{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T03:02:38Z","timestamp":1783393358457,"version":"3.54.6"},"reference-count":108,"publisher":"Emerald","issue":"1","license":[{"start":{"date-parts":[[2019,11,27]],"date-time":"2019-11-27T00:00:00Z","timestamp":1574812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IMDS"],"published-print":{"date-parts":[[2019,11,27]]},"abstract":"<jats:sec><jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title><jats:p>The purpose of this paper is three-fold: to review the categories explaining mainly optimization algorithms (techniques) in that needed to improve the generalization performance and learning speed of the Feedforward Neural Network (FNN); to discover the change in research trends by analyzing all six categories (i.e. gradient learning algorithms for network training, gradient free learning algorithms, optimization algorithms for learning rate, bias and variance (underfitting and overfitting) minimization algorithms, constructive topology neural networks, metaheuristic search algorithms) collectively; and recommend new research directions for researchers and facilitate users to understand algorithms real-world applications in solving complex management, engineering and health sciences problems.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title><jats:p>The FNN has gained much attention from researchers to make a more informed decision in the last few decades. The literature survey is focused on the learning algorithms and the optimization techniques proposed in the last three decades. This paper (Part II) is an extension of Part I. For the sake of simplicity, the paper entitled \u201cMachine learning facilitated business intelligence (Part I): Neural networks learning algorithms and applications\u201d is referred to as Part I. To make the study consistent with Part I, the approach and survey methodology in this paper are kept similar to those in Part I.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Findings<\/jats:title><jats:p>Combining the work performed in Part I, the authors studied a total of 80 articles through popular keywords searching. The FNN learning algorithms and optimization techniques identified in the selected literature are classified into six categories based on their problem identification, mathematical model, technical reasoning and proposed solution. Previously, in Part I, the two categories focusing on the learning algorithms (i.e. gradient learning algorithms for network training, gradient free learning algorithms) are reviewed with their real-world applications in management, engineering, and health sciences. Therefore, in the current paper, Part II, the remaining four categories, exploring optimization techniques (i.e. optimization algorithms for learning rate, bias and variance (underfitting and overfitting) minimization algorithms, constructive topology neural networks, metaheuristic search algorithms) are studied in detail. The algorithm explanation is made enriched by discussing their technical merits, limitations, and applications in their respective categories. Finally, the authors recommend future new research directions which can contribute to strengthening the literature.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Research limitations\/implications<\/jats:title><jats:p>The FNN contributions are rapidly increasing because of its ability to make reliably informed decisions. Like learning algorithms, reviewed in Part I, the focus is to enrich the comprehensive study by reviewing remaining categories focusing on the optimization techniques. However, future efforts may be needed to incorporate other algorithms into identified six categories or suggest new category to continuously monitor the shift in the research trends.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Practical implications<\/jats:title><jats:p>The authors studied the shift in research trend for three decades by collectively analyzing the learning algorithms and optimization techniques with their applications. This may help researchers to identify future research gaps to improve the generalization performance and learning speed, and user to understand the applications areas of the FNN. For instance, research contribution in FNN in the last three decades has changed from complex gradient-based algorithms to gradient free algorithms, trial and error hidden units fixed topology approach to cascade topology, hyperparameters initial guess to analytically calculation and converging algorithms at a global minimum rather than the local minimum.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title><jats:p>The existing literature surveys include comparative study of the algorithms, identifying algorithms application areas and focusing on specific techniques in that it may not be able to identify algorithms categories, a shift in research trends over time, application area frequently analyzed, common research gaps and collective future directions. Part I and II attempts to overcome the existing literature surveys limitations by classifying articles into six categories covering a wide range of algorithm proposed to improve the FNN generalization performance and convergence rate. The classification of algorithms into six categories helps to analyze the shift in research trend which makes the classification scheme significant and innovative.