Search

The goal of this project is to develop a unique simulation environment that can be used to increase students' interest and expertise in Computer Science curriculum. Hands-on experience with physical or simulated equipment is an essential ingredient for learning, but many approaches to training develop a separate piece of equipment or software for each topic area. We describe the development of a simulation environment that provides a foundation for cross-disciplinary exercises. The Wireless Intelligent agent Simulation Environment (WISE), which combines activities from virtual and physical versions of the Wumpus World game, provides a dynamic learning environment that can enhance a number of Computer Science courses. In this paper, we describe the WISE environment design. We also describe steps for integrating WISE into Computer Science curriculum. As a demonstration of the effectiveness of the tool, we describe its use in the artificial intelligence, multimedia, and wireless networks courses at the University of Texas at Arlington.

Describes the development of a Web-based multimedia delivery method of increasing students' interest in artificial intelligence (AI). The course material features an integrated simulation environment that allows students to develop and test AI algorithms in a dynamic and uncertain visual environment. Evaluated the effect of the simulation on the interest level and confidence in class material of students over 3 years. (SLD)

Discusses structural components of databases that require data-mining algorithms and describes the SUBDUE system that is designed to discover knowledge in structural databases. Analyses the ability of SUBDUE to scale to large databases and describes parallel and distributed implementations to investigate methods for improving the scalability of scientific-discovery systems. (LRW)

Three successive multiple generations of rats were exposed to different toxicants and then bred to the transgenerational F5 generation to assess the impacts of multiple generation different exposures. The current study examines the actions of the agricultural fungicide vinclozolin on the F0 generation, followed by jet fuel hydrocarbon mixture exposure of the F1 generation, and then pesticide dichlorodiphenyltrichloroethane on the F2 generation gestating females. The subsequent F3 and F4 generations and F5 transgenerational generation were obtained and F1–F5 generations examined for male sperm epigenetic alterations and pathology in males and females. Significant impacts on the male sperm differential DNA methylation regions were observed. The F3–F5 generations were similar in ∼50% of the DNA methylation regions. The pathology of each generation was assessed in the testis, ovary, kidney, and prostate, as well as the presence of obesity and tumors. The pathology used a newly developed Deep Learning, artificial intelligence-based histopathology analysis. Observations demonstrated compounded disease impacts in obesity and metabolic parameters, but other pathologies plateaued with smaller increases at the F5 transgenerational generation. Observations demonstrate that multiple generational exposures, which occur in human populations, appear to increase epigenetic impacts and disease susceptibility. [ABSTRACT FROM AUTHOR]

The ability to transfer knowledge learned in one environment in order to improve performance in a different environment is one of the hallmarks of human intelligence. Insights into human transfer learning help us to design computer-based agents that can better adapt to new environments without the need for substantial reprogramming. In this paper, we study the transfer of knowledge by humans playing various scenarios in a graphically realistic urban setting that are specifically designed to test various levels of transfer. We determine the amount and type of transfer that is being performed based on the performance of trained and untrained human players. In addition, we use a graph-based relational learning algorithm to extract patterns from player graphs. These analyses reveal that indeed humans are transferring knowledge from one set of games to another and the amount and type of transfer varies according to player experience and scenario complexity. The results of this analysis help us understand the nature of human transfer in such environments and shed light on how we might endow computer-based agents with similar capabilities. The game simulator and human data collection also represent a significant testbed in which other AI capabilities can be tested and compared to human performance. Index Terms--Data mining, graph algorithms, transfer learning, games.

Discovering repetitive, interesting, and functional substructures in a structural database improves the ability to interpret and compress the data. However, scientists working with a database in their area of expertise often search for predetermined types of structures or for structures exhibiting characteristics specific to the domain. This paper presents a method for guiding the discovery process with domain-specific knowledge. In this paper, the SUBDUE discovery system is used to evaluate the benefits of using domain knowledge to guide the discovery process. Domain knowledge is incorporated into SUBDUE following a single general methodology to guide the discovery process. Results show that domain-specific knowledge improves the search for substructures that are useful to the domain and leads to greater compression of the data. To illustrate these benefits, examples and experiments from the computer programming, computer-aided design circuit, and artificially generated domains are presented. Index Terms - Data mining, minimum description length principle, data compression, inexact graph match, domain knowledge.

This paper describes a decision-theoretic approach to cooperative sensor planning between multiple autonomous vehicles executing a military mission. For this autonomous vehicle application, intelligent cooperative reasoning must be used to select optimal vehicle viewing locations and select optimal camera pan and tilt angles throughout the mission. Decisions are made in such a way as to maximize the value of information gained by the sensors while maintaining vehicle stealth. Because the mission involves multiple vehicles, cooperation can be used to balance the work load and to increase information gain. This paper presents the theoretical foundations of our cooperative sensor planning research and describes the application of these techniques to ARPA's Unmanned Ground Vehicle program. Index Terms - Sensor planning, decision theory, multi-agent planning, Unmanned Ground Vehicle, active vision.

The Subdue system for knowledge discovery in databases can be made to perform better by augmenting its domain-independent discovery techniques with domain-specific knowledge. The Subdue system discovers substructures that can reduce the size of the input database. Experimental results indicate that the addition of domain-specific knowledge enhances the search for such substructures and allows further reduction in the size of the database.

Concept discovery in structural data requires the identification of repetitive substructures in the data. We describe a method for discovering substructures in data using an inexact graph match. A previous implementation of our SUBDUE system discovers substructures based on the psychologically-motivated criteria of cognitive savings, compactness, connectivity and coverage. However, the instances in the data must exactly match the discovered substructures. We describe a new implementation of SUBDUE that employs an inexact graph match to discover substructures which occur often in the data, but not always in the same form. This inexact substructure discovery can be used to formulate fuzzy concepts, compress the data description, and discover interesting structures in data that are found either in an identical or in a slightly convoluted form. Examples from the domains of scene analysis and chemical compound analysis demonstrate the benefits of the inexact discovery technique.