DSpace Arşivi :: by Yazar "Gharehchopogh, Farhad Soleimanian" değerine göre listeleniyor

Yazar "Gharehchopogh, Farhad Soleimanian" seçeneğine göre listele

Listeleniyor 1 - 15 / 15

A software defect prediction method using binary gray wolf optimizer and machine learning algorithms
(Pergamon-Elsevier Science, 2024) Wang, Hao; Arasteh, Bahman; Arasteh, Keyvan; Gharehchopogh, Farhad Soleimanian; Rouhi, Alireza
Context: Software defect prediction means finding defect-prone modules before the testing process which will reduce testing cost and time. Machine learning methods can provide valuable models for developers to classify software faulty modules. Problem: The inherent problem of the classification is the large volume of the training dataset's features, which reduces the accuracy and precision of the classification results. The selection of the effective features of the training dataset for classification is an NP-hard problem that can be solved using heuristic algorithms. Method: In this study, a binary version of the Gray Wolf optimizer (bGWO) was developed to select the most effective features of the training dataset. By selecting the most influential features in the classification, the precision and accuracy of the software module classifiers can be increased. Contribution: Developing a binary version of the gray wolf optimization algorithm to optimally select the effective features and creating an effective defect predictor are the main contributions of this study. To evaluate the effectiveness of the proposed method, five real-world and standard datasets have been used for the training and testing stages of the classifier. Results: The results indicate that among the 21 features of the train datasets, the basic complexity, sum of operators and operands, lines of codes, number of lines containing code and comments, and sum of operands have the greatest effect in predicting software defects. In this research, by combining the bGWO method and machine learning algorithms, accuracy, precision, recall, and F1 criteria have been considerably increased.
A survey of beluga whale optimization and its variants: Statistical analysis, advances, and structural reviewing
(Elsevier Ireland ltd, 2025) Lee, Sang-Woong; Haider, Amir; Rahmani, Amir Masoud; Arasteh, Bahman; Gharehchopogh, Farhad Soleimanian; Tang, Shengda; Liu, Zhe; Aurangzeb, Khursheed; Hosseinzadeh, Mehdi
Optimization, as a fundamental pillar in engineering, computer science, economics, and many other fields, plays a decisive role in improving the performance of systems and achieving desired goals. Optimization problems involve many variables, various constraints, and nonlinear objective functions. Among the challenges of complex optimization problems is the extensive search space with local optima that prevents reaching the global optimal solution. Therefore, intelligent and collective methods are needed to solve problems, such as searching for large problem spaces and identifying near-optimal solutions. Metaheuristic algorithms are a successful method for solving complex optimization problems. Usually, metaheuristic algorithms, inspired by natural and social phenomena, try to find optimal or near-optimal solutions by using random searches and intelligent explorations in the problem space. Beluga Whale Optimization (BWO) is one of the metaheuristic algorithms for solving optimization problems that has attracted the attention of researchers in recent years. The BWO algorithm tries to optimize the search space and achieve optimal solutions by simulating the collective behavior of whales. A study and review of published articles on the BWO algorithm show that this algorithm has been used in various fields, including optimization of mathematical functions, engineering problems, and even problems related to artificial intelligence. In this article, the BWO algorithm is classified according to four categories (combination, improvement, variants, and optimization). An analysis of 151 papers shows that the BWO algorithm has the highest percentage (49%) in the improvement field. The combination, variants, and optimization fields comprise 12%, 7%, and 32%, respectively.
Advances in Artificial Rabbits Optimization: A Comprehensive Review
(Springer Science and Business Media B.V., 2024) Anka, Ferzat; Ağaoğlu, Nazım; Nematzadeh, Sajjad; Torkamanian afshar, Mahsa; Gharehchopogh, Farhad Soleimanian
This study provides an in-depth review and analysis of the Artificial Rabbit Optimization (ARO) algorithm inspired by the survival strategies of rabbits. The ARO tries to find the global solution in the search space according to the rabbits’ detour foraging strategy and searches locally according to their random hiding structure. This algorithm has various advantages such as a simple structure, fast running model, easy adaptation feature, few parameters, independent mechanism in exploration and exploitation phases, transitions between phases with a specific mechanism, reasonable convergence rate, and property of escaping local optima. Therefore, it has been preferred by many researchers to solve various complex optimization problems. ARO-based studies have been published at prestigious international publishers such as Elsevier, Springer, MDPI, and IEEE since its launch in July 2022. The rates of studies in these publishers are 34%, 19%, 18%, and 15%, respectively. The remaining 14% includes papers published by other publishers. Besides, the cited studies on this algorithm are examined in four categories: Improved, hybrid, variants, and adapted. Research trends demonstrate that 27%, 31%, 9%, and 33% of ARO-based studies fall into these categories. © The Author(s) under exclusive licence to International Center for Numerical Methods in Engineering (CIMNE) 2024.
