. In this study, we develop, implement, and experimentally validate a metareasoning system that monitors and attempts to correct beliefs established by the base-level abductive reasoning system. We first identify that the presence of an anomaly, which we define as an observation or other evidence that cannot plausibly and consistently be explained, as a signal that the cognitive system's world estimate might be incorrect or, alternatively, that the unexplainable datum is noise. The metareasoning system responds to the presence of anomalies by asking exactly that question: which anomalies are due to mistakes in the world estimate, and warrant specific belief revisions, and which anomalies are due to noise, and should not instigate belief revisions? Various considerations regarding the nature of the anomalies and the system's reasoning history are brought to bear to answer this question. Fundamentally, we see the metareasoning question ("what explains these anomalies: mistaken beliefs, or noise?") as structurally similar to the cognitive system's original question, "what explains these observations?" Thus, the metareasoning system is an abductive reasoning system, just like the base-level system. The anomalies constitute meta-evidence which may be explained by meta-hypotheses. These meta-hypotheses describe the various kinds of causes of anomalies and specify particular belief revisions in order to resolve the anomalies. The same abductive reasoning algorithms employed by the base-level reasoner are activated to find the best explanation for the anomalies. An anomaly is judged to be the result of noise when no meta-hypothesis is judged to be a good enough explanation. In this manner, the cognitive system may engage in corrective belief revision and noise identification via abductive metareasoning. We experimentally validate both the abductive reasoning and combined abductive reasoning and metareasoning systems with a software implementation. We explore three intentionally-simplified problem domains: simulated object tracking, aerial tracking, and inference to the best explanation with arbitrary Bayesian networks. These domains are intentionally simplified so that we can clearly identify how performance in these tasks is affected by various parameterizations of the reasoning and metareasoning systems. Our experiments show that (1) abductive reasoning is an effective way of reasoning in these problem domains, and (2) abductive metareasoning brings a significant boost in accuracy and noise identification. These experimental results, plus the system's architectural simplicity, together give strong evidence that abductive metareasoning is an appropriate and effective strategy for a cognitive system to revise its beliefs and arrive at more accurate estimates of its world.

Committee:

John Josephson, Dr. (Advisor); Balakrishnan Chandrasekaran, Prof. (Committee Member); Neil Tennant, Prof. (Committee Member)

Subjects:

Artificial Intelligence; Computer Science

Keywords:

artificial intelligence; cognitive systems; abductive reasoning; metareasoning; metacognition; abductive metareasoning; belief revision; anomalies; anomaly-driven belief revision; anomaly-driven metareasoning

Sista, Subrahmanya SrivathsavaAdversarial Game Playing Using Monte Carlo Tree Search
MS, University of Cincinnati, 2016, Engineering and Applied Science: Computer Science
Monte Carlo methods are a general collection of computational algorithms that obtain results by random sampling. Monte Carlo techniques, while great for simulation, have also found great application in the field of general game playing. We investigate the effectiveness of Monte Carlo methods as applied to general two player games (In this case we use a more interesting variant of the popular game Tic-Tac-Toe: fully observable, deterministic, static, single-agent environment). We set up AI agents, one using Monte Carlo simulation to play and the other using a more traditional mini-max setup. We compare and contrast their performance in all aspects, including efficiency, effectiveness, and cost in terms of memory/processing. After all the data collection and analysis we found that Monte Carlo Techniques tended to perform better relative to the Minimax algorithm when applied to a game of our choice and with restrictive time limits.

