{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:34:17Z","timestamp":1787027657098,"version":"build-2736575974"},"reference-count":75,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T00:00:00Z","timestamp":1757721600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Italian Ministry of University and Research","award":["PNC0000007"],"award-info":[{"award-number":["PNC0000007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biomimetics"],"abstract":"<jats:p>Exoskeletons are a fast-growing technology that enables multiple use-cases in clinical scenarios. They can be useful tools for the rehabilitation of patients with motor dysfunctions caused by neurological conditions, aging or trauma. Assistive exoskeletons modulate the torque exerted by the electrical motors moving their joints to allow the patients wearing them to achieve an intended movement, such as gait, correctly. Their effectiveness, therefore, requires accurate online control of such torques to complement those generated by the patient. Hereby we explored Deep Learning (DL) models to generate an online prediction of the gait phase, i.e., stance or swing, during assisted walking with a lower-limb exoskeleton based on surface electromyography (sEMG) data. We leveraged the lead of muscular activation with respect to the movement of the limbs to adjust the labeling based on joints kinematics. The cross-subject design allowed to generalize over subjects not considered for training A hyperparameter optimization algorithm was also implemented to further explore the capabilities of DL models of a reduced size. We simulated a use case scenario to assess whether online implementation of the proposed technique is feasible. We also proposed a new metric called trade-of score (TOS) for evaluating the cost-performance compromise of the optimized models which lead to identifying a DL model capable of classifying gait phases with an accuracy of about 95% while significantly reducing the number of parameters compared to the full architecture. Its mean computational time of less than 10 ms offers the opportunity for accurate, online exoskeleton control based on sEMG data.<\/jats:p>","DOI":"10.3390\/biomimetics10090617","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T11:51:43Z","timestamp":1757937103000},"page":"617","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Deep Learning Models Optimization for Gait Phase Identification from EMG Data During Exoskeleton-Assisted Walking"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9671-2199","authenticated-orcid":false,"given":"Roberto","family":"Soldi","sequence":"first","affiliation":[{"name":"Laboratory of Bioengineering, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5169-4431","authenticated-orcid":false,"given":"Bruna Maria Vittoria","family":"Guerra","sequence":"additional","affiliation":[{"name":"Laboratory of Bioengineering, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefania","family":"Sozzi","sequence":"additional","affiliation":[{"name":"Laboratory of Bioengineering, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9800-2228","authenticated-orcid":false,"given":"Leo","family":"Russo","sequence":"additional","affiliation":[{"name":"Laboratory of Bioengineering, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Serena","family":"Pizzocaro","sequence":"additional","affiliation":[{"name":"Laboratory of Bioengineering, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy"},{"name":"Department of Research and Development, LUNEX International University of Health, Exercise and Sports, Avenue du Parc des Sports, 50, 4671 Differdange, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0162-2333","authenticated-orcid":false,"given":"Renato","family":"Baptista","sequence":"additional","affiliation":[{"name":"Department of Research and Development, LUNEX International University of Health, Exercise and Sports, Avenue du Parc des Sports, 50, 4671 Differdange, Luxembourg"},{"name":"Luxembourg Health & Sport Sciences Research Institute ASBL, Avenue du Parc des Sports, 50, 4671 