乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T22:07:13Z","timestamp":1740175633852,"version":"3.37.3"},"reference-count":43,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T00:00:00Z","timestamp":1673308800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"Deep feedforward neural networks (DFNNs) have attained remarkable success in almost every computational task. However, the selection of DFNN architecture is still based on handcraft or hit-and-trial methods. Therefore, an essential factor regarding DFNN is about designing its architecture. Unfortunately, creating architecture for DFNN is a very laborious and time-consuming task for performing state-of-art work. This article proposes a new hybrid methodology (BatTS) to optimize the DFNN architecture based on its performance. BatTS is a result of integrating the Bat algorithm, Tabu search (TS), and Gradient descent with a momentum backpropagation training algorithm (GDM). The main features of the BatTS are the following: a dynamic process of finding new architecture based on Bat, the skill to escape from local minima, and fast convergence in evaluating new architectures based on the Tabu search feature. The performance of BatTS is compared with the Tabu search based approach and random trials. The process goes through an empirical evaluation of four different benchmark datasets and shows that the proposed hybrid methodology has improved performance over existing techniques which are mainly random trials.<\/jats:p>","DOI":"10.7717\/peerj-cs.1194","type":"journal-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T08:07:32Z","timestamp":1673338052000},"page":"e1194","source":"Crossref","is-referenced-by-count":3,"title":["BatTS: a hybrid method for optimizing deep feedforward neural network"],"prefix":"10.7717","volume":"9","author":[{"given":"Sichen","family":"Pan","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, Guangdong Province, China"}]},{"given":"Tarun Kumar","family":"Gupta","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Jamia Millia Islamia, New Delhi, Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3646-6828","authenticated-orcid":true,"given":"Khalid","family":"Raza","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Jamia Millia Islamia, New Delhi, Delhi, India"}]}],"member":"4443","published-online":{"date-parts":[[2023,1,10]]},"reference":[{"issue":"6","key":"10.7717\/peerj-cs.1194\/ref-1","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1109\/TAC.1974.1100705","article-title":"A new look at the statistical model identification","volume":"19","author":"Akaike","year":"1974","journal-title":"IEEE Transactions on Automatic Control"},{"issue":"2","key":"10.7717\/peerj-cs.1194\/ref-2","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1016\/S0893-6080(98)00117-8","article-title":"Model selection in neural networks","volume":"12","author":"Anders","year":"1999","journal-title":"Neural Networks"},{"issue":"2","key":"10.7717\/peerj-cs.1194\/ref-3","doi-asserted-by":"publisher","first-page":"974","DOI":"10.1016\/j.neucom.2015.10.036","article-title":"A new model selection strategy in time series forecasting with artificial neural networks: IHTS","volume":"174","author":"Aras","year":"2016","journal-title":"Neurocomputing"},{"issue":"3","key":"10.7717\/peerj-cs.1194\/ref-4","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s11063-011-9196-7","article-title":"A novel pruning algorithm for optimizing feedforward neural network of classification problems","volume":"34","author":"Augasta","year":"2011","journal-title":"Neural Processing Letters"},{"issue":"16","key":"10.7717\/peerj-cs.1194\/ref-5","doi-asserted-by":"publisher","first-page":"7591","DOI":"10.3390\/app11167591","article-title":"Comparative analysis of low discrepancy sequence-based initialization approaches using population-based algorithms for solving the global optimization problems","volume":"11","author":"Bangyal","year":"2021","journal-title":"Applied Sciences (Switzerland)"},{"article-title":"Particle swarm optimization of neural network architectures and weights","year":"2007","author":"Carvalho","key":"10.7717\/peerj-cs.1194\/ref-6"},{"volume-title":"ISOLET Dataset","year":"2019","author":"Dua","key":"10.7717\/peerj-cs.1194\/ref-7"},{"issue":"2","key":"10.7717\/peerj-cs.1194\/ref-8","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1162\/neco.1990.2.2.198","article-title":"The upstart algorithm: a method for constructing and training feedforward neural networks","volume":"2","author":"Frean","year":"1990","journal-title":"Neural Computation"},{"issue":"7\u20139","key":"10.7717\/peerj-cs.1194\/ref-9","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1016\/j.neucom.2005.12.017","article-title":"Applications of multi-objective structure optimization","volume":"69","author":"Gepperth","year":"2006","journal-title":"Neurocomputing"},{"issue":"5","key":"10.7717\/peerj-cs.1194\/ref-10","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1016\/0305-0548(86)90048-1","article-title":"Future paths for integer programming and links to artificial intelligence","volume":"13","author":"Glover","year":"1986","journal-title":"Computers and Operations Research"},{"issue":"1","key":"10.7717\/peerj-cs.1194\/ref-11","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/89.260355","article-title":"Introduction