Lov Kumar

Statistical and Machine Learning Methods for Software Fault Prediction Using CK Metric Suite: A Comparative Analysis

Experimental validation of software metrics in fault prediction for object-oriented methods using statistical and machine learning methods is necessary. By the process of validation the quality of software product in a software organization is ensured. Object-oriented metrics play a crucial role in predicting faults. This paper examines the application of linear regression, logistic regression, and artificial neural network methods for software fault prediction using Chidamber and Kemerer (CK) metrics. Here, fault is considered as dependent variable and CK metric suite as independent variables. Statistical methods such as linear regression, logistic regression, and machine learning methods such as neural network (and its different forms) are being applied for detecting faults associated with the classes. The comparison approach was applied for a case study, that is, Apache integration framework (AIF) version 1.6. The analysis highlights the significance of weighted method per class (WMC) metric for fault classification, and also the analysis shows that the hybrid approach of radial basis function network obtained better fault prediction rate when compared with other three neural network models.

Empirical Analysis on Effectiveness of Source Code Metrics for Predicting Change-Proneness

Change-prone classes or modules are defined as software components in the source code which are likely to change in the future. Change-proneness prediction are useful to the maintenance team as they can optimize and focus their testing resources on the modules which have a higher likelihood of change. The quality of change-proneness prediction model can be best assessed by the use of software metrics that are considered to design the prediction model. In this work, 62 software metrics with four metrics dimensions, including 7 size metrics, 18 cohesion metrics, 20 coupling metrics, and 17 inheritance metrics are considered to develop a model for predicting change-proneness modules. Since the performance of the change-proneness model depends on the source code metrics, they are used as input of the change-proneness model. We also considered five different types of feature selection techniques to remove irrelevant feature and select best set of features. The effectiveness of these set of source code metrics are evaluated using eight different machine learning algorithms and two ensemble techniques. Experimental results demonstrates that the model developed by considering selected set of source code metrics by feature selection technique as input achieves better results as compared to considering all source code metrics. The experimental results also ravel that the change-proneness model developed by using coupling metrics achieved better performance as compared other dimension metrics such as size metrics, cohesion metrics, and inheritance metrics.

Hybrid functional link artificial neural network approach for predicting maintainability of object-oriented software

Among all quality parameters, Maintainability is more important to achieve success.This paper focus on maintainability of software using object oriented metrics.Hybrid approach of neural network is used to design a model for prediction.Two feature selection techniques are used to select best set of metrics.We achieved better prediction rate for maintainability as compared to others. In present day, software development methodology is mostly based on object-oriented paradigm. With the increase in the number of these software system, their effective maintenance aspects becomes a crucial factor. Most of the maintainability prediction models in literature are based on techniques such as regression analysis and simple neural network. In this paper, three artificial intelligence techniques (AI) such as hybrid approach of functional link artificial neural network (FLANN) with genetic algorithm (GA), particle swarm optimization (PSO) and clonal selection algorithm (CSA), i.e., FLANN-Genetic (FGA and AFGA), FLANN-PSO (FPSO and MFPSO), FLANN-CSA (FCSA) are applied to design a model for predicting maintainability. These three AI techniques are applied to predict maintainability on two case studies such as Quality Evaluation System (QUES) and User Interface System (UIMS). This paper also focuses on the effectiveness of feature reduction techniques such as rough set analysis (RSA) and principal component analysis (PCA) when they are applied for predicting maintainability. The results show that feature reduction techniques are very effective in obtaining better results while using FLANN-Genetic.

Predicting Object-Oriented Software Maintainability using Hybrid Neural Network with Parallel Computing Concept

Software maintenance is an important aspect of software life cycle development, hence prior estimation of effort for maintainability plays a vital role. Existing approaches for maintainability estimation are mostly based on regression analysis and neural network approaches. It is observed that numerous software metrics are even used as input for estimation. In this study, Object-Oriented software metrics are considered to provide requisite input data for designing a model. It helps in estimating the maintainability of Object-Oriented software. Models for estimating maintainability are designed using the parallel computing concept of Neuro-Genetic algorithm (hybrid approach of neural network and genetic algorithm). This technique is employed to estimate the software maintainability of two case studies such as the User Interface System (UIMS), and Quality Evaluation System (QUES). This paper also focuses on the effectiveness of feature reduction techniques such as rough set analysis (RSA) and principal component analysis (PCA). The results show that, RSA and PCA obtained better results for UIMS and QUES respectively. Further, it observed the parallel computing concept is helpful in accelerating the training procedure of the neural network model.

Source code metrics for programmable logic controller (PLC) ladder diagram (LD) visual programming language

The IEC 611131-3, an open international standard for Programmable Logic Controllers (PLC) defines several domain specific languages for industrial and process automation. Domain specific languages have several features, programming constructs and notations which are different than general purpose languages and hence the traditional source code metrics for general purpose programming languages cannot be directly applied to domain specific languages for writing control programs in the area of industrial automation. We propose source code level metrics to measure size, vocabulary, cognitive complexity and testing complexity of a visual Programmable Logic Controller (PLC) programming language. We present metrics for Ladder Diagram (LD) programming language which is one of the five languages defined in the IEC 61131-3 standard. The proposed metric is based on factors like number of distinct operators and operands, total number of operators and operands, number of rungs, weights of different basic control structures, structure of the program and control flow. We apply Weyukurs property to validate the metrics and evaluate the number of properties satisfied by the proposed metric.