Differdange, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4862-6742","authenticated-orcid":false,"given":"Alessandro Marco","family":"De Nunzio","sequence":"additional","affiliation":[{"name":"Department of Research and Development, LUNEX International University of Health, Exercise and Sports, Avenue du Parc des Sports, 50, 4671 Differdange, Luxembourg"},{"name":"Luxembourg Health & Sport Sciences Research Institute ASBL, Avenue du Parc des Sports, 50, 4671 Differdange, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Micaela","family":"Schmid","sequence":"additional","affiliation":[{"name":"Laboratory of Bioengineering, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5932-186X","authenticated-orcid":false,"given":"Stefano","family":"Ramat","sequence":"additional","affiliation":[{"name":"Laboratory of Bioengineering, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Perry, J., and Burnfield, J. (2024). Gait Analysis, CRC Press.","DOI":"10.1201\/9781003525592"},{"key":"ref_2","unstructured":"Whittle, M.W. (2007). Chapter 2\u2014Normal Gait. Gait Analysis, Butterworth-Heinemann. [4th ed.]."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/B978-0-444-63916-5.00007-0","article-title":"Gait","volume":"Volume 159","author":"Mirelman","year":"2018","journal-title":"Handbook of Clinical Neurology"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"946","DOI":"10.1109\/TNSRE.2013.2291907","article-title":"Segmentation and Classification of Gait Cycles","volume":"22","author":"Agostini","year":"2014","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2623","DOI":"10.1016\/j.jbiomech.2005.08.017","article-title":"Muscles That Support the Body Also Modulate Forward Progression during Walking","volume":"39","author":"Liu","year":"2006","journal-title":"J. Biomech."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/S0966-6362(02)00073-5","article-title":"Individual Muscle Contributions to Support in Normal Walking","volume":"17","author":"Anderson","year":"2003","journal-title":"Gait Posture"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Skvortsov, D.V., Kaurkin, S.N., Grebenkina, N.V., and Ivanova, G.E. (2025). Typical Changes in Gait Biomechanics in Patients with Subacute Ischemic Stroke. Diagnostics, 15.","DOI":"10.3390\/diagnostics15050511"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"562","DOI":"10.1177\/1545968315600524","article-title":"Influence of Spinal Cord Integrity on Gait Control in Human Spinal Cord Injury","volume":"30","author":"Awai","year":"2015","journal-title":"Neurorehabil. Neural Repair."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1186\/s42269-023-01052-7","article-title":"Gait Analysis of Patients with Parkinson-plus Syndromes: A Research Article","volume":"47","author":"Tandon","year":"2023","journal-title":"Bull. Natl. Res. Cent."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.gaitpost.2016.09.026","article-title":"Gait Deficits in People with Multiple Sclerosis: A Systematic Review and Meta-Analysis","volume":"51","author":"Comber","year":"2017","journal-title":"Gait Posture"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Hui, Z., Qi, W., Zhang, Y., Wang, M., Zhang, J., Li, D., and Zhu, D. (2024). Efficacy of a Soft Robotic Exoskeleton to Improve Lower Limb Motor Function in Children with Spastic Cerebral Palsy: A Single-Blinded Randomized Controlled Trial. Brain Sci., 14.","DOI":"10.3390\/brainsci14050425"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Schr\u00f6der, J., Yperzeele, L., Embrechts, E., Loureiro-Chaves, R., Hallemans, A., Lafosse, C., Truijen, S., Kwakkel, G., and Saeys, W. (2024). Exoskeleton-Assisted Training to Enhance Lower Limb Motor Recovery in Subacute Stroke: Does Timing Matter? A Pilot Randomized Trial. Front. Stroke, 3.","DOI":"10.3389\/fstro.2024.1379083"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1186\/s12984-021-00815-5","article-title":"Systematic Review on Wearable Lower-Limb Exoskeletons for Gait Training in Neuromuscular Impairments","volume":"18","year":"2021","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1186\/s12984-015-0048-y","article-title":"The H2 Robotic