Search strategies play an essential role in artificial bee colony (ABC) algorithm. Different optimisation problems and search stages may need different search strategies. However, it is difficult to choose an appropriate search strategy. To tackle this issue, this paper proposes a data-driven ABC algorithm based on radial basis function neural network (called RBF-ABC). Firstly, a strategy pool with three distinct search strategies is built. The radial basis function (RBF) network is applied to evaluate offspring generated by the search strategies. The search strategy with the best evaluation value is used to guide the search. Dimension perturbation is employed to update multiple dimensions simultaneously, and it improves the convergence speed and the accuracy of the surrogate model. A set of 22 classical benchmark problems with 30 and 100 dimensions are utilised to verify the performance of RBF-ABC. Results show RBF-ABC can effectively save computational evaluations and outperform six other ABC algorithms.
Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL Reinforcement Learning Driven Dual Neighborhood Structure Artificial Bee Colony Algorithm with Adaptive Neighborhood Search 35 Pages Posted: 24 Feb 2024 See all articles by Tingyu YeTingyu YeSouth China University of TechnologyPing ZhangSouth China University of TechnologyHongliang ZengSouth China University of TechnologyJiahua WangSouth China University of Technology Abstract Artificial bee colony algorithm (ABC) is one of the most popular swarm intelligence optimization algorithms currently. Although ABC has strong exploration capability, its exploitation ability is weak. It is difficult to find the optimal solution for complex optimization problem. Neighborhood topology-based search method has been proposed and achieved excellent results for the above problem. In fact, the neighborhood topology size seriously affects the efficiency of search, and most of the current works has not been well considered. Obtaining the appropriate neighborhood size is a challenge task. To further explore the potential of neighborhood topology, this paper proposed a reinforcement learning driven dual neighborhood structure ABC with adaptive neighborhood search (called RL_DNSABC). In RL_DNSABC, a dual neighborhood structure combining reinforcement learning driven random neighborhood structure (RL_RNS) and the classical neighborhood structure based on Euclidean distance (EDNS) is built. In RL_RNS, an adaptive neighborhood search method is designed based on reinforcement learning. Then, a novel probability selection technique based on RL_RNS in the onlooker bee phase. Moreover, three search strategies with different preferences are devised to exploration and exploitation based on RL_RNS and EDNS. To verify the effectiveness of RL_DNSABC, nineteen ABC variants are compared on the classical benchmark set and the CEC 2013 benchmark set. Experimental results show that RL_DNSABC obtained competitive performance than the compared algorithms. Keywords: Artificial bee colony, Adaptive neighborhood search, Dual neighborhood structure, Reinforcement learning, Search strategy. Suggested Citation: Suggested Citation Ye, Tingyu and Zhang, Ping and Zeng, Hongliang and Wang, Jiahua, Reinforcement Learning Driven Dual Neighborhood Structure Artificial Bee Colony Algorithm with Adaptive Neighborhood Search. Available at SSRN: https://ssrn.com/abstract=4737763 Tingyu Ye South China University of Technology ( email ) WushanGuangzhou, AR 510640China Ping Zhang (Contact Author) South China University of Technology ( email ) WushanGuangzhou, AR 510640China Hongliang Zeng South China University of Technology ( email ) WushanGuangzhou, AR 510640China Jiahua Wang South China University of Technology ( email ) WushanGuangzhou, AR 510640China Download This Paper Open PDF in Browser Do you have negative results from your research you’d like to share? Submit Negative Results Paper statistics Downloads 0 Abstract Views 2 58 References PlumX Metrics Feedback Feedback to SSRN Feedback (required) Email (required) Submit If you need immediate assistance, call 877-SSRNHelp (877 777 6435) in the United States, or +1 212 448 2500 outside of the United States, 8:30AM to 6:00PM U.S. Eastern, Monday - Friday.
Artificial bee colony (ABC) is an efficient global optimisation algorithm. It has attracted the attention of many researchers because of its simple concept and strong exploration. However, it exhibits weak exploitation capability. To improve this case, a novel ABC with modified search strategy (namely MSABC) is proposed in this work. In MSABC, some modified elite solutions are preserved and used to guide the search. In addition, MSABC uses the modified elite solutions to generate offspring to replace the probability selection in the onlooker bee phase. To evaluate the capability of MSABC, 22 classical problems are tested. Results demonstrate MSABC achieves superior performance than five other ABC variants.
With the advance of sequencing technology, the number of sequenced plant genomes has been rapidly increasing. However, understanding of the gene function in these sequenced genomes lags far behind; as a result, many coding plant sequences in public databases are annotated as proteins with domains of unknown function (DUF). Function of a protein family DUF810 in rice is not known. In this study, we analysed seven members of OsDU810 (OsDUF810.1-OsDUF810.7) family with three distinct motifs in rice Nipponbare. By phylogenetic analysis, OsDUF810 proteins fall into three major groups (I, II, III). Expression patterns of the seven corresponding OsDUF810 protein-encoding genes in 15 different rice tissues vary. Under drought, salt, cold and heat stress conditions and ABA treatment, the expression of OsDUF810.7 significantly increases. Overexpression of this protein in E. coli lead to a significant enhancement of catalase (CAT) and peroxidase (POD) activities, and improved bacterial resistance to salt and drought.
Precise perception of articulated objects is vital for empowering service robots. Recent studies mainly focus on point cloud, a single-modal approach, often neglecting vital texture and lighting details and assuming ideal conditions like optimal viewpoints, unrepresentative of real-world scenarios. To address these limitations, we introduce MARS, a novel framework for articulated object characterization. It features a multi-modal fusion module utilizing multi-scale RGB features to enhance point cloud features, coupled with reinforcement learning-based active sensing for autonomous optimization of observation viewpoints. In experiments conducted with various articulated object instances from the PartNet-Mobility dataset, our method outperformed current state-of-the-art methods in joint parameter estimation accuracy. Additionally, through active sensing, MARS further reduces errors, demonstrating enhanced efficiency in handling suboptimal viewpoints. Furthermore, our method effectively generalizes to real-world articulated objects, enhancing robot interactions. Code is available at https://github.com/robhlzeng/MARS.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)