Article
Mathematics
Khalid Abdulaziz Alnowibet, Shalini Shekhawat, Akash Saxena, Karam M. Sallam, Ali Wagdy Mohamed
Summary: Metaheuristics, including bio-inspired ones, have been widely used to solve complex optimization problems. In this paper, a variant of the popular Whale Optimization Algorithm (WOA) called the Augmented Whale Optimization Algorithm (AWOA) is proposed. The AWOA incorporates opposition-based learning and Cauchy mutation operator to improve the exploration and exploitation capabilities of WOA. Experimental results and analyses demonstrate that the proposed AWOA outperforms the original WOA and achieves better optimization performance for both benchmark functions and real-world problems.
Article
Computer Science, Interdisciplinary Applications
Juliano Pierezan, Leandro dos Santos Coelho, Viviana Cocco Mariani, Emerson Hochsteiner de Vasconcelos Segundo, Doddy Prayogo
Summary: The paper introduces a modified COA method based on chaotic sequences generated by Tinkerbell map for tuning scatter and association probabilities, along with an adaptive procedure for updating parameters related to social conditions. Validation on several benchmark optimization problems shows that the proposed MCOA method presents competitive solutions in terms of solution quality.
COMPUTERS & STRUCTURES
(2021)
Article
Mathematics
Marcelo Becerra-Rozas, Felipe Cisternas-Caneo, Broderick Crawford, Ricardo Soto, Jose Garcia, Gino Astorga, Wenceslao Palma
Summary: When faced with real problems using computational resources, it is important to find efficient solutions for combinatorial problems in binary domains. This paper proposes a hybrid approach that combines the whale optimization algorithm with Q-learning to address discrete domain problems, and the results show promise based on statistical analysis.
Article
Computer Science, Information Systems
Mohammad H. Nadimi-Shahraki, Shokooh Taghian, Seyedali Mirjalili, Laith Abualigah, Mohamed Abd Elaziz, Diego Oliva
Summary: The optimal power flow is a crucial tool in optimizing control parameters of a power system, with the whale optimization algorithm being widely used for such problems. This paper proposes an enhanced whale optimization algorithm to improve exploration ability and achieve better solutions across diverse power system scales. The comparison of results demonstrates that the enhanced algorithm outperforms other comparative algorithms in solving both single- and multi-objective optimal power flow problems.
Article
Computer Science, Artificial Intelligence
Amir Seyyedabbasi, Royal Aliyev, Farzad Kiani, Murat Ugur Gulle, Hasan Basyildiz, Mohammed Ahmed Shah
Summary: This paper introduces three hybrid algorithms that combine reinforcement learning and metaheuristic methods to solve global optimization problems. The proposed algorithms show higher success rates and more balanced performance compared to classical metaheuristic approaches in finding new areas and during exploration and exploitation phases. The algorithms use reinforcement agents to select environments based on predefined actions and tasks, employing a reward and penalty system dynamically to discover the environment.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Interdisciplinary Applications
Mahmoud Alimoradi, Hossein Azgomi, Ali Asghari
Summary: This paper presents a new metaheuristic algorithm called Trees Social Relations Optimization Algorithm (TSR) inspired by the hierarchical and collective life of trees in the jungle. TSR uses trees and sub-jungles to represent solutions and employs parallel and synchronized sub-jungles with dedicated operators to increase accuracy and reduce response time. Experimental results demonstrate that TSR algorithm provides appropriate and acceptable answers in both time and accuracy.
