A Novel Approach of Software Fault Prediction Using Deep Learning Technique

Ghosh, Debolina; Singh, Jagannath

doi:10.1007/978-3-030-38006-9_5

Cited by 10 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zakari et al [26] reviewed existing research on Multiple fault localization (MFL) in software fault localization. Ghosh et al [27] used a framework based on deep learning which was able to calculate the suspicious score of each statement and rank accordingly.…”

Section: Literature Reviewmentioning

confidence: 99%

A Learning-Based Fault Localization Approach Using Subset of Likely and Dynamic Invariants

Shaikh¹,

Rizwan²,

Alghamdi³

et al. 2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Fault localization is one of the main tasks of software debugging. Developers spend a lot of time, cost, and effort to locate the faults correctly manually. For reducing this effort, many automatic fault localization techniques have been proposed, which inputs test suites and outputs a sorted list of faulty entities of the program. For further enhancement in this area, we developed a system called SILearning, which is based on invariant analysis. It learns from some existing fixed bugs to locate faulty methods in the program. It combines machine-learned ranking, program invariant differences, and spectrum-based fault localization (SBFL). Using the execution of test cases and code coverage analysis, it obtains each method's invariant differences and the suspiciousness value based on the program spectral location and uses them as features for ranking the faulty methods. The experimental analysis of SILearning has been performed on the dataset of real fault which is extracted from the database Defects4J. The tools used in this research are Daikon and cobertura for detection of the invariants and code coverage, respectively. The results show that SILearning performs better when combined features are utilized and can successfully locate the faulty methods on average for 76.1, 90.4, 108.2, 123, and 143.5 at the top positions of 1, 2, 3, 4, and 5.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Learning-Based Fault Localization Approach Using Subset of Likely and Dynamic Invariants

Shaikh¹,

Rizwan²,

Alghamdi³

et al. 2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

show abstract

“…1-There are others deep learning algorithms in the literature, therefore as future work, we plan to mitigate this threat further by addressing even more Deep learning algorithms and conduct a comprehensive comparisons. In spite of this threat, in this work we studied the most commonly used deep learning algorithms by past software engineering studies to evaluate the factors effectiveness in fault prediction [2], [18], [32], [35], [36], etc. Thus, we believe there is little threat to construct validity from this part side.…”

Section: Table 15 Effects Of Modification (Mlps)mentioning

confidence: 99%

The Influence of Deep Learning Algorithms Factors in Software Fault Prediction

2020

View full text Add to dashboard Cite

The discovery of software faults at early stages plays an important role in improving software quality; reduce the costs, time, and effort that should be spent on software development. Machine learning (ML) have been widely used in the software faults prediction (SFP), ML algorithms provide varying results in terms of predicting software fault. Deep learning achieves remarkable performance in various areas such as computer vision, natural language processing, speech recognition, and other fields. In this study, two deep learning algorithms are studied, Multi-layer perceptron's (MLPs) and Convolutional Neural Network (CNN) to address the factors that might have an influence on the performance of both algorithms. The experiment results show how modifying parameters is directly affecting the resulting improvement, these parameters are manipulated until the optimal number for each of them is reached. Moreover, the experiments show that the effect of modifying parameters had an important role in prediction performance, which reached a high rate in comparison with the traditional ML algorithm. To validate our assumptions, the experiments are conducted on four common NASA datasets. The result shows how the addressed factors might increase or decrease the fault detection rate measurement. The improvement rate was as follows up to 43.5% for PC1, 8% for KC1, 18% for KC2 and 76.5% for CM1.

show abstract

“…Table 5 enlists prominent contributors in the field of neural network implementation to solve various optimization problems. Ghosh and Singh 2020 [211] The above table presents a detail of the articles with the authors who have worked towards using neural network-based approaches to solve various problems such as classification problems, pattern recognition, association rules, missing data prediction, data normalization, and various optimization problems. This will enable the coming fellows who want to propose different techniques for solving complex problems of computer science as well as real-life problems.…”

Section: Neural Networkmentioning

confidence: 99%

An Exploratory Retrospective Assessment on the Usage of Bio-Inspired Computing Algorithms for Optimization

Dahiya¹

2020

IJETER

View full text Add to dashboard Cite

In the era of digitalization, every task is performed with the help of software-dependent applications. Therefore, the developed software is required to be robust, reliable, and fault free. Testing is performed to check the functioning of the developed software to evaluate whether the software product is error-free or not. Test cases play a vital role in the testing process. However, with the advancement of time, a particular test suite becomes so lengthy that the execution of all the test cases is not possible due to limited time and resources. Researchers have proposed diverse techniques to make the testing process an effective one. This study has worked towards finding the usage of bio-inspired computing algorithms used for optimization. The reason behind this is because these algorithms have performed exceptionally well in addressing complex problems to provide workable solutions in a reasonable time. It is observed that only a handful of these algorithms were applied in testing, such as ant colony optimization, bee colony optimization, neural networks, and genetic algorithms. Even progress is made in the limited area of these algorithms. This study was conducted with a motive to sort out the most popular bio-inspired algorithms and to explore their working principles, developments made till now, along with the scope of their application. This paper has discussed how the development of these algorithms has progressed from already explored algorithms to the development of many new ones such as cuckoo search, artificial bee colony, bat algorithm, firefly algorithm, flower pollination algorithm, and many more. This study will help the researchers to gain insight into choosing the algorithm and explore them in developing new techniques for optimization.

show abstract

A Novel Approach of Software Fault Prediction Using Deep Learning Technique

Cited by 10 publications

References 18 publications

A Learning-Based Fault Localization Approach Using Subset of Likely and Dynamic Invariants

A Learning-Based Fault Localization Approach Using Subset of Likely and Dynamic Invariants

The Influence of Deep Learning Algorithms Factors in Software Fault Prediction

An Exploratory Retrospective Assessment on the Usage of Bio-Inspired Computing Algorithms for Optimization

Contact Info

Product

Resources

About