Exoskeleton for Gait Rehabilitation after Stroke: Early Findings from a Clinical Study Wearable Robotics in Clinical Testing","volume":"12","author":"Bortole","year":"2015","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/s12984-023-01158-z","article-title":"Exoskeleton-Based Training Improves Walking Independence in Incomplete Spinal Cord Injury Patients: Results from a Randomized Controlled Trial","volume":"20","author":"Pons","year":"2023","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"209","DOI":"10.23736\/S1973-9087.18.05308-X","article-title":"Assistive Powered Exoskeleton for Complete Spinal Cord Injury: Correlations between Walking Ability and Exoskeleton Control","volume":"55","author":"Guanziroli","year":"2019","journal-title":"Eur. J. Phys. Rehabil. Med."},{"key":"ref_17","first-page":"1","article-title":"EMG-Based Gait Speed Control of a Lower-limb Exoskeleton for Gait Rehabilitation: A Proof-of-Concept Study with Post-stroke Chronic Hemiparetic Patients","volume":"2025","author":"Choi","year":"2025","journal-title":"Int. J. Precis. Eng. Manuf."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1186\/s12984-025-01649-1","article-title":"Comparative Efficacy of Robotic Exoskeleton and Conventional Gait Training in Patients with Spinal Cord Injury: A Meta-Analysis of Randomized Controlled Trials","volume":"22","author":"Liu","year":"2025","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Lee, J.H., and Kim, G. (2025). Effectiveness of Robot-Assisted Gait Training in Stroke Rehabilitation: A Systematic Review and Meta-Analysis. J. Clin. Med., 14.","DOI":"10.3390\/jcm14134809"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Yu, Y., Huang, W., Tuerxun, H., Zheng, Y., Su, L., Li, X., and Dou, Z. (2025). Enhanced Neuroplasticity and Gait Recovery in Stroke Patients: A Comparative Analysis of Active and Passive Robotic Training Modes. BMC Neurol., 25.","DOI":"10.1186\/s12883-025-04226-0"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"5759","DOI":"10.1109\/JSEN.2024.3352005","article-title":"Interactive Control of Lower Limb Exoskeleton Robots: A Review","volume":"24","author":"Zhang","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Han, Y., Tao, Q., and Zhang, X. (2025). Multijoint Continuous Motion Estimation for Human Lower Limb Based on Surface Electromyography. Sensors, 25.","DOI":"10.3390\/s25030719"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e11023","DOI":"10.2196\/11023","article-title":"Walking With a Robotic Exoskeleton Does Not Mimic Natural Gait: A Within-Subjects Study","volume":"6","author":"Swank","year":"2019","journal-title":"JMIR Rehabil. Assist. Technol."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Barbareschi, G., Richards, R., Thornton, M., Carlson, T., and Holloway, C. (2015, January 25\u201329). Statically vs Dynamically Balanced Gait: Analysis of a Robotic Exoskeleton Compared with a Human. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, Milan, Italy.","DOI":"10.1109\/EMBC.2015.7319937"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5272","DOI":"10.1109\/JBHI.2023.3304639","article-title":"SEMG-Based End-to-End Continues Prediction of Human Knee Joint Angles Using the Tightly Coupled Convolutional Transformer Model","volume":"27","author":"Liang","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Morbidoni, C., Cucchiarelli, A., Fioretti, S., and Di Nardo, F. (2019). A Deep Learning Approach to EMG-Based Classification of Gait Phases during Level Ground Walking. Electronics, 8.","DOI":"10.3390\/electronics8080894"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Park, H., Han, S., Sung, J., Hwang, S., Youn, I., and Kim, S.J. (2023). Classification of Gait Phases Based on a Machine Learning Approach Using Muscle Synergy. Front. Hum. Neurosci., 17.","DOI":"10.3389\/fnhum.2023.1201935"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Guerra, B.M.V., Schmid, M., Sozzi, S., Pizzocaro, S., De Nunzio, A.M., and Ramat, S. (2024). A Recurrent Deep Network for Gait Phase Identification from EMG Signals During Exoskeleton-Assisted Walking. Sensors, 