Browsing by Author "Dr. Thomas Honeycutt, Committee Member"
Now showing 1 - 3 of 3
- Results Per Page
- Sort Options
- Advancement of Online Systems in Engineering by Expert TA(2006-09-04) Morton, Jeremy Andrew; Dr. Thomas Honeycutt, Committee Member; Dr. Kevin Lyons, Committee Member; Dr. Larry Silverberg, Committee Chair; Dr. Eric Klang, Committee MemberThis dissertation introduces a new online system called Expert TA. The system was developed based on the hypothesis that expressions are key elements in engineering problems and that the treatment of expressions is critical to the advancement of online systems. This dissertation identifies ergonomic problems with expression entry that Expert TA overcomes through the use of a problem-customize integrated expression editor, called a palate. Then the dissertation shows, using an expression analyzer that operates in the background of Expert TA, that specific mathematical mistakes within an entered expression can now be located. Emulating standard instructional practices, detailed feedback pertaining to specific mistakes and grading on the basis of specific mistakes is now possible.
- Data Mining and Its Potential Use in Textiles: A Spinning Mil(2002-05-08) Schertel, Stacey Lee; Dr. Thomas Honeycutt, Committee Member; Dr. Nancy Cassill, Committee Member; Dr. George Hodge, Committee Co-Chair; Dr. William Oxenham, Committee Co-ChairThe purpose of this research has been to understand the possible uses of data mining in the Textile Industry, specifically a spinning mill. There is a lot of information published on the theory of data mining, however there is not a lot published on its use in a manufacturing setting. A case study approach was used to help understand how data mining could be used in the manufacturing of textiles. The focus of this research was on a spinning mill in the textiles industry and the processing that is followed with the different data elements available. Data was collected from a spinning mill operation and then cleansed and merged to create a data warehouse that could be mined using the SAS Enterprise Miner software. An example ideal data warehouse was created for a spinning mill. In this warehouse the different elements and formats that are needed were listed for each process in the production of a cotton fiber. Initially a simple data mining process was used however this proved to be ineffective. Due to the successes and failures that were experienced during the research a new data mining process model was created. This model has six major steps, which contains a total of 28 specific activities that may be included in the data mining process model. The proposed model describes how data mining can be implemented in a manufacturing setting.
- Dynamic Ontology Driven Learning and Control of Robotic Tool Using Behavior(2009-12-07) Williams, Lloyd Carter; Dr. Robert St. Amant , Committee Chair; Dr. Ronald Endicott, Committee Member; Dr. Thomas Honeycutt, Committee Member; Dr. R. Michael Young, Committee MemberOne of the most interesting and rich fields of recent artificial intelligence (AI) research has come from examining embodied agents, the creation of which, poses interesting challenges and opportunities. Many traditional AI approaches which have previously proven successful quickly fail in the face of the unique challenges facing embodied agents. There is extensive multidisciplinary research into solving these problems, employing ideas and theory from not just computer science, but cognitive science, psychology, philosophy, neuroscience, as well as a range of other fields. Although the nature of embodied intelligence has risen to prominence in AI research relatively recently, animal behaviorists have been examining it for decades. One of the most explored areas of research into the nature of natural embodied intelligent agents (animals) involves their use of tools. We believe that the creation of artificial tool using behaviors yields insights into the nature of intelligence. The proposed research will survey animal tool using behaviors and argue that some form of imitation may serve as an integral part of most animal tool using behavior. This claim, for the significance of imitation in tool use, will be supported with results from ethology, psychology and neuroscience. We will present a system based on multidisciplinary research that employs action ontologies to enable robotic imitation. We will demonstrate with this research that if mechanisms for imitative behaviors are implemented on a robotic platform, these imitative mechanisms may then be employed to enable tool using behaviors. While the achievement of tool using behaviors through this type of imitative mechanism is a novel and significant technical achievement in and of itself, it’s success also provides insight into how tool using behaviors may have first arisen in animals.