<\/jats:p><\/jats:sec>","DOI":"10.1108\/imds-06-2019-0351","type":"journal-article","created":{"date-parts":[[2020,1,10]],"date-time":"2020-01-10T04:28:38Z","timestamp":1578630518000},"page":"128-163","source":"Crossref","is-referenced-by-count":32,"title":["Machine learning facilitated business intelligence (Part II)"],"prefix":"10.1108","volume":"120","author":[{"given":"Waqar Ahmed","family":"Khan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S.H.","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Usman","family":"Awan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0279-6869","authenticated-orcid":false,"given":"Xin","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"140","reference":[{"issue":"10","key":"key2020011009265393700_ref001","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","article-title":"Convolutional neural networks for speech recognition","volume":"22","year":"2014","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"key2020011009265393700_ref002","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1016\/j.patcog.2017.09.040","article-title":"A deep convolutional neural network for video sequence background subtraction","volume":"76","year":"2018","journal-title":"Pattern Recognition"},{"issue":"8","key":"key2020011009265393700_ref003","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1109\/TNNLS.2013.2293637","article-title":"On the complexity of neural network classifiers: A comparison between shallow and deep architectures","volume":"25","year":"2014","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"4","key":"key2020011009265393700_ref004","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1108\/IMDS-04-2018-0164","article-title":"Modelling wholesale distribution operations: an artificial intelligence framework","volume":"119","year":"2019","journal-title":"Industrial Management & Data Systems"},{"key":"key2020011009265393700_ref005","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1016\/j.ins.2015.09.002","article-title":"An iterative learning algorithm for feedforward neural networks with random weights","volume":"328","year":"2016","journal-title":"Information Sciences"},{"issue":"4","key":"key2020011009265393700_ref006","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"4","key":"key2020011009265393700_ref007","first-page":"730","article-title":"Sustainable fashion supply chain management: a system of systems analysis","volume":"66","year":"2018","journal-title":"IEEE Transactions on Engineering Management"},{"issue":"8","key":"key2020011009265393700_ref008","first-page":"1443","article-title":"Cascading delay risk of airline workforce deployments with crew pairing and schedule optimization","volume":"37","year":"2017","journal-title":"Risk Analysis, Wiley Online Library"},{"key":"key2020011009265393700_ref009","first-page":"1","article-title":"Reliability analysis of chatter stability for milling process system with uncertainties based on neural network and fourth moment method","year":"2019","journal-title":"International Journal of Production Research"},{"issue":"2","key":"key2020011009265393700_ref010","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/s10462-011-9208-z","article-title":"An optimizing BP neural network algorithm based on genetic algorithm","volume":"36","year":"2011","journal-title":"Artificial Intelligence Review"},{"issue":"2","key":"key2020011009265393700_ref011","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","article-title":"Image super-resolution Using deep convolutional networks","volume":"38","year":"2016","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"key2020011009265393700_ref012","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"key2020011009265393700_ref013","first-page":"39","article-title":"A new optimizer using particle swarm theory","year":"1995"},{"key":"key2020011009265393700_ref014","volume-title":"An Empirical Study of Learning Speed in Back-Propagation Networks","year":"1988"},{"key":"key2020011009265393700_ref015","first-page":"524","article-title":"The cascade-correlation learning architecture","year":"1990","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"key2020011009265393700_ref016","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1080\/00031305.1981.10479358","article-title":"The GMDH algorithm of Ivakhnenko","volume":"35","year":"1981","journal-title":"The American Statistician"},{"issue":"8","key":"key2020011009265393700_ref017","doi-asserted-by":"crossref","first-page":"1352","DOI":"10.1109\/TNN.2009.2024147","article-title":"Error minimized extreme learning machine with growth of hidden nodes and incremental learning","volume":"20","year":"2009","journal-title":"IEEE Transactions Neural Networks"},{"issue":"1","key":"key2020011009265393700_ref018","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/TNN.2004.836233","article-title":"Smooth function