Software Defect Prediction via Convolutional Neural Network

WITHDRAWN: Software bug prediction and classification by global pooling of different activation of convolution layers

In order to improve software reliability, software defect prediction is applied to the process of software maintenance to identify potential bugs. Traditional methods of software defect prediction mainly focus on designing static code metrics, which are input into machine learning classifiers to predict defect probabilities of the code. However, the characteristics of these artificial metrics do not contain the syntactic structures and semantic information of programs. Such information is more significant than manual metrics and can provide a more accurate predictive model. In this paper, we propose a framework called defect prediction via attention-based recurrent neural network (DP-ARNN). More specifically, DP-ARNN first parses abstract syntax trees (ASTs) of programs and extracts them as vectors. Then it encodes vectors which are used as inputs of DP-ARNN by dictionary mapping and word embedding. After that, it can automatically learn syntactic and semantic features. Furthermore, it employs the attention mechanism to further generate significant features for accurate defect prediction. To validate our method, we choose seven open-source Java projects in Apache, using F1-measure and area under the curve (AUC) as evaluation criteria. The experimental results show that, in average, DP-ARNN improves the F1-measure by 14% and AUC by 7% compared with the state-of-the-art methods, respectively.

Software Defect Prediction (SDP) plays an active area in many research domain of Software Quality of Assurance (SQA). Many existing research studies are based on software traditional metric sets and defect prediction models are built in machine language to detect the bug for limited source code line. Inspired by the above existing system. In this paper, defect prediction is focused on predicting defects in source code. The objective of this thesis is to improve the software quality for accurate defect prediction is source code for file level. So, that it helps the developer to find the bug and fix the issue, to make better use of a resource which reduces the test effort, minimize the cost and improve the quality of software. A new approach is introduced to improve the prediction performance of Bidirectional RNNLM in Deep Neural Network. To build the defect prediction model a defect learner framework is proposed and first it need to build a Neural Language Model. Using this Language Model it helps to learn to deep semantic features in source code and it train & test the model. Based on language model it combined with software traditional metric sets to measure the code and find the defect. The probability of language model and metric set Cross-Entropy with Abstract Syntax Tree (CE-AST) metric is used to evaluate the defect proneness and set as a metric label. For classification the metric label K-NN classifier is used. BPTT algorithm for learning RNN will provide additional improvement, it improves the predictions performance to find the dynamic error.

In the last few years, with the development of deep learning theory, researchers have tried to introduce the method of artificial intelligence into the field of software defect prediction (SDP) to improve its prediction effect. To be fed into the neural network, the sample codes are represented as an abstract syntax tree (AST), and the AST is encoded as real numbers. However, in most cross-project defect prediction (CPDP) task, the method for converting the AST into a real number cannot effectively estimate the semantic distance between the ASTs, resulting in a significant reduction in training effects. To solve that problem, we present a new encoding framework, tree-based-embedding (TBE), to convert AST into real vectors and make the semantic gap between the ASTs measurable. To estimate the effect of this encoding method, we promise a tree-based-embedding convolutional neural network with transferable hybrid feature learning (TBCNN-THFL) to perform the CPDP tasks. TBCNN-THFL is fed data encoded with TBE method for learning the transferable joint features between different projects; meanwhile, TBCNN-THFL introduces a transfer component analysis algorithm. Furthermore, the model combines the handcrafted and deep-learning-generated features and then feeds them into the classifier to train a defect prediction model. A sufficient number of experiments demonstrate that TBCNN-THFL is superior to referential models on 72 pairs of CPDP tasks formed by 9 open-source projects.

In order to enhance software reliability, software defect prediction is used to predict potential defects and to improve efficiency of software examination. Traditional defect prediction methods mainly focus on design static code metrics, and building machine learning classifiers to predict pieces of code that potentially defective. However, these manual extracted features do not contain syntactic and semantic information of programs. These information is much more important than those metrics and can improve the accuracy of defect prediction. In this paper, we propose a framework called software defect prediction via transformer (DP-Transformer) which capture syntactic and semantic features from programs and use them to improve defect prediction. Specifically, we first parse source code into ASTs and then select representative nodes from ASTs to form token vectors. Then we employ mapping and word embedding to convert token vectors into numerical vectors and send the numerical vectors to transformer. Transformer will automatically extract syntactic and semantic features and eventually feed these features into a Logistic Regression classifier. We evaluate our method on seven open-source Java projects with certain labels and take F-measure as evaluation criteria. The experimental results show that averagely, the proposed DP-Transformer improves the state-of-art method by 8%.