Committee:

Anca Ralescu, Ph.D. (Committee Chair); Chia Han, Ph.D. (Committee Member); Paul G. Talaga, Ph.D. (Committee Member)

Subjects:

Computer Science

Keywords:

monte carlo tree search;artificial intelligence;game playing;tic tac toe

Allen, Mary KayThe development of an artificial intelligence system for inventory management using multiple experts /
Doctor of Philosophy, The Ohio State University, 1986, Graduate School

Committee:

Not Provided (Other)

Subjects:

Business Administration

Keywords:

Expert systems ;Artificial intelligence;Inventory control;Business logistics

Jin, ChaoMethodology on Exact Extraction of Time Series Features for Robust Prognostics and Health Monitoring
PhD, University of Cincinnati, 2017, Engineering and Applied Science: Mechanical Engineering
Maintaining health model robustness has always been a challenge in prognostics and health management. Research on developing advanced machine learning algorithms has shown great promise, but the prognostic performance is limited when the feature quality is poor. This thesis proposes an extensible preprocessing methodology that applies time series pattern recognition to transient-rich and background-rich systems for robust prognostics and health monitoring. This method recognizes patterns-of-interest accurately to facilitate exact extraction of diagnostic information, namely, features. It takes three phases to realize exact feature extraction. First, hierarchical time series classifiers filter out the signals with few critical patterns and prepare the pattern recognition tools for segmentation. Second, time series pattern recognition identifies and segments the patterns-of-interest. Third, extract pattern-specific features as the input for health modeling. The developed exact feature extraction method is validated on two case studies: semiconductor etching process health monitoring and gas type classification using uncalibrated chemical sensors in complex environment. The proposed method is validated to outperform conventional feature extraction such as summary statistics and observation in both studies. The benefits of exact feature extraction include accuracy, consistency, generality, and extensibility. The recognition of patterns enables accurate description of critical process properties and accelerates segmentation compared to human observation. The extracted features are more consistent in healthy condition and more sensitive to faults. Also, the pattern recognition tools are designed for general engineering systems which can be applied to a wide range of industries. Besides, the semi-automated process allows human intervention to include additional patterns for an extensible and customized solution. This thesis embraces domain knowledge and attempts to generalize them and build engineering syntax and semantics at the fundamental level in the PHM system with the assistance of pattern recognition. Instead of making a decisive conclusion, this study hopes to usher in more research on feature quality and broaden the research frontier for prognostics and health management.

Committee:

Jay Lee, Ph.D. (Committee Chair); Jay Kim, Ph.D. (Committee Member); James Moyne, Ph.D. (Committee Member); Jing Shi, Ph.D. (Committee Member)

Subjects:

Mechanical Engineering; Mechanics

Keywords:

prognostics and health management;time series pattern recognition;machine learning;artificial intelligence;data-driven

Pech, Thomas JoelA Deep-Learning Approach to Evaluating the Navigability of Off-Road Terrain from 3-D Imaging
Master of Sciences (Engineering), Case Western Reserve University, 2017, EECS - Computer and Information Sciences
This work investigates a strategy for evaluating the navigability of terrain from 3-D imaging. Labeled training data was automatically generated by running a simulation of a mobile robot nai¨vely exploring a virtual world. During this exploration, sections of terrain were perceived through simulated depth imaging and saved with labels of safe or unsafe, depending on the outcome of the robot's experience driving through the perceived regions. This labeled data was used to train a deep convolutional neural network. Once trained, the network was able to evaluate the safety of perceived regions. The trained network was shown to be effective in achieving safe, autonomous driving through novel, challenging, unmapped terrain.

Committee:

Wyatt Newman (Advisor); Cenk Cavusoglu (Committee Member); Michael Lewicki (Committee Member)

Subjects:

Computer Science; Robotics; Robots

Keywords:

Mobile robots, Autonomous Navigation, Machine Learning, Artificial Neural Networks, Terrain, Simulation, Training Data, Data Generation, Labeling, Classifiers, Convolutional Neural Networks, Point Clouds, Perception, Prediction, Artificial Intelligence