Advances in Manta Ray Foraging Optimization: A Comprehensive Survey
(Springer Singapore Pte Ltd, 2024) Gharehchopogh, Farhad Soleimanian; Ghafouri, Shafi; Namazi, Mohammad; Arasteh, Bahman
This paper comprehensively analyzes the Manta Ray Foraging Optimization (MRFO) algorithm and its integration into diverse academic fields. Introduced in 2020, the MRFO stands as a novel metaheuristic algorithm, drawing inspiration from manta rays' unique foraging behaviors-specifically cyclone, chain, and somersault foraging. These biologically inspired strategies allow for effective solutions to intricate physical challenges. With its potent exploitation and exploration capabilities, MRFO has emerged as a promising solution for complex optimization problems. Its utility and benefits have found traction in numerous academic sectors. Since its inception in 2020, a plethora of MRFO-based research has been featured in esteemed international journals such as IEEE, Wiley, Elsevier, Springer, MDPI, Hindawi, and Taylor & Francis, as well as at international conference proceedings. This paper consolidates the available literature on MRFO applications, covering various adaptations like hybridized, improved, and other MRFO variants, alongside optimization challenges. Research trends indicate that 12%, 31%, 8%, and 49% of MRFO studies are distributed across these four categories respectively.
An advanced deep reinforcement learning algorithm for three-layer D2D-edge-cloud computing architecture for efficient task offloading in the Internet of things
(Elsevier, 2024) Moghaddasi, Komeil; Rajabi, Shakiba; Gharehchopogh, Farhad Soleimanian; Ghaffari, Ali
The Internet of Things (IoTs) has transformed the digital landscape by interconnecting billions of devices worldwide, paving the way for smart cities, homes, and industries. With the exponential growth of IoT devices and the vast amount of data they generate, concerns have arisen regarding efficient task-offloading strategies. Traditional cloud and edge computing methods, paired with basic Machine Learning (ML) algorithms, face several challenges in this regard. In this paper, we propose a novel approach to task offloading in a Device-toDevice (D2D)-Edge-Cloud computing using the Rainbow Deep Q-Network (DQN), an advanced Deep Reinforcement Learning (DRL) algorithm. This algorithm utilizes advanced neural networks to optimize task offloading in the three-tier framework. It balances the trade-offs among D2D, Device-to-Edge (D2E), and Device/ Edge-to-Cloud (D2C/E2C) communications, benefiting both end users and servers. These networks leverage Deep Learning (DL) to discern patterns, evaluate potential offloading decisions, and adapt in real time to dynamic environments. We compared our proposed algorithm against other state -of -the -art methods. Through rigorous simulations, we achieved remarkable improvements across key metrics: an increase in energy efficiency by 29.8%, a 27.5% reduction in latency, and a 43.1% surge in utility.