to the special issue on neural networks for speech processing","volume":"2","author":"Gorin","year":"1994","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"10.7717\/peerj-cs.1194\/ref-12","doi-asserted-by":"crossref","DOI":"10.1016\/B978-0-12-816086-2.00007-2","article-title":"Optimization of ANN architecture: a review on nature-inspired techniques","volume-title":"Machine Learning in Bio-Signal Analysis and Diagnostic Imaging","author":"Gupta","year":"2019"},{"issue":"3","key":"10.7717\/peerj-cs.1194\/ref-13","doi-asserted-by":"publisher","first-page":"2855","DOI":"10.1007\/s11063-020-10234-7","article-title":"Optimizing deep feedforward neural network architecture: a tabu search based approach","volume":"51","author":"Gupta","year":"2020","journal-title":"Neural Processing Letters"},{"key":"10.7717\/peerj-cs.1194\/ref-14","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1007\/978-3-030-96308-8_26","article-title":"Optimization of artificial neural network: a bat algorithm-based approach","volume-title":"Intelligent Systems Design and Applications","volume":"418","author":"Gupta","year":"2022"},{"issue":"3","key":"10.7717\/peerj-cs.1194\/ref-15","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/j.neucom.2012.07.023","article-title":"A structure optimisation algorithm for feedforward neural network construction","volume":"99","author":"Han","year":"2013","journal-title":"Neurocomputing"},{"issue":"6","key":"10.7717\/peerj-cs.1194\/ref-16","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1109\/79.637299","article-title":"The past, present, and future of neural networks for signal processing: the neural networks for signal processing technical committee","volume":"14","author":"Hwang","year":"1997","journal-title":"IEEE Signal Processing Magazine"},{"issue":"6","key":"10.7717\/peerj-cs.1194\/ref-17","doi-asserted-by":"publisher","first-page":"1590","DOI":"10.1109\/TSMCB.2009.2021849","article-title":"A new constructive algorithm for architectural and functional adaptation of artificial neural networks","volume":"39","author":"Islam","year":"2009","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics"},{"key":"10.7717\/peerj-cs.1194\/ref-18","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1016\/j.ins.2014.08.050","article-title":"Multi-population cooperative bat algorithm-based optimization of artificial neural network model","volume":"294","author":"Jaddi","year":"2015a","journal-title":"Information Sciences"},{"key":"10.7717\/peerj-cs.1194\/ref-19","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.asoc.2015.08.002","article-title":"Optimization of neural network model using modified bat-inspired algorithm","volume":"37","author":"Jaddi","year":"2015b","journal-title":"Applied Soft Computing Journal"},{"issue":"1","key":"10.7717\/peerj-cs.1194\/ref-20","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.ipl.2015.08.001","article-title":"A solution representation of genetic algorithm for neural network weights and structure","volume":"116","author":"Jaddi","year":"2016","journal-title":"Information Processing Letters"},{"issue":"1","key":"10.7717\/peerj-cs.1194\/ref-21","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/34.824819","article-title":"Statistical pattern recognition: a review","volume":"22","author":"Jain","year":"2000","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.1194\/ref-22","article-title":"Discrete binary version of the particle swarm algorithm","volume":"5","author":"Kennedy","year":"1997"},{"issue":"3","key":"10.7717\/peerj-cs.1194\/ref-23","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/0925-2312(94)00013-I","article-title":"Optimal design of neural networks using the Taguchi method","volume":"7","author":"Khaw","year":"1995","journal-title":"Neurocomputing"},{"issue":"3","key":"10.7717\/peerj-cs.1194\/ref-24","doi-asserted-by":"publisher","first-page":"348","DOI":"10.3390\/e24030348","article-title":"Neural network structure optimization by simulated annealing","volume":"24","author":"Kuo","year":"2022","journal-title":"Entropy"},{"article-title":"MNIST handwritten digit database","year":"2010","author":"LeCun","key":"10.7717\/peerj-cs.1194\/ref-25"},{"article-title":"Improved algorithm of the back propagation neural network and its application in fault diagnosis of air-cooling condenser","year":"2009","author":"Li","key":"10.7717\/peerj-cs.1194\/ref-26"},{"issue":"6","key":"10.7717\/peerj-cs.1194\/ref-27","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TNN.2006.881047","article-title":"An optimization methodology for neural network weights and architectures","volume":"17","author":"Ludermir","year":"2006","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"4","key":"10.7717\/peerj-cs.1194\/ref-28","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.3758\/s13428-014-0532-5","article-title":"The Chicago face database: a free stimulus set of faces and norming data","volume":"47","author":"Ma","year":"2015","journal-title":"Behavior Research Methods"},{"issue":"12","key":"10.7717\/peerj-cs.1194\/ref-29","doi-asserted-by":"publisher","first-page":"2191","DOI":"10.1088\/0305-4470\/22\/12\/019","article-title":"Learning in feedforward layered networks: the tiling algorithm","volume":"22","author":"M\u00e9zard","year":"1989","journal-title":"Journal of