Publication | Closed Access
A benchmarking framework using nonlinear manifold detection techniques for software defect prediction
12
Citations
0
References
2020
Year
Software MaintenanceEngineeringMachine LearningIntelligent DiagnosticsDiagnosisFault ForecastingSoftware EngineeringSoftware AnalysisData ScienceData MiningPattern RecognitionBenchmarking FrameworkHidden Markov ModelSystems EngineeringStatisticsManifold LearningSoftware QualityFeature EngineeringPredictive AnalyticsKnowledge DiscoveryComputer ScienceSoftware DefectsNonlinear Dimensionality ReductionAutomatic Fault DetectionSoftware DesignSoftware Defect PredictionProgram AnalysisSoftware TestingSoftware MetricDefect PredictionFailure Prediction
Prediction of software defects in time improves quality and helps in locating the defect-prone areas accurately. Although earlier considerable methods were applied, actually none of those measures was found to be fool-proof and accurate. Hence, a newer framework includes nonlinear manifold detection model, and its algorithm originated for defect prediction using different techniques of nonlinear manifold detection (nonlinear MDs) along with 14 different machine learning techniques (MLTs) on eight defective software datasets. A critical analysis cum exhaustive comparative estimation revealed that nonlinear manifold detection model has a more accurate and effective impact on defect prediction as compared to feature selection techniques. The outcome of the experiment was statistically tested by Friedman and post hoc analysis using Nemenyi test, which validates that hidden Markov model (HMM) along with nonlinear manifold detection model outperforms and is significantly different from MLTs.