Application of Soft Computing Techniques to Prediction of Faulty Classes in Object Oriented Software
Journal Title: International Journal of Marketing and Technology - Year 2011, Vol 1, Issue 5
Abstract
Estimating number of defects or predicting fault-proneness in object oriented software modules plays a key role in quality control of software products. Over the last few years, software quality has become one of the most important requirements in the development of systems. Faultproneness of a software module is the probability that the module contains faults. The objective of this paper is to analyze experimentally the object oriented metrics as predictors of fault-prone classes and, therefore, determine whether they can be used as early quality indicators. This early detection of fault-prone software components enables verification experts to concentrate their time and resources on the problem areas of the software system under development. In this paper we describe how we calculated the object oriented metrics given by Chidamber and Kemerer to illustrate how fault-proneness detection can be carried out. Empirical validation of software metrics to predict quality using machine learning methods is important to ensure their practical relevance in the software organizations. The aim of this research work is to establish a method for identifying software defects using machine learning methods. In this work we used NASA’s Metrics Data Program (MDP) as software metrics data. The repository at NASA IV & V Facility MDP contains software metric data and error data at the function/method level. In this paper we introduce Generalized Regression Neural Networks, fuzzy subtractive clustering and AdaptiveNeuro Fuzzy Inference System (ANFIS) for predicting number of defects using Object Oriented metrics.
Authors and Affiliations
Divya Jain and Vibhor Sharma
Keywords
Related Articles
- EP ID EP19267
- DOI -
- Views 398
- Downloads 19
The Relationship between Energy Consumption and Economic Growth in Nigeria: A Causality Analysis
This study investigates the causal relation between energy consumption and economic growth in Nigeria. Time series data was generated covering 1970 to 2009 periods. The study used both aggregated and disaggregated data...
Consumer Preferences for Mobile Service Providers: An Empirical Study in Bardoli
Huge competitions, advancement in technology and reduced tariff have propelled the growth of mobile services in India. In the last five years, the industry has made tremendous growth in terms of subscriber base. Today,...
Threshold effects in the relationship between oil revenues and growth in oil exporting countries
While there is much evidence to support the resource curse hypothesis for resource abundant countries, some studies have found that oil booms raise the economic growth of oil exporting countries. This paper examines th...
E-tailing: Tapping The Customers Online
The word 'retail' is derived from the French word 'retaillier' meaning 'to cut a piece off' or 'to break bulk'. In simple terms it involves activities whereby product or services are sold to final consumers in small qu...
A Study of Marketing Strategies Part 1: for Selected Pharmaceutical Medicine adopted by Pharmaceutical Companies in and around Pune Region
This paper of current marketing practices in the pharmaceutical sector, examining Medical Representative, Drug Stores, Doctors and Consumer-oriented promotions. It presents examples of marketing practices and their imp...