Data Mining: How Research Meets Practical Development?

At the 2001 IEEE International Conference on Data Mining in San Jose, California, on November 29 to December 2, 2001, there was a panel discussion on how data mining research meets practical development. One of the motivations for organizing the panel discussion was to provide useful advice for industrial people to explore their directions in data mining development. Based on the panel discussion, this paper presents the views and arguments from the panel members, the Conference Chair and the Program Committee Co-Chairs. These people as a group have both academic and industrial experiences in different data mining related areas such as databases, machine learning, and neural networks. We will answer questions such as (1) how far data mining is from practical development, (2) how data mining research differs from practical development, and (3) what are the most promising areas in data mining for practical development.     

FAULT-TOLERANT MULTI-AGENT EXACT BELIEF PROPAGATION

Multiply sectioned Bayesian networks (MSBNs) support multi-agent probabilistic inference in distributed large problem domains, where agents (subdomains) are organized by a tree structure (called hypertree). In earlier work, all belief updating methods on a hypertree are made of two rounds of propagation, each of which is implemented as a recursive process. Both processes need to be started from the same designated (root) hypernode. Agents perform local belief updating at most in a partial parallel manner. Such methods may not be suitable for practical multi-agent environments because they are easy to crush for the problems happened in communication or local belief updating. In this paper, we present a fault-tolerant belief updating method for multi-agent probabilistic inference. In this method, multiple agents concurrently perform exact belief updating in a complete parallel. Temporary problems happened from time to time at some agents or some communication channels would not prevent agents from eventually converging to the correct beliefs. Permanently disconnected communication channels would not keep the properly connected portions of the system from appropriately finishing their belief updating within portions. Compared to the previous traversal-based belief updating, the proposed approach is not only fault-tolerant but also robust and scalable.     

Optimizing fiber wetout for composites manufacturing

Decreased mechanical strength in a fiber reinforced plastic part can often be traced to poor or incomplete impregnation of the reinforcing fiber with the matrix. To properly understand the impregnation process in the design of new composites manufacturing machinery (specifically in unidirectional tape machines), or to optimize wetout in existing machine designs, the raw process materials and their relationship within the process environment must be examined. The critical factors are: resin viscosity vs. temperature; the work of adhesion between the fiber and resin; and the problem of forcing the resin to completely penetrate a fiber bundle. If these factors are known, nip rolls can be designed to meet a specific process envelope, or in the case of existing equipment, the existing process envelope for specific fiber/matrix combinations can be manipulated for maximum fiber wetout.     

A graphical user-interface for knowledge discovery in databases

This paper describes a graphical user-interface for database-oriented knowledge discovery systems, DBLEARN, which has been developed for extracting knowledge rules from relational databases. The interface, designed using a query-by-example approach, provides a graphical means of specifying knowledge-discovery tasks. The interface supplies a graphical browsing facility to help users to perceive the nature of the target database structure. In order to guide users' task specification, a cooperative, menu-based guidance facility has been integrated into the interface. The interface also supplies a graphical interactive adjusting facility for helping users to refine the task specification to improve the quality of learned knowledge rules.