MATHEMATICS AND COMPUTERS IN SIMULATION
(2022)
Article
Computer Science, Artificial Intelligence
Mario A. Navarro, Diego Oliva, Alfonso Ramos-Michel, Daniel Zaldivar, Bernardo Morales-Castaneda, Marco Perez-Cisneros, Arturo Valdivia, Huiling Chen
Summary: This article proposes a method called K-WOA that combines clustering techniques and metaheuristic algorithms to increase the diversity of optimization problem solutions. The algorithm divides the population into different subgroups and evolves them separately to explore different regions of the search space simultaneously, showing competitiveness.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2022)
Article
Computer Science, Artificial Intelligence
Ya Shen, Chen Zhang, Farhad Soleimanian Gharehchopogh, Seyedali Mirjalili
Summary: In this work, a multi-population evolution based variant of the whale optimization algorithm (MEWOA) is proposed to solve the slow convergence and local optimum problems. MEWOA divides individuals into three sub-populations and assigns different moving strategies to each sub-population, performing global and local search. The introduction of a novel population evolution strategy further enhances MEWOA's global optimization ability. Experimental results demonstrate the competitiveness and merits of MEWOA, achieving faster convergence speed, shorter runtime, and higher solution accuracy compared to other algorithms on benchmark functions and real-world problems.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Mehmet Akif Sahman, Sedat Korkmaz
Summary: The Job-Shop Scheduling Problem is a complex optimization problem that can be solved using heuristic algorithms. This study proposes a new version of the Artificial Algae Algorithm and integrates three different encoding schemes with this algorithm to solve high-dimensional Job-Shop Scheduling Problems. Through comparison and analysis, it is found that integrating the Smallest Position Value encoding scheme into the Artificial Algae Algorithm produces the best makespan value results.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Shathanaa Rajmohan, E. Elakkiya, S. R. Sreeja
Summary: This paper proposes a novel variant of the whale optimization algorithm, which divides the population into cohorts for exploration, introduces a new boundary update method, and employs opposition-based initialization and elitism for quick convergence. The proposed algorithm achieves a 53.75% improvement in average fitness compared to the original algorithm.
NEURAL COMPUTING & APPLICATIONS
(2023)
Review
Computer Science, Artificial Intelligence
Feng Qin, Azlan Mohd Zain, Kai-Qing Zhou
Summary: This article systematically reviews the harmony search (HS) algorithm and its variants from three aspects: describing the basic HS principle, discussing the impact of HS improvement on algorithm performance, and analyzing the characteristics and applications of HS variants. It is found that the improvement of HS mainly focuses on parameter enhancement and the integration with other metaheuristic algorithms, providing future directions for enhancing HS.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Artificial Intelligence
Mahdis Banaie-Dezfouli, Mohammad H. Nadimi-Shahraki, Zahra Beheshti
Summary: In this study, an improved binary GWO algorithm called BE-GWO is introduced. The proposed algorithm uses a cosine transfer function (CTF) to convert the continuous GWO to the binary form and introduces an extremum search strategy to improve the efficiency of the converted binary solutions. The experimental results showed that the BE-GWO algorithm enhances the performance of binary GWO in terms of solution accuracy, convergence speed, exploration, and balancing between exploration and exploitation.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Zhong-kai Feng, Wen-jing Niu, Shuai Liu
Summary: The CSA method, inspired by team cooperation behaviors, uses team communication, reflective learning, and internal competition operators to solve global optimization problems, demonstrating fast convergence and high search accuracy. It performs well in mathematical and engineering optimization problems, providing an effective tool for solving complex global optimization problems.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Wojciech Bozejko, Anna Burduk, Kamil Musial, Jaroslaw Pempera
Summary: The research focuses on minimizing the production time of tasks on machines while limiting the availability of machine operators. A mathematical model is formulated and a neuro-tabu algorithm is proposed for its solution. The efficiency of the algorithm is verified on test examples based on real data from the production process.
Article
Computer Science, Artificial Intelligence
Lalit Kumar, Manish Pandey, Mitul Kumar Ahirwal
Summary: The computational time of swarm optimization algorithms, including Particle Swarm Optimization (PSO), is increased due to the large number of decision variables in complex problems. A new Global Best-Worst Particle Swarm Optimization (GBWPSO) algorithm, combining PSO and Jaya algorithm, is proposed to provide a more parallel version of the algorithm. The proposed algorithm outperforms other parallel PSO versions and Jaya algorithm in terms of computational time and optimal solution.
APPLIED SOFT COMPUTING
(2023)
Article
Automation & Control Systems
Rizk M. Rizk-Allah, Aboul Ella Hassanien
Summary: This paper proposes a novel algorithm named EO-PS, based on the hybridization of equilibrium optimizer and pattern search techniques, for accurate and reliable wind farm layout optimization design. The algorithm operates in two phases, utilizing equilibrium optimizer in the first phase to explore the search space and pattern search in the second phase to guide the searching towards better solutions. The algorithm is implemented and tested on irregular land space in Egypt, achieving optimal layout configuration for practical planning trends. The comprehensive results and analyses confirm the competitive performance of EO-PS in terms of solution quality and reliability.
