Article
Computer Science, Information Systems
Lin Lan, Shengsheng Wang
Summary: In this study, a multi-level threshold image segmentation method based on African vultures optimization algorithm (OLAVOA) is proposed. The 2D Kapur's entropy is employed as a fitness value function to solve the issues in the traditional methods. The experimental results demonstrate that OLAVOA outperforms other algorithms in multi-threshold image segmentation, showing good convergence speed and ability to depart from local optima. Furthermore, the effectiveness and adaptability of OLAVOA in medical image segmentation are demonstrated through experiments.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Qizhao Zhang, Hongshun Liu, Jian Guo, Yifan Wang, Luyao Liu, Hongzheng Liu, Haoxi Cong
Summary: The continuous and reliable operation of the transformer is crucial for the normal functioning of the power system. Relevant departments collect heterogeneous parameter data from various sources during the operation, maintenance, and repair of transformers, which directly reflects the current operating status of the transformer. This paper proposes an improved algorithm called GWO-MCSVM based on support vector machine and grey wolf optimization algorithm, using nonlinear convergence factor and Tent chaotic mapping. By optimizing the algorithm parameters through training samples and evaluating the results, the accuracy of the status assessment can be enhanced. The effectiveness of the proposed algorithm for transformer condition assessment is verified through comparison with existing genetic algorithms and particle swarm optimization algorithms by evaluating multiple sets of measured samples.
ELECTRIC POWER SYSTEMS RESEARCH
(2023)
Article
Mathematical & Computational Biology
Yaning Xiao, Yanling Guo, Hao Cui, Yangwei Wang, Jian Li, Yapeng Zhang
Summary: This paper proposes an improved hybrid AO and AVOA optimizer, called IHAOAVOA, which combines the strengths of both algorithms and introduces new learning methods and selection strategies. The proposed algorithm demonstrates superior performance in solving global optimization problems and has been validated on various benchmark functions and engineering design problems.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2022)
Article
Computer Science, Information Systems
Farhad Soleimanian Gharehchopogh, Turgay Ibrikci
Summary: Image segmentation is a critical procedure in image pre-processing and analysis. Metaheuristic optimization algorithms, such as the African Vultures Optimization Algorithm (AVOA), can efficiently solve problems with different dimensions and demonstrate various functions. This paper introduces an improved AVOA that uses three binary thresholds in multi-threshold image segmentation. The algorithm incorporates Quantum Rotation Gate (QRG) and Association Strategy (AS) mechanisms to increase population diversity and search for optimal solutions, resulting in a good and significant performance.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Interdisciplinary Applications
Benyamin Abdollahzadeh, Farhad Soleimanian Gharehchopogh, Seyedali Mirjalili
Summary: Metaheuristics, especially the African Vultures Optimization Algorithm (AVOA), play a crucial role in solving optimization problems, outperforming existing algorithms in standard benchmarks and engineering design problems. The statistical evaluation further confirms the significant superiority of AVOA.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Computer Science, Interdisciplinary Applications
Bo Liu, Yongquan Zhou, Qifang Luo, Huajuan Huang
Summary: The production scheduling problem is a challenging task of assigning manufacturing resources to jobs while meeting all constraints. In this study, a novel optimization algorithm called QEMAVOA is proposed to address this issue. QEMAVOA incorporates three new improvement strategies to enhance its diversification and exploitation capabilities, resulting in better solutions.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2023)
Article
Computer Science, Interdisciplinary Applications
Rong Zheng, Abdelazim G. Hussien, Raneem Qaddoura, Heming Jia, Laith Abualigah, Shuang Wang, Abeer Saber
Summary: The African vultures optimization algorithm (AVOA) is a metaheuristic inspired by the African vultures' behaviors. However, it suffers from slow convergence rate and local optimal stagnation. In this study, an enhanced version called EAVOA is introduced, using techniques such as representative vulture selection strategy, rotating flight strategy, and selecting accumulation mechanism. EAVOA outperforms other methods in terms of numerical results and convergence curves, and shows practical applicability in engineering design optimization problems and classification tasks.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Mingyang Xi, Qixian Song, Min Xu, Zhaorong Zhou
Summary: This article proposes a Binary African Vultures Optimization Algorithm (BAVOA) to solve discrete optimization problems. BAVOA improves its performance by using a conversion function and optimization strategies. Experimental results show that BAVOA outperforms eight other algorithms in various optimization problems.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Baiyi Wang, Zipeng Zhang, Patrick Siarry, Xinhua Liu, Grzegorz Krolczyk, Dezheng Hua, Frantisek Brumercik, Z. Li
Summary: The African vultures optimization algorithm (AVOA) has some shortcomings in solving complex problems. To address these issues, a nonlinear African vulture optimization algorithm (HWEAVOA) is proposed, which outperforms other algorithms in terms of convergence speed, optimization ability, and solution stability, according to experimental results.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Narinder Singh, Essam H. Houssein, Seyedali Mirjalili, Yankai Cao, Ganeshsree Selvachandran
Summary: This study proposes a new optimization algorithm called DLHAV to solve complex continuous and discrete applications, and the experimental results show that the proposed algorithm outperforms other alternative optimizers significantly.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2022)
Article
Physics, Multidisciplinary
Kunpeng Zhang, Yanheng Liu, Fang Mei, Geng Sun, Jingyi Jin
Summary: Feature selection is a crucial process in machine learning and data mining, and the proposed IBGJO algorithm significantly improves the performance of the GJO algorithm by introducing the CTM mechanism and a position update strategy based on cosine similarity. The experiments conducted on classical datasets demonstrate that IBGJO achieves faster convergence and higher accuracy compared to other algorithms.
