{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:35:05Z","timestamp":1750224905308,"version":"3.37.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T00:00:00Z","timestamp":1722556800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T00:00:00Z","timestamp":1722556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007637","name":"German University in Cairo","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007637","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This paper proposes a solution to enhance and compare different neural network (NN)-based side-slip angle estimators. The feed-forward neural networks (FFNNs), recurrent neural networks, long short-term memory units (LSTMs), and gated recurrent units are investigated. However, there is a lack in the selection criteria of the architectures\u2019 hyper-parameters. Therefore, the genetic algorithm is integrated with the NN-based estimators to find the optimal hyper-parameters for the studied architectures. The tuned hyper-parameters in this work include the number of neurons, number of layers, activation function, optimizer type, and learning rate. The objective function of the optimization problem is minimizing the root-mean-square error (RMSE) on multiple testing data. The optimal models are further included in the design of a hybrid NN estimator with Kalman filter. In the hybrid estimators, the optimal NN estimators are used as virtual sensors to correct the prediction of the side-slip angle resulting from the mathematical lateral vehicle model. Eventually, the performance of the best selected model is evaluated in terms of different metrics; mean RMSE, mean error variance, mean training time, and mean estimation time. LSTMs are found to achieve the lowest mean RMSE while being tested on highly generalized data yielding the highest training and estimation time. However, FFNNs achieve the lowest RMSE while being tested on low generalized data and the lowest training and estimation time. Meanwhile, it is observed that the hybrid estimators achieved lower RMSE with great enhancement compared to the non-hybridized ones proving the effectiveness of the proposed approach and increasing the side-slip estimation generalization ability in unknown environments with high uncertainties, which are not covered by the training dataset for the NNs estimators.<\/jats:p>","DOI":"10.1007\/s00521-024-10115-3","type":"journal-article","created":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T15:03:31Z","timestamp":1722611011000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Utilization of genetic algorithm in tuning the hyper-parameters of hybrid NN-based side-slip angle estimators"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9950-7714","authenticated-orcid":false,"given":"Mohamed G.","family":"Essa","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1444-9816","authenticated-orcid":false,"given":"Catherine M.","family":"Elias","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3604-3534","authenticated-orcid":false,"given":"Omar M.","family":"Shehata","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,2]]},"reference":[{"key":"10115_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-94463-0","volume-title":"Neural networks and deep learning","author":"CC Aggarwal","year":"2018","unstructured":"Aggarwal CC et al (2018) Neural networks and deep learning. Cham, springer, pp 3"},{"issue":"9","key":"10115_CR2","doi-asserted-by":"publisher","first-page":"1497","DOI":"10.1080\/00423114.2010.527994","volume":"49","author":"S Antonov","year":"2011","unstructured":"Antonov S, Fehn A, Kugi A (2011) Unscented kalman filter for vehicle state estimation. Veh Syst Dyn 49(9):1497\u20131520","journal-title":"Veh Syst Dyn"},{"key":"10115_CR3","unstructured":"Bergstra J, Bardenet R, Bengio Y, K\u00e9gl B (2011) Algorithms for hyper-parameter optimization. Adv Neural Inf Process Syst 24"},{"key":"10115_CR4","unstructured":"Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13(2)"},{"key":"10115_CR5","doi-asserted-by":"crossref","unstructured":"Bertipaglia A, Alirezaei M, Happee R, Shyrokau B (2023) An unscented kalman filter-informed neural network for vehicle sideslip angle estimation. arXiv preprint arXiv:2303.05238","DOI":"10.1109\/TVT.2024.3389493"},{"issue":"24","key":"10115_CR6","doi-asserted-by":"publisher","first-page":"8435","DOI":"10.3390\/s21248435","volume":"21","author":"S Blume","year":"2021","unstructured":"Blume S, Benedens T, Schramm D (2021) Hyperparameter optimization techniques for designing software sensors based on artificial neural networks. Sensors 21(24):8435","journal-title":"Sensors"},{"key":"10115_CR7","doi-asserted-by":"crossref","unstructured":"Blume S, Sieberg PM, Maas N, Schramm D (2019) Neural roll angle estimation in a model predictive control system. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), IEEE, pp 1625\u20131630","DOI":"10.1109\/ITSC.2019.8917106"},{"key":"10115_CR8","volume-title":"Users guide version 8.1.1 IPG automotive","author":"I CarMaker","year":"2020","unstructured":"CarMaker I (2020) Users guide version 8.1.1 IPG automotive. Karlsruhe, Germany"},{"issue":"S1","key":"10115_CR9","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1080\/00423110801958550","volume":"46","author":"BC Chen","year":"2008","unstructured":"Chen BC, Hsieh FC (2008) Sideslip angle estimation using extended kalman filter. Veh Syst Dyn 46(S1):353\u2013364","journal-title":"Veh Syst Dyn"},{"key":"10115_CR10","doi-asserted-by":"crossref","unstructured":"Chindamo D, Gadola M (2018) Estimation of vehicle side-slip angle using an artificial neural network. In: MATEC web of conferences, vol. 166, p. 02001. EDP Sciences","DOI":"10.1051\/matecconf\/201816602001"},{"issue":"4","key":"10115_CR11","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1504\/IJVD.2014.066071","volume":"66","author":"N Ding","year":"2014","unstructured":"Ding N, Chen W, Zhang Y, Xu G, Gao F (2014) An extended luenberger observer for estimation of vehicle sideslip angle and road friction. Int J Veh Des 66(4):385\u2013414","journal-title":"Int J Veh Des"},{"key":"10115_CR12","doi-asserted-by":"crossref","unstructured":"Du X, Sun H, Qian K, Li Y, Lu L (2010) A prediction model for vehicle sideslip angle based on neural network. In: 2010 2nd IEEE International Conference on Information and Financial Engineering, IEEE, pp 451\u2013455","DOI":"10.1109\/ICIFE.2010.5609398"},{"key":"10115_CR13","doi-asserted-by":"crossref","unstructured":"Essa MG, Elias CM, Shehata OM (2021) Comprehensive performance assessment of various nn-based side-slip angle estimators (ann-sse). In: 2021 IEEE 93rd vehicular technology conference (VTC2021-Spring), IEEE, pp 1\u20136","DOI":"10.1109\/VTC2021-Spring51267.2021.9448647"},{"key":"10115_CR14","doi-asserted-by":"crossref","unstructured":"Gorgolis N, Hatzilygeroudis I, Istenes Z, Gyenne LG (2019) Hyperparameter optimization of lstm network models through genetic algorithm. In: 2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA), IEEE, pp 1\u20134","DOI":"10.1109\/IISA.2019.8900675"},{"issue":"1","key":"10115_CR15","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/TIV.2018.2886687","volume":"4","author":"T Gr\u00e4ber","year":"2018","unstructured":"Gr\u00e4ber T, Lupberger S, Unterreiner M, Schramm D (2018) A hybrid approach to side-slip angle estimation with recurrent neural networks and kinematic vehicle models. IEEE Trans Intell Veh 4(1):39\u201347","journal-title":"IEEE Trans Intell Veh"},{"key":"10115_CR16","doi-asserted-by":"publisher","first-page":"1324","DOI":"10.1016\/j.applthermaleng.2018.12.139","volume":"149","author":"Y Jo","year":"2019","unstructured":"Jo Y, Min K, Jung D, Sunwoo M, Han M (2019) Comparative study of the artificial neural network with three hyper-parameter optimization methods for the precise LP-EGR estimation using in-cylinder pressure in a turbocharged GDI engine. Appl Therm Eng 149:1324\u20131334","journal-title":"Appl Therm Eng"},{"key":"10115_CR17","doi-asserted-by":"crossref","unstructured":"Kim DJ, Kim JS, Lee SH, Chung CC (2019) A comparative study of estimating road surface condition using support vector machine and deep neural networ. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), IEEE, pp 1066\u20131071","DOI":"10.1109\/ITSC.2019.8916965"},{"key":"10115_CR18","doi-asserted-by":"crossref","unstructured":"Liang Y, M\u00fcller S, Rolle D, Ganesch D, Schaffer I (2020) Vehicle side-slip angle estimation with deep neural network and sensor data fusion. In: 10th International Munich Chassis Symposium 2019, Springer, pp 159\u2013178","DOI":"10.1007\/978-3-658-26435-2_15"},{"key":"10115_CR19","doi-asserted-by":"crossref","unstructured":"Liu W, Liu W, Ding H, Guo K (2012) Side-slip angle estimation for vehicle electronic stability control based on sliding mode observer. In: Proceedings of 2012 International Conference on Measurement, Information and Control vol 2, IEEE, pp 992\u2013995","DOI":"10.1109\/MIC.2012.6273468"},{"issue":"10","key":"10115_CR20","first-page":"252","volume":"9","author":"S Loussaief","year":"2018","unstructured":"Loussaief S, Abdelkrim A (2018) Convolutional neural network hyper-parameters optimization based on genetic algorithms. Int J Adv Comput Sci Appl 9(10):252\u2013266","journal-title":"Int J Adv Comput Sci Appl"},{"key":"10115_CR21","doi-asserted-by":"crossref","unstructured":"Nal\u00e7akan Y, Ensari T(2018)Decision of neural networks hyperparameters with a population-based algorithm. In: International Conference on Machine Learning, Optimization, and Data Science. Springer, pp 276\u2013281","DOI":"10.1007\/978-3-030-13709-0_23"},{"key":"10115_CR22","doi-asserted-by":"crossref","unstructured":"Pieralice, C., Lenzo, B., Bucchi, F., Gabiccini, M(2018) Vehicle sideslip angle estimation using kalman filters: modelling and validation. In: The International Conference of IFToMM Italy, Springer, pp 114\u2013122","DOI":"10.1007\/978-3-030-03320-0_12"},{"key":"10115_CR23","doi-asserted-by":"crossref","unstructured":"Sasaki H, Nishimaki T (2000) A side-slip angle estimation using neural network for a wheeled vehicle. SAE Trans, 1026\u20131031","DOI":"10.4271\/2000-01-0695"},{"key":"10115_CR24","doi-asserted-by":"crossref","unstructured":"Schramm D, Hiller M, Bardini R (2014) Vehicle dynamics. In: Modeling and Simulation, Springer, p 151","DOI":"10.1007\/978-3-540-36045-2"},{"key":"10115_CR25","doi-asserted-by":"crossref","unstructured":"Sieberg, P.M., Blume, S., Harnack, N., Maas, N., Schramm, D (2019) Hybrid state estimation combining artificial neural network and physical model. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), IEEE, pp 894\u2013899","DOI":"10.1109\/ITSC.2019.8916954"},{"issue":"9","key":"10115_CR26","doi-asserted-by":"publisher","first-page":"3513","DOI":"10.3390\/s22093513","volume":"22","author":"PM Sieberg","year":"2022","unstructured":"Sieberg PM, Schramm D (2022) Ensuring the reliability of virtual sensors based on artificial intelligence within vehicle dynamics control systems. Sensors 22(9):3513","journal-title":"Sensors"},{"key":"10115_CR27","doi-asserted-by":"publisher","first-page":"3107910","DOI":"10.1155\/2016\/3107910","volume":"2016","author":"W Wei","year":"2016","unstructured":"Wei W, Shaoyi B, Lanchun Z, Kai Z, Yongzhi W, Weixing H (2016) Vehicle sideslip angle estimation based on general regression neural network. Math Probl Eng 2016:3107910","journal-title":"Math Probl Eng"},{"key":"10115_CR28","unstructured":"Welch G, Bishop G, et\u00a0al (1995) An introduction to the kalman filter"},{"key":"10115_CR29","unstructured":"Zimmermann HG, Neuneier R (2000) Modeling dynamical systems by recurrent neural networks. WIT Trans Inf Commun Technol 25:557\u2013566"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10115-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10115-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10115-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T15:08:34Z","timestamp":1722611314000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10115-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,2]]},"references-count":29,"alternative-id":["10115"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10115-3","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2024,8,2]]},"assertion":[{"value":"31 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable. As we have not involved human subjects in our research.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable. As we have not involved human subjects in our research.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to publish"}},{"value":"Not applicable. As we have not involved human or animal subjects in our research.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}]}}