{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T02:06:23Z","timestamp":1794535583269,"version":"4.9.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,3,23]],"date-time":"2023-03-23T00:00:00Z","timestamp":1679529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,3,23]],"date-time":"2023-03-23T00:00:00Z","timestamp":1679529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Decoding human action intention prior to motion onset with surface electromyograms (sEMG) is an emerging neuroengineering topic with interesting clinical applications such as intelligent control of powered prosthesis\/exoskeleton devices. Despite extensive prior works in the related fields, it remains a technical challenge due to considerable variability of complex multi-muscle activation patterns in terms of volatile spatio-temporal characteristics. To address this issue, we first hypothesize that the inherent variability of the<jats:italic>idle<\/jats:italic>state immediately preceding the motion initiation needs to be addressed explicitly. We therefore design a hierarchical dynamic Bayesian learning network model that integrates an array of Gaussian mixture model \u2013 hidden Markov models (GMM-HMMs), where each GMM-HMM learns the multi-sEMG processes either during the idle state, or during the motion initiation phase of a particular motion task. To test the hypothesis and evaluate the new learning network, we design and build a upper-limb sEMG-joystick motion study system, and collect data from 11 healthy volunteers. The data collection protocol adapted from the psychomotor vigilance task includes repeated and randomized binary hand motion tasks (push or pull) starting from either of two designated<jats:italic>idle<\/jats:italic>states: relaxed (with minimal muscle tones), or prepared (with muscle tones). We run a series of cross-validation tests to examine the performance of the method in comparison with the conventional techniques. The results suggest that the idle state recognition favors the dynamic Bayesian model over a static classification model. The results also show a statistically significant improvement in motion prediction accuracy by the proposed method (93.83\u00b16.41%) in comparison with the conventional GMM-HMM method (89.71\u00b18.98%) that does not explicitly account for the idle state. Moreover, we examine the progress of prediction accuracy over the course of motion initiation and identify the important hidden states that warrant future research.<\/jats:p>","DOI":"10.1038\/s41598-023-30716-7","type":"journal-article","created":{"date-parts":[[2023,3,23]],"date-time":"2023-03-23T11:04:14Z","timestamp":1679569454000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["A hierarchical dynamic Bayesian learning network for EMG-based early prediction of voluntary movement intention"],"prefix":"10.1038","volume":"13","author":[{"given":"Yongming","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8571-5675","authenticated-orcid":false,"given":"Haihong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanchu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3053-6311","authenticated-orcid":false,"given":"Kai Keng","family":"Ang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soon Huat","family":"Ng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiwen","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1587-1226","authenticated-orcid":false,"given":"Zhiping","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,23]]},"reference":[{"key":"30716_CR1","doi-asserted-by":"publisher","unstructured":"Gantenbein, J., Dittli, J., Meyer, J.