Graham, James T.Development of Functional Requirements for Cognitive Motivated Machines
Doctor of Philosophy (PhD), Ohio University, 2016, Electrical Engineering & Computer Science (Engineering and Technology)
Machine Intelligence, and all of its associated fields and specialties, is a wide and complex area actively researched in laboratories around the world. This work aims to address some of the critical problems inherent in such research, from the most basic neural network structures, to handling of information, to higher level cognitive processes. All of these components and more are needed to construct a functioning intelligent machine. However, creating and implementing machine intelligence is easier said than done, especially when working from the ground up as many researchers have attempted. Instead, it is proposed that the problem be approached from both bottom-up and top-down level design paradigms, so that the two approaches will benefit from and support one another. To clarify, my research looks at both low level learning, and high level cognitive models and attempts to work toward a middle ground where the two approaches are combined into a single cognitive system. Specifically, this work covers the development of the Motivated Learning Embodied Cognition (MLECOG) model, and the associated components required for it to function. These consist of the Motivated Learning approach, various types of memory, action monitoring, visual and mental saccades, focus of attention, attention switching, planning, etc. Additionally, some elements needed for processing sensory data will be briefly examined because they are relevant to the eventual creation of a full cognitive model with proper sensory/motor I/O. The development of the Motivated Learning cognitive architecture is covered from its initial beginnings as a simple Motivated Learning algorithm to its advancement to a more complex architecture and eventually the proposed MLECOG model. The objective of this research is to show that a cognitive architecture that uses motivated learning principles is feasible, and to provide a path toward its development.

Committee:

Janusz Starzyk (Advisor); Mehmet Celenk (Committee Member); Savas Kaya (Committee Member); Jeff Dill (Committee Member); Jeff Vancouver (Committee Member); Annie Shen (Committee Member)

Subjects:

Cognitive Psychology; Computer Science; Electrical Engineering

Keywords:

artificial intelligence; motivated learning; reinforcement learning; cognitive model; embodied intelligence; cognitive architecture

Roth, Donald AllanEnhancing manufacturing productivity through the design and development of expert systems
Master of Science (MS), Ohio University, 1992, Electrical Engineering & Computer Science (Engineering and Technology)

The purpose of this thesis is to illustrate Expert Systems as a type of Artificial Intelligence technology and demonstrate how these systems can enhance manufacturing efficiency. Brief descriptions of some technologies involved with Artificial Intelligence and fundamental schemes of knowledge representation are presented.

Three applications are discussed, covering the development cycle of one application. Choosing appropriate applications and development software are covered. Knowledge engineering and development of code will be detailed using an actual application.

Conclusions and recommendations on the three programs will demonstrate the strengths of Expert System technology and the commitment and support needed to insure a useful system. Analysis of the program development will exemplify the methodology of Expert System technology.

Committee:

Constantinos Vassiliadis (Advisor)

Keywords:

manufacturing productivity; Expert Systems; Artificial Intelligence technology

DORAISWAMY, PRATHIBHAEXPERIMENTS ON APPROXIMATIONS OF CLOSED CONVEX SHAPED BOUNDARIES USING SUPPORT VECTOR MACHINES
MS, University of Cincinnati, 2004, Engineering : Computer Science
In a two-class classification problem, Support Vector Machines (SVM) find hyperplanes to separate these classes. Moreover, when the classes are inearly separable, the hyperplanes found by the SVM approach have maximum generalization. This is different from other statistical and heuristic techniques such as Neural Networks and Bayesian Networks, which may find a hyperplane, but which do not characterize its generalization power. Traditionally SVM's are based on kernels, which are inner product preserving mappings, of the class data from the original feature space into a new, higher dimensional feature space. When the classes are not linearly separable in the original feature space, this mapping ensures their linear separability in the new feature space. The main difficulty in using kernels is that given a particular classification problem, there is no definite rule for designing a good kernel for it. As an alternative to using kernels, a method for approximating nonlinear class boundaries by a piecewise separation surface has been proposed [3]. This thesis builds upon and improves on previous results [3]. More precisely, the experiments considered in this work show that the previous approach has two main shortcomings: (1) selection of good training points, and (2) inference of the final separating surface. In addition, in this thesis closed convex class boundaries are considered (previous work[3] considered only open nonlinear class boundaries). With respect to (1), after indicating possible shortcomings of various approaches, a new method for identifying good training data points is proposed (Nearest Three Point Algorithm). With respect to (2) knowledge of the convexity of the class boundary is used to derive the final separating surface as the convex hull (smallest convex set containing the class) of the learned piecewise linear class boundary. Experimental results illustrate and support the approaches developed in this thesis: average class recognition accuracy, based on 100 runs, for several closed convex classes, ranges from 94.5% to 97%.