An advanced deep reinforcement learning algorithm for three-layer D2D-edge-cloud computing architecture for efficient task offloading in the ınternet of thıngs
(Elsevier Inc., 2024) Moghaddasi, Komeil; Rajabi, Shakiba; Gharehchopogh, Farhad Soleimanian; Ghaffari, Ali
The Internet of Things (IoTs) has transformed the digital landscape by interconnecting billions of devices worldwide, paving the way for smart cities, homes, and industries. With the exponential growth of IoT devices and the vast amount of data they generate, concerns have arisen regarding efficient task-offloading strategies. Traditional cloud and edge computing methods, paired with basic Machine Learning (ML) algorithms, face several challenges in this regard. In this paper, we propose a novel approach to task offloading in a Device-to-Device (D2D)-Edge-Cloud computing using the Rainbow Deep Q-Network (DQN), an advanced Deep Reinforcement Learning (DRL) algorithm. This algorithm utilizes advanced neural networks to optimize task offloading in the three-tier framework. It balances the trade-offs among D2D, Device-to-Edge (D2E), and Device/Edge-to-Cloud (D2C/E2C) communications, benefiting both end users and servers. These networks leverage Deep Learning (DL) to discern patterns, evaluate potential offloading decisions, and adapt in real time to dynamic environments. We compared our proposed algorithm against other state-of-the-art methods. Through rigorous simulations, we achieved remarkable improvements across key metrics: an increase in energy efficiency by 29.8%, a 27.5% reduction in latency, and a 43.1% surge in utility. © 2024
An intrusion detection system on the internet of things using deep learning and multi-objective enhanced gorilla troops optimizer
(Springer, 2024) Asgharzadeh, Hossein; Ghaffari, Ali; Masdari, Mohammad; Gharehchopogh, Farhad Soleimanian
In recent years, developed Intrusion Detection Systems (IDSs) perform a vital function in improving security and anomaly detection. The effectiveness of deep learning-based methods has been proven in extracting better features and more accurate classification than other methods. In this paper, a feature extraction with convolutional neural network on Internet of Things (IoT) called FECNNIoT is designed and implemented to better detect anomalies on the IoT. Also, a binary multi-objective enhance of the Gorilla troops optimizer called BMEGTO is developed for effective feature selection. Finally, the combination of FECNNIoT and BMEGTO and KNN algorithm-based classification technique has led to the presentation of a hybrid method called CNN-BMEGTO-KNN. In the next step, the proposed model is implemented on two benchmark data sets, NSL-KDD and TON-IoT and tested regarding the accuracy, precision, recall, and F1-score criteria. The proposed CNN-BMEGTO-KNN model has reached 99.99% and 99.86% accuracy on TON-IoT and NSL-KDD datasets, respectively. In addition, the proposed BMEGTO method can identify about 27% and 25% of the effective features of the NSL-KDD and TON-IoT datasets, respectively.
Generating the structural graph-based model from a program source-code using chaotic forrest optimization algorithm
(Wiley, 2023) Arasteh, Bahman; Ghanbarzadeh, Reza; Gharehchopogh, Farhad Soleimanian; Hosseinalipour, Ali
One of the most important and costly stages in software development is maintenance. Understanding the structure of software will make it easier to maintain it more efficiently. Clustering software modules is thought to be an effective reverse engineering technique for deriving structural models of software from source code. In software module clustering, the most essential objectives are to minimize connections between produced clusters, maximize internal connections within created clusters, and maximize clustering quality. Finding the appropriate software system clustering model is considered an NP-complete task. The previously proposed approaches' key limitations are their low success rate, low stability, and poor modularization quality. In this paper, for optimal clustering of software modules, Chaotic based heuristic method using a forest optimization algorithm is proposed. The impact of chaos theory on the performance of the other SFLA-GA and PSO-GA has also been investigated. The results show that using the logistic chaos approach improves the performance of these methods in the software-module clustering problem. The performance of chaotic based FOA, SFLA-GA and PSO-GA is superior to the other heuristic methods in terms of modularization quality and stability of the results.
An improved farmland fertility algorithm with hyper-heuristic approach for solving travelling salesman problem
(TECH SCIENCE PRESS, 2022) Gharehchopogh, Farhad Soleimanian; Abdollahzadeh, Benyamin; Arasteh, Bahman
ravelling Salesman Problem (TSP) is a discrete hybrid optimization problem considered NP-hard. TSP aims to discover the shortest Hamilton route that visits each city precisely once and then returns to the starting point, making it the shortest route feasible. This paper employed a Farmland Fertility Algorithm (FFA) inspired by agricultural land fertility and a hyper-heuristic technique based on the Modified Choice Function (MCF). The neighborhood search operator can use this strategy to automatically select the best heuristic method for making the best decision. Lin-Kernighan (LK) local search has been incorporated to increase the efficiency and performance of this suggested approach. 71 TSPLIB datasets have been compared with different algorithms to prove the proposed algorithm's performance and efficiency. Simulation results indicated that the proposed algorithm outperforms comparable methods of average mean computation time, average percentage deviation (PDav), and tour length.