The impact of feature selection on maintainability prediction of service-oriented applications

Service-oriented development methodologies are very often considered for distributed system development. The quality of service-oriented computing can be best assessed by the use of software metrics that are considered to design the prediction model. Feature selection technique is a process of selecting a subset of features that may lead to build improved prediction models. Feature selection techniques can be broadly classified into two subclasses such as feature ranking and feature subset selection technique. In this study, eight different types of feature ranking and four different types of feature subset selection techniques have been considered for improving the performance of a prediction model focusing on maintainability criterion. The performance of these feature selection techniques is evaluated using support vector machine with different types of kernels over a case study, i.e., five different versions of eBay Web service. The performances are measured using accuracy and F-measure value. The results show that maintainability of the service-oriented computing paradigm can be predicted by using object-oriented metrics. The results also show that it is possible to find a small subset of object-oriented metrics which helps to predict maintainability with higher accuracy and also reduces the value of misclassification errors.

Effective fault prediction model developed using Least Square Support Vector Machine (LSSVM)

Abstract Software developers and project teams spend considerable amount of time in identifying and fixing faults reported by testers and users. Predicting defects and identifying regions in the source code containing faults before it is discovered or invoked by users can be valuable in terms of saving maintenance resources, user satisfaction and preventing major system failures post deployment. Fault prediction can also improve the effectiveness of software quality assurance activities by guiding the test team to focus efforts on fault prone components. The work presented in this paper involves building an effective fault prediction tool by identifying and investigating the predictive power of several well-known and widely used software metrics for fault prediction. We apply ten different feature selection techniques to choose the best set of metrics from a set of twenty source code metrics. We build the fault prediction model using Least Squares Support Vector Machine (LSSVM) learning method associated with linear, polynomial and radial basis function kernel functions. We perform experiments on 30 Open Source Java projects. Experimental results reveals that our prediction model is best suitable for projects with faulty classes less than the threshold value depending on fault identification efficiency (low- 52.139%, median- 46.206%, and high- 32.080%).

Maintainability prediction of web service using support vector machine with various kernel methods

The present day software are mostly developed based on Service-Oriented Computing (SOC), which assembles loosely coupled pieces of software called services. With the increase in the number of development of these varieties of service oriented software, their effective maintenance plays an important role for the developers. The quality of SOC can be best assessed by the use of software metrics. In this paper, different object-oriented software metrics have been considered in order to design a model for predicting maintainability of SOC paradigm. Further support vector machine with different type of kernels have been considered for predicting maintainability of SOC paradigm. This paper also focuses on the effectiveness of feature selection techniques such as univariate logistic regression analysis, cross correlation analysis, rough set analysis, and principal component analysis. The results show that, maintainability of SOC paradigm can be predicted by application of various object-oriented metrics. The results further indicated that, it is possible to find a small subset of object-oriented metrics out of total available various object-oriented metrics, that enables prediction of maintainability with higher accuracy.

Using Structured Text Source Code Metrics and Artificial Neural Networks to Predict Change Proneness at Code Tab and Program Organization Level

Structured Text (ST) is a high-level text-based programming language which is part of the IEC 61131-3 standard. ST is widely used in the domain of industrial automation engineering to create Programmable Logic Controller (PLC) programs. ST is a Domain Specific Language (DSL) which is specialized to the Automation Engineering (AE) application domain. ST has specialized features and programming constructs which are different than general purpose programming languages. We define, develop a tool and compute 10 source code metrics and their correlation with each-other at the Code Tab (CT) and Program Organization Unit (POU) level for two real-world industrial projects at a leading automation engineering company. We study the correlation between the 10 ST source code metrics and their relationship with change proneness at the CT and POU level by creating experimental dataset consisting of different versions of the system. We build predictive models using Artificial Neural Network (ANN) based techniques to predict change proneness of the software. We conduct a series of experiments using various training algorithms and measure the performance of our approach using accuracy and F-measure metrics. We also apply two feature selection techniques to select optimal features aiming to improve the overall accuracy of the classifier.

Using Source Code Metrics and Multivariate Adaptive Regression Splines to Predict Maintainability of Service Oriented Software

Prediction of maintainability parameter for Object-Oriented Software using source code metrics is an area that hasattracted the attention of several researchers in academia andindustry. However, maintainability prediction of Service-Orientedsoftware is a relatively unexplored area. In this work, we conductan empirical analysis on maintainability prediction of eBay webservices using several source code metrics. We consider elevendifferent types of source code metrics as input for developinga maintainability prediction model using Multivariate AdaptiveRegression Splines (MARS) method. We compare and evaluatethe performance of the maintainability prediction model withMultivariate Linear Regression (MLR) approach and SupportVector Machine (SVM). Eight different types of feature selectiontechniques have been implemented to reduce dimension andremove irrelevant features. The experiment results reveals thatthe maintainability prediction model developed using MARSmethod achieved better performance as compared to MLR andSVM methods. Experimental results also demonstrate that themodel developed by considering a selected set of source codemetrics by feature selection technique as input achieves betterresults as compared to the approach which considers all sourcecode metrics.