approximation using neural networks","volume":"16","year":"2005","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"1","key":"key2020011009265393700_ref019","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/neco.1992.4.1.1","article-title":"Neural networks and the bias\/variance dilemma","volume":"4","year":"1992","journal-title":"Neural Computation"},{"issue":"1","key":"key2020011009265393700_ref020","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/34.107014","article-title":"On the problem of local minima in back propagation","volume":"14","year":"1992","journal-title":"IEEE Transactions on Pattern Analysis & Machine Intelligence"},{"issue":"6","key":"key2020011009265393700_ref021","doi-asserted-by":"crossref","first-page":"989","DOI":"10.1109\/72.329697","article-title":"Training feedforward networks with the Marquardt algorithm","volume":"5","year":"1994","journal-title":"IEEE Transactions on Neural Networks"},{"key":"key2020011009265393700_ref022","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.neucom.2016.09.092","article-title":"An improved incremental constructive single-hidden-layer feedforward networks for extreme learning machine based on particle swarm optimization","volume":"228","year":"2017","journal-title":"Neurocomputing"},{"key":"key2020011009265393700_ref023","unstructured":"Han, S., Pool, J., Tran, J. and Dally, W.J. (2015), \u201cLearning both weights and connections for efficient neural networks\u201d, in Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M. and Garnett, R. (Eds), Advances in Neural Information Processing Systems, MIT press, Montreal, pp. 1135-1143."},{"issue":"10","key":"key2020011009265393700_ref024","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1109\/34.58871","article-title":"Neural network ensembles","volume":"12","year":"1990","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"8","key":"key2020011009265393700_ref025","doi-asserted-by":"crossref","first-page":"856","DOI":"10.1016\/j.knosys.2010.05.010","article-title":"Understanding consumer heterogeneity: a business intelligence application of neural networks","volume":"23","year":"2010","journal-title":"Knowledge-Based Systems"},{"key":"key2020011009265393700_ref026","first-page":"593","article-title":"Theory of the back propagation neural network","year":"1989"},{"key":"key2020011009265393700_ref027","unstructured":"Hinton, G.E., Srivastava, N. and Swersky, K. (2012), \u201cLecture 6a \u2013 overview of mini-batch gradient descent\u201d, available at: www.cs.toronto.edu\/~tijmen\/csc321\/slides\/lecture_slides_lec6.pdf (accessed July 19, 2018)."},{"issue":"11","key":"key2020011009265393700_ref028","doi-asserted-by":"crossref","first-page":"2629","DOI":"10.1109\/TCSI.2012.2189060","article-title":"Orthogonal least squares algorithm for training cascade neural networks","volume":"59","year":"2012","journal-title":"IEEE Transactions on Circuits and Systems I: Regular Papers"},{"key":"key2020011009265393700_ref029","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.neunet.2014.10.001","article-title":"Trends in extreme learning machines: a review","volume":"61","year":"2015","journal-title":"Neural Networks"},{"issue":"16-18","key":"key2020011009265393700_ref030","doi-asserted-by":"crossref","first-page":"3056","DOI":"10.1016\/j.neucom.2007.02.009","article-title":"Convex incremental extreme learning machine","volume":"70","year":"2007","journal-title":"Neurocomputing"},{"issue":"16\u201318","key":"key2020011009265393700_ref031","first-page":"3460","article-title":"Enhanced random search based incremental extreme learning machine","volume":"71","year":"2008","journal-title":"Neurocomputing"},{"issue":"4","key":"key2020011009265393700_ref032","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1109\/TNN.2006.875977","article-title":"Universal approximation using incremental constructive feedforward networks with random hidden nodes","volume":"17","year":"2006","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"1\u20133","key":"key2020011009265393700_ref033","first-page":"489","article-title":"Extreme learning machine: theory and applications","volume":"70","year":"2006","journal-title":"Neurocomputing"},{"issue":"2","key":"key2020011009265393700_ref034","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1109\/TSMCB.2011.2168604","article-title":"Extreme learning machine for regression and multiclass classification","volume":"42","year":"2012","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics"},{"issue":"2","key":"key2020011009265393700_ref035","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1109\/TII.2012.2187914","article-title":"Selection of proper neural network sizes and architectures \u2013 a comparative study","volume":"8","year":"2012","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"2","key":"key2020011009265393700_ref036","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1109\/72.485631","article-title":"The cascade-correlation learning: a projection pursuit learning perspective","volume":"7","year":"1996","journal-title":"IEEE Transactions on Neural Networks"},{"key":"key2020011009265393700_ref037","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.patcog.2016.01.012","article-title":"Human action recognition using genetic algorithms and convolutional neural networks","volume":"59","year":"2016","journal-title":"Pattern Recognition"},{"key":"key2020011009265393700_ref038","unstructured":"Ioffe, S. and Szegedy, C. (2015), \u201cBatch normalization: accelerating deep network training by reducing internal covariate shift\u201d, available at: https:\/\/doi.org\/10.1007\/s13398-014-0173-7.2 (accessed August 6, 2018)."