A metaheuristic approach based on coronavirus herd immunity optimiser for breast cancer diagnosis
(Springer, 2024) Hosseinalipour, Ali; Ghanbarzadeh, Reza; Arasteh, Bahman; Gharehchopogh, Farhad Soleimanian; Mirjalili, Seyedali
As one of the important concepts in epidemiology, herd immunity was recommended to control the COVID-19 pandemic. Inspired by this technique, the Coronavirus Herd Immunity Optimiser has recently been introduced, demonstrating promising results in addressing optimisation problems. This particular algorithm has been utilised to address optimisation problems widely; However, there is room for enhancement in its performance by making modifications to its parameters. This paper aims to improve the Coronavirus Herd Immunity Optimisation algorithm to employ it in addressing breast cancer diagnosis problem through feature selection. For this purpose, the algorithm was discretised after the improvements were made. The Opposition-Based Learning approach was applied to balance the exploration and exploitation stages to enhance performance. The resulting algorithm was employed in the diagnosis of breast cancer, and its performance was evaluated on ten benchmark functions. According to the simulation results, it demonstrates superior performance in comparison with other well-known approaches of the similar nature. The results demonstrate that the new approach performs well in diagnosing breast cancer with high accuracy and less computational complexity and can address a variety of real-world optimisation problems.
A Modified Horse Herd Optimization Algorithm and Its Application in the Program Source Code Clustering
(Wiley-Hindawi, 2023) Arasteh, Bahman; Gunes, Peri; Bouyer, Asgarali; Gharehchopogh, Farhad Soleimanian; Banaei, Hamed Alipour; Ghanbarzadeh, Reza
Maintenance is one of the costliest phases in the software development process. If architectural design models are accessible, software maintenance can be made more straightforward. When the software's source code is the only available resource, comprehending the program profoundly impacts the costs associated with software maintenance. The primary objective of comprehending the source code is extracting information used during the software maintenance phase. Generating a structural model based on the program source code is an effective way of reducing overall software maintenance costs. Software module clustering is considered a tremendous reverse engineering technique for constructing structural design models from the program source code. The main objectives of clustering modules are to reduce the quantity of connections between clusters, increase connections within clusters, and improve the quality of clustering. Finding the perfect clustering model is considered an NP-complete problem, and many previous approaches had significant issues in addressing this problem, such as low success rates, instability, and poor modularization quality. This paper applied the horse herd optimization algorithm, a distinctive population-based and discrete metaheuristic technique, in clustering software modules. The proposed method's effectiveness in addressing the module clustering problem was examined by ten real-world standard software test benchmarks. Based on the experimental data, the quality of the clustered models produced is approximately 3.219, with a standard deviation of 0.0718 across the ten benchmarks. The proposed method surpasses former methods in convergence, modularization quality, and result stability. Furthermore, the experimental results demonstrate the versatility of this approach in effectively addressing various real-world discrete optimization challenges.
A multi-objective mutation-based dynamic Harris Hawks optimization for botnet detection in IoT
(Elsevier, 2023) Gharehchopogh, Farhad Soleimanian; Abdollahzadeh, Benyamin; Barshandeh, Saeid; Arasteh, Bahman
The increasing trend toward using the Internet of Things (IoT) increased the number of intrusions and intruders annually. Hence, the integration, confidentiality, and access to digital resources would be threatened continually. The significance of security implementation in digital platforms and the need to design defensive systems to discover different intrusions made the researchers study updated and effective methods, such as Botnet Detection for IoT systems. Many problem space features and network behavior unpredictability made the Intrusion Detection System (IDS) the main problem in maintaining computer networks' security. Furthermore, many insignificant features have turned the feature selection (FS) problem into a vast IDS aspect. This paper introduces a novel binary multi-objective dynamic Harris Hawks Optimization (HHO) enhanced with mutation operator (MODHHO) and applies it to Botnet Detection in IoT. Afterward, the Feature Selection (FS) is undertaken, and the K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Multilayer Perceptron (MLP), and Decision Tree (DT) classifiers are used to estimate the potential of the selected features in the precise detection of intrusions. The simulation results illustrated that the MODHHO algorithm performs well in Botnet Detection in IoT and is preferred to other approaches in its performance metrics. Besides, the computational complexity analysis results suggest that the MODHHO algorithm's overhead is more optimal than similar approaches. The MODHHO algorithm has performed better in comparison with other compared algorithms in all 5 data sets. In contrast with the machine learning methods of the proposed model in all five data sets, it has had a better error rate according to the AUC, G-mean, and TPR criteria. And according to the comparison made with filter-based methods, it has performed almost better in three datasets.
