{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:31:47Z","timestamp":1777703507751,"version":"3.51.4"},"reference-count":34,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2018,2,27]],"date-time":"2018-02-27T00:00:00Z","timestamp":1519689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2018,4,19]]},"abstract":"<jats:p>Artificial neural network (ANN) has been well applied in pattern recognition, classification and machine learning thanks to its high performance. Most ANNs are designed by a static structure whose weights are trained during a learning process by supervised or unsupervised methods. These training methods require a set of initial weights values, which are normally randomly generated, with different initial sets of weight values leading to different convergent ANNs for the same training set. Dealing with these drawbacks, a trend of dynamic ANN was invoked in the past year. However, they are either too complex or far from practical applications such as in the pathology predictor in binary multi-input multi-output (MIMO) problems, when the role of a symptom is considered as an agent, a pathology predictor\u2019s outcome is formed by action of active agents while other agents\u2019 activities seem to be ignored or have mirror effects. In this paper, we propose a new dynamic structural ANN for MIMO problems based on the dependency graph, which gives clear cause and result relationships between inputs and outputs. The new ANN has the dynamic structure of hidden layer as a directed graph showing the relation between input, hidden and output nodes. The properties of the new dynamic structural ANN are experienced with a pathology problem and its learning methods\u2019 performances are compared on a real well known dataset. The result shows that both approaches for structural learning process improve the quality of ANNs during learning iteration.<\/jats:p>","DOI":"10.3233\/jifs-171947","type":"journal-article","created":{"date-parts":[[2018,2,27]],"date-time":"2018-02-27T12:39:03Z","timestamp":1519735143000},"page":"2479-2490","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":48,"title":["Dynamic structural neural network"],"prefix":"10.1177","volume":"34","author":[{"given":"Cu Nguyen","family":"Giap","sequence":"first","affiliation":[{"name":"Faculty of Management Information System and E-Commerce, Thuong Mai University, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le Hoang","family":"Son","sequence":"additional","affiliation":[{"name":"Institute of Research and Development, Duy Tan University, Danang, Vietnam"},{"name":"VNU University of Science, Vietnam National University, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francisco","family":"Chiclana","sequence":"additional","affiliation":[{"name":"Centre for Computational Intelligence, School of Computer Science and Informatics, Faculty of Technology, De Montfort University, Leicester, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2018,2,27]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"AczonM. LedbetterD. HoL. GunnyA. FlynnA. WilliamsJ. and WetzelR. Dynamic mortality risk predictions in pediatric critical care using recurrent neural networks (2017) arXiv preprint arXiv:1701.06675."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.2478\/v10136-012-0031-x"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2016.01.003"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-012-1026-y"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69432-8_13"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40763-5_51"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2009.06.040"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.06.007"},{"key":"e_1_3_2_10_2","unstructured":"GauntA. JohnsonM. RiechertM. TarlowD. TomiokaR. VytiniotisD. and WebsterS. AMPNet: Asynchronous Model-Parallel Training for Dynamic Neural Networks (2017). arXiv preprint arXiv:1705.09786"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2008.11.027"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.11.022"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2011.02.014"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2011.2129544"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2674624"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2013.0175"},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","DOI":"10.1109\/TMTT.2017.2657501","article-title":"A wiener-type dynamic neural network approach to the modeling of nonlinear microwave devices","author":"Liu W.","year":"2017","unstructured":"LiuW., NaW., ZhuL., MaJ. and ZhangQ.J., A wiener-type dynamic neural network approach to the modeling of nonlinear microwave devices, IEEE Transactions on Microwave Theory and Techniques (2017).","journal-title":"IEEE Transactions on Microwave Theory and Techniques"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2451213"},{"key":"e_1_3_2_19_2","first-page":"1","article-title":"A comparative review of dynamic neural networks and hidden Markov model methods for mobile on-device speech recognition","author":"Mustafa M.K.","year":"2017","unstructured":"MustafaM.K., AllenT. and AppiahK., A comparative review of dynamic neural networks and hidden Markov model methods for mobile on-device speech recognition, Neural Computing and Applications (2017), 1\u20139. doi: 10.1007\/s00521-017-3028-2","journal-title":"Neural Computing and Applications"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhydrol.2016.05.014"},{"key":"e_1_3_2_21_2","unstructured":"NeubigG. DyerC. GoldbergY. MatthewsA. AmmarW. AnastasopoulosA. and DuhK. DyNet: The Dynamic Neural Network Toolkit (2017). arXiv preprint arXiv:1701.03980."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2011.2144600"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.05.015"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2527501"},{"key":"e_1_3_2_25_2","article-title":"Metacognitive learning approach for online tool condition monitoring","author":"Pratama M.","year":"2017","unstructured":"PratamaM., DimlaE. and LughoferE., Metacognitive learning approach for online tool condition monitoring, Journal of Intelligent Manufacturing (2017). doi: 10.1007\/s10845-017-1348-9","journal-title":"Journal of Intelligent Manufacturing"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.10.093"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40815-016-0236-3"},{"key":"e_1_3_2_28_2","first-page":"8","article-title":"Quantitative analysis of diffusion weighted MR images of\u00a0brain tumor using signal intensity gradient technique","author":"Shanbhag S.S.","year":"2014","unstructured":"ShanbhagS.S., UdupiG.R., PatilK.M. and RanganathK., Quantitative analysis of diffusion weighted MR images of\u00a0brain tumor using signal intensity gradient technique, Journal of Medical Engineering (2014), pp. 8. Article ID 619081. doi: 10.1155\/2014\/619081","journal-title":"Journal of Medical Engineering"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2013.12.002"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.02.036"},{"key":"e_1_3_2_31_2","unstructured":"UCI 2015 \u201cHeart Attack dataset \u201d Available at: https:\/\/archive.ics.uci.edu\/ml\/datasets\/Heart+Disease (Accessed on: September 15 2015)."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2013.05.032"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-5225-2255-3.ch011"},{"key":"e_1_3_2_34_2","unstructured":"WittenI.H. FrankE. HallM.A. and PalC.J. Data Mining: Practical machine learning tools and techniques Morgan Kaufmann (2016)."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537340"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-171947","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-171947","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-171947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:38:48Z","timestamp":1777455528000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-171947"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,27]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,4,19]]}},"alternative-id":["10.3233\/JIFS-171947"],"URL":"https:\/\/doi.org\/10.3233\/jifs-171947","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2,27]]}}}