},{"issue":"4","key":"key2020011009265393700_ref039","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1109\/TNN.2003.813832","article-title":"A constructive algorithm for training cooperative neural network ensembles","volume":"14","year":"2003","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"5","key":"key2020011009265393700_ref040","first-page":"1245","article-title":"Shakeout: a new approach to regularized deep neural network training","volume":"40","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"key2020011009265393700_ref041","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1109\/72.80236","article-title":"A simple procedure for pruning back-propagation trained neural networks","volume":"1","year":"1990","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"5","key":"key2020011009265393700_ref042","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.1016\/j.ipm.2019.05.003","article-title":"The impact of deep learning on document classification using semantically rich representations","volume":"56","year":"2019","journal-title":"Information Processing & Management"},{"issue":"6","key":"key2020011009265393700_ref043","first-page":"31","article-title":"Representational learning with extreme learning machine for big data","volume":"28","year":"2013","journal-title":"IEEE Intelligent System"},{"issue":"1","key":"key2020011009265393700_ref044","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1108\/IMDS-07-2017-0317","article-title":"Business environmental analysis for textual data using data mining and sentence-level classification","volume":"119","year":"2019","journal-title":"Industrial Management & Data Systems"},{"key":"key2020011009265393700_ref045","article-title":"Adam: a method for stochastic optimization","year":"2014"},{"issue":"4","key":"key2020011009265393700_ref046","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1021\/ci980325n","article-title":"Neural network studies. 3: variable selection in the cascade-correlation learning architecture","volume":"38","year":"1998","journal-title":"Journal of Chemical Information and Computer Sciences"},{"key":"key2020011009265393700_ref047","unstructured":"Krogh, A. and Hertz, J.A. (1992), \u201cA simple weight decay can improve generalization\u201d, in Hanson, S.J., Cowan, J.D. and Giles, C.L. (Eds), Advances in Neural Information Processing Systems, Morgan Kaufmann, Denver, pp. 950-957."},{"key":"key2020011009265393700_ref048","first-page":"231","article-title":"Neural network ensembles, cross validation, and active learning","year":"1995","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"key2020011009265393700_ref049","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1007\/BF00996189","article-title":"An empirical comparison of neural network and logistic regression models","volume":"6","year":"1995","journal-title":"Marketing Letters"},{"issue":"6","key":"key2020011009265393700_ref050","doi-asserted-by":"crossref","first-page":"1242","DOI":"10.1108\/IMDS-11-2015-0463","article-title":"Thailand tourism forecasting based on a hybrid of discrete wavelet decomposition and NARX neural network","volume":"116","year":"2016","journal-title":"Industrial Management and Data Systems"},{"issue":"3","key":"key2020011009265393700_ref051","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1109\/72.572102","article-title":"Constructive algorithms for structure learning in feedforward neural networks for regression problems","volume":"8","year":"1997","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"5","key":"key2020011009265393700_ref052","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1108\/IMDS-08-2013-0329","article-title":"Customer relationship mining system for effective strategies formulation","volume":"114","year":"2014","journal-title":"Industrial Management & Data Systems"},{"key":"key2020011009265393700_ref053","first-page":"52","article-title":"Learning to tell two spirals apart","year":"1989"},{"issue":"7553","key":"key2020011009265393700_ref054","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","year":"2015","journal-title":"Nature"},{"issue":"3","key":"key2020011009265393700_ref055","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1109\/72.846749","article-title":"Modified cascade-correlation learning for classification","volume":"11","year":"2000","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"1-2","key":"key2020011009265393700_ref056","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/s10107-012-0514-2","article-title":"Nonsmooth optimization via quasi-Newton methods","volume":"141","year":"2013","journal-title":"Mathematical