Software quality prediction using fuzzy integration: a case study

Abstract

Given the complexity of many contemporary software systems, it is often difficult to gauge the overall quality of their underlying software components. A potential technique to automatically evaluate such qualitative attributes is to use software metrics as quantitative predictors. In this case study, an aggregation technique based on fuzzy integration is presented that combines the predicted qualitative assessments from multiple classifiers. Multiple linear classifiers are presented with randomly selected subsets of automatically generated software metrics describing components from a sophisticated biomedical data analysis system. The external reference test is a software developer's thorough assessment of complexity, maintainability, and usability, which is used to assign corresponding quality class labels to each system component. The aggregated qualitative predictions using fuzzy integration are shown to be superior to the predictions from the respective best single classifiers.

Predicting Faults before Testing Phase using Halstead's Metrics

“…al., compare the performance of predictive models which use design level metrics with those uses code level metrics and those that use both. [14] Nick J. Pizzi purposes in his case study an aggregation technique based on fuzzy integration that combines that combines the predictive quantitative assessments from multiple classifier [15] Cagatay Catal surveys the software engineering literature on software fault prediction and both machine learning based and statistical based approaches on 90 software fault prediction papers [16] YANG Weimin, LI Longshu purposes the correlation of software metrics focusing on the data sets of software defect prediction. A rough set model is presented to reduce the attributes of data sets of software defect prediction [17].…”

On the Role of Soft Computing in Modelling the Spread of Infectious Diseases

“…Past software engineering experience [54] and recent literature [55][56][57] [58] suggest several guidelines to which agent-based model development should adhere: spiral development methodology; version control; careful code reviews; validation; system profiling; and system determinism. In contrast to compartmental models, which are in general easier to communicate and analyze, agent-based model descriptions are frequently incomplete and therefore less accessible to the reader.…”

The Analysis of Software Complexity Using Stochastic Metric Selection

“…The use of metrics requires a fundamental understanding of what is being measured and the proper interpretation of how the measurements are being acquired both of which are necessary prerequisites to software refactoring, that is, changing a software module to improve its conceptual structure without affecting its behaviour [17] [18]. Software metrics may be broken down into three main types [19]: historical measures related to the conventional procedural programming paradigm; Software Science metrics introduced in the seminal paper by Halstead [20]; measures related to the object-oriented programming paradigm, many of which were introduced in another seminal paper by Chidamber and Kemerer [21].…”