Article
Computer Science, Artificial Intelligence
Jiao Hu, Ali Asghar Heidari, Lejun Zhang, Xiao Xue, Wenyong Gui, Huiling Chen, Zhifang Pan
Summary: SCGWO is a variant of GWO that combines an improved spread strategy and a chaotic local search mechanism to overcome performance limitations. Experimental results show significant advantages in processing function optimization and feature selection tasks.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Jiao Hu, Huiling Chen, Ali Asghar Heidari, Mingjing Wang, Xiaoqin Zhang, Ying Chen, Zhifang Pan
Summary: This research introduces an enhanced variant of the GWO algorithm named GWOCMALOL, which outperforms other algorithms in terms of convergence speed and accuracy, showing better performance in solving complex problems.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Xiaobing Yu, WangYing Xu, Xuejing Wu, Xueming Wang
Summary: The Grey Wolf Optimizer (GWO) has been criticized for easily getting stuck in solving complex and multimodal problems, leading to the development of the Reinforced Exploitation and Exploration GWO (REEGWO) algorithm. REEGWO improves upon GWO by assigning different weights to the top three wolves based on their knowledge about the location of the prey, and using a random search based on tournament selection to balance exploration and exploitation, demonstrating competitive results compared to other heuristic algorithms.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Xiaobo Li, Qiyong Fu, Qi Li, Weiping Ding, Feilong Lin, Zhonglong Zheng
Summary: Feature selection is a multi-objective problem that aims to choose a subset of features with minimal feature-feature correlation and maximum feature-class correlation. Grey wolf optimization mimics the hunting mechanism of grey wolves but can face local optimization in multi-objective problems. To address this, a novel multi-objective binary grey wolf optimization algorithm called MOBGWO-GMS is proposed, which utilizes a guided mutation strategy (GMS). Experimental results show that the proposed approach outperforms other algorithms in terms of the optimal trade-off between fitness evaluation criteria and the ability to escape local optima.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Shitu Singh, Jagdish Chand Bansal
Summary: This paper proposes a new variant of the Grey wolf optimizer (GWO) called Mutation-driven Modified Grey wolf optimizer (MDM-GWO), which improves the performance of the conventional GWO by introducing a new search mechanism, modified control parameter, mutation-driven scheme, and greedy approach of selection. The proposed MDM-GWO is evaluated on standard benchmark problems and real-world engineering design problems, and the results show its superiority over other algorithms.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Pradip Dhal, Chandrashekhar Azad
Summary: In this study, a binary version of the hybrid two-phase multi-objective FS approach based on PSO and GWO is proposed. The approach aims to minimize classification error rate and reduce the number of selected features. By utilizing global and local search strategies, the method shows efficient and effective performance in selecting prominent features in high-dimensional data.
APPLIED SOFT COMPUTING
(2021)
Article
Business
R. Rajakumar, Kaushik Sekaran, Ching-Hsien Hsu, Seifedine Kadry
Summary: This paper introduces a novel SI algorithm, Accelerated Gray Wolf Optimization (AGWO), which incorporates the enhanced hierarchy into GWO technique. The algorithm strengthens the local and global search process by introducing a mathematical model and proposes a diversity measure to eradicate the local confinement while maintaining a perfect balance between intensification and diversification process. The proposed methodology also includes a parameter tuned strategy to speed up the convergence rate and is tested on various benchmark problems, showing better performance compared to other algorithms.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2021)
Article
Computer Science, Artificial Intelligence
Dorin Moldovan, Adam Slowik