A Novel Metaheuristic Based Method for Software Mutation Test Using the Discretized and Modified Forrest Optimization Algorithm
(Springer, 2023) Arasteh, Bahman; Gharehchopogh, Farhad Soleimanian; Gunes, Peri; Kiani, Farzad; Torkamanian-Afshar, Mahsa
The number of detected bugs by software test data determines the efficacy of the test data. One of the most important topics in software engineering is software mutation testing, which is used to evaluate the efficiency of software test methods. The syntactical modifications are made to the program source code to make buggy (mutated) programs, and then the resulting mutants (buggy programs) along with the original programs are executed with the test data. Mutation testing has several drawbacks, one of which is its high computational cost. Higher execution time of mutation tests is a challenging problem in the software engineering field. The major goal of this work is to reduce the time and cost of mutation testing. Mutants are inserted in each instruction of a program using typical mutation procedures and tools. Meanwhile, in a real-world program, the likelihood of a bug occurrence in the simple and non-bug-prone sections of a program is quite low. According to the 80-20 rule, 80 percent of a program's bugs are discovered in 20% of its fault-prone code. The first stage of the suggested solution uses a discretized and modified version of the Forrest optimization algorithm to identify the program's most bug-prone paths; the second stage injects mutants just in the identified bug-prone instructions and data. In the second step, the mutation operators are only injected into the identified instructions and data that are bug-prone. Studies on standard benchmark programs have shown that the proposed method reduces about 27.63% of the created mutants when compared to existing techniques. If the number of produced mutants is decreased, the cost of mutation testing will also decrease. The proposed method is independent of the platform and testing tool. The results of the experiments confirm that the use of the proposed method in each testing tool such as Mujava, Muclipse, Jester, and Jumble makes a considerable mutant reduction.
Slime mould algorithm: a comprehensive survey of ıts variants and applications
(SPRINGER, 2023) Gharehchopogh, Farhad Soleimanian; Ucan, Alaettin; Ibrikci, Turgay; Arasteh, Bahman; Isik, Gultekin
Meta-heuristic algorithms have a high position among academic researchers in various fields, such as science and engineering, in solving optimization problems. These algorithms can provide the most optimal solutions for optimization problems. This paper investigates a new meta-heuristic algorithm called Slime Mould algorithm (SMA) from different optimization aspects. The SMA algorithm was invented due to the fluctuating behavior of slime mold in nature. It has several new features with a unique mathematical model that uses adaptive weights to simulate the biological wave. It provides an optimal pathway for connecting food with high exploration and exploitation ability. As of 2020, many types of research based on SMA have been published in various scientific databases, including IEEE, Elsevier, Springer, Wiley, Tandfonline, MDPI, etc. In this paper, based on SMA, four areas of hybridization, progress, changes, and optimization are covered. The rate of using SMA in the mentioned areas is 15, 36, 7, and 42%, respectively. According to the findings, it can be claimed that SMA has been repeatedly used in solving optimization problems. As a result, it is anticipated that this paper will be beneficial for engineers, professionals, and academic scientists.
A source-code aware method for software mutation testing using artificial bee colony algorithm
(SPRINGER, 2022) Arasteh, Bahman; Imanzadeh, Parisa; Arasteh, Keyvan; Gharehchopogh, Farhad Soleimanian; Zarei, Bagher
The effectiveness of software test data relates to the number of found faults by the test data. Software mutation test is used to evaluate the effectiveness of the software test methods and is one of the challenging fields of software engineering. In order to evaluate the capability of test data in finding the program faults, some syntactical changes are made in the program source code to cause faulty program; then, the generated mutants (faulty programs) and original program are executing with the corresponding test data. One of the main drawbacks of mutation testing is its computational cost. Indeed, high execution time of mutation testing is a challenging research problem. Reducing the time and cost of mutation test is the main objective of this paper. In the traditional mutation methods and tools the mutants are injected randomly in each instructions of a program. Meanwhile, in the real-world program, the probability of fault occurrences in the simple locations (instructions and data) of a program is negligible. With respect to the 80-20 rule, 80% of the faults are found in 20% of the fault-prone code of a program. In the first stage of the proposed method, Artificial Bee Colony optimization algorithm is used to identifying the most fault prone paths of a program; in the next stage, the mutation operators (faults) are injected only on the identified fault-prone instructions and data. Regarding the results of conducted experiments on the standard benchmark programs, Compared to existing methods, the proposed method reduces 28.10% of the generated mutants. Reducing the number of generated mutants will reduce the cost of mutation testing. The traditional mutation testing tools (Mujava, Muclipse, Jester, Jumble) can perform the mutation testing with a lower cost using the method presented in this study.

Yazar "Gharehchopogh, Farhad Soleimanian" seçeneğine göre listele

Sayfa Başına Sonuç

Sıralama seçenekleri