Computer Sciences Commons^™

Learning To See Analogies: A Connectionist Exploration, Douglas S. Blank

Computer Science Faculty Research and Scholarship

The goal of this dissertation is to integrate learning and analogy-making. Although learning and analogy-making both have long histories as active areas of research in cognitive science, not enough attention has been given to the ways in which they may interact. To that end, this project focuses on developing a computer program, called Analogator, that learns to make analogies by seeing examples of many different analogy problems and their solutions. That is, it learns to make analogies by analogy. This approach stands in contrast to most existing computational models of analogy in which particular analogical mechanisms are assumed a priori …

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

Electrical & Computer Engineering Faculty Research

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

Velocity Estimation Via A Neural Network Enhanced By Classical Detection Algorithms, Zeki Berk Hamşioğlu

Electrical & Computer Engineering Theses & Dissertations

The goal of this research is to show how to solve a velocity estimation problem using a neural network connected to an array of sensors. Motivated by biological studies involving insect vision, the neural network utilized is a member of a class of shunting neural networks. When an object moves across the face of the sensor array, the neural network's pulse response is first temporally located using classical M-ary detection techniques. Both the deterministic and stochastic cases are considered. Then the network's pulse response is post-processed via an existing velocity estimation algorithm based on a Volterra series model of the …

A Synthesized Methodology For Eliciting Expert Judgment For Addressing Uncertainty In Decision Analysis, Richard W. Monroe

Engineering Management & Systems Engineering Theses & Dissertations

This dissertation describes the development, refinement, and demonstration of an expert judgment elicitation methodology. The methodology has been developed by synthesizing the literature across several social science and scientific fields. The foremost consideration in the methodology development has been to incorporate elements that are based on reasonable expectations for the human capabilities of the user, the expert in this case.

Many methodologies exist for eliciting assessments for uncertain events. These are frequently elicited in probability form. This methodology differs by incorporating a qualitative element as a beginning step for the elicitation process. The qualitative assessment is a more reasonable way …

Autonomous Construction Of Multi Layer Perceptron Neural Networks, Thomas F. Rathbun

Theses and Dissertations

The construction of Multi Layer Perceptron (MLP) neural networks for classification is explored. A novel algorithm is developed, the MLP Iterative Construction Algorithm (MICA), that designs the network architecture as it trains the weights of the hidden layer nodes. The architecture can be optimized on training set classification accuracy, whereby it always achieves 100% classification accuracies, or it can be optimized for generalization. The test results for MICA compare favorably with those of backpropagation on some data sets and far surpasses backpropagation on others while requiring less FLOPS to train. Feature selection is enhanced by MICA because it affords the …

The "Hoover" Project: Home Occupants Vehicular Electronic Reconnaissance, Kelvin Chan

SWITCH

The article explains telepresence, as well as its potential in safety and security, along with its traditional usage of traversing dangerous situations. This article describes a dystopian plan to place drones equipped with cameras and microphones in all homes in the Silicon Valley as a vehicle for telepresence. The data achieved through this method would also be stored into a public domain browser on the internet, free for anyone in the public to view, including larger corporations and the government. The idea behind this is the assimilation of data behind all cultures for understanding and to assist law enforcement in …

The Toysim Project, Anthony Rodriguez

Theses : Honours

No abstract provided.

Expert System For The Generation Of A Work Breakdown Structure, Bernard O'Callaghan

Theses

This thesis outlines research work carried out in the Mechanical & Manufacturing Department in Cork Regional Technical College, Ireland. With computers now having an increasingly dominant role in all areas of business, it was inevitable that computer-based project management packages would become more popular. To date however, these packages have concentrated on monitoring and controlling projects. The definition and brainstorming phases required to generate a project plan are still largely manual tasks. Planning a project initially involves generating a complete and organised list of all the tasks needing to be completed in order to achieve a project’s goal. This list …

