Yazar "Arasteh, B." seçeneğine göre listele
Listeleniyor 1 - 5 / 5
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A Cost-effective and Machine-learning-based method to identify and cluster redundant mutants in software mutation testing(Springer, 2024) Arasteh, B.; Ghaffari, A.The quality of software test data is assessed through mutation testing. This technique involves introducing various modifications (mutants) to the original code of the program. The test data’s effectiveness, known as the test score, is quantified by the proportion of mutants that are successfully detected. A prominent issue within software mutation testing is the generation of an excessive quantity of mutants in programs. The primary objectives of this research are to diminish the total count of mutants by consolidating those that are duplicative, to decrease the overall mutation testing time by lessening the quantity of mutants produced, and to lower the expenses associated with mutation testing. This research introduces a machine learning-based strategy to recognise and eliminate redundant mutants. Building a machine learning-based classifier to classify the instructions according to the rate of error propagation is the first contribution of this study. Next, the remaining instructions of the source code are analyzed by the designed parser to generate single-line mutants. Unlike traditional approaches, mutants are not generated as distinct full-fledged programs. Instead, mutants consisting of a single line are selectively run using a developed instruction evaluator. Following this, a clustering technique is employed to categorise single-line mutants yielding identical outcomes into groups, where only one complete execution is needed per group. Testing on Java benchmarks with the new method has shown a decrease in the mutant count by 56.33% and a time reduction of 56.71% when compared with parallel tests using the MuJava and MuClipse tools. Despite the marked decrease in both mutant count and testing time, the mutation score remained consistent. Comparable outcomes were also observed with other mutation testing tools such as Pitest, Jester, Jumble, and JavaLancer. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.Öğe A new binary chaos-based metaheuristic algorithm for software defect prediction(Springer, 2024) Arasteh, B.; Arasteh, K.; Ghaffari, A.; Ghanbarzadeh, R.Software defect prediction is a critical challenge within software engineering aimed at enhancing software quality by proactively identifying potential defects. This approach involves selecting defect-prone modules ahead of the testing phase, thereby reducing testing time and costs. Machine learning methods provide developers with valuable models for categorising faulty software modules. However, the challenge arises from the numerous elements present in the training dataset, which frequently reduce the accuracy and precision of classification. Addressing this, selecting effective features for classification from the dataset becomes an NP-hard problem, often tackled using metaheuristic algorithms. This study introduces a novel approach, the Binary Chaos-based Olympiad Optimisation Algorithm, specifically designed to select the most impactful features from the training dataset. By selecting these influential features for classification, the precision and accuracy of software module classifiers can be notably improved. The study's primary contributions involve devising a binary variant of the chaos-based Olympiad optimisation algorithm to meticulously select effective features and construct an efficient classification model for identifying faulty software modules. Five real-world and standard datasets were utilised across both the training and testing phases of the classifier to evaluate the proposed method's effectiveness. The findings highlight that among the 21 features within the training datasets, specific metrics such as basic complexity, the sum of operators and operands, lines of code, quantity of lines containing code and comments, and the sum of operands have the most significant influence on software defect prediction. This research underscores the combined effectiveness of the proposed method and machine learning algorithms, significantly boosting accuracy (91.13%), precision (92.74%), recall (97.61%), and F1 score (94.26%) in software defect prediction. © The Author(s) 2024.Öğe A new hybrid whale optimization algorithm and golden jackal optimization for data clustering(Elsevier, 2023) Gharehchopogh, F.S.; Mirjalili, S.; Işık, G.; Arasteh, B.Data clustering is an unsupervised learning method essential in many different sciences. The main goal of clustering is to find the similarity between samples of a data set to form optimal clusters. The K-Means algorithm is one of the most basic models for data clustering. It strongly depends on the initial search points and leads to local solutions. This book chapter proposes a hybrid model based on Whale Optimization Algorithm (WOA) and Golden Jackal Optimization (GJO) algorithm for the data clustering problem. The GJO algorithm is inspired by the hunting behavior of golden jackals and maintains a good balance between exploration and exploitation. Therefore, the GJO algorithm aims to improve WOA solutions and avoid local optimality. In the proposed model, WOA and GJO mechanisms are used to discover the centers of clusters. The evaluation is performed on eight known datasets from the UCI site. According to the findings, the proposed model performs better than traditional clustering methods in terms of accuracy and eliminates mistakes in the vast majority of the datasets. © 2024 Elsevier Inc. All rights reserved.Öğe Securing internet of things using machine and deep learning methods: a survey(Springer, 2024) Ghaffari, A.; Jelodari, N.; pouralish, S.; derakhshanfard, N.; Arasteh, B.The Internet of Things (IoT) is a vast network of devices with sensors or actuators connected through wired or wireless networks. It has a transformative effect on integrating technology into people’s daily lives. IoT covers essential areas such as smart cities, smart homes, and health-based industries. However, security and privacy challenges arise with the rapid growth of IoT devices and applications. Vulnerabilities such as node spoofing, unauthorized access to data, and cyberattacks such as denial of service (DoS), eavesdropping, and intrusion detection have emerged as significant concerns. Recently, machine learning (ML) and deep learning (DL) methods have significantly progressed and are robust solutions to address these security issues in IoT devices. This paper comprehensively reviews IoT security research focusing on ML/DL approaches. It also categorizes recent studies on security issues based on ML/DL solutions and highlights their opportunities, advantages, and limitations. These insights provide potential directions for future research challenges. © The Author(s) 2024.Öğe A self-predictive diagnosis system of liver failure based on multilayer neural networks(Springer, 2024) Dashti, F.; Ghaffari, A.; Seyfollahi, A.; Arasteh, B.The lack of symptoms in the early stages of liver disease may cause wrong diagnosis of the disease by many doctors and endanger the health of patients. Therefore, earlier and more accurate diagnosis of liver problems is necessary for proper treatment and prevention of serious damage to this vital organ. We attempted to develop an intelligent system to detect liver failure using data mining and artificial neural networks (ANN), this approach considers all factors impacting patient identification and enhances the probability of success in diagnosing liver failure. We employ multilayer perceptron neural networks for diagnosing liver failure via a liver patient dataset (ILDP). The proposed approach using the backpropagation algorithm, improves the diagnosis rate, and predicts liver failure intelligently. The simulation and data analysis outputs revealed that the proposed method has 99.5% accuracy, 99.65% sensitivity, and 99.57% specificity, making it more accurate than Previous related methods. © The Author(s) 2024.
