Article
Computer Science, Artificial Intelligence
Tingyu Ye, Wenjun Wang, Hui Wang, Zhihua Cui, Yun Wang, Jia Zhao, Min Hu
Summary: This article introduces a new artificial bee colony algorithm (RNSABC) based on random neighborhood structure to enhance the performance of the original ABC algorithm. The authors construct a random neighborhood structure and design an improved search strategy for optimization. Additionally, a depth-first search method is used to enhance the role of the onlooker bee phase. Experimental results demonstrate that RNSABC achieves competitive performance compared to nine other recent ABC variants.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Tao Zeng, Wenjun Wang, Hui Wang, Zhihua Cui, Feng Wang, Yun Wang, Jia Zhao
Summary: The paper introduces an efficient ABC algorithm named ASRGABC based on adaptive search strategy and random grouping mechanism. It adapts search strategy, introduces random grouping mechanism, and utilizes opposition-based learning to enhance the scout bee phase, outperforming thirteen other ABC variants in benchmark problem tests.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Xing Li, Shaoping Zhang, Le Yang, Peng Shao
Summary: An enhanced algorithm called EMABC-NS is proposed to improve the shortcomings of the artificial bee colony (ABC) algorithm in terms of convergence speed and exploitation ability for complex practical problems. By employing information from the global optimal individual and individuals in the neighborhood, as well as introducing a modification rate, EMABC-NS achieves better performance than other competitors and ranks first in the Friedman test.
Article
Biology
Hang Su, Dong Zhao, Fanhua Yu, Ali Asghar Heidari, Yu Zhang, Huiling Chen, Chengye Li, Jingye Pan, Shichao Quan
Summary: This paper proposes an improved artificial bee colony algorithm (CCABC) and a multilevel thresholding image segmentation (MTIS) method based on CCABC. The performance of the CCABC algorithm is demonstrated through comparative experiments, and the improved image segmentation method is applied to the segmentation of COVID-19 X-ray images, achieving good results.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Biology
Xiaowei Chen, Hui Huang, Ali Asghar Heidari, Chuanyin Sun, Yinqiu Lv, Wenyong Gui, Guoxi Liang, Zhiyang Gu, Huiling Chen, Chengye Li, Peirong Chen
Summary: This paper proposes a multilevel Lupus Nephritis (LN) image segmentation method based on an improved slime mould algorithm to enhance the diagnosis of LN. The experimental results demonstrate the superiority of the proposed method and compare it with other methods.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Information Systems
Kai Li, Hui Wang, Wenjun Wang, Feng Wang, Zhihua Cui
Summary: This paper proposes an artificial bee colony algorithm based on a modified nearest neighbor sequence to enhance optimization capability. Experimental results show that the algorithm performs competitively on various benchmark problems and complex problems.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Chunfeng Wang, Pengpeng Shang, Peiping Shen
Summary: This paper presents a novel ABC algorithm based on Bayesian estimation (BEABC) to improve the performance of the original ABC algorithm. By replacing the selection probability with a probability calculated by Bayesian estimation and designing a directional guidance mechanism, BEABC achieves better results in single-objective, multi-objective, and real-world optimization problems.
COMPLEX & INTELLIGENT SYSTEMS
(2022)
Article
Computer Science, Information Systems
Jiaxu Ning, Haitong Zhao, Chang Liu
Summary: An improved exhausted food source identification mechanism based on space partitioning is designed to address the issue of inefficient exploration and excessive searching resources allocation in existing ABC algorithms. The mechanism is applied to both the basic ABC algorithm and a recently improved version, showing better performance in almost all functions on the CEC2015 test suit compared to the original ABC algorithms.
Article
Biology
Manrong Shi, Chi Chen, Lei Liu, Fangjun Kuang, Dong Zhao, Xiaowei Chen
Summary: Medical image segmentation, a crucial step in medical image processing, is significantly improved by the development of a multi-strategy-driven slime mould algorithm (RWGSMA) for multi-threshold image segmentation. This algorithm utilizes random sparse, double adaptive weights, and grade-based search strategies to enhance segmentation performance, surpassing similar rivals in segmenting histopathological images.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Mathematics, Applied
Ya Zhang, Tong Li, Zhen Li, Yu-Mei Wu, Hong Miao
Summary: This paper proposes a BAS-ABC hybrid algorithm for parameter estimation in software defect prediction. The experimental results show that the hybrid algorithm outperforms the single algorithm in terms of accuracy, convergence, and stability, making it suitable for parameter estimation of the software reliability model.
Article
Chemistry, Analytical
Wenjie Yu, Xiangmei Li, Zhi Zeng, Miao Luo
Summary: This study proposes a modified and enhanced Artificial Bee Colony algorithm for optimizing the lifetime of a two-tiered wireless sensor network by deploying relay nodes effectively. The algorithm incorporates the problem dimension and a dynamic search balance strategy to balance exploration and exploitation. It also includes a feasible solution formation method to ensure stable network lifetime and reasonable relay node deployment. Simulation results demonstrate the competitive performance of the proposed algorithm compared to other classical and state-of-the-art algorithms.
Article
Computer Science, Artificial Intelligence
Hui Wang, Shuai Wang, Zichen Wei, Tao Zeng, Tingyu Ye
Summary: This paper proposes an improved many-objective artificial bee colony algorithm based on decomposition and dimension learning to solve many-objective optimization problems. The multi-objective problem is converted into several sub-problems by decomposition, and a new fitness function is defined. Elite solutions are selected based on their fitness values. The algorithm uses an elite set guided search strategy and dimension learning to improve convergence, and dynamically allocates computing resources in the scout bee stage. Experimental results show that this method outperforms seven other many-objective evolutionary algorithms.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Chemistry, Multidisciplinary
Zhengying Cai, Gengze Li, Jinming Zhang, Shasha Xiong
Summary: A novel artificial Physarum polycephalum colony algorithm is proposed to solve threshold segmentation problems. By expanding and contracting artificial hyphae and using a fitness function for optimization, this algorithm can quickly and accurately find the optimal threshold segmentation solutions.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Interdisciplinary Applications
Yunlou Qian, Jiaqing Tu, Gang Luo, Ce Sha, Ali Asghar Heidari, Huiling Chen
Summary: This paper investigates the application of remote sensing images in urban surface morphology and geographic conditions, using the multi-threshold image segmentation method for image segmentation research. The performance of the original algorithm is enhanced by introducing salp foraging behavior. The experimental results demonstrate the advantages of SSACO in remote sensing image segmentation.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2023)
Article
Computer Science, Information Systems
Bibi Aamirah Shafaa Emambocus, Muhammed Basheer Jasser
Summary: Optimization problems are commonly solved using heuristic algorithms, and the Dragonfly Algorithm has been found to be more effective than other swarm intelligence algorithms. However, it still suffers from low exploitation. In this paper, the authors propose using hill climbing as a local search technique to enhance the performance of the Dragonfly Algorithm. The optimized algorithm shows improved results in training artificial neural networks for classification problems.