{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:06:06Z","timestamp":1775837166485,"version":"3.50.1"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T00:00:00Z","timestamp":1686873600000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52275097"],"award-info":[{"award-number":["52275097"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61806058"],"award-info":[{"award-number":["61806058"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2018A030310063"],"award-info":[{"award-number":["2018A030310063"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010256","name":"Guangzhou Science and Technology Plan","doi-asserted-by":"publisher","award":["201804010299"],"award-info":[{"award-number":["201804010299"]}],"id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,7,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Because of the good performance of convolutional neural network (CNN), it has been extensively used in many fields, such as image, speech, text, etc. However, it is easily affected by hyperparameters. How to effectively configure hyperparameters at a reasonable time to improve the performance of CNNs has always been a complex problem. To solve this problem, this paper proposes a method to automatically optimize CNN hyperparameters based on the local autonomous competitive harmony search (LACHS) algorithm. To avoid the influence of complicated parameter adjustment of LACHS algorithm on its performance, a parameter dynamic adjustment strategy is adopted, which makes the pitch adjustment probability PAR and step factor BW dynamically adjust according to the actual situation. To strengthen the fine search of neighborhood space and reduce the possibility of falling into local optima for a long time, an autonomous decision-making search strategy based on the optimal state is designed. To help the algorithm jump out of the local fitting situation, this paper proposes a local competition mechanism to make the new sound competes with the worst harmonic progression of local selection. In addition, an evaluation function is proposed, which integrates the training times and recognition accuracy. To achieve the purpose of saving the calculation cost without affecting the search result, it makes the training time for each model depending on the learning rate and batch size. In order to prove the feasibility of LACHS algorithm in configuring CNN superparameters, the classification of the Fashion-MNIST dataset and CIFAR10 dataset is tested. The comparison is made between CNN based on empirical configuration and CNN based on classical algorithms to optimize hyperparameters automatically. The results show that the performance of CNN based on the LACHS algorithm has been improved effectively, so this algorithm has certain advantages in hyperparametric optimization. In addition, this paper applies the LACHS algorithm to expression recognition. Experiments show that the performance of CNN optimized based on the LACHS algorithm is better than that of the same type of artificially designed CNN. Therefore, the method proposed in this paper is feasible in practical application.<\/jats:p>","DOI":"10.1093\/jcde\/qwad050","type":"journal-article","created":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T02:11:20Z","timestamp":1686881480000},"page":"1280-1297","source":"Crossref","is-referenced-by-count":7,"title":["Hyperparameters optimization of convolutional neural network based on local autonomous competition harmony search algorithm"],"prefix":"10.1093","volume":"10","author":[{"given":"Dongmei","family":"Liu","sequence":"first","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Guangzhou University , Guangzhou, 510006 , China"}]},{"given":"Haibin","family":"Ouyang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Guangzhou University , Guangzhou, 510006 , China"},{"name":"School of Computer Science and Engineering, South China University of Technology , Guangzhou, 510006 , China"}]},{"given":"Steven","family":"Li","sequence":"additional","affiliation":[{"name":"Graduate School of Business and Law, RMIT University , Melbourne, 3000 , Australia"}]},{"given":"Chunliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Guangzhou University , Guangzhou, 510006 , China"}]},{"given":"Zhi-Hui","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology , Guangzhou, 510006 , China"}]}],"member":"286","published-online":{"date-parts":[[2023,6,15]]},"reference":[{"issue":"6","key":"2023070408364926100_bib1","doi-asserted-by":"crossref","DOI":"10.14569\/IJACSA.2019.0100638","article-title":"Hyperparameter optimization in convolutional neural network using genetic algorithms","volume":"10","author":"Aszemi","year":"2019","journal-title":"International Journal of Advanced Computer Science and Applications"},{"key":"2023070408364926100_bib2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2012.06400","article-title":"Differential evolution for neural architecture