Committee:

Dr. Anca Ralescu (Advisor)

Subjects:

Computer Science

Keywords:

support vector machines; class boundary; convex polygons; piecewise approximation; artificial intelligence; machine learning

Holter, Tammy D.Development of a prototype for the integration of scheduling and control in manufacturing using artificial intelligence techniques
Master of Science (MS), Ohio University, 1994, Industrial and Manufacturing Systems Engineering (Engineering)

This thesis addresses the development and implementation of real-time scheduling and control decision-making in hierarchical manufacturing environments. The objective was to develop a prototype of a "controller" for a single manufacturing machine. This prototype will serve as an important tool to study the integration of several functions and the utilization of status data to evaluate scheduling and control decision alternatives. The emphasis is on creating a prediction capability to aid in assessing the long-term system performance impact resulting from decisions made and environmental changes. This "look-ahead" capability is implemented by using neural networks, simulation, and genetic algorithms (GAs). Neural networks predict the behavior of different sequencing policies (i.e., dispatching rules) available in the system. This prediction mechanism could reduce significantly the alternatives available. The contribution of the GAs to the decision- making process is the development of a "new" scheduling rule based on a "building blocks" procedure initiated by the neural networks. GAs have been selected due to the extreme difficulty of the direct application of traditional methodologies. In addition, this prototype could be part of a larger hierarchical system. The research findings and the prototype developed have direct applications in the construction of real-time systems that are capable of using adaptive status data and could gracefully degrade with unforeseen situations.

Committee:

Luis Rabelo (Advisor)

Subjects:

Engineering, Industrial

Keywords:

prototype; integration; manufacturing; artificial intelligence techniques

Walker, DonaldSimilarity Determination and Case Retrieval in an Intelligent Decision Support System for Diabetes Management
Master of Science (MS), Ohio University, 2007, Computer Science (Engineering)
This thesis presents a metric for similarity determination and case retrieval for an intelligent decision support system. This system may greatly reduce the burden of diabetes management for both diabetic patients and their physicians through the use of case-based reasoning. Diabetes is a disease which affects over 20 million Americans with almost as many being at high risk of developing the disease. In order to live a healthy life with diabetes, individuals must continuously regulate their blood glucose levels. The current state of the art of diabetes management requires frequent doctor visits, careful measurements of the blood glucose levels, and mathematical calculations of insulin doses by the patient. This research is an intermediate step toward development of a method and system to analyze a patient's current state, recognize problems in blood glucose control and suggest therapy adjustments to remedy those problems.

Committee:

Cynthia Marling (Advisor)

Keywords:

artificial intelligence; AI; case-based reasoning; CBR; decision support; medical decision support; diabetes; glucose management; similarity determination; case retrieval; healthcare