Neural Network Classification Of Environmental Samples, Jeffrey L. Blackmon

Theses and Dissertations

This research develops a general methodology for designing neural network classifiers for real-world environmental problems. This methodology is demonstrated through the design of a multi-layer perceptron to classify stainless steel and actinide samples. Neural networks, sometimes called artificial neural networks, have been shown capable of classifying complex patterns. Artificial neural networks are physiologically motivated computer algorithms which attempt to mimic the function of the large interconnected network of neurons in the human brain, which has extraordinary pattern recognition capabilities. These artificial neural networks learn to map a set of input features, elemental composition, onto a set of outputs such as …

Development Of Object-Based Teleoperator Control For Unstructured Applications, Hyunki Cho

Theses and Dissertations

For multi-fingered end effectors in unstructured applications, the main issues are control in the presence of uncertainties and providing grasp stability and object manipulability. The suggested concept in this thesis is object based teleoperator control which provides an intuitive way to control the robot in terms of the grasped object and reduces the operator's conceptual constraints. The general control law is developed using a hierarchical control structure, i.e., human interface I gross motion control level in teleoperation control and fine motion control/object grasp stability in autonomous control. The gross motion control is required to provide the position/orientation of the Super …

Exploring Knowledge Processes For Technology Assimilation, Rochelle K. Young

Engineering Management & Systems Engineering Theses & Dissertations

In the emerging knowledge society, the ability to make the experience and expertise of those involved in and affected by new technology unconditionally available to all members of an organization is becoming increasingly important. One of the problems in developing such knowledge processes for technology assimilation is that current social structures do not easily accommodate unconditional participation. Since the implementation of modern information technology is changing the workplace and the nature of work itself, alternative social structures are needed. This research takes as given that deep questions concerning knowledge processes and social transformation are in principle undecidable; and, only questions …

The Emergence Of Alife, P.D. Quick

SWITCH

Interview with Kenneth E. Rinaldo, an artist who is on the Board of Directors of YLEM. Within this interview, many topics are covered, including artificial life, simulations, the meaning of art, spirituality, and television. The interview also goes into the personal work and life of Rinaldo, whose focus includes many of these subjects. Some of the more specific subjects include intelligence without consciousness, the combination of science and art, and Ken Rinaldo’s The Flock, an interactive A-Life sculpture.

Rudy Rucker's Calife, Rudy Rucker

SWITCH

This page performs as a guide to Rudy Rucker’s alife programs. The first page explains how to download the source codes as well as the compiled software. It is noted that the compiler used was Borland C++ 4.0. The second page performs as a list of each program and explains what they are used for. The zip files can be found at the bottom of the software download page 2.

Rucker, Rudy Rucker

SWITCH

In this article, Rudy Rucker shares his thoughts on hacking. He summarizes it as normal actions, such as building a car, or kneading clay. He compares hacking to things that are buildable by hand, and views creating computer programs the same way. One of the benefits of creating your own computer programs is that you can customize themn however you want. However customizing software on your own is extremely time consuming. He then goes into further detail about artificial life and how hyperspace works. Hacking bends the cyber reality that we are accustomed to, and modifying programs outside of what …

Artificial Love Life Is As Real As The Real Thing, Professor S. Farsad

SWITCH

This article explains how an experiment by two human subjects stimulates love compared to artificial life. Professor Farsad’s experiment consisted of seven procedures from Stendhal’s work on romantic love, Love (1822). Both this article and experiment aimed to answer the question; Can artificial life feel love in romance?

Rudy Rucker's Spirograph, Rudy Rucker

SWITCH

This article showcases the main aspects of how this spirograph was to be used. The spirograph is part of Rudy Rucker’s quest for the gnarl. The main page shows how to download this spirograph and how to utilize the program to its full potential.