search","author":"Awad","year":"2020"},{"key":"2023070408364926100_bib3","first-page":"2546","article-title":"Algorithms for hyper-parameter optimization","volume-title":"Proceedings of the 24th International Conference on Neural Information Processing Systems","author":"Bergstra","year":"2011"},{"issue":"1","key":"2023070408364926100_bib4","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"2023070408364926100_bib5","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1016\/j.ins.2014.04.001","article-title":"Geometric selective harmony search","volume":"279","author":"Castelli","year":"2014","journal-title":"Information Sciences"},{"key":"2023070408364926100_bib6","first-page":"3110","article-title":"Cross-modal matching CNN for autonomous driving sensor data monitoring","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Chen","year":"2021"},{"key":"2023070408364926100_bib7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/PUNECON.2018.8745428","article-title":"Cifar-10 classification using deep convolutional neural network","volume-title":"Proceedings of the 2018 IEEE Punecon","author":"Doon","year":"2018"},{"key":"2023070408364926100_bib8","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.ins.2020.11.009","article-title":"Pruning deep convolutional neural networks architectures with evolution strategy","volume":"552","author":"Fernandes","year":"2021","journal-title":"Information Sciences"},{"key":"2023070408364926100_bib9","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-05318-5_1","article-title":"Hyperparameter optimization","volume-title":"Automated machine learning: Methods, systems, challenges","author":"Feurer","year":"2019"},{"issue":"2","key":"2023070408364926100_bib10","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1177\/003754970107600201","article-title":"A new heuristic optimization algorithm: Harmony search","volume":"76","author":"Geem","year":"2001","journal-title":"Simulation"},{"key":"2023070408364926100_bib11","first-page":"1319","article-title":"Maxout networks","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Goodfellow","year":"2013"},{"issue":"2","key":"2023070408364926100_bib12","first-page":"1","article-title":"Efficient hyperparameter optimization for convolution neural networks in deep learning: A distributed particle swarm optimization approach","volume":"52","author":"Guo","year":"2020","journal-title":"Cybernetics and Systems"},{"key":"2023070408364926100_bib13","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","volume-title":"Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He","year":"2016"},{"key":"2023070408364926100_bib14","doi-asserted-by":"publisher","first-page":"2261","DOI":"10.1109\/CVPR.2017.243","article-title":"Densely connected convolutional networks","volume-title":"Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Huang","year":"2016"},{"key":"2023070408364926100_bib15","doi-asserted-by":"crossref","DOI":"10.1109\/TEVC.2022.3217290","article-title":"Particle swarm optimization for compact neural architecture search for image classification","author":"Huang","year":"2022","journal-title":"IEEE Transactions on Evolutionary Computation"},{"issue":"4","key":"2023070408364926100_bib16","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1109\/TEVC.2021.3065659","article-title":"Region encoding helps evolutionary computation evolve faster: A new solution encoding scheme in particle swarm for large-scale optimization","volume":"25","author":"Jian","year":"2021","journal-title":"IEEE Transactions on Evolutionary Computation"},{"issue":"3","key":"2023070408364926100_bib17","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1007\/s13042-019-01030-4","article-title":"Large-scale evolutionary optimization: A survey and experimental comparative study","volume":"11","author":"Jian","year":"2020","journal-title":"International Journal of Machine Learning and Cybernetics"},{"key":"2023070408364926100_bib18","article-title":"Neural architecture search with Bayesian optimisation and optimal transport","volume-title":"NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems, 2020\u20132029","author":"Kandasamy","year":"2018"},{"key":"2023070408364926100_bib19","article-title":"CS231n convolutional neural networks for visual recognition","volume-title":"Neural Networks","author":"Karpathy","year":"2016"},{"key":"2023070408364926100_bib20","doi-asserted-by":"crossref","first-page":"5455","DOI":"10.1007\/s10462-020-09825-6","article-title":"A survey of the recent architectures of deep convolutional neural networks","volume":"53","author":"Khan","year":"2020","journal-title":"Artificial Intelligence Review"},{"key":"2023070408364926100_bib21","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Advances in neural information processing systems","author":"Krizhevsky","year":"2012"},{"key":"2023070408364926100_bib22","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1145\/1273496.1273556","article-title":"An empirical evaluation of deep