Gao, ZhenningParallel and Distributed Implementation of A Multilayer Perceptron Neural Network on A Wireless Sensor Network
Master of Science, University of Toledo, Engineering (Computer Science)
This thesis presents a study on implementing the multilayer perceptron neural network on the wireless sensor network in a parallel and distributed way. We take advantage of the topological resemblance between the multilayer perceptron and wireless sensor network. A single neuron in the multilayer perceptron neural network is implemented on a wireless sensor node, and the connections between neurons are achieved by the wireless links between nodes. While the computation of the multilayer perceptron benefits from the massive parallelism and the fully distribution when the wireless sensor network is serving as the hardware platform, it is still unknown whether the delay and drop phenomena for message packets carrying neuron outputs would prohibit the multilayer perceptron from getting a decent performance. A simulation-based empirical study is conducted to assess the performance profile of the multilayer perceptron on a number of different problems. Simulation study is performed using a simulator which is developed in-house for the unique requirements of the study proposed herein. The simulator only simulates the major effects of wireless sensor network operation which influence the running of multilayer perceptron. A model for delay and drop in wireless sensor network is proposed for creating the simulator. The setting of the simulation is well defined. Back-Propagation with Momentum learning is employed as the learning algorithms for the neural network. A formula for the number of neurons in the hidden layer neuron is chosen by empirical study. The simulation is done under different network topology and condition of delay and drop for the wireless sensor network. Seven data sets, namely Iris, Wine, Ionosphere, Dermatology, Handwritten Numerical, Isolet and Gisette, with the attributes counts up to 5000 and instances counts up to 7797 are employed to profile the performance. The simulation results are compared with those from the literature and through the non-distributed multilayer perceptron. Comparative performance evaluation suggests that the performance of multilayer perceptron using wireless sensor network as the hardware platform is comparable with other machine learning algorithms and as good as the non-distributed multilayer perceptron. The time and message complexity have been analyzed and it shows the scalability of the proposed method is promising.

Committee:

Gursel Serpen (Advisor); Mohsin Jamali (Committee Member); Ezzatollah Salari (Committee Member)

Subjects:

Artificial Intelligence; Computer Science

Keywords:

Artificial Intelligence; Artificial Neural Network; Machine Learning; Multilayer Perceptron; Wireless Sensor Network; Parallel Computing; Distributed Computing

Shankar, ArunprasathONTOLOGY-DRIVEN SEMI-SUPERVISED MODEL FOR CONCEPTUAL ANALYSIS OF DESIGN SPECIFICATIONS
Master of Sciences (Engineering), Case Western Reserve University, 2014, EECS - Computer Engineering
The integration of reusable IP blocks/cores is a common process in system-on-chip design and involves manually comparing/mapping IP specifications against system requirements. The informal nature of specification limits its automatic analysis. Ex- isting techniques fail to utilize the underlying conceptual information embedded in specifications. In this thesis, we present a methodology for specification analysis, which involves concept mining of specifications to generate domain ontologies. We employ a semi-supervised model with semantic analysis capability to create a col- laborative framework for cumulative knowledge acquisition. Our system then uses the generated ontologies to perform component retrieval and spec comparisons. We demonstrate our approach by evaluating several IP specifications.

Committee:

Christos Papachristou (Advisor)

Subjects:

Computer Engineering; Computer Science; Information Systems; Systems Design

Keywords:

Ontology, Specification Mining, Neuro-fuzzy, Information Retrieval, Artificial Intelligence, Expert Systems, Fuzzy Logic, Knowledge Representation, Data Mining, Specification Analysis, Natural Language Processing

Abbas, Syed MurtuzaAdvanced Hybrid Simulation Model based on Phenomenology and Artificial Intelligence
PhD, University of Cincinnati, 2015, Engineering and Applied Science: Civil Engineering
Hybrid simulation technology is being widely used in the field of structural engineering for testing of structural systems to study their dynamic behavior under seismic loads. It involves coupling of experimental laboratory testing of complex parts of a system with computational models of the remaining parts of the system whose behavior can be simulated with confidence in a finite element program. A hybrid engine program helps the experimental and computational modules to interact with each other in real-time under seismic loading, and gives the overall response of the entire system as a whole. However, to conduct hybrid testing of even the simplest of systems, the number of experimental tests required exceed the capabilities of any laboratory in the country. All research in this field to date has been conducted either using highly simplified models, or by compromising the accuracy of the overall results by performing experimental testing of only a few most complex sub-structures of the structural system. The current project delivers an advanced hybrid simulation (AHS) model that removes the current limitations of hybrid simulation technology. It engages a single experimental module per type of sub-structure that is complex enough to require experimental testing, and predicts the hysteretic response of all similar sub-structures present in the entire structural system using phenomenology and artificial intelligence. This, coupled with the response of computational models of rest of the system at every increment, provides highly realistic and economical results by drastically cutting down the number of experimental tests required for hybrid testing. The present work removes the limitations of the existing phenomenological models and employs them to make the predictions. The AHS model is independent of material and geometry of the sub-structure, as it just requires inputs from the experimental response of a sub-structure at every load increment to predict the response of all similar sub-structures to any type of loading.