Article
Computer Science, Artificial Intelligence
Rizk M. Rizk-Allah, Aboul Ella Hassanien
Summary: This paper provides a comprehensive overview of the Sine-Cosine optimization algorithm and its applications in optimization problems. The SCA imitates transcendental functions and uses sine and cosine functions to explore and exploit the search space. It is known for its simple concept, ease of implementation, and rapid convergence.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Artificial Intelligence
Mohamed A. Tolba, Essam H. Houssein, Ayman A. Eisa, Fatma A. Hashim
Summary: This study introduces an optimization method to minimize power losses and voltage deviations in electrical distribution networks (EDNs), and validates its effectiveness through validation and demonstration. A comprehensive analysis comparing the method with other optimizers is also conducted, demonstrating its superiority.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Mohamed Torky, Ghada Dahy, Aboul Ella Hassanein
Summary: This paper introduces a deep-learning approach (GH2_MobileNet) for predicting the quantity of green hydrogen production from an organic waste mixture dataset in images. Two methodologies (DOWE and WOWE) are proposed for estimating the weight value of dry and wet organic waste images. The validation results show that the proposed model performs well in recognizing and classifying organic waste.
APPLIED SOFT COMPUTING
(2023)
Article
Biology
Essam H. Houssein, Awny Sayed
Summary: With the increasing availability of healthcare data, machine learning is becoming more significant in healthcare domains. It is crucial to ensure the integrity and reliability of machine learning models to maintain the quality of healthcare services. Due to privacy and security concerns, healthcare data is often treated as independent sources and limited computational capabilities of wearable healthcare devices hinder traditional machine learning. Federated Learning, which protects data privacy by storing only learned models on a server and advances with data from scattered clients, shows potential to transform healthcare by enabling the development of new machine learning applications.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Engineering, Electrical & Electronic
Mohamed H. Hassan, Salah Kamel, Abdelazim G. Hussien
Summary: In recent years, there have been rapid developments in electricity networks worldwide, particularly with the incorporation of various renewable energy sources (RES) in order to improve energy efficiency. However, integrating conventional power generation with RES poses complex challenges, which are further compounded by the addition of stochastic RES to the network. To address this problem, this article proposes an enhanced hybrid technique called EESWHO, based on the Wild Horse Optimizer (WHO) improved by an elite evolutionary strategy (EES). The effectiveness and robustness of the proposed technique were demonstrated through extensive numerical optimization tests and application to a modified IEEE-30 bus test system.
IET GENERATION TRANSMISSION & DISTRIBUTION
(2023)
Article
Computer Science, Artificial Intelligence
Ibrahim Al-Shourbaji, Pramod Kachare, Sajid Fadlelseed, Abdoh Jabbari, Abdelazim G. Hussien, Faisal Al-Saqqar, Laith Abualigah, Abdalla Alameen
Summary: This paper proposes a new feature selection algorithm, AEO-DMOA, which integrates AEO and DMOA algorithms to achieve a better balance between exploration and exploitation. The results show that AEO-DMOA has competitive performance and enhanced performance in high-dimensional search space.
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS
(2023)
Article
Multidisciplinary Sciences
Essam H. Houssein, Rehab E. Mohamed, Abdelmgeid A. Ali
Summary: Heart disease remains a major cause of death, and detecting risk factors in clinical notes can aid in disease progression modeling and clinical decision-making. Previous studies have proposed hybrid systems combining knowledge-driven and data-driven techniques, but none have identified all risk factors. The use of stacked word embeddings has shown significant improvement in identifying risk factors for heart disease.
SCIENTIFIC REPORTS
(2023)
Article
Environmental Sciences
Sanaz Afzali Ahmadabadi, Jafar Jafari-Asl, Elham Banifakhr, Essam H. Houssein, Mohamed El Amine Ben Seghier
Summary: English Summary: In this study, the placement of contamination warning systems (CWSs) in water distribution systems (WDSs) was investigated. A novel optimization model called WOA-SCSO, based on a hybrid algorithm combining whale optimization algorithm (WOA) and sand cat swarm optimization (SCSO), was developed. The effectiveness of the WOA-SCSO algorithm was evaluated using benchmark functions, showing superior performance compared to other algorithms. The results demonstrated that the WOA-SCSO algorithm can effectively optimize the placement of CWSs in WDSs, reducing contamination risks.