Summary: This study applied a multi-objective binary grey wolf optimization method to predict the energy consumption of household appliances, aiming to maximize the algorithms' prediction performance and minimize the number of selected features. The method was tested on the UCI Machine Learning Repository dataset and compared with similar methods, showing good predictive accuracy.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Mohammad H. Nadimi-Shahraki, Shokooh Taghian, Seyedali Mirjalili
Summary: An Improved Grey Wolf Optimizer (I-GWO) is proposed in this article to tackle global optimization and engineering design problems by introducing a dimension learning-based hunting (DLH) search strategy. The IGWO algorithm addresses the lack of population diversity, imbalance between exploitation and exploration, and premature convergence seen in the GWO algorithm. Experimental results show that I-GWO is competitive against six other state-of-the-art metaheuristics, demonstrating its efficiency and applicability in engineering design problems.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Mohammed Qaraad, Souad Amjad, Nazar K. Hussein, Mostafa A. Elhosseini
Summary: This paper proposes a novel hybrid meta-heuristic algorithm called SSA-FGWO based on the Salp swarm algorithm (SSA) and the Grey Wolf Algorithm (GWO). The experimental results show that SSA-FGWO significantly improves the convergence speed, precision, and global optimization capability compared to the basic SSA, GWO, and other algorithms.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Qingsong Fan, Haisong Huang, Yiting Li, Zhenggong Han, Yao Hu, Dong Huang
Summary: This paper introduces a grey wolf optimization method based on a beetle antenna strategy (BGWO) to enhance global search ability by providing the leader wolf with a sense of hearing. A nonlinear dynamic control parameter update strategy is proposed to balance exploration and exploitation. Experimental results demonstrate that BGWO outperforms many state-of-the-art algorithms in terms of solution accuracy, convergence rate, and stability.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Mathematics, Applied
N. Pazhaniraja, Shakila Basheer, Kalaipriyan Thirugnanasambandam, Rajakumar Ramalingam, Mamoon Rashid, J. Kalaivani
Summary: In itemset mining, the important goals are frequency and utility, which are addressed as a multi-objective issue. Researchers have focused on achieving both goals without compromising solution quality. This work proposes an effective method, using a modified bio-inspired algorithm, for high-frequency and high-utility itemset mining in a transaction database. The algorithm, called the multi-objective Boolean grey wolf optimization based decomposition algorithm, is compared with existing models and shows significant impact.
Article
Computer Science, Artificial Intelligence
Qusay M. Alzubi, Mohammed Anbar, Yousef Sanjalawe, Mohammed Azmi Al-Betar, Rosni Abdullah
Summary: The proposed hybrid optimization approach outperforms existing solutions in terms of detection accuracy, detection rate, false alarm rate reduction, feature reduction, and processing time.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Automation & Control Systems
Gilberto Rivera, Raul Porras, J. Patricia Sanchez-Solis, Rogelio Florencia, Vicente Garcia
Summary: This paper introduces a novel metaheuristic called Outranking-based Particle Swarm Optimization (O-PSO) for addressing the multi-objective Unrelated Parallel Machine Scheduling Problem. O-PSO is an optimization algorithm that combines particle swarm optimization with the preferences of the Decision Maker (DM) expressed in a fuzzy relational system based on ELECTRE III. Unlike other multi-objective metaheuristics, O-PSO focuses on finding the Region of Interest (RoI) instead of approximating a sample of the complete Pareto frontier. The efficiency of O-PSO is validated through experiments on synthetic instances and a real-world case study, showing its capability of generating high-quality solutions and supporting multicriteria decision analysis.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Xiaoqing Zhang, Yuye Zhang, Zhengfeng Ming
Summary: The dynamic grey wolf optimizers improve the iterative convergence rate by eliminating the waiting period for updating the search wolf's position. Research shows that, for the same improved algorithm, the performance of the dynamic GWO-based algorithm is generally better than that of the static GWO-based algorithm.
FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING
(2021)
Article
Chemistry, Multidisciplinary
Mohammad Adnan Aladaileh, Mohammed Anbar, Ahmed J. Hintaw, Iznan H. Hasbullah, Abdullah Ahmed Bahashwan, Taief Alaa Al-Amiedy, Dyala R. Ibrahim
Summary: Software-defined networking (SDN) is a network architecture that separates the control plane from the data plane, providing programmable features for efficient network management. However, SDN is vulnerable to DDoS attacks, which can degrade or even collapse the network. Entropy-based approaches are considered effective for detecting DDoS attacks on SDN controllers.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Mohammad Shahrul Mohd Shah, Yu-Beng Leau, Mohammed Anbar, Ali Abdulqader Bin-Salem
Summary: The concept of Information-Centric Networking (ICN) focuses on content exchanged rather than connected devices. ICN architectures such as Content Centric Network (CCN) and Named Data Networking (NDN) aim to shift from host-centric to content-centric communication and address challenges in traditional IP networks. They differ from host-centric IP networking in naming, routing, forwarding, and caching. NDN uses unique global names provided by content-based security and encryption to ensure content integrity and authenticity. This paper surveys the security aspects of NDN/CCN, discussing integrity attacks and providing countermeasures, as well as highlighting an open challenge and future research directions in security.
Article
Engineering, Chemical
Israa M. M. Hayder, Taief Alaa Al-Amiedy, Wad Ghaban, Faisal Saeed, Maged Nasser, Ghazwan Abdulnabi Al-Ali, Hussain A. A. Younis
Summary: Flood disasters are a global natural occurrence that cause numerous casualties. Developing an accurate flood forecasting model is crucial to minimize damages and reduce the number of victims. Rain forecasting benefits water resource allocation, management, planning, flood warning and forecasting, and flood damage mitigation. This study aims to build a forecasting model based on the ES-LSTM structure and RNNs for predicting hourly precipitation seasons, as well as classify precipitation using the ANN model and DT algorithm. The findings demonstrate the effectiveness of the proposed model, with ES-LSTM and RNN achieving MAPE of 3.17 and 6.42, respectively, and ANN and DT models achieving prediction accuracy rates of 96.65% and 84.0%, respectively. ES-LSTM and ANN outperformed other models.
Article
Chemistry, Analytical
Basim Ahmad Alabsi, Mohammed Anbar, Shaza Dawood Ahmed Rihan
Summary: The increasing use of IoT devices has led to a rise in DDoS and DoS attacks. This paper proposes an IDS based on CTGAN for detecting these attacks on IoT networks. The CGAN-based IDS generates synthetic traffic to mimic legitimate traffic patterns and uses deep learning classifiers trained with CTGAN-generated tabular data to improve detection performance. Experimental results show accurate detection of DDoS and DoS attacks using the proposed approach, highlighting the significant contribution of CTGAN.
Review
Chemistry, Analytical
Abdullah Ahmed Bahashwan, Mohammed Anbar, Selvakumar Manickam, Taief Alaa Al-Amiedy, Mohammad Adnan Aladaileh, Iznan H. H. Hasbullah
Summary: Software-defined networking (SDN) is a revolutionary innovation in network technology with many desirable features, but it is vulnerable to distributed denial of service (DDoS) attacks. Despite efforts to detect DDoS attacks, the issue remains a challenge. This study presents a systematic literature review (SLR) on DDoS attack approaches based on machine learning (ML), deep learning (DL), or hybrid methods published between 2014 and 2022, identifying trends and highlighting the need for further research.
Article
Chemistry, Analytical
Methaq A. Shyaa, Zurinahni Zainol, Rosni Abdullah, Mohammed Anbar, Laith Alzubaidi, Jose Santamaria
Summary: Concept drift refers to the change in the statistical distribution of data over time in data streaming scenarios. This article proposes an extended variant of the genetic programming combiner (GPC) to handle concept drift in data stream classification. Experimental results demonstrate that the proposed method outperforms traditional GPC and other existing methods in handling various types of concept drift.