Committee:

Gian Rassati, Ph.D. (Committee Chair); Steven Crowley, M.S. (Committee Member); Randall Allemang, Ph.D. (Committee Member); James Swanson, Ph.D. (Committee Member)

Subjects:

Civil Engineering

Keywords:

hybrid simulation;phenomenology;seismic loading;beam-to-column connections;artificial intelligence

Place, Alison L.IRL Feminism: Bridging Physical and Digital Spaces to Empower Millennial Activists
Master of Fine Arts, Miami University, 2017, Art
Millennial women were sold a promise of equality that society was not prepared to deliver. Raised to believe they could do and be anything, they followed their passions and pursued their dreams. Now, as they collectively move into adulthood, they are encountering both overt and normalized forms of discrimination that shatter the narrative of equality they once believed. Frustrated, bewildered and unprepared to fight a battle they believed was already won by generations of women before them, young women today are turning to feminism in a new way. They seek a community of peers with whom to bring issues of inequality to light and resources to take action against injustice. This research examines millennials in Cincinnati, Ohio and emerging forms of protest against gender inequality. Traditional methods for civic action are combined with modern digital tools to produce a contemporary model for social activism that appeals to the unique values and aspirations of the millennial generation. By bridging their physical and digital worlds, young activists can connect locally with peers to empower each other and gain tools for identifying and eliminating gender hierarchy in their lives and their communities.

Committee:

Dennis Cheatham (Advisor); Gaile Pohlhaus (Committee Member); James Coyle (Committee Member)

Subjects:

Design; Gender; Gender Studies; Social Research; Technology; Womens Studies

Keywords:

feminism; feminist research; gender; gender inequality; social justice; activism; consciousness raising; millennials; artificial intelligence; experience design; social design; design research

KAMEI, RINAKOEXPERIMENTS IN PIECEWISE APPROXIMATION OF CLASS BOUNDARY USING SUPPORT VECTOR MACHINES
MS, University of Cincinnati, 2003, Engineering : Computer Science
This work is concerned with issues that arise in implementation and use of Support Vector Machines (SVM). First, an analytical computational approach to solve the convex optimization problem for SVM without any conventional heuristic optimization techniques is considered. The second issue concerns the application of SVM with linear kernels to data sets which are not linearly separable by approximating the separating surface with a collection of hyperplanes derived on small subsets of the training data. The simulation experiments on two-dimensional non-linear datasets result in good approximations of the true separating surface by the algorithm proposed. Finally, the non-linear transformation to obtain a non-linear separating surface by SVM is proposed and the piecewise linear approximation is extended to the piecewise non-linear approximation. The experimental results from both methods are compared.

Committee:

Dr. Anca Ralescu (Advisor)

Subjects:

Computer Science

Keywords:

support vector machines; class boundary; piecewise approximation; artificial intelligence; machine learning