Nanotechnology, Fullereness, & The Golden Mean, Loretta L. Lange

SWITCH

This article explains how nanotechnology can be used in digital art forms and how it may be used in the near future. The development of nanotechnology has led to breathroughts such as the discovery of buckyballs and fullerenes. Such concepts eventually led to the research into nanobiology. The world of nanotechnology is still considered new and all of the concepts that dabbled into this medium can be expectred to evolve as time goes by.

An Adaptive Fuzzy Logic Controller For Intelligent Networking And Control, Irshad Nainar

Theses: Doctorates and Masters

In this thesis, we present a fuzzy logic control scheme to regulate the flow of traffic approaching a set of intersections. An adaptive Fuzzy Logic Traffic Controller (FLTC) is used to adjust the green phase split of the north-south and east-west approaches of a set of traffic signals based on the actual traffic approaching the intersection. Each intersection is coordinated with its neighbouring intersections by adjusting the offset of the local intersection. The offset is adjusted by a local fuzzy logic controller loacted at each intersection. A new fuzzy control scheme, using a supervisory Fuzzy Logic Controller, is also proposed …

Combinatorial Approaches For Hard Problems In Manpower Scheduling, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Manpower scheduling is concerned with the construction of a workers' schedule which meets demands while satisfying given constraints. We consider a manpower scheduling Problem, called the Change Shift Assignment Problem(CSAP). In previous work, we proved that CSAP is NP-hard and presented greedy methods to solve some restricted versions. In this paper, we present combinatorial algorithms to solve more general and realistic versions of CSAP which are unlikely solvable by greedy methods. First, we model CSAP as a fixed-charge network and show that a feasible schedule can be obtained by finding disjoint paths in the network, which can be derived from …

Randomized Approximation Of The Constraint Satisfaction Problem, Hoong Chuin Lau, Osamu Watanabe

Research Collection School Of Computing and Information Systems

We consider the Weighted Constraint Satisfaction Problem (W-CSP) which is a fundamental problem in Artificial Intelligence and a generalization of important combinatorial problems such as MAX CUT and MAX SAT. In this paper, we prove non-approximability properties of W-CSP and give improved approximations of W-CSP via randomized rounding of linear programming and semidefinite programming relaxations. Our algorithms are simple to implement and experiments show that they are run-time efficient.

Design And Evaluation Of Standard Telerobotic Control Software, Kevin P. Anchor

Theses and Dissertations

This thesis represents the first implementation of a proposed Air Force standard telerobotic control architecture. This architecture was developed by the NASA Jet Propulsion Laboratory and the National Institute of Standards and Technology under contract to the Air Force Materiel Command Robotics and Automation Center of Excellence (RACE) as the Unified Telerobotics Architecture Project (UTAP). The AFIT Robotics and Automation Applications Group (RAAG) Lab B facility computational structure was redesigned to be compliant with the UTAP architecture. This thesis shows that the UTAP specification to be implementable. However, if the underlying operating system does not support generic message passing, an …

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

Electrical & Computer Engineering Faculty Research

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

Text Independent Speaker Verification Using Binary-Pair Partitioned Neural Networks, Claude A. Norton Iii

Electrical & Computer Engineering Theses & Dissertations

A method is presented for the application of binary-pair partitioned neural networks to the task of speaker verification. This technique is based on a previously developed neural network classifier for speaker identification.

The main focus of this research was the development and testing of the algorithms necessary to extend the binary-pair partitioning approach from speaker identification to speaker verification. The method is based on the development of a user profile which is obtained from discriminative data provided by the binary-pair partitioned neural networks.