Article
Social Sciences, Interdisciplinary
Amran Mansoor, Mohammed Anbar, Abdullah Ahmed Bahashwan, Basim Ahmad Alabsi, Shaza Dawood Ahmed Rihan
Summary: The rapid growth of cloud computing has driven the development of Software-Defined Network (SDN) to provide dynamic management and improved performance. However, security threats, particularly targeting the SDN controller, have become a concern, including potential Distributed Denial of Service (DDoS) attacks. Existing DDoS detection approaches suffer from high false positives due to the use of non-qualified features and non-realistic datasets. To address this, a deep learning (DL) algorithmic technique is proposed for detecting DDoS attacks on SDN controllers. The proposed approach involves three stages: data preprocessing, cross-feature selection, and detection using the Recurrent Neural Networks (RNNs) model, achieving an average detection accuracy, precision, false positive rate, and F1-measure of 94.186%, 92.146%, 8.114%, and 94.276% respectively, according to the evaluation on a benchmark dataset.
Article
Chemistry, Analytical
Shaza Dawood Ahmed Rihan, Mohammed Anbar, Basim Ahmad Alabsi
Summary: The increasing number of IoT devices poses challenges to network security. This paper proposes a meta-learning approach to identify attacks in IoT networks, achieving high accuracy and recall rates through the combination of deep learning models and various methods.
Article
Chemistry, Analytical
Basim Ahmad Alabsi, Mohammed Anbar, Shaza Dawood Ahmed Rihan
Summary: This paper presents an approach for detecting attacks on IoT networks using a combination of two convolutional neural networks (CNN-CNN). The results show that the proposed approach achieves high accuracy, precision, recall, and classification rate, and outperforms other deep learning algorithms and feature selection methods.
Article
Chemistry, Analytical
Shaza Dawood Ahmed Rihan, Mohammed Anbar, Basim Ahmad Alabsi
Summary: This paper proposes an approach for detecting attacks on IoT networks using ensemble feature selection and deep learning models. The impact of the selected feature set on the performance of Deep Learning (DL) models is evaluated. The DL models achieved high detection accuracy, precision, recall, and F1 measure values.
Article
Chemistry, Multidisciplinary
Ziyad R. Alashhab, Mohammed Anbar, Shaza Dawood Ahmed Rihan, Basim Ahmad Alabsi, Karamath Ateeq
Summary: This research proposes a publicly available benchmark dataset based on an actual cloud computing environment for evaluating and improving the detection system of distributed denial-of-service attacks. The dataset has the advantages of trustworthiness and validity, enabling reliable evaluations and comparisons. It includes both internal and external HTTP-GET flood DDoS attacks, aiming to enhance the security of cloud computing environments.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Dima Kasasbeh, Mohammed Anbar, Ghassan Issa, Basim Ahmad Alabsi, Shaza Dawood Ahmed Rihan
Summary: In this paper, a novel embedding process based on multiple cumulative peak region localization (MCPRL) is proposed to enhance reversible data hiding (RDH). The technique utilizes the correlation between the pixel's local complexity and its directional prediction error to improve security and robustness. Experimental results demonstrate that the proposed method outperforms other state-of-the-art techniques in terms of embedding capacity, image quality, and resistance to attacks.
Article
Computer Science, Information Systems
Shadi Al-Sarawi, Mohammed Anbar, Basim Ahmad Alabsi, Mohammad Adnan Aladaileh, Shaza Dawood Ahmed Rihan
Summary: An Internet of Things (IoT) is a network of smart devices that enable data collection and exchange, and RPL is a protocol designed for connecting IPv6 to IoT networks. However, RPL is vulnerable to sinkhole attacks, which exploit vulnerabilities in RPL by manipulating routing preferences. This paper proposes a Passive Rule-based Approach (PRBA) to detect sinkhole nodes in RPL-based IoT networks.
Review
Computer Science, Information Systems
Taief Alaa Al-Amiedy, Mohammed Anbar, Bahari Belaton, Abdullah Ahmed Bahashwan, Iznan Husainy Hasbullah, Mohammad Adnan Aladaileh, Ghada AL Mukhaini
Summary: The Internet of Things (IoT) is a rapidly evolving networking concept that offers various applications for human benefit. Research has shown that security mechanisms based on trust, threshold, secure routing, authentication, and encryption have promising results in detecting anomalous activities in RPL-based 6LoWPAN.
INTERNET OF THINGS
(2023)