24.","DOI":"10.3390\/s24206666"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.gaitpost.2025.02.009","article-title":"Anticipatory Muscle Activations to Coordinate Balance and Movement during Motor Transitions: A Narrative Review","volume":"118","author":"Bechet","year":"2025","journal-title":"Gait Posture"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.gaitpost.2012.07.013","article-title":"Intention Detection of Gait Initiation Using EMG and Kinematic Data","volume":"37","author":"Wentink","year":"2013","journal-title":"Gait Posture"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/j.gaitpost.2013.08.008","article-title":"Detection of the Onset of Gait Initiation Using Kinematic Sensors and EMG in Transfemoral Amputees","volume":"39","author":"Wentink","year":"2014","journal-title":"Gait Posture"},{"key":"ref_32","unstructured":"Iosifidis, A., and Tefas, A. Recurrent Neural Networks. Deep Learning for Robot Perception and Cognition, Academic Press."},{"key":"ref_33","first-page":"100733","article-title":"Machine Learning for Autonomous Vehicle\u2019s Trajectory Prediction: A Comprehensive Survey, Challenges, and Future Research Directions","volume":"46","author":"Bharilya","year":"2024","journal-title":"Veh. Commun."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"109092","DOI":"10.1016\/j.asoc.2022.109092","article-title":"Network Self Attention for Forecasting Time Series","volume":"124","author":"Hu","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Aviles, M., Alvarez-Alvarado, J.M., Robles-Ocampo, J.B., Sevilla-Camacho, P.Y., and Rodr\u00edguez-Res\u00e9ndiz, J. (2024). Optimizing RNNs for EMG Signal Classification: A Novel Strategy Using Grey Wolf Optimization. Bioengineering, 11.","DOI":"10.3390\/bioengineering11010077"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Guerra, B.M.V., Schmid, M., Beltrami, G., and Ramat, S. (2022). Neural Networks for Automatic Posture Recognition in Ambient-Assisted Living. Sensors, 22.","DOI":"10.3390\/s22072609"},{"key":"ref_37","unstructured":"(2025, June 12). Product Page-EAII | ExoAtlet. Available online: https:\/\/exoatlet.lu\/product-page-exoatlet-ii\/."},{"key":"ref_38","unstructured":"(2025, June 12). ExoAtlet Main Page. Available online: https:\/\/exoatlet.lu\/."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Winter, D.A. (2009). Biomechanics and Motor Control of Human Movement, Wiley.","DOI":"10.1002\/9780470549148"},{"key":"ref_40","unstructured":"Guerra, B.M.V., Schmid, M., Sozzi, S., Pizzocaro, S., De Nunzio, A.M., and Ramat, S. (2024, January 26\u201328). Adopting BiLSTM for Gait Phase Recognition in Exoskeleton Control via SEMG Signals. Proceedings of the 2024 IEEE International Symposium on Medical Measurements and Applications (MeMeA), Eindhoven, The Netherlands."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/0021-9290(85)90043-0","article-title":"The Frequency Content of Gait","volume":"18","author":"Antonsson","year":"1985","journal-title":"J. Biomech."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1339","DOI":"10.1007\/s00702-007-0657-0","article-title":"Cortical Control of Postural Responses","volume":"114","author":"Jacobs","year":"2007","journal-title":"J. Neural Transm. (Vienna)"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"111634","DOI":"10.1016\/j.mad.2022.111634","article-title":"Impact of Ageing, Fall History and Exercise on Postural Reflexes Following Unpredictable Perturbations: A Systematic Review and Meta-Analyses","volume":"203","author":"Phu","year":"2022","journal-title":"Mech. Ageing Dev."