Programming"},{"issue":"9","key":"key2020011009265393700_ref057","doi-asserted-by":"crossref","first-page":"1804","DOI":"10.1108\/IMDS-12-2017-0582","article-title":"Multi-class Twitter sentiment classification with emojis","volume":"118","year":"2018","journal-title":"Industrial Management & Data Systems"},{"issue":"1-4","key":"key2020011009265393700_ref058","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0020-0255(97)10071-8","article-title":"Improvement of cascade correlation learning","volume":"112","year":"1998","journal-title":"Information Sciences"},{"issue":"6","key":"key2020011009265393700_ref059","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1109\/TNN.2006.880583","article-title":"A fast and accurate online sequential learning algorithm for feedforward networks","volume":"17","year":"2006","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"99","key":"key2020011009265393700_ref060","first-page":"6168","article-title":"L\u00e9vy flight trajectory-based whale optimization algorithm for global optimization","volume":"5","year":"2017","journal-title":"IEEE Access"},{"issue":"6","key":"key2020011009265393700_ref061","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1109\/TNN.2007.915114","article-title":"Optimized approximation algorithm in neural networks without overfitting","volume":"19","year":"2008","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"1","key":"key2020011009265393700_ref062","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/00401706.1990.10484583","article-title":"Exponentially weighted moving average control schemes: properties and enhancements","volume":"32","year":"1990","journal-title":"Technometrics, IEEE"},{"key":"key2020011009265393700_ref063","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.advengsoft.2016.01.008","article-title":"The whale optimization algorithm","volume":"95","year":"2016","journal-title":"Advances in Engineering Software"},{"key":"key2020011009265393700_ref064","doi-asserted-by":"crossref","unstructured":"Mitchell, M. (1998), \u201cGenetic algorithms: an overview\u201d, in Watson, T., Robbins, C., Belew, R.K., Wilson, S.W., Holland, J.H., Waltz, D.L., Koza, J.R. et al. (Eds), An Introduction to Genetic Algorithms, MIT Press, London, pp. 1-15.","DOI":"10.7551\/mitpress\/3927.003.0003"},{"issue":"1","key":"key2020011009265393700_ref065","first-page":"393","article-title":"An optimized ANN model based on genetic algorithm for predicting ripping production","volume":"28","year":"2017","journal-title":"Neural Computing and Applications"},{"key":"key2020011009265393700_ref066","doi-asserted-by":"crossref","first-page":"5577","DOI":"10.1109\/ACCESS.2018.2883957","article-title":"Neural network based brain tumor detection using wireless infrared imaging sensor","volume":"7","year":"2019","journal-title":"IEEE Access"},{"issue":"12","key":"key2020011009265393700_ref067","doi-asserted-by":"crossref","first-page":"10402","DOI":"10.1016\/j.eswa.2012.01.202","article-title":"Machine learning approach for finding business partners and building reciprocal relationships","volume":"39","year":"2012","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"key2020011009265393700_ref068","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1108\/IMDS-12-2017-0579","article-title":"A comparative data analytic approach to construct a risk trade-off for cardiac patients\u2019 re-admissions","volume":"119","year":"2019","journal-title":"Industrial Management & Data Systems"},{"issue":"9","key":"key2020011009265393700_ref069","doi-asserted-by":"crossref","first-page":"4515","DOI":"10.1109\/TNNLS.2017.2753725","article-title":"Universal approximation by using the correntropy objective function","volume":"29","year":"2018","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"key2020011009265393700_ref070","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/S0893-6080(98)00116-6","article-title":"On the momentum term in gradient descent learning algorithms","volume":"12","year":"1999","journal-title":"Neural Networks"},{"key":"key2020011009265393700_ref071","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1016\/j.neucom.2015.12.003","article-title":"Constructive algorithm for fully connected cascade feedforward neural networks","volume":"182","year":"2016","journal-title":"Neurocomputing"},{"issue":"5","key":"key2020011009265393700_ref072","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1109\/72.248452","article-title":"Pruning algorithms-a survey","volume":"4","year":"1993","journal-title":"IEEE Transactions on Neural Networks"},{"key":"key2020011009265393700_ref073","first-page":"586","article-title":"A direct adaptive method for faster backpropagation learning: the RPROP algorithm","year":"1993"},{"issue":"6088","key":"key2020011009265393700_ref074","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","year":"1986","journal-title":"Nature"},{"issue":"1","key":"key2020011009265393700_ref075","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1023\/A:1022935810223","article-title":"A learning algorithm for evolving cascade neural