Article
Green & Sustainable Science & Technology
Edwidge Raissa Mache Kengne, Alain Soup Tewa Kammogne, Thomas Tatietse Tamo, Ahmad Taher Azar, Ahmed Redha Mahlous, Saim Ahmed
Summary: This paper focuses on the modeling and theoretical study of an average-current-mode-controlled photovoltaic power conversion chain. The dynamics of the system are studied using bifurcation diagrams, largest Lyapunov exponents, Floquet theory, and time series. The theoretical results reveal the presence of subharmonic and period-1 oscillations in the system. Numerical simulations demonstrate the occurrence of period doubling and chaotic dynamics when the battery voltage at the converter's output is fixed and ramp amplitude is used as a control parameter. Bifurcation diagrams also show that the critical values of ramp amplitude for border collision bifurcation and period-1 occurrence increase with the battery terminal voltage. The numerical and theoretical results are consistent. Finally, an external control based on a non-adaptive controller with a sinusoidal function as a target is applied to suppress chaotic behavior in the overall system.
Article
Green & Sustainable Science & Technology
Edwige Raissa Mache Kengne, Alain Soup Tewa Kammogne, Martin Siewe Siewe, Thomas Tatietse Tamo, Ahmad Taher Azar, Ahmed Redha Mahlous, Mohamed Tounsi, Zafar Iqbal Khan
Summary: The presence of high ripple in the inductor current of a DC-DC converter in a photovoltaic converter chain decreases the energy efficiency of the converter. To solve this problem, a current-mode control is considered and a single inductor current sensor with a low-pass filter is used for economic reasons. The objective of this paper is to study the stability of the photovoltaic system as a function of the filter frequency while maintaining a good power level. The stability of the system is analyzed using Floquet theory and bifurcation diagrams and Lyapunov exponents are plotted to investigate the system's behavior.
Article
Multidisciplinary Sciences
Oleg Sergiyenko, Alexey Zhirabok, Ibrahim A. Hameed, Ahmad Taher Azar, Alexander Zuev, Vladimir Filaretov, Vera Tyrsa, Ibraheem Kasim Ibraheem
Summary: This study investigates the problem of designing virtual sensors for nonlinear systems under disturbance. Two different mathematical techniques, algebra of functions and logic-dynamic approach, are used to solve the problem. The first technique provides a general solution, while the second technique uses linear algebra methods to find a solution specifically for nonlinear systems. The virtual sensors are designed to be robust against disturbance by utilizing invariant functions and estimating the prescribed function of the original system state vector. A practical example is provided to illustrate the theoretical results.
Article
Biology
Essam H. Houssein, Nagwan Abdel Samee, Noha F. Mahmoud, Kashif Hussain
Summary: Medical datasets are often filled with irrelevant and redundant elements, which are not necessary for medical decision-making. Recent research has shown that feature selection can effectively address this issue.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Saroj Kumar Sahoo, Essam H. Houssein, M. Premkumar, Apu Kumar Saha, Marwa M. Emam
Summary: In this study, an upgraded variant of Moth flame optimization algorithm (Es-MFO) is proposed for higher accuracy in classifying COVID-19 CT images. The algorithm is evaluated and compared with other optimization techniques and MFO variants. Its robustness and durability are tested and it is applied to solve the COVID-19 CT image segmentation problem with superior results compared to other algorithms.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Fatma A. Hashim, Nabil Neggaz, Reham R. Mostafa, Laith Abualigah, Robertas Damasevicius, Abdelazim G. Hussien
Summary: Hunger Games Search (HGS) is a swarm-based algorithm inspired by animals' hunting strategies. However, it has slow convergence and unbalanced exploration and exploitation phases. To address these issues, a modified version called mHGS is proposed, which shows significant performance improvements in dimensionality reduction and real-world applications.
NEURAL COMPUTING & APPLICATIONS
(2023)