Bhatt, DeepakComputer Aided Algorithms Based on Mathematics and Machine Learning for Integrated GPS and INS Land Vehicle Navigation Systems
Doctor of Philosophy in Engineering, University of Toledo, College of Engineering
An integrated navigation system consisting of INS and GPS is usually preferred due to the reduced dependency on GPS-only navigator in an area prone to poor signal reception or affected by multipath. The performance of the integrated system largely depends upon the quality of the Inertial Measurement Unit (IMU) and the integration methodology. Considering the restricted use of high grade IMU and their associated price, low-cost IMUs are becoming the preferred choice for civilian navigation purposes. MEMS based inertial sensors have made possible the development of civilian land vehicle navigation as it offers small size and low-cost. However, these low-cost inertial sensors possess high inherent sensor errors such as biases, drift, noises etc. As a result, the accuracy of the integrated system degrades rapidly in a GPS denied environment. Thus, an accurate in-lab calibration and modeling of inertial sensor errors become mandatory before being deployed. This dissertation introduces a Support Vector Regression (SVR) based IMU error modeling approach for improving the low-cost navigation system accuracy. A low-cost MEMS based IMU offered by cloud cap technology, Crista IMU is used to evaluate the SVR based error modeling approach effectiveness. Alternatively, the IMU derived navigation solution and GPS data is fused to output the more reliable navigation solution and model the errors in the inertial navigation solution simultaneously. This fusion and error modeling continues during the GPS signal availability. In the case of GPS outages, the developed error model is utilized to improve the integrated navigation system accuracy. Thus, in a continued effort to improve the standalone low-cost IMU derived navigation solution reliability during GPS outages, an intelligent technique utilizing neural networks and a hybrid of mathematics and support vector based fusion algorithms are proposed fusing INS and GPS data in an open and closed loop fashion. The performance of the proposed techniques and algorithm is evaluated using real field test data utilizing low-cost MEMS IMU, Crossbow IMU 300CC-100 and a Novatel OEM GPS receiver. The test results demonstrated the improved positioning accuracy in comparison to existing techniques and showed a substantial reduction in standalone Inertial Navigation System (INS) position error drift during GPS outages. Further, a feasibility of statistical based approaches consisting of Cubist, Random Forest and Support Vector Regression is evaluated for a low-cost INS and GPS integrated system. Through experimental demonstration, Random forest regression was found to be a suitable candidate for INS and GPS data fusion as it offers the least training time and ability to tuned the parameter automatically

Committee:

Vijay Devabhaktuni (Advisor)

Subjects:

Electrical Engineering

Keywords:

GPS, INS, Algorithms, Dempster Shafer, Artificial Intelligence

Lakumarapu, Shravan KumarCommittee Neural Networks for Image Based Facial Expression Classification System: Parameter Optimization
Master of Science in Engineering, University of Akron, 2010, Biomedical Engineering
There has been a significant growth in the application of Artificial Neural Networks (ANNs) in the medical field including clinical decision support systems which call for high reliability and performance often involving multi-classification problems. Committee Neural Networks (CNNs) were developed for increased reliability and performance and were successfully applied to several multi-classification problems. However, the effect of the number of input parameters on the performance of the CNNs has not been investigated. The purpose of the present study was to investigate this effect on the CNN performance in a multi-classification problem of facial image based mood detection. Kulkarni et al (2009) used 15 parameters to develop a CNN system for classifying a given facial image into one of the six basic moods. Six subsets of parameters, for each image, were extracted from the parameter database used by Kulkarni et al, with an increasing number of parameters (from five to ten). The entire data was divided into training data, initial testing data, and final evaluation data. The training data from the six subsets were used to train six groups of neural networks and these networks were subjected to initial testing using the corresponding initial testing data. CNNs of different sizes were formed for each group by selecting the best performing networks based on the initial testing results. These CNNs were further tested using the initial testing data and the best performing CNN from each group was selected for further evaluation. All the selected committees were further evaluated using the final testing data from subjects not used in training or initial testing. Two approaches were used for converting neural network output into binary: “winner takes all” approach and the “thresholding” approach. The results from both the approaches show that with an increasing number of input parameters, the accuracy increased initially and then decreased. The committee decision was more accurate than individual member networks‟ decision. The highest accuracies obtained were from the CNNs having eight input parameters: 87.9% using the “winner takes all approach” and 87.2% using the “thresholding” approach. In contrast, Kulkarni et al developed a dual committee system consisting of the primary committee and a specialized committee using 15 parameters and reported an accuracy of 90.4%. In the present study, a single committee using only eight input parameters produced similar accuracy. To increase the reliability of neural network based intelligent systems for medical applications, the number of parameters should be optimized.