Physics A: Mathematical and General"},{"issue":"6","key":"10.7717\/peerj-cs.1194\/ref-30","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1109\/72.329683","article-title":"Network information criterion\u2014determining the number of hidden units for an artificial neural network model","volume":"5","author":"Murata","year":"1994","journal-title":"IEEE Transactions on Neural Networks"},{"key":"10.7717\/peerj-cs.1194\/ref-31","doi-asserted-by":"publisher","first-page":"5990999","DOI":"10.1155\/2021\/5990999","article-title":"A systematic literature review on particle swarm optimization techniques for medical diseases detection","volume":"2021","author":"Pervaiz","year":"2021","journal-title":"Computational and Mathematical Methods in Medicine"},{"issue":"5","key":"10.7717\/peerj-cs.1194\/ref-32","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1504\/IJBRA.2015.071940","article-title":"A comprehensive evaluation of machine learning techniques for cancer class prediction based on microarray data","volume":"11","author":"Raza","year":"2015","journal-title":"International Journal of Bioinformatics Research and Applications"},{"issue":"4","key":"10.7717\/peerj-cs.1194\/ref-33","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.chemolab.2013.10.012","article-title":"On the calibration of sensor arrays for pattern recognition using the minimal number of experiments","volume":"130","author":"Rodriguez-Lujan","year":"2014","journal-title":"Chemometrics and Intelligent Laboratory Systems"},{"issue":"2","key":"10.7717\/peerj-cs.1194\/ref-34","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1214\/aos\/1176344136","article-title":"Estimating the dimension of a model","volume":"6","author":"Schwarz","year":"2007","journal-title":"The Annals of Statistics"},{"issue":"3","key":"10.7717\/peerj-cs.1194\/ref-35","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1109\/TNN.2002.1000141","article-title":"Neural-network approximation of piecewise continuous functions: Application to friction compensation","volume":"13","author":"Selmic","year":"2002","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"1","key":"10.7717\/peerj-cs.1194\/ref-36","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1016\/j.physa.2007.07.064","article-title":"The investigation of model selection criteria in artificial neural networks by the Taguchi method","volume":"386","author":"Tortum","year":"2007","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"issue":"1\u20133","key":"10.7717\/peerj-cs.1194\/ref-37","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.snb.2012.01.074","article-title":"Chemical gas sensor drift compensation using classifier ensembles","volume":"166\u2013167","author":"Vergara","year":"2012","journal-title":"Sensors and Actuators, B: Chemical"},{"key":"10.7717\/peerj-cs.1194\/ref-38","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/978-3-642-12538-6","article-title":"A new metaheuristic bat-inspired algorithm","volume":"284","author":"Yang","year":"2010","journal-title":"Studies in Computational Intelligence"},{"issue":"4\u20136","key":"10.7717\/peerj-cs.1194\/ref-39","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.1016\/j.neucom.2007.10.013","article-title":"Evolving artificial neural networks using an improved PSO and DPSO","volume":"71","author":"Yu","year":"2008","journal-title":"Neurocomputing"},{"issue":"3","key":"10.7717\/peerj-cs.1194\/ref-40","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/s11063-007-9053-x","article-title":"An improved particle swarm optimization for evolving feedforward artificial neural networks","volume":"26","author":"Yu","year":"2007","journal-title":"Neural Processing Letters"},{"issue":"4","key":"10.7717\/peerj-cs.1194\/ref-41","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1109\/TSMCB.2011.2107035","article-title":"Hybrid training method for MLP: optimization of architecture and training","volume":"41","author":"Zanchettin","year":"2011","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics"},{"issue":"7\u20139","key":"10.7717\/peerj-cs.1194\/ref-42","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1016\/j.neucom.2005.04.010","article-title":"Hidden neuron pruning of multilayer perceptrons using a quantified sensitivity measure","volume":"69","author":"Zeng","year":"2006","journal-title":"Neurocomputing"},{"issue":"4","key":"10.7717\/peerj-cs.1194\/ref-43","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1109\/5326.897072","article-title":"Neural networks for classification: a survey","volume":"30","author":"Zhang","year":"2000","journal-title":"IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-1194.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1194.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1194.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1194.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T08:07:40Z","timestamp":1673338060000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-1194"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,10]]},"references-count":43,"alternative-id":["10.7717\/peerj-cs.1194"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.1194","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"type":"electronic","value":"2376-5992"}],"subject":[],"published":{"date-parts":[[2023,1,10]]},"article-number":"e1194"}}