PathPair2Vec: An AST path pair-based code representation method for defect prediction

Cross-project defect prediction (CPDP) is a promising approach to help to allocate testing efforts efficiently and guarantee software reliability in the early software lifecycle. A CPDP method usually trains a software defect classifier based on labeled data sets. Then the trained classifier can predict new projects without labeled data. Most previous CPDP techniques focused on manually designing handcrafted features. However, these handcrafted features ignore the programs’ semantic information. Moreover, some other existing defect prediction approaches learned semantic features from source code to build classifiers directly. However, they did not consider the distribution divergence between source and target projects. To address these limitations, we put forward a new method called Adversarial Discriminative Convolutional Neural Network (ADCNN). It can extract the transferable semantic features from source code for CPDP tasks. Specifically, we first parse source files into token vectors and then map them to integer vectors via word embedding. Second, we combine adversarial learning with discriminative feature learning to train the ADCNN model. The key of the ADCNN model is to learn the discriminative mapping of the target project to the source feature space by deceiving a domain discriminator. A domain discriminator tries to distinguish the target project files from the source project files. Finally, we use the extracted transferable semantic features to build a classifier for CPDP tasks. We evaluate our method on ten benchmark projects in terms of F-measure, AUC, and PofB20 (an effort-aware evaluation metric). The experimental results demonstrate that our ADCNN method performs better compared with other related CPDP methods.

Cross-project defect prediction (CPDP) is a practical solution that allows software defect prediction (SDP) to be used earlier in the software lifecycle. With the CPDP technique, the software defect predictor trained by labeled data of mature projects can be applied for the prediction task of a new project. Most previous CPDP approaches ignored the semantic information in the source code, and existing semantic-feature-based SDP methods do not take into account the data distribution divergence between projects. These limitations may weaken defect prediction performance. To solve these problems, we propose a novel approach, the transfer convolutional neural network (TCNN), to mine the transferable semantic (deep-learning (DL)-generated) features for CPDP tasks. Specifically, our approach first parses the source file into integer vectors as the network inputs. Next, to obtain the TCNN model, a matching layer is added into convolutional neural network where the hidden representations of the source and target project-specific data are embedded into a reproducing kernel Hilbert space for distribution matching. By simultaneously minimizing classification error and distribution divergence between projects, the constructed TCNN could extract the transferable DL-generated features. Finally, without losing the information contained in handcrafted features, we combine them with transferable DL-generated features to form the joint features for CPDP performing. Experiments based on 10 benchmark projects (with 90 pairs of CPDP tasks) showed that the proposed TCNN method is superior to the reference methods.

Machine learning (ML) is becoming increasingly important as a research tool due to its various frameworks and learning approaches. With the ever-increasing scale of software, reliability has become a crucial issue and software defect prediction is utilized to assist developers in finding potential defect and allocating their testing efforts. Traditional methods of software defect prediction mainly focus on designing static code metrics which are fed into ML classifiers to predict defects in the code. Even with the same ML techniques, many researchers apply statistical approaches to classify software modules and decide whether each module is defect prone or not and, accordingly, train their model. Deep neural network (DNN) and convolutional neural network (CNN) models built by the appropriate design decisions are crucial to obtain the desired classifier performance. This is especially significant when predicting fault proneness of software modules. When correctly identified, this could help in reducing the testing cost by directing the efforts more toward the modules identified to be fault prone. This paper proposed a N ovel CNN (NCNN) model to predict software defects. The framework used is Python Programming Language with Keras and TensorFlow. A comparative analysis with ML algorithms [such as Random Forest (RF), Decision Trees (DT), and Naïve Bayes (NB)] and DNN model in terms of F-measure (known as F1-score), recall, precision, and accuracy has been presented from four NASA system data sets (KC1, PC1, PC2, and KC3) selected from PROMISE repository. The experimental results indicated that NCNN model was comparable to the existing classifiers and outperformed them in most of the experiments.

Software defect prediction is an integral part of the software development process. Defect prediction helps focus on the grey areas beforehand, thus saving the considerable amount of money that is otherwise wasted in finding and fixing the faults once the software is already in production. One of the popular areas of defect prediction in recent years is Heterogeneous Defect Prediction, which predicts defects in a target project using a source project with different metrics. Through our paper, we provide a novel feature selection based approach, En-BPSO, based on binary particle swarm optimization, coupled with majority voting ensemble classifier based fitness function for heterogeneous defect prediction. The datasets we are using are MORPH and SOFTLAB. The results show that the En-BPSO method provides the highest Friedman mean rank amongst all the feature selection methods used for comparison. En-BPSO technique also helps us dynamically determine the optimal number of features to build an accurate heterogeneous defect prediction model.

Just-in-time defect prediction based on AST change embedding

Software defects and quality assurance are crucial aspects of software development that should be considered during the software development cycle. To ensure high-quality software, it is essential to have a robust quality assurance process in place. System reliability and quality are very key components that must be considered during software development, and this can only be achieved when software undergoes a thorough test process for errors, anomalies, defects, omissions, and bugs. Early software defect prediction and detection play an essential role in ensuring the reliability and quality of software systems, ensuring that software companies discover errors or defects early enough and allocate more resources to defect-prone modules. This study proposes the development of an enhanced classifier model for software defect prediction and detection. The aim is to harness the collective intelligence of selected base classifiers like Support Vector Machine, Logistic regression, Decision Trees, Random Forest, AdaBoost, Gradient Boosting, K-Nearest Neighbor, GaussianNB, and Multi-Layer Perception to improve accuracy, robustness, and generalization in identifying potential defects using a soft voting ensemble technique. The ensemble model leveraged the confidence probability of the soft voting technique and the generalization advantage of cross-validation leading to a more robust and dynamic model. The performance of the model with existing classifiers was evaluated using accuracy, F1 score, Precision, and area under the ROC curve (ROC- AUC) as the evaluation metrics. The results of the experiment revealed that the Proposed Classifier produced an overall Accuracy rate of 93%, and ROC AUC of 98%. The results demonstrate the effectiveness of our enhanced ensemble classifier in software defect detection and prediction. By harnessing the strengths of diverse base classifiers, our approach provides a robust and adaptive solution to the challenges of early detection and mitigating defects in software systems. This research contributes to the advancement of reliable software development practices and lays the foundation for future enhancements in ensemble-based defect detection methodologies.