\u00a0T., Gassert, R. & Lambercy, O. Intention detection strategies for robotic upper-limb orthoses: A scoping review considering usability, daily life application, and user evaluation. Front. Neurorobotics16, https:\/\/doi.org\/10.3389\/fnbot.2022.815693 (2022).","DOI":"10.3389\/fnbot.2022.815693"},{"key":"30716_CR2","doi-asserted-by":"publisher","first-page":"2265","DOI":"10.1109\/TNSRE.2020.3021691","volume":"28","author":"S Park","year":"2020","unstructured":"Park, S. et al. User-driven functional movement training with a wearable hand robot after stroke. IEEE Trans. Neural Syst. Rehabil. Eng. 28, 2265\u20132275. https:\/\/doi.org\/10.1109\/TNSRE.2020.3021691 (2020).","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"30716_CR3","doi-asserted-by":"publisher","unstructured":"Fatimah, B., Singh, P., Singhal, A. & Pachori, R.\u00a0B. Hand movement recognition from sEMG signals using Fourier decomposition method. Biocybern. Biomed. Eng.41, 690\u2013703, https:\/\/doi.org\/10.1016\/j.bbe.2021.03.004 (2021).","DOI":"10.1016\/j.bbe.2021.03.004"},{"key":"30716_CR4","doi-asserted-by":"publisher","unstructured":"Amanpreet, K. Machine learning-based novel approach to classify the shoulder motion of upper limb amputees. Biocybern. Biomed. Eng.39, 857\u2013867, https:\/\/doi.org\/10.1016\/j.bbe.2019.07.007 (2019).","DOI":"10.1016\/j.bbe.2019.07.007"},{"key":"30716_CR5","doi-asserted-by":"publisher","unstructured":"Gaudet, G., Raison, M. & Achiche, S. Classification of upper limb phantom movements in transhumeral amputees using electromyographic and kinematic features. Eng. Appl. Artif. Intell.68, 153\u2013164, https:\/\/doi.org\/10.1016\/j.engappai.2017.10.017 (2018).","DOI":"10.1016\/j.engappai.2017.10.017"},{"key":"30716_CR6","doi-asserted-by":"publisher","first-page":"84070","DOI":"10.1109\/ACCESS.2020.2991812","volume":"8","author":"SY Gordleeva","year":"2020","unstructured":"Gordleeva, S. Y. et al. Real-time EEG-EMG human-machine interface-based control system for a lower-limb exoskeleton. IEEE Access 8, 84070\u201384081. https:\/\/doi.org\/10.1109\/ACCESS.2020.2991812 (2020).","journal-title":"IEEE Access"},{"key":"30716_CR7","doi-asserted-by":"publisher","unstructured":"De la Cruz-S\u00e1nchez, B.\u00a0A., Arias-Montiel, M. & Lugo-Gonz\u00e1lez, E. EMG-controlled hand exoskeleton for assisted bilateral rehabilitation. Biocybern. Biomed. Eng.42, 596\u2013614, https:\/\/doi.org\/10.1016\/j.bbe.2022.04.001 (2022).","DOI":"10.1016\/j.bbe.2022.04.001"},{"key":"30716_CR8","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1109\/LRA.2018.2890199","volume":"4","author":"S Park","year":"2019","unstructured":"Park, S. et al. Multimodal sensing and interaction for a robotic hand orthosis. IEEE Robot. Autom. Lett. 4, 315\u2013322. https:\/\/doi.org\/10.1109\/LRA.2018.2890199 (2019).","journal-title":"IEEE Robot. Autom. Lett."},{"key":"30716_CR9","doi-asserted-by":"publisher","unstructured":"Sim\u00e3o, M., Neto, P. & Gibaru, O. EMG-based online classification of gestures with recurrent neural networks. Pattern Recognit. Lett.128, https:\/\/doi.org\/10.1016\/j.patrec.2019.07.021 (2019).","DOI":"10.1016\/j.patrec.2019.07.021"},{"key":"30716_CR10","doi-asserted-by":"publisher","first-page":"1250","DOI":"10.1109\/TBME.2012.2232293","volume":"60","author":"AJ Young","year":"2013","unstructured":"Young, A. J., Smith, L. H., Rouse, E. J. & Hargrove, L. J. Classification of simultaneous movements using surface EMG pattern recognition. IEEE Trans. Biomed. Eng. 60, 1250\u20131258. https:\/\/doi.org\/10.1109\/TBME.2012.2232293 (2013).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"30716_CR11","doi-asserted-by":"publisher","first-page":"1801","DOI":"10.1109\/TBME.2005.856295","volume":"52","author":"Y Huang","year":"2005","unstructured":"Huang, Y., Englehart, K. B., Hudgins, B. & Chan, A. D. A Gaussian mixture model based classification scheme for myoelectric control of powered upper limb prostheses. IEEE Trans. Biomed. Eng. 52, 1801\u20131811 (2005).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"30716_CR12","doi-asserted-by":"publisher","unstructured":"Khairuddin, I.\u00a0M., Sidek, S.\u00a0N., Majeed, A. P.\u00a0A. & Puzi, A.