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Mienye, I.D., Swart, T.G., and Obaido, G. (2024). Recurrent Neural Networks: A Comprehensive Review of Architectures, Variants, and Applications. Information, 15.","DOI":"10.20944\/preprints202408.0748.v1"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Gunaratne, P.N., and Tamura, H. (2025). An EMG-Based GRU Model for Estimating Foot Pressure to Support Active Ankle Orthosis Development. Sensors, 25.","DOI":"10.3390\/s25113558"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Cai, S., Chen, D., Fan, B., Du, M., Bao, G., and Li, G. (2023). Gait Phases Recognition Based on Lower Limb SEMG Signals Using LDA-PSO-LSTM Algorithm. Biomed. Signal Process Control, 80.","DOI":"10.1016\/j.bspc.2022.104272"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Ilyas, Z., Anam, K., Avian, C., Muttaqin, A.Z., and Ramadhan, M.E. (2022, January 6\u20137). Evaluation of Gated-Recurrent Unit for Estimating Finger-Joint Angle Using Surface Electromyography Signal. Proceedings of the International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), Jakarta, Indonesia.","DOI":"10.23919\/EECSI56542.2022.9946461"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Wang, F., Liang, W., Afzal, H.M.R., Fan, A., Li, W., Dai, X., Liu, S., Hu, Y., Li, Z., and Yang, P. (2023). Estimation of Lower Limb Joint Angles and Joint Moments during Different Locomotive Activities Using the Inertial Measurement Units and a Hybrid Deep Learning Model. Sensors, 23.","DOI":"10.3390\/s23229039"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Li, Y.H., Harfiya, L.N., Purwandari, K., and Lin, Y. (2020). Der Real-Time Cuffless Continuous Blood Pressure Estimation Using Deep Learning Model. Sensors, 20.","DOI":"10.3390\/s20195606"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1109\/TMRB.2022.3144025","article-title":"Subject-Independent, Biological Hip Moment Estimation during Multimodal Overground Ambulation Using Deep Learning","volume":"4","author":"Molinaro","year":"2022","journal-title":"IEEE Trans. Med. Robot. Bionics"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Du, J., Liu, Z., Dong, W., Zhang, W., and Miao, Z. (2024). A Novel TCN-LSTM Hybrid Model for SEMG-Based Continuous Estimation of Wrist Joint Angles. Sensors, 24.","DOI":"10.3390\/s24175631"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"012047","DOI":"10.1088\/1742-6596\/2637\/1\/012047","article-title":"Multi-Modal Physiological Signal Fusion for Emotion Classification: A Multi-Head Attention Approach","volume":"2637","author":"Xuemei","year":"2023","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"113944","DOI":"10.1016\/j.measurement.2023.113944","article-title":"A Temporal Convolutional Network for EMG Compressed Sensing Reconstruction","volume":"225","author":"Zhang","year":"2024","journal-title":"Measurement"},{"key":"ref_54","unstructured":"Bai, S., Kolter, J.Z., and Koltun, V. (2018). An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling. 2018. arXiv."},{"key":"ref_55","unstructured":"(2025, June 13). GitHub-Philipperemy\/Keras-Tcn: Keras Temporal Convolutional Network. Supports Python and R. Available online: https:\/\/github.com\/philipperemy\/keras-tcn."},{"key":"ref_56","unstructured":"(2025, June 13). Temporal Convolutional Networks and Forecasting\u2014Unit8. Available online: https:\/\/unit8.com\/resources\/temporal-convolutional-networks-and-forecasting\/."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Feurer, M., and Hutter, F. (2019). Hyperparameter Optimization, Springer.","DOI":"10.1007\/978-3-030-05318-5_1"},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1007\/BFb0048702","article-title":"Bayes\u2019 Theorem","volume":"31","author":"Koch","year":"1990","journal-title":"Bayesian Inference with Geodetic Applications"},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Nguyen, V. (2019, January 3\u20135). Bayesian Optimization for Accelerating Hyper-Parameter Tuning. Proceedings of the IEEE 2nd International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), Sardinia, Italy.","DOI":"10.1109\/AIKE.2019.00060"},{"key":"ref_60","first-page":"26","article-title":"Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimization","volume":"17","author":"Wu","year":"2019","journal-title":"J. Electron. Sci. Technol."},{"key":"ref_61","first-page":"2951","article-title":"Practical Bayesian Optimization of Machine Learning Algorithms","volume":"4","author":"Snoek","year":"2012","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"ref_62","unstructured":"MATLAB & Simulink (2025, June 16). Bayesian Optimization Algorithm. Available online: https:\/\/it.mathworks.com\/help\/stats\/bayesian-optimization-algorithm.html."