Committee:

Dr. Narender Reddy, Dr. (Advisor)

Subjects:

Engineering

Keywords:

Artificial Neural Networks; Committee Neural Networks, Artificial Intelligence, decision support systems, optimization

ZHU, YAOYAOUNSUPERVISED DATABASE DISCOVERY BASED ON ARTIFICIAL INTELLIGENCE TECHNIQUES
MS, University of Cincinnati, 2002, Engineering : Computer Engineering
Competitive business pressures and a desire to leverage existing information technology investments have led people to explore the benefits of data mining technology. This technology is designed to help businesses discover hidden patterns in their data - patterns that can help them understand the purchasing behavior of their key customers, detect likely credit card or insurance claim fraud, predict probable changes in financial markets, etc. One approach of data mining is to use some form of supervised discovery. However, supervised discovery limits results as it is necessary to determine in advance what is of interest. This is contra-intuitive to the broadest goals of finding unexpected, interesting things.In this thesis, we make an experimental investigation into autonomous or unsupervised discovery. It is based on the novel paradigm proposed by Dr. L. J. Mazlack [ 1996]. This testable approach is that increasing coherence increases conceptual information; and this in turn reveals previously unrecognized, useful, implicit information. This can be done by recursive partitioning. In order to refine partitioning, we use some artificial intelligence techniques and also proposed the algorithms in clustering and generalizing on both scalar and non-scalar data. The algorithms are tested on some data sets and the results are discussed.

Committee:

Dr. Lawrence J. Mazlack (Advisor)

Subjects:

Computer Science

Keywords:

data mining; artificial intelligence; database discovery; mountain method

Bharathan, VivekBelief Revision in Dynamic Abducers through Meta-Abduction
Master of Science, The Ohio State University, 2010, Computer Science and Engineering

Abduction machines (or abducers) infer to the best explanation for the data presented to them, and may accumulate beliefs (the conclusions of the inferences) about the world. An abducer’s beliefs are justified as being the best explanation in contrast with alternative hypotheses. However, the best explanation available to (achievable by) an abducer need not be the true explanation for a variety of reasons including: incomplete search for alternative explanations, insufficient data, and inadequate background knowledge for evaluating alternatives. In light of this fallibility, algorithms were investigated for detecting and correcting errors, for dynamic abducers, by comparing a range of alternative algorithms with regard to effectiveness and computational costs. Dynamic abducers interpret an incoming information stream by producing their best explanations at any point in time. They accumulate new beliefs, and update older beliefs, in the light of new information.

In the present work, algorithms were developed for detecting and correcting errors in the accumulated beliefs of such abducers. These algorithms treat the problem of identifying errors as meta-abduction, where certain anomalies that occur during processing are explained as resulting from specific mistakes in previous abductive processing. Errors are then corrected, and beliefs revised, by adopting alternative explanations. A brute-force algorithm for this meta-abduction is computationally intractable, so heuristics were developed with prospects of improving performance. Since a priori mathematical analysis of the algorithms using these heuristics did not reveal useful bounds, simulation experiments were conducted, using a specimen domain. The domain was that of multi-object tracking, where an abduction machine, over time, attempts to maintain the track history of mobile entities, based on sensor reports. The experimental results suggest that, using only the heuristics that were investigated, belief revision by meta-abduction enables only small improvements in correctness, and is computationally expensive.

Committee:

John Josephson, PhD (Advisor); Balakrishnan Chandrasekaran, PhD (Advisor)

Subjects:

Artificial Intelligence; Computer Science

Keywords:

Artificial Intelligence; Abductive Inference; Belief Revision; Entity Tracking

Next Page