Abstract

A novel hybrid classification approach that combines support vector machine (SVM) and ant colony optimization (ACO) (SVM-ACO) has been developed to enhance fault detection in object-oriented software systems. Object-oriented metrics are instrumental in identifying faults and errors, offering valuable insights into reusability and dynamic behavior of software systems. Given the complexities of application interactions and the dynamic nature of software development, our method integrates SVM's robust classification abilities with the optimization prowess of ACO. This integration optimizes feature selection and SVM parameter tuning through the probabilistic and heuristic-driven strategies of ACO. The implementation of the SVM-ACO algorithm proceeds in phases, beginning with feature selection via ACO, followed by training the SVM on these optimized features. This process iteratively refines the feature set and SVM parameters to heighten fault prediction accuracy. Our experimental results demonstrate that SVM-ACO significantly surpasses traditional SVM approaches in accuracy, particularly in early training epochs. This early success indicates effective initial learning and optimization of parameters, with performance becoming more consistent in later epochs. These outcomes affirm that SVM-ACO not only elevates fault detection capabilities but also boosts the model’s adaptability and efficiency in managing the complexities associated with object-oriented software metrics.

Keyword

Support vector machine, Ant colony optimization, Fault detection, Object-oriented software, Hybrid classification.

Cite this article

Khan A, Hashmi MA, Khan A, Hashmi MA.Enhancing fault detection in object-oriented software with hybrid SVM-ACO classification . ACCENTS Transactions on Information Security. 2024;9(35):9-14. DOI:10.19101/TIS.2024.935001

Refference

[1]Nikravesh N, Keyvanpour MR. Parameter tuning for software fault prediction with different variants of differential evolution. Expert Systems with Applications. 2024; 237:121251.

[2]Bhandari K, Kumar K, Sangal AL. Alleviating class imbalance issue in software fault prediction using DBSCAN-based induced graph under-sampling method. Arabian Journal for Science and Engineering. 2024:1-39.

[3]Brundha Elci J, Nandagopalan S. SS-WDRN: sparrow search optimization-based weighted dual recurrent network for software fault prediction. Knowledge and Information Systems. 2024; 66(2):1037-64.

[4]Kaliraj S, Kishoore AM, Sivakumar V. Software fault prediction using cross-project analysis: a study on class imbalance and model generalization. IEEE Access. 2024.

[5]Bhandari K, Kumar K, Sangal AL. DBOS_US: a density-based graph under-sampling method to handle class imbalance and class overlap issues in software fault prediction. The Journal of Supercomputing. 2024:1-44.

[6]Arasteh B, Golshan S, Shami S, Kiani F. Sahand: a software fault-prediction method using autoencoder neural network and k-means algorithm. Journal of Electronic Testing. 2024:1-5.

[7]Agrawalla B, Shukla AK, Tripathi D, Singh KK, Ramachandra Reddy B. Ensemble feature ranking approach for software fault prediction. Journal of Intelligent & Fuzzy Systems.(Preprint):1-4.

[8]Singh R, Kumar K. Software fault prediction in service-oriented based systems. In international conference on computing, power and communication technologies (IC2PCT) 2024 (pp. 1131-6). IEEE.

[9]Gou X, Zhang A, Wang C, Liu Y, Zhao X, Yang S. Software fault localization based on network spectrum and graph neural network. IEEE Transactions on Reliability. 2024.

[10]Sharma D, Chandra P. An empirical analysis of software fault proneness using factor analysis with regression. Multimedia Tools and Applications. 2024; 83(17):52535-91.

[11]Sreekala K, Sivajyothi M, Chiranjevi D, Sunitha G, Swetha M. A novel integration of hierarchical clustering and ensemble classification algorithms for news classification. In international conference on cognitive robotics and intelligent systems (ICC-ROBINS) 2024 (pp. 524-8). IEEE.

[12]Balaji T, Khanna V, Nalini T. A hybrid machine learning approach for document classification: a comparative study. In 2nd international conference on edge computing and applications (ICECAA) 2023 (pp. 1198-201). IEEE.

[13]Quazi S, Musa SM. Performing text classification and categorization through unsupervised learning. In 1st international conference on advanced engineering and technologies (ICONNIC) 2023 (pp. 1-6). IEEE.

[14]Dhir S, Rastogi N, Sinha A, Rani R, Goel N. News in vectors: optimizing news analysis through advanced embeddings and clustering. In 2nd international conference on advancement in computation & computer technologies (InCACCT) 2024 (pp. 40-5). IEEE.

[15]Zhu P, Lang Q, Liu X. Word embedding of dimensionality reduction for document clustering. In 35th chinese control and decision conference (CCDC) 2023 (pp. 4371-6). IEEE.

[16]Hui S. A novel 2-step very large-scale short text clustering algorithm. In 7th international conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud)(I-SMAC) 2023 (pp. 856-61). IEEE.

[17]Hasani MF, Heryadi Y, Arifin Y, Suparta W. Density based spatial clustering of applications with noise and sentence bert embedding for Indonesian utterance clustering. In international conference on computer science, information technology and engineering (ICCoSITE) 2023 (pp. 386-91). IEEE.

[18]Devassy BM, George S. Forensic document analysis using hyperspectral imaging and deep convolutional spectral clustering. In 13th workshop on hyperspectral imaging and signal processing: evolution in remote sensing (WHISPERS) 2023 (pp. 1-5). IEEE.

[19]Alla KR, Thangarasu G. Robust text clustering to cluster the text documents in a meta-heuristic optimization. In 13th symposium on computer applications & industrial electronics (ISCAIE) 2023 (pp. 181-5). IEEE.

[20]Dhanalakshmi S, Sathiyabama S, Ayyamuthukumar D. A novel text clustering approach based on bacterial colony optimization. In 7th international conference on electronics, communication and aerospace technology (ICECA) 2023 (pp. 1847-53). IEEE.