\u00a0A. Classifying motion intention from EMG signal: A k-nn approach. In 2019 7th International Conference on Mechatronics Engineering (ICOM), 1\u20134, https:\/\/doi.org\/10.1109\/ICOM47790.2019.8952042 (2019).","DOI":"10.1109\/ICOM47790.2019.8952042"},{"key":"30716_CR13","doi-asserted-by":"crossref","unstructured":"Bian, F., Li, R. & Liang, P. SVM based simultaneous hand movements classification using sEMG signals. In 2017 IEEE International Conference on Mechatronics and Automation (ICMA), 427\u2013432 (IEEE, 2017).","DOI":"10.1109\/ICMA.2017.8015855"},{"key":"30716_CR14","doi-asserted-by":"publisher","first-page":"81630","DOI":"10.1109\/ACCESS.2019.2923455","volume":"7","author":"Y Li","year":"2019","unstructured":"Li, Y., Zhang, Q., Zeng, N., Chen, J. & Zhang, Q. Discrete hand motion intention decoding based on transient myoelectric signals. IEEE Access 7, 81630\u201381639. https:\/\/doi.org\/10.1109\/ACCESS.2019.2923455 (2019).","journal-title":"IEEE Access"},{"key":"30716_CR15","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.1109\/TNSRE.2020.3024947","volume":"28","author":"VH Cene","year":"2020","unstructured":"Cene, V. H. & Balbinot, A. Resilient EMG classification to enable reliable upper-limb movement intent detection. IEEE Trans. Neural Syst. Rehabil. Eng. 28, 2507\u20132514. https:\/\/doi.org\/10.1109\/TNSRE.2020.3024947 (2020).","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"30716_CR16","doi-asserted-by":"publisher","unstructured":"He, Y., Fukuda, O., Bu, N., Okumura, H. & Yamaguchi, N. Surface EMG pattern recognition using long short-term memory combined with multilayer perceptron. In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 5636\u20135639, https:\/\/doi.org\/10.1109\/EMBC.2018.8513595 (2018).","DOI":"10.1109\/EMBC.2018.8513595"},{"key":"30716_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2021.102642","volume":"79","author":"F Xiao","year":"2021","unstructured":"Xiao, F. et al. Real time motion intention recognition method with limited number of surface electromyography sensors for a 7-dof hand\/wrist rehabilitation exoskeleton. Mechatronics 79, 102642 (2021).","journal-title":"Mechatronics"},{"key":"30716_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.102592","volume":"68","author":"R Wen","year":"2021","unstructured":"Wen, R., Wang, Q. & Li, Z. Human hand movement recognition using infinite hidden markov model based sEMG classification. Biomed. Signal Process. Control 68, 102592 (2021).","journal-title":"Biomed. Signal Process. Control"},{"key":"30716_CR19","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/TBME.2004.836492","volume":"52","author":"AD Chan","year":"2004","unstructured":"Chan, A. D. & Englehart, K. B. Continuous myoelectric control for powered prostheses using hidden Markov models. IEEE Trans. Biomed. Eng. 52, 121\u2013124 (2004).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"30716_CR20","doi-asserted-by":"publisher","first-page":"383","DOI":"10.3233\/THC-199035","volume":"27","author":"Y Chen","year":"2019","unstructured":"Chen, Y., Liang, L., Wu, M. & Dong, Q. A SEMG-angle model based on HMM for human robot interaction. Technol. Health Care 27, 383\u2013395 (2019).","journal-title":"Technol. Health Care"},{"key":"30716_CR21","doi-asserted-by":"publisher","first-page":"2882","DOI":"10.3390\/s21082882","volume":"21","author":"Z Ding","year":"2021","unstructured":"Ding, Z., Yang, C., Wang, Z., Yin, X. & Jiang, F. Online adaptive prediction of human motion intention based on sEMG. Sensors 21, 2882 (2021).","journal-title":"Sensors"},{"key":"30716_CR22","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/TSMCA.2005.855781","volume":"36","author":"S Polak","year":"2006","unstructured":"Polak, S., Barniv, Y. & Baram, Y. Head motion anticipation for virtual-environment applications using kinematics and EMG energy. IEEE Trans. Syst. Man, Cybern.-Part A: Syst. Humans 36, 569\u2013576 (2006).","journal-title":"IEEE Trans. Syst. Man, Cybern.