Experimental results are provided which demonstrate the viability of this approach, using the TIMIT speech corpus for …

Virtual Celluoid, Switch Staffs

SWITCH

The article is an analysis of the author’s research pertaining to films relating to or containing the concept of virtual reality. The author lists several films such as Johnny Mnemnonic, Virtuosity, The Net, and Disclosure and provides a brief synopsis and review of each movie. Each film explains the concept of virtual reality through differing plots and methods such as cyberspace, progressive software, and artificial intelligence. The author also gives their own insight into and ratings of the films, explaining what they think is the most relatable in terms of overall storyline as well as how realisticly the movie portrays …

Vr Products, P.D. Quick

SWITCH

The article is an analysis of the author’s experience testing several virtual reality items at Siggraph, an annual convention displaying computer machinery and interactive technology products. The author explains each device and how they work, the company behind the invention, as well as how it can help with future technological advancements. Several products are explained in more depth; the i-Glasses by Virtual I/O, Red Planet by Virtual World Entertainment Inc., Venturer S-2 by Thomson Entertainment Systems, and several more. Each item explores virtual reality in differing ways such as interactive video games, more user-friendly 3D modeling, and virtual movie theater …

Interview: Brenda Laurel, Jason Challas

SWITCH

This interview with Brenda Laurel, Virtual Reality (VR) author and thinker, discusses the applications and challenges of VR. Creating an emphatic experience using VR technology is possible, but the challenge lies in designing an environment that models the senses to stimulate emotions. VR enables experiences of different genders, but physiological differences between the sexes exist and are important to understand. However, technology used to create the environment and simulation of physical objects in VR is only in the developmental stage. Laurel believes in the importance of keeping the mind grounded in the physical body, in order to strengthen the appreciation …

Teaching Accommodation Task Skills: From Human Demonstration To Robot Control Via Artificial Neural Networks, Paul V. Whalen

Theses and Dissertations

A simple edge-mating task, performed automatically by accommodation control, was used to study the feasibility of using data collected during a human demonstration to train an artificial neural network (ANN) to control a common robot manipulator to complete similar tasks. The 2-dimensional (planar) edge-mating task which aligns a peg normal to a fiat table served as the basis for the investigation. A simple multi-layered perceptron (MLP) ANN with a single hidden layer and linear output nodes was trained using the back-propagation algorithm with momentum. The inputs to the ANN were the planar components of the contact force between the peg …

Comparing Traditional Statistical Models With Neural Network Models: The Case Of The Relation Of Human Performance Factors To The Outcomes Of Military Combat, William Oliver Hedgepeth

Engineering Management & Systems Engineering Theses & Dissertations

Statistics and neural networks are analytical methods used to learn about observed experience. Both the statistician and neural network researcher develop and analyze data sets, draw relevant conclusions, and validate the conclusions. They also share in the challenge of creating accurate predictions of future events with noisy data.

Both analytical methods are investigated. This is accomplished by examining the veridicality of both with real system data. The real system used in this project is a database of 400 years of historical military combat. The relationships among the variables represented in this database are recognized as being hypercomplex and nonlinear.

The …

Artificially Intelligent Air Combat Simulation Agents, Daniel E. Gisselquist

Theses and Dissertations

The Advanced Research Projects Agency (ARPA), in an effort to improve military simulations, has proposed a standard for Distributed Interactive Simulation (DIS). This network protocol will allow dissimilar applications to communicate simulation information. In the field of air combat, this will allow pilots in remote simulators to fly in a common simulation. The success of this standard is dependent on applications being able to work within that standard, as well as a large variety of Computer Generated Forces (CGFs) to complement interactive forces. CGFs are needed to help simulate the large combat scenarios that can only occur in wartime. By …

Survey And Implementation Of Commercial Manual Controllers For A Generic Telerobotics Architecture, Thomas E. Deeter

Theses and Dissertations

The purpose of this study is to determine an input device for the Air Force's generic telerobotics architecture for large aircraft maintenance and repair. One area of concern is the human to machine interface, more specifically, which manual controller should be used for the specified tasks in this architecture. We mailed a survey to 68 companies in order to compile a list of possible input devices that the telerobotics architecture could use. 32 companies responded which gave me enough data to generate a list that described the physical traits of the input devices. We then divided the required tasks into …