Software defect prediction is an important part to ensure software quality and increase cost-efficiency. The core aspect prior to software defect prediction is software metrics. More research of process metrics existed and rapidly developed as the fact that process metrics can outperform code metrics. The development of process metrics is diverse aligning with various process metrics generated in the different publication using different dataset and granularity level, thus the development state of process metrics need to be further tracked. Recent research on software defect prediction using process metrics has been carried which complements or argues another studied related to the implementation of process metrics, dataset, and granularity level. This literature review has collected 17 literature studies that aim to depict the current research used of software defect prediction applying software process metrics, dataset, and granularity. Seven commonly used process metrics are identified such as NDC, NML, ADEV, EXP, LA, LD, and COMM. Process metrics development has been implemented in the previous research such as the application of aggregated process metrics and commits detailed information metrics. The selected research shows that 87% of research are using a public dataset while the rest are using a combined dataset. This result depicts the limited accessibility of private and industrial dataset for defect prediction. Following analysis of software granularity presents 4 levels of granularity used in selected research such as a functional, class, file, and features level. File-level defect predictions are mostly used for defect prediction in selected research and prove good defect prediction performance. The results of this literature review also identify the proposed studies which is software defect prediction using developed process metrics in the different datasets and features-level granularity to strengthen the previous research.

The occurrence of faults in software systems represents an inevitable predicament. Testing is the most common means to detect such faults; however, exhaustive testing is not feasible for any nontrivial system. Software fault prediction (SFP), which identifies software components that are more prone to errors, seeks to supplement the testing process. Thus, testing efforts can be focused on such modules. Various approaches exist for SFP, with machine learning (ML) emerging as the prevailing methodology. ML-based SFP relies on a wide range of metrics, ranging from file-level and class-level to method-level and even line-level metrics. More granularized metrics are expected to possess a higher degree of micro-level coverage of the code. The Halstead metric suite offers coverage at the line level and has been extensively employed across diverse domains such as fault prediction, quality assessment, and similarity approximation for the past three decades. In this article, we propose to decompose Halstead base metrics and evaluate their fault prediction capability. The Halstead base metrics consist of operators and operands. In the context of the Java language, we partition operators into five distinct categories, i.e., assignment operators, arithmetic operators, logical operators, relational operators, and all other types of operators. Similarly, operands are classified into two classes: constants and variables. For the purpose of empirical evaluation, two experiments were designed. In the first experiment, the Halstead base metrics were used along with McCabe, Lines of Code (LoC), and Halstead-derived metrics as predictors. In the second experiment, decomposed Halstead base metrics were used along with McCabe, LoC, and Halstead-derived metrics. Five public datasets were selected for the experiments. The ML classifiers used included logistic regression, naïve Bayes, decision tree, multilayer perceptron, random forest, and support vector machines. The ML classifiers’ effectiveness was assessed through metrics such as accuracy, F-measure, and AUC. Accuracy saw an enhancement from 0.82 to 0.97, while F-measure exhibited improvement from 0.81 to 0.99. Correspondingly, the AUC value advanced from 0.79 to 0.99. These findings highlight the superior performance of decomposed Halstead metrics, as opposed to the original Halstead base metrics, in predicting faults across all datasets.

Just-in-time software defect prediction (JIT-SDP) is an active topic in software defect prediction, which aims to identify defect-inducing changes. Recently, some studies have found that the variability of defect data sets can affect the performance of defect predictors. By using local models, it can help improve the performance of prediction models. However, previous studies have focused on module-level defect prediction. Whether local models are still valid in the context of JIT-SDP is an important issue. To this end, we compare the performance of local and global models through a large-scale empirical study based on six open-source projects with 227417 changes. The experiment considers three evaluation scenarios of cross-validation, cross-project-validation, and timewise-cross-validation. To build local models, the experiment uses the k-medoids to divide the training set into several homogeneous regions. In addition, logistic regression and effort-aware linear regression (EALR) are used to build classification models and effort-aware prediction models, respectively. The empirical results show that local models perform worse than global models in the classification performance. However, local models have significantly better effort-aware prediction performance than global models in the cross-validation and cross-project-validation scenarios. Particularly, when the number of clusters k is set to 2, local models can obtain optimal effort-aware prediction performance. Therefore, local models are promising for effort-aware JIT-SDP.