Article
Materials Science, Characterization & Testing
Dildar Gurses, Pranav Mehta, Sadiq M. Sait, Ali Riza Yildiz
Summary: Nature-inspired optimization algorithms, known as meta-heuristics, have been found to be versatile in engineering design fields, including the Internet of things, structural design, and thermal system design. In the context of industrial modernization, waste heat recovery is crucial for reducing emissions and complying with government regulations. The shell and tube heat exchangers (SHTHEs) are commonly used components for heat recovery, and cost minimization is a major aspect in their design. This study proposes the use of the African vultures optimization algorithm (AVOA) for cost minimization of SHTHEs, and it is found to be effective in achieving optimized results.
Article
Computer Science, Artificial Intelligence
Nima Khodadadi, Farhad Soleimanian Gharehchopogh, Seyedali Mirjalili
Summary: This paper presents a multi-objective version of the artificial vultures optimization algorithm and demonstrates its effectiveness and advantages through testing on various problems.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Hao-Ming Song, Cheng Xing, Jie-Sheng Wang, Yu-Cai Wang, Yu Liu, Jun-Hua Zhu, Jia-Ning Hou
Summary: Pelican Optimization Algorithm (POA) is a new heuristic algorithm that simulates the natural behavior of pelicans in hunting. An improved POA based on chaotic interference factor and elementary mathematical function is proposed to enhance the convergence speed and accuracy, as well as to address the local optimization problem. Experimental results demonstrate the effectiveness of the improved algorithms, showing improved performance compared to the original POA in terms of exploration and exploitation balance.
Article
Computer Science, Artificial Intelligence
Guanglei Sun, Youlin Shang, Kehong Yuan, Huimin Gao
Summary: This study proposes a modified Whale Optimization Algorithm (MSWOA) to address the deficiencies of the original algorithm by implementing multiple strategies. Experimental results demonstrate that MSWOA outperforms the standard WOA in terms of solution accuracy and convergence speed. The inertia weight strategy is identified as the most important factor affecting the performance of WOA.
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Xueting Cui, Ying Li, Jiahao Fan, Tan Wang
Summary: A novel feature selection algorithm, Multidirectional Relief (MRelief), is proposed to address the weaknesses of Relief algorithm and improve classification accuracy. Experimental results show that MRelief outperforms other algorithms significantly on various datasets.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Xue-Tao Chen, Ying Li, Jia-Hao Fan, Rui Wang
Summary: This paper introduces a novel network architecture called RGAM, with four improvements over existing networks, including multi-scale ring grouping learning, neighborhood information fusion, spatial attention module, and channel attention module. Experimental results show that RGAM has stronger recognition ability in 3D point cloud semantic segmentation compared to existing networks.
INFORMATION SCIENCES
(2021)
Article
Multidisciplinary Sciences
Ying Li, Wenyue Li, Zhijie Zhao, JiaHao Fan
Summary: This study proposes a cascaded depth residual inference network, called DRI-MVSNet, for high-precision 3D reconstruction. The network combines channel attention mechanism, feature map fusion, and residual prediction, and extensive experiments demonstrate its advantages in accuracy and completeness.
Article
Computer Science, Hardware & Architecture
Ying Li, Xueting Cui, Jiahao Fan, Tan Wang
Summary: In this study, a global chaotic bat algorithm (GCBA) is proposed to address the premature convergence issue in the wrapper algorithm, by applying chaotic map for population initialization, introducing adaptive learning factors to balance exploration and exploitation, and proposing an improved transfer function to enhance classification performance.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Multidisciplinary Sciences
Ying Li, Hanyu Wang, Jiahao Fan, Yanyu Geng
Summary: This paper proposes a new Q-learning algorithm called Paired Whale Optimization Q-learning Algorithm (PWOQLA) that leverages the whale optimization algorithm to initialize Q-table and introduces several improvements to enhance the convergence speed and exploration efficiency. Experimental results show that PWOQLA achieves higher accuracy and faster convergence speed compared to existing path planning algorithms in mobile robotics.
Article
Computer Science, Information Systems
Taiqiao Yin, Ying Li, Jiahao Fan, Tan Wang, Yunxia Shi
Summary: The EnMFO-ImGRU method improves behavior decision-making by introducing a double-layer GRU, using SVM to train the output of ImGRU, optimizing SVM's key parameters with MFO, and proposing the Enhanced Moth-Flame Optimization algorithm. Experimental results demonstrate that EnMFO-ImGRU enhances the accuracy of behavior decision-making for autonomous vehicles.
Article
Computer Science, Information Systems
Rui Wang, Ying Li, Jiahao Fan, Tan Wang, Xuetao Chen
Article
Computer Science, Information Systems
Xueting Cui, Ying Li, Jiahao Fan, Tan Wang, Yuefeng Zheng
Article
Computer Science, Information Systems
Yunxia Shi, Ying Li, Jiahao Fan, Tan Wang, Taiqiao Yin