},{"key":"ref_63","unstructured":"Hu, W., Henderson, P., and Cano, J. (2025). ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks. 2025. arXiv."},{"key":"ref_64","unstructured":"Liu, J., Tripathi, S., Kurup, U., and Shah, M. (2020). Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey. 2020. arXiv."},{"key":"ref_65","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1016\/j.neucom.2021.07.045","article-title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","volume":"461","author":"Liang","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_66","unstructured":"(2025, June 30). GitHub-Onnx\/Onnx: Open Standard for Machine Learning Interoperability. Available online: https:\/\/github.com\/onnx\/onnx."},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Di Nardo, F., Morbidoni, C., Mascia, G., Verdini, F., and Fioretti, S. (2020). Intra-Subject Approach for Gait-Event Prediction by Neural Network Interpretation of EMG Signals. Biomed. Eng. Online, 19.","DOI":"10.1186\/s12938-020-00803-1"},{"key":"ref_68","doi-asserted-by":"crossref","unstructured":"Pe, S., Nicora, G., Guerra, B.M.V., Sozzi, S., and Parimbelli, E. (2024, January 18\u201320). Systematic Comparison of Machine Learning for Activity Recognition in Cross-Subject vs. NonCross-Subject Scenarios: A Preliminary Analysis. Proceedings of the 2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI), Milano, Italy.","DOI":"10.1109\/RTSI61910.2024.10761630"},{"key":"ref_69","doi-asserted-by":"crossref","first-page":"1474","DOI":"10.1134\/S000511791808009X","article-title":"Deep Learning Model Selection of Suboptimal Complexity","volume":"79","author":"Bakhteev","year":"2018","journal-title":"Autom. Remote Control."},{"key":"ref_70","doi-asserted-by":"crossref","unstructured":"Sarv Ahrabi, S., Scarpiniti, M., Baccarelli, E., and Momenzadeh, A. (2021). An Accuracy vs. Complexity Comparison of Deep Learning Architectures for the Detection of COVID-19 Disease. Computation, 9.","DOI":"10.3390\/computation9010003"},{"key":"ref_71","doi-asserted-by":"crossref","unstructured":"Trihinas, D., Michael, P., and Symeonides, M. (2024). Evaluating DL Model Scaling Trade-Offs During Inference via an Empirical Benchmark Analysis. Future Internet, 16.","DOI":"10.3390\/fi16120468"},{"key":"ref_72","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1016\/S0377-2217(00)00171-5","article-title":"An Investigation of Model Selection Criteria for Neural Network Time Series Forecasting","volume":"132","author":"Qi","year":"2001","journal-title":"Eur. J. Oper. Res."},{"key":"ref_73","doi-asserted-by":"crossref","first-page":"4177","DOI":"10.1109\/JLT.2024.3386886","article-title":"Computational Complexity Optimization of Neural Network-Based Equalizers in Digital Signal Processing: A Comprehensive Approach","volume":"42","author":"Freire","year":"2024","journal-title":"J. Light. Technol."},{"key":"ref_74","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1093\/ptj\/82.1.69","article-title":"Central Pattern Generation of Locomotion: A Review of the Evidence","volume":"82","year":"2002","journal-title":"Phys. Ther."},{"key":"ref_75","doi-asserted-by":"crossref","unstructured":"Sylos-Labini, F., La Scaleia, V., d\u2019Avella, A., Pisotta, I., Tamburella, F., Scivoletto, G., Molinari, M., Wang, S., Wang, L., and van Asseldonk, E. (2014). EMG Patterns during Assisted Walking in the Exoskeleton. Front. Hum. Neurosci., 8.","DOI":"10.3389\/fnhum.2014.00423"}],"container-title":["Biomimetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-7673\/10\/9\/617\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:45:12Z","timestamp":1760035512000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-7673\/10\/9\/617"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,13]]},"references-count":75,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["biomimetics10090617"],"URL":"https:\/\/doi.org\/10.3390\/biomimetics10090617","relation":{},"ISSN":["2313-7673"],"issn-type":[{"value":"2313-7673","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,13]]}}}