networks","volume":"17","year":"2003","journal-title":"Neural Processing Letters"},{"key":"key2020011009265393700_ref076","first-page":"21","article-title":"Model complexity, model selection and regularization","year":"2010","journal-title":"Ensemble Methods in Data Mining: Improving Accuracy Through Combining Predictions"},{"issue":"1","key":"key2020011009265393700_ref077","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1109\/72.363426","article-title":"Use of a quasi-Newton method in a feedforward neural network construction algorithm","volume":"6","year":"1995","journal-title":"IEEE Transactions on Neural Networks"},{"key":"key2020011009265393700_ref078","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.amc.2017.06.012","article-title":"Comparative analysis of GMDH neural network based on genetic algorithm and particle swarm optimization in stable channel design","volume":"313","year":"2017","journal-title":"Applied Mathematics and Computation"},{"issue":"111","key":"key2020011009265393700_ref079","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1090\/S0025-5718-1970-0274029-X","article-title":"Conditioning of quasi-Newton methods for function minimization","volume":"24","year":"1970","journal-title":"Mathematics of Computation"},{"issue":"1","key":"key2020011009265393700_ref080","first-page":"1740001-1","article-title":"Forecast information sharing for managing supply chains in the big data era: recent development and future research","volume":"34","year":"2017","journal-title":"Asia-Pacific Journal of Operational Research"},{"key":"key2020011009265393700_ref081","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1016\/j.techfore.2017.09.003","article-title":"Selling green first or not? A Bayesian analysis with service levels and environmental impact considerations in the Big Data Era","volume":"144","year":"2019","journal-title":"Technological Forecasting and Social Change"},{"issue":"15-16","key":"key2020011009265393700_ref082","doi-asserted-by":"crossref","first-page":"4898","DOI":"10.1080\/00207543.2018.1467062","article-title":"A review on supply chain contracting with information considerations: information updating and information asymmetry","volume":"57","year":"2019","journal-title":"International Journal of Production Research"},{"key":"key2020011009265393700_ref083","first-page":"69","article-title":"A modified particle swarm optimizer","year":"1998"},{"issue":"1","key":"key2020011009265393700_ref084","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/0893-6080(90)90049-Q","article-title":"Probabilistic neural networks","volume":"3","year":"1990","journal-title":"Neural Networks"},{"issue":"6","key":"key2020011009265393700_ref085","doi-asserted-by":"crossref","first-page":"568","DOI":"10.1109\/72.97934","article-title":"A general regression neural network","volume":"2","year":"1991","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"1","key":"key2020011009265393700_ref086","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","year":"2014","journal-title":"Journal of Machine Learning Research"},{"issue":"4","key":"key2020011009265393700_ref087","doi-asserted-by":"crossref","first-page":"809","DOI":"10.1109\/TNNLS.2015.2424995","article-title":"Extreme learning machine for multilayer perceptron","volume":"27","year":"2016","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"2","key":"key2020011009265393700_ref088","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1108\/IMDS-08-2014-0231","article-title":"The effects of convenience and speed in m-payment","volume":"115","year":"2015","journal-title":"Industrial Management & Data Systems"},{"key":"key2020011009265393700_ref089","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1016\/j.asoc.2015.09.040","article-title":"Artificial neural networks in business: two decades of research","volume":"38","year":"2016","journal-title":"Applied Soft Computing"},{"issue":"11","key":"key2020011009265393700_ref090","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1016\/S0895-4356(96)00002-9","article-title":"Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes","volume":"49","year":"1996","journal-title":"Journal of Clinical Epidemiology"},{"key":"key2020011009265393700_ref091","first-page":"109","article-title":"Regularization of neural networks using dropconnect","year":"2013"},{"issue":"2","key":"key2020011009265393700_ref092","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1007\/s00521-015-1874-3","article-title":"Self-adaptive extreme learning machine","volume":"27","year":"2016","journal-title":"Neural Computing and Applications"},{"issue":"1","key":"key2020011009265393700_ref093","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1504\/IJBIDM.2005.007318","article-title":"Support vector machines based on K-means clustering for real-time business intelligence systems","volume":"1","year":"2005","journal-title":"International Journal of Business Intelligence and Data Mining, Citeseer"},{"key":"key2020011009265393700_ref094","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.neunet.2017.06.003","article-title":"Accelerating deep neural network training with inconsistent