Performance Assessment and Incremental Evaluation of Rule-based Systems
نویسنده
چکیده
Rule-based systems that are easily testable are required for high reliability applications. However, as a rule base evolves, developers prefer incremental evaluation owing to the high cost of regression testing. For, quality aatd reliability improvement, researchers advocate that the evaluation phase be integrated with development: thus, incremental evaluation becomes more important in this context. In this paper, we propose a three-tiered lifecycle model for integrating evaluation in a rulebased system life cycle. We then explore two specific issues from a system’s evaluation perspective: (1) the limitation of functional testing for performance evaluation; and (2) the optimization the cost and effort for evaluation by using incremental methods, whenever possible. This research was motivated by our experience in the design and evaluation of rule-based systems. Introduction and Motivation The design of rule bases is often plagued by various anomalies whose detection requires a variety of evaluation procedures (O’Keefe & Lee 1990; O’Keefe & O’Leary 1993; Kiper 1992; Guida & Mauri 1993). The evaluation processes have been traditionally classified as verification, validation, and performance analysis (or measurement). Verification detects the anomalies due to redundancy, deficiency, circularity and ambivalence; functional validation tests the conformance of a system with its functional requirements; structural validation checks whether the observed functional performance is the result of the correct structure (rule) interactions and tries to capture the system structure in a well defined way; and performance assessment measures the adequacy, optimality, and test case coverage of the system. Not only are these processes non-trivial, but system developers are often unclear where they fit in a system life-cycle (Hamilton, Kelley, & Culbert 1991). One of the primary reasons that makes the evaluation of rule-based systems harder is the lack of a well defined link between system conception and its realization. In fact, in many cases, there does Life-cycle
منابع مشابه
Incremental explosive analysis and its application to performance-based assessment of stiffened and unstiffened plates
In this paper, the dynamic behavior of square plates with various thicknesses and stiffening configurations subjected to underwater explosion (UNDEX) are evaluated through a relatively novel approach which is called Incremental Explosive Analysis (IEA). The IEA estimates the different limit-states and deterministic assessment of plats’ behavior, considering uncertainty of loading conditions and...
متن کاملEntropy Based Fuzzy Rule Weighting for Hierarchical Intrusion Detection
Predicting different behaviors in computer networks is the subject of many data mining researches. Providing a balanced Intrusion Detection System (IDS) that directly addresses the trade-off between the ability to detect new attack types and providing low false detection rate is a fundamental challenge. Many of the proposed methods perform well in one of the two aspects, and concentrate on a su...
متن کاملUSING DISTRIBUTION OF DATA TO ENHANCE PERFORMANCE OF FUZZY CLASSIFICATION SYSTEMS
This paper considers the automatic design of fuzzy rule-basedclassification systems based on labeled data. The classification performance andinterpretability are of major importance in these systems. In this paper, weutilize the distribution of training patterns in decision subspace of each fuzzyrule to improve its initially assigned certainty grade (i.e. rule weight). Ourapproach uses a punish...
متن کاملS3PSO: Students’ Performance Prediction Based on Particle Swarm Optimization
Nowadays, new methods are required to take advantage of the rich and extensive gold mine of data given the vast content of data particularly created by educational systems. Data mining algorithms have been used in educational systems especially e-learning systems due to the broad usage of these systems. Providing a model to predict final student results in educational course is a reason for usi...
متن کاملNEW CRITERIA FOR RULE SELECTION IN FUZZY LEARNING CLASSIFIER SYSTEMS
Designing an effective criterion for selecting the best rule is a major problem in theprocess of implementing Fuzzy Learning Classifier (FLC) systems. Conventionally confidenceand support or combined measures of these are used as criteria for fuzzy rule evaluation. In thispaper new entities namely precision and recall from the field of Information Retrieval (IR)systems is adapted as alternative...
متن کامل