{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T12:31:46Z","timestamp":1753878706868,"version":"3.41.2"},"reference-count":26,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T00:00:00Z","timestamp":1663545600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>On\u2010board training of artificial neural network (ANN) is important in instances where real time data are required for model training. Provision of on\u2010board intelligence enables the developed systems to self\u2010recalibrate and enhances their efficiencies. In this work, investigations have been performed to determine optimized parameters of ANN model for linear systems. The performance parameters that is, model parameters, memory requirements, accuracy and processing time are chosen by considering the model to be installed on commercially available microcontrollers that have very limited on\u2010board memory. Minimum data requirements for training ANN models of linear systems are also explored for better performance. All dataset ranges are normalized in order to exclude the effects of range differences. It is shown that for linear systems, 1\u20133\u20131 architecture produces best results against \u2264100 data points when Bayesian Regularization (BR) training function is used along with Log Sigmoid Activation function. Simulations for 1\u20133\u20131 architecture are then performed for datasets having 10, 25, 50 and 100 data points. The results show that training with 25 data points produces over\u2010all better performance than other datasets. A large dataset utilizes more training time and memory whereas a smaller dataset produces relatively lesser accuracy. The effects of clustered data and uniformly distributed data are also explored. It is found that total epochs in case of clustered data are significantly higher than uniformly distributed data. The combination of these optimized parameters that is, 1\u20133\u20131 architecture, with BR and Log function, for \u2264100 data points can be used for the development and implementation of linear components or systems in resource\u2010constrained embedded systems.<\/jats:p>","DOI":"10.1111\/exsy.13142","type":"journal-article","created":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T03:48:25Z","timestamp":1663645705000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Artificial neural network and dataset optimization for implementation of linear system models in resource\u2010constrained embedded systems"],"prefix":"10.1111","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8523-1665","authenticated-orcid":false,"given":"Abdul","family":"Sami","sequence":"first","affiliation":[{"name":"Department of Physics GC University Lahore  Lahore Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8539-1260","authenticated-orcid":false,"given":"Ali","family":"Asif","sequence":"additional","affiliation":[{"name":"Department of Physics GC University Lahore  Lahore Pakistan"}]},{"given":"Muhammad","family":"Imran","sequence":"additional","affiliation":[{"name":"Department of Physics GC University Lahore  Lahore Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0264-7962","authenticated-orcid":false,"given":"Farah","family":"Aziz","sequence":"additional","affiliation":[{"name":"Department of Physics GC University Lahore  Lahore Pakistan"}]},{"given":"Muhammad Yasir","family":"Noor","sequence":"additional","affiliation":[{"name":"Department of Physics GC University Lahore  Lahore Pakistan"}]}],"member":"311","published-online":{"date-parts":[[2022,9,19]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8010033"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.18178\/JOCET.2017.5.6.416"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.3390\/s18082561"},{"key":"e_1_2_9_5_1","doi-asserted-by":"crossref","unstructured":"Awasthi A. Ugalen R. Kumar A.(2020).ANN based robust control of linear induction motor Proceedings of the ECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society. pp.870\u2013875.","DOI":"10.1109\/IECON43393.2020.9255408"},{"key":"e_1_2_9_6_1","unstructured":"Baghirli O(2015).Comparison of lavernberg\u2010marquart scaled conjugate gradient and Bayesian regularization backpropagation algorithms for multistrp ahead wind speed forecasting using multilayer perceptron feedforward neural network[Unpublished Master thesis]."},{"issue":"1","key":"e_1_2_9_7_1","first-page":"1","article-title":"Design and development of microcontroller based instrumentation for studying complex bioelectrical impedance of fruits using electrical impedance spectroscopy","volume":"41","author":"Chowdhury A.","year":"2017","journal-title":"Journal of Food Process Engineering"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2010.2098377"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/int.22161"},{"key":"e_1_2_9_10_1","first-page":"53","article-title":"An optimization method of hidden nodes for neural network","author":"Gao P.","year":"2010","journal-title":"Second International Workshop on Education Technology and Computer Science"},{"key":"e_1_2_9_11_1","unstructured":"Haim L. Biri A. Qu Z.(2021).Thiele L.Measuring what really matters: Optimizing neural networks for Tinyml arXiv preprint arXiv:2104.10645."},{"key":"e_1_2_9_12_1","first-page":"27","volume-title":"Artificial neural networks\u2010models and applications","author":"Hayrettin O.","year":"2016"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.21307\/ijssis-2019-007"},{"key":"e_1_2_9_14_1","first-page":"449","article-title":"Comparative analysis on hidden neurons estimation in multi layer perceptron neural networks for wind speed forecasting","volume":"48","author":"Madhiarasan M.","year":"2016","journal-title":"Cross Mark"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19081814"},{"key":"e_1_2_9_16_1","doi-asserted-by":"crossref","unstructured":"MenacerF KadriA DjeffalF DibiZ(2017).Modeling and investigation of smart capacitive pressure sensor using artificial neural networks.Proceedings of the 6th international conference on systems and control pp.455\u2013460.","DOI":"10.1109\/ICoSC.2017.7958746"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.yamp.2019.07.010"},{"key":"e_1_2_9_18_1","doi-asserted-by":"crossref","unstructured":"Quintero D. A. Claro H. Regino F. Gomez J. A.(2019).Development of a data acquisition system using LabVIEW and arduino microcontroller for a centrifugal pump test bench connected in series and parallel.Proceedings of the 5th International meeting of Technological Innovation. pp.1\u20138.","DOI":"10.1088\/1742-6596\/1257\/1\/012002"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3036853"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1111\/ext.12011"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.3390\/jlpea2040265"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.3390\/s7081509"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06014-6"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2540582"},{"key":"e_1_2_9_25_1","doi-asserted-by":"crossref","unstructured":"Thomas A. J. Petridis M. WaltersD.S Walters S. D. Gheytassi S. M. Morgan R. E. (2017).Two hidden layers are usually better than one.Proceedings of the International conference on engineering applications of neural networks pp.279\u2013290.","DOI":"10.1007\/978-3-319-65172-9_24"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.18178\/ijmlc.2016.6.5.605"},{"key":"e_1_2_9_27_1","unstructured":"Venzke M. Klisch D. Kubik P. Ali A. Missier J. D. (2020).Artificial neural networks for sensor data classification on small embedded systems.1\u201321."}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.13142","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.13142","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.13142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T02:14:35Z","timestamp":1733192075000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.13142"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,19]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1111\/exsy.13142"],"URL":"https:\/\/doi.org\/10.1111\/exsy.13142","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"type":"print","value":"0266-4720"},{"type":"electronic","value":"1468-0394"}],"subject":[],"published":{"date-parts":[[2022,9,19]]},"assertion":[{"value":"2022-01-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e13142"}}