James R. Sweigart

A Dynamic Programming Based Pruning Method for Decision Trees

This paper concerns a decision-tree pruning method, a key issue in the development of decision trees. We propose a new method that applies the classical optimization technique, dynamic programming, to a decision-tree pruning procedure. We show that the proposed method generates a sequence of pruned trees that are optimal with respect to tree size. The dynamic-programming-based pruning (DPP) algorithm is then compared with cost-complexity pruning (CCP) in an experimental study. The results of our study indicate that DPP performs better than CCP in terms of classification accuracy.

An Integrative Model-Based Approach to Hospital Layout

Abstract The issues of facility layout and bed allocation in health care settings are typically evaluated separately using very different model-based approaches. This paper describes a two-phase approach to the hospital layout problem that incorporates a number of considerations from typical layout models and methods used in determining bed allocations. The first phase involves a quadratic integer goal programming model that determines a configuration and recommended allocation of beds to hospital services. The detailed ramifications of the proposed layout are then evaluated in the second phase via a simulation model. The application of the optimization-simulation approach in a general purpose hospital is described. Handled by the Department of Health Systems.

Coordinated transportation systems: An alternative approach to traditional independent systems

Abstract Public service agencies are servicing increasing numbers of clients as their operating funds continue to decrease. As a result, it is becoming more and more difficult for these agencies to maintain their effectiveness. This paper focuses upon shared transportation programs which is just one of the many cost-savings approaches public service agencies are beginning to implement. As alternatives to current transportation procedures, two coordinated transportation systems are presented, evaluated, and compared in a two agency-two vehicle system network scenario on the basis of total optimal vehicle route lengths. It is illustrated that significant cost savings can be achieved by coordinating transportation resources among local agencies. The main contributions of this paper are the two optimization models that will serve as benchmarks against which heuristic vehicle routing and scheduling models for coordinated transportation systems can be compared and tested. Such heuristics could then be incorporated into affordable software for use by local public service agencies.

A comparison of two intelligent scheduling systems for flexible manufacturing systems

Abstract Despite the existence of hardware suitable for the development of advanced automated manufacturing systems, the implementation of such systems has been hampered by the lack of appropriate software necessary for the scheduling and control of these systems. Artificial Intelligence (AI) has been suggested as a methodology suited to the development of this software. As a result, in this paper two intelligent scheduling and control systems are developed with the cooperation of an “expert” at an existing FMS in Aiken, South Carolina, USA. The literature related to scheduling FMS using AI methodologies is unclear as to whether scheduling should be done in a real-time manner similar to simple job-shop scheduling or in a predictive manner that shows detailed start times and finish times for some scheduling horizon. As such, one intelligent scheduler developed in this research utilizes a real-time scheduling methodology, while the second utilizes a predictive methodology. Both systems were developed in conjuction with a scheduling expert at the FMS. Results from a simulation model of the FMS using each of the two scheduling methodologies are compared in an effort to address the issue of which methodology is better suited for the scheduling and control of automated manufacturing systems such as FMS.

An interactive decision framework for multiple objective production planning

The formation of realistic implementable medium-range production plans requires explicit recognition of the multiple conflicting objectives of production planning. However, suggested applications of multiobjective optimization to production planning have been limited to goal programming procedures which fail to capitalize on the intrinsic flexibility of a multiobjective model. Alternatively, interactive multiobjective solution techniques could be used to allow planners to enhance decision making without excessive computational effort. This study describes an interactive multiple objective decision framework and evaluates its effectiveness via a multiobjective capacitated lot sizing model based on a real manufacturing facility. The results suggest that this approach is an effective solution strategy and useful decision aid for complex production planning problems.