architectures on problems with many factors of variation","volume-title":"Proceedings of the 24th International Conference on Machine Learning","author":"Larochelle","year":"2007"},{"issue":"7553","key":"2023070408364926100_bib52","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"key":"2023070408364926100_bib23","first-page":"562","article-title":"Deeply-supervised nets","volume-title":"Proceedings of the 18th International Conference on Artificial Intelligence and Statistics","author":"Lee","year":"2015"},{"issue":"5","key":"2023070408364926100_bib25","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1109\/TEVC.2020.2979740","article-title":"Boosting data-driven evolutionary algorithm with localized data generation","volume":"24","author":"Li","year":"2020","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"2023070408364926100_bib26","doi-asserted-by":"crossref","first-page":"2338","DOI":"10.1109\/TNNLS.2021.3106399","article-title":"Surrogate-assisted hybrid-model estimation of distribution algorithm for mixed-variable hyperparameters optimization in convolutional neural networks","volume":"34","author":"Li","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2023070408364926100_bib24","doi-asserted-by":"crossref","first-page":"3624","DOI":"10.1109\/TCYB.2022.3158391","article-title":"Dual differential grouping: A more general decomposition method for large-scale optimization","volume":"53","author":"Li","year":"2023","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"1","key":"2023070408364926100_bib27","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s11633-022-1317-4","article-title":"Evolutionary computation for expensive optimization: A survey","volume":"19","author":"Li","year":"2022","journal-title":"Machine Intelligence Research"},{"key":"2023070408364926100_bib28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.4400","article-title":"Network in network","author":"Lin","year":"2013"},{"key":"2023070408364926100_bib29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2206.07229","article-title":"Accurate emotion strength assessment for seen and unseen speech based on data-driven deep learning","author":"Liu","year":"2022"},{"issue":"2","key":"2023070408364926100_bib30","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1109\/TEVC.2020.3024708","article-title":"Multiobjective evolutionary design of deep convolutional neural networks for image classification","volume":"25","author":"Lu","year":"2020","journal-title":"IEEE Transactions on Evolutionary Computation"},{"issue":"2","key":"2023070408364926100_bib31","doi-asserted-by":"crossref","first-page":"1567","DOI":"10.1016\/j.amc.2006.11.033","article-title":"An improved harmony search algorithm for solving optimization problems","volume":"188","author":"Mahdavi","year":"2007","journal-title":"Applied Mathematics and Computation"},{"issue":"2","key":"2023070408364926100_bib32","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1016\/j.amc.2007.09.004","article-title":"Global-best harmony search","volume":"198","author":"Omran","year":"2008","journal-title":"Applied Mathematics & Computation"},{"issue":"3","key":"2023070408364926100_bib33","doi-asserted-by":"crossref","first-page":"830","DOI":"10.1016\/j.amc.2010.01.088","article-title":"A self-adaptive global best harmony search algorithm for continuous optimization problems","volume":"216","author":"Pan","year":"2010","journal-title":"Applied Mathematics and Computation"},{"key":"2023070408364926100_bib34","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1007\/s11831-021-09587-6","article-title":"A comprehensive overview of image enhancement techniques","volume":"29","author":"Qi","year":"2022","journal-title":"Archives of Computational Methods in Engineering"},{"issue":"1","key":"2023070408364926100_bib35","first-page":"72","article-title":"A comparison between genetic algorithms and evolutionary programming based on cutting stock problem","volume":"14","author":"Raymond","year":"2007","journal-title":"Engineering Letters"},{"key":"2023070408364926100_bib36","first-page":"2902","article-title":"Large-scale evolution of image classifiers","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Real","year":"2017"},{"key":"2023070408364926100_bib37","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"CoRR","author":"Simonyan","year":"2014"},{"key":"2023070408364926100_bib39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6806","article-title":"Striving for simplicity: The all convolutional net","author":"Springenberg","year":"2014"},{"issue":"1","key":"2023070408364926100_bib40","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1162\/evco_a_00253","article-title":"Evolution of deep convolutional neural networks using cartesian genetic programming","volume":"28","author":"Suganuma","year":"2020","journal-title":"Evolutionary Computation"},{"issue":"2","key":"2023070408364926100_bib41","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1109\/TEVC.2019.2916183","article-title":"Evolving