Earticle

This paper discusses software performability evaluation considering the real-time property. We assume that the software system has two operational states from the viewpoint of the end users: one is operating with the desirable performance level according to specification and the other is with degraded performance level. The time-dependent behavior of the system is described by the Markovian software availability model with performance degradation. Assuming that the system can process the multiple tasks simultaneously, we analyze the distribution of the number of tasks whose processes can be completed within the processing time limit with the infinite server queueing model. We derive several software performability measures; these are given as the functions of time and the number of debugging activities. Finally, we illustrate several numerical examples of the measures to investigate the impact of consideration of the performance degradation on the system performability evaluation.

Regression testing is a critical activity which occurs during the maintenance stage of the software lifecycle. However, it requires large amounts of test cases to assure the attainment of a certain degree of quality. As a result, test suite sizes may grow significantly. To address this issue, Test Suite Reduction techniques have been proposed. However, suite size reduction may lead to significant loss of fault detection efficacy. To deal with this problem, a greedy algorithm is presented in this paper. This algorithm attempts to select a test case which satisfies the maximum number of testing requirements while having minimum overlap in requirements coverage with other test cases. In order to evaluate the proposed algorithm, experiments have been conducted on the Siemens suite and the Space program. The results demonstrate the effectiveness of the proposed algorithm by retaining the fault detection capability of the suites while achieving significant suite size reduction

This paper proposes a new practical method for determining when to stop software testing. This issue has been widely known as the optimal release problem of software product, and many researchers have been developing mathematical/computational models for finding the solution for decades. We try to develop a new quality control charting to help making the right decision for it by employing the moving average model and bootstrap scheme. After discussing the modeling, we show an example of the statistical decision making of the optimal software release time.

Machine-learning approaches have been widely used for fault-proneness detection. Introduction of machine learning approaches induces development of new software metrics for fault-prone module detection. We have proposed an approach to detect fault-prone modules using the spam-filtering technique. To treat our approach as the conventional faultprone approaches, we summarize the output of spam-filtering based approach as a metric. In this paper, we show the effectiveness of our new metric comparing the conventional software metrics using two open source projects.

The product development in mechanical industry can be modeled as an engineering process defined on the collaboration of various engineering services. An e-Engineering framework aims to integrate engineering services and mediate them, so as to promote collaboration within the context of product development. The collaboration of engineering services is very similar to a business process, in terms of web service composition. By using the web service composition, the e-Engineering framework can be operated in an open environment, and provide better engineering services to its users. However, the existing web service composition methodology shows some limitations when dealing with engineering services. This paper presents a service composition system for the engineering services in consideration of their characteristics.

Software test data generation is an important part of software testing. This paper presents a multi-agent cooperation framework for software test data generation. The framework is constituted by Graph Miner, Method Selector and test data generation method agent group. Graph Miner extracts software information sequences from UML graphs, and sends them to Method Selector. Then Method Selector selects out relevant method agents to generate test data. This framework can solve the problems of test data generation methods extension and low level of intelligence exist in traditional methods. Based on the framework proposed in this paper, a software prototype is developed. It is proved that this framework is feasible.