Cross-projects software defect prediction using spotted hyena optimizer algorithm

Abstract

Cross-projects software defect prediction improves the quality of new software projects or projects with a shortage of historical data. Therefore, various data mining techniques are recommended in this field. The classification accuracy issue is considered one of the most significant problems due to the shortage and heterogeneous in historical data. To address this challenge, this research utilizes a spotted hyena optimizer algorithm as a classifier to predict defects through cross-projects. Confidence and Support are utilized as a multi-objective fitness function to look for the best classification rules. These classification rules are used to predict defects for new projects or other projects with insufficient data. The datasets of NASA such as JM1, KC1, and KC2 are used. By applying spotted hyena optimizer algorithm as a classifier on one dataset and predicting defects in the other two datasets, accuracy is reported 84.6, 92.0, 82.4, 90.7, 86.6 and 81.8 for JM1, KC1, and KC2 respectively. These accuracy values are better than the most significant data mining techniques in the field such as Support Vector Machine, Naïve Bayes, Boosting, C4.5, and Bagging. Also, the proposed research discusses other performance measures such as precision, recall, and f-measure. The conclusion proves that there are many features of McCabe and Halstead that have a strong impact to generate highly accurate predictors for defects such as McCabe's line count of code, McCabe's cyclomatic complexity, McCabe's essential complexity, McCabe's design complexity iv, Halstead's effort, Halstead's time estimator, Halstead's line count, Halstead's count of line of comments and total operators.

A Hybrid Approach of Spotted Hyena Optimization Integrated with Quadratic Approximation for Training Wavelet Neural Network

“…Though SHO is a recent algorithm, it has been widely used to resolve various engineering problems [ 30 – 36 ]. Rather than engineering problems, SHO is also castoff to resolve numerous mechanical and electrical glitches such as reduction of load for brake constituents belonging to automobiles, PID factor optimization for AVR systems, soil strength estimation, economic load dispatch problem, and improvement in software project quality also [ 37 – 41 ]. The same algorithm has also been used with neural networks, to solve feature selection and classification problems [ 42 – 46 ].…”

Meta‐heuristic optimization algorithm for predicting software defects

“…Kumar et al (2014) proposed two classifiers for predicting defects using asymmetric kernel PCA and partial least squares, applying them using a kernel function with SOFTLAB on NASA datasets. Elsabagh et al (2020) optimized an ML classifier to predict defects in cross-projects. The classifier is trained on projects available in the NASA dataset, and then the classification model is used on different or new projects.…”

“…To deal with this issue, our work optimizes if-then classification rules by a novel meta-heuristic optimization algorithm, SHO, based on the conduct of spotted hyenas (Elsabagh et al, 2020) for within-project defect prediction.…”

“…These metrics are used in JM1, KC2, and KC1 datasets. We preferred to describe them separately in Table 3 (Elsabagh et al, 2020). There are some common metrics between the four used datasets.…”

“…Our research uses the spotted hyena optimizer (SHO; Dhiman & Kumar, 2017;Kumar & Kaur, 2020), a novel meta-heuristic algorithm, as a classifier for foreseeing faults in within-project (training and testing phases in the same project; Elsabagh et al, 2020). The principal idea of the SHO is the behaviour of spotted hyenas.…”