deep convolutional neural networks for image classification","volume":"24","author":"Sun","year":"2019","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"2023070408364926100_bib43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/CVPR.2015.7298594","article-title":"Going deeper with convolutions","volume-title":"Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Szegedy","year":"2014"},{"key":"2023070408364926100_bib44","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Tan","year":"2019"},{"key":"2023070408364926100_bib45","doi-asserted-by":"crossref","first-page":"1926","DOI":"10.1016\/j.procs.2014.05.177","article-title":"A hybrid harmony search algorithm for solving dynamic optimisation problems","volume":"29","author":"Turky","year":"2014","journal-title":"Procedia Computer Science"},{"key":"2023070408364926100_bib38","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1109\/ICFHR.2016.0028","article-title":"Deep knowledge training and heterogeneous CNN for handwritten Chinese text recognition","volume-title":"Proceedings of the 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR)","author":"Wang","year":"2016"},{"key":"2023070408364926100_bib47","first-page":"1","article-title":"Scale adaptive fitness evaluation-based particle swarm optimisation for hyperparameter and architecture optimisation in neural networks and deep learning","author":"Wang","year":"2022","journal-title":"CAAI Transactions on Intelligence Technology"},{"key":"2023070408364926100_bib48","doi-asserted-by":"crossref","DOI":"10.1109\/TEVC.2022.3185665","article-title":"Gene targeting differential evolution: A simple and efficient method for large scale optimization","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Evolutionary Computation"},{"issue":"8","key":"2023070408364926100_bib46","doi-asserted-by":"crossref","first-page":"3727","DOI":"10.1109\/TNNLS.2021.3054400","article-title":"Surrogate-assisted particle swarm optimization for evolving variable-length transferable blocks for image classification","volume":"33","author":"Wang","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"3","key":"2023070408364926100_bib49","doi-asserted-by":"crossref","first-page":"1175","DOI":"10.1109\/TCYB.2020.2977956","article-title":"Adaptive granularity learning distributed particle swarm optimization for large-scale optimization","volume":"51","author":"Wang","year":"2020","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"3","key":"2023070408364926100_bib50","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/TEVC.2021.3051608","article-title":"SAFE: Scale-adaptive fitness evaluation method for expensive optimization problems","volume":"25","author":"Wu","year":"2021","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"2023070408364926100_bib51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1708.07747","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"2023070408364926100_bib53","first-page":"4845","article-title":"Very deep convolutional networks for end-to-end speech recognition","volume-title":"Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Yu","year":"2017"},{"key":"2023070408364926100_bib55","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/s10462-021-10042-y","article-title":"A survey on evolutionary computation for complex continuous optimization","volume":"55","author":"Zhan","year":"2022","journal-title":"Artificial Intelligence Review"},{"key":"2023070408364926100_bib54","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.neucom.2022.01.099","article-title":"Evolutionary deep learning: A survey","volume":"483","author":"Zhan","year":"2022","journal-title":"Neurocomputing"},{"key":"2023070408364926100_bib56","first-page":"37","article-title":"Recent advances in convolutional neural network acceleration","volume":"325","author":"Zhang","year":"2018","journal-title":"Neurocomputing"},{"key":"2023070408364926100_bib57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1611.01578","article-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2016"}],"container-title":["Journal of Computational Design and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jcde\/advance-article-pdf\/doi\/10.1093\/jcde\/qwad050\/50624903\/qwad050.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/10\/4\/1280\/50793894\/qwad050.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/10\/4\/1280\/50793894\/qwad050.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T11:35:32Z","timestamp":1688470532000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcde\/article\/10\/4\/1280\/7199167"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,15]]},"references-count":56,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,7,4]]}},"URL":"https:\/\/doi.org\/10.1093\/jcde\/qwad050","relation":{},"ISSN":["2288-5048"],"issn-type":[{"value":"2288-5048","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,8]]},"published":{"date-parts":[[2023,6,15]]}}}