stochastic gradient descent","volume":"93","year":"2017","journal-title":"Neural Networks"},{"key":"key2020011009265393700_ref095","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.neunet.2012.09.020","article-title":"The No-Prop algorithm: a new learning algorithm for multilayer neural networks","volume":"37","year":"2013","journal-title":"Neural Networks"},{"issue":"11","key":"key2020011009265393700_ref096","doi-asserted-by":"crossref","first-page":"1793","DOI":"10.1109\/TNN.2010.2073482","article-title":"Neural network learning without backpropagation","volume":"21","year":"2010","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"10","key":"key2020011009265393700_ref097","doi-asserted-by":"crossref","first-page":"3784","DOI":"10.1109\/TIE.2008.2003319","article-title":"Computing gradient vector and Jacobian matrix in arbitrarily connected neural networks","volume":"55","year":"2008","journal-title":"IEEE Transactions on Industrial Electronics"},{"issue":"10","key":"key2020011009265393700_ref098","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.1016\/S0893-6080(03)00138-2","article-title":"The general inefficiency of batch training for gradient descent learning","volume":"16","year":"2003","journal-title":"Neural Networks"},{"issue":"4","key":"key2020011009265393700_ref099","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1108\/IMDS-07-2017-0313","article-title":"Examining the key determinants towards online pro-brand and anti-brand community citizenship behaviours: a two-stage approach","volume":"118","year":"2018","journal-title":"Industrial Management & Data Systems, Emerald Publishing Limited"},{"issue":"9","key":"key2020011009265393700_ref100","doi-asserted-by":"crossref","first-page":"1498","DOI":"10.1109\/TNNLS.2012.2202289","article-title":"Bidirectional extreme learning machine for regression problem and its learning effectiveness","volume":"23","year":"2012","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"2","key":"key2020011009265393700_ref101","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1109\/TIP.2017.2765830","article-title":"Multi-task convolutional neural network for pose-invariant face recognition","volume":"27","year":"2018","journal-title":"IEEE Transactions on Image Processing"},{"issue":"1","key":"key2020011009265393700_ref102","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/s00521-014-1567-3","article-title":"Orthogonal incremental extreme learning machine for regression and multiclass classification","volume":"27","year":"2016","journal-title":"Neural Computing and Applications"},{"issue":"4","key":"key2020011009265393700_ref103","first-page":"531","article-title":"Historical development of the Newton\u2013Raphson method","volume":"37","year":"1995","journal-title":"SIAM Review, Society for Industrial and Applied Mathematics"},{"issue":"5","key":"key2020011009265393700_ref104","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1108\/02635570910957669","article-title":"Text classification: neural networks vs support vector machines","volume":"109","year":"2009","journal-title":"Industrial Management & Data Systems"},{"key":"key2020011009265393700_ref105","unstructured":"Zeiler, M.D. (2012), \u201cADADELTA: an adaptive learning rate method\u201d, available at: https:\/\/doi.org\/http:\/\/doi.acm.org.ezproxy.lib.ucf.edu\/10.1145\/1830483.1830503 (accessed August 6, 2018)."},{"issue":"2","key":"key2020011009265393700_ref106","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1016\/j.amc.2006.07.025","article-title":"A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training","volume":"185","year":"2007","journal-title":"Applied Mathematics and Computation"},{"key":"key2020011009265393700_ref107","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1016\/j.neucom.2012.08.010","article-title":"Weighted extreme learning machine for imbalance learning","volume":"101","year":"2013","journal-title":"Neurocomputing"},{"issue":"12","key":"key2020011009265393700_ref108","doi-asserted-by":"crossref","first-page":"3403","DOI":"10.1109\/TCYB.2018.2830338","article-title":"Fault diagnosis of Tennessee-Eastman process using orthogonal incremental extreme learning machine based on driving amount","volume":"48","year":"2018","journal-title":"IEEE Transactions on Cybernetics"}],"container-title":["Industrial Management &amp; Data Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IMDS-06-2019-0351\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IMDS-06-2019-0351\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T21:52:28Z","timestamp":1753393948000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/imds\/article\/120\/1\/128-163\/185277"}},"subtitle":["Neural networks optimization techniques and applications"],"short-title":[],"issued":{"date-parts":[[2019,11,27]]},"references-count":108,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,11,27]]}},"alternative-id":["10.1108\/IMDS-06-2019-0351"],"URL":"https:\/\/doi.org\/10.1108\/imds-06-2019-0351","relation":{},"ISSN":["0263-5577"],"issn-type":[{"value":"0263-5577","type":"print"}],"subject":[],"published":{"date-parts":[[2019,11,27]]}}}