-Part A: Syst. Humans"},{"key":"30716_CR23","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1109\/TNSRE.2007.891391","volume":"15","author":"TR Farrell","year":"2007","unstructured":"Farrell, T. R. & Weir, R. F. The optimal controller delay for myoelectric prostheses. IEEE Trans. Neural Syst. Rehabil. Eng. 15, 111\u2013118. https:\/\/doi.org\/10.1109\/TNSRE.2007.891391 (2007).","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"30716_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12984-019-0512-1","volume":"16","author":"E Trigili","year":"2019","unstructured":"Trigili, E. et al. Detection of movement onset using EMG signals for upper-limb exoskeletons in reaching tasks. J. Neuroeng. Rehabil. 16, 1\u201316 (2019).","journal-title":"J. Neuroeng. Rehabil."},{"key":"30716_CR25","doi-asserted-by":"publisher","first-page":"652","DOI":"10.3758\/BF03200977","volume":"17","author":"DI Dinges","year":"1985","unstructured":"Dinges, D. I. & Powell, J. W. Microcomputer analysis of performance on a portable, simple visual RT task sustained operations. Behav. Res. Methods, Instrum. Comput. 17, 652\u2013655 (1985).","journal-title":"Behav. Res. Methods, Instrum. Comput."},{"key":"30716_CR26","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.1016\/S0167-8655(01)00075-7","volume":"22","author":"B Obermaier","year":"2001","unstructured":"Obermaier, B., Guger, C., Neuper, C. & Pfurtscheller, G. Hidden Markov models for online classification of single trial EEG data. Pattern Recogn. Lett. 22, 1299\u20131309 (2001).","journal-title":"Pattern Recogn. Lett."},{"key":"30716_CR27","doi-asserted-by":"crossref","unstructured":"Argun\u015fah, A.\u00a0\u00d6. & Cetin, M. AR-PCA-HMM approach for sensorimotor task classification in EEG-based brain-computer interfaces. In 2010 20th International Conference on Pattern Recognition, 113\u2013116 (IEEE, 2010).","DOI":"10.1109\/ICPR.2010.36"},{"key":"30716_CR28","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1109\/34.990138","volume":"24","author":"MAT Figueiredo","year":"2002","unstructured":"Figueiredo, M. A. T. & Jain, A. K. Unsupervised learning of finite mixture models. IEEE Trans. Pattern Anal. Mach. Intell. 24, 381\u2013396 (2002).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"30716_CR29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster, A. P., Laird, N. M. & Rubin, D. B. Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc.: Ser. B (Methodol.) 39, 1\u201322 (1977).","journal-title":"J. Roy. Stat. Soc.: Ser. B (Methodol.)"},{"key":"30716_CR30","first-page":"126","volume":"4","author":"JA Bilmes","year":"1998","unstructured":"Bilmes, J. A. et al. A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models. Int. Comput. Sci. Inst. 4, 126 (1998).","journal-title":"Int. Comput. Sci. Inst."},{"key":"30716_CR31","unstructured":"Wen, R., Wang, Q., Ma, X. & Li, Z. Human hand movement recognition based on HMM with hyperparameters optimized by maximum mutual information. In 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 944\u2013951 (IEEE, 2020)."},{"key":"30716_CR32","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1080\/10803548.2007.11076725","volume":"13","author":"P Bartuzi","year":"2007","unstructured":"Bartuzi, P., Roman-Liu, D. & Tokarski, T. A study of the influence of muscle type and muscle force level on individual frequency bands of the EMG power spectrum. Int. J. Occup. Saf. Ergon. 13, 241\u2013254 (2007).","journal-title":"Int. J. Occup. Saf. Ergon."},{"key":"30716_CR33","doi-asserted-by":"crossref","unstructured":"Buongiorno, D., Cascarano, G.\u00a0D., Brunetti, A., Feudis, I.\u00a0D. & Bevilacqua, V. A survey on deep learning in electromyographic signal analysis. In International Conference on Intelligent Computing, 751\u2013761 (2019).","DOI":"10.1007\/978-3-030-26766-7_68"},{"key":"30716_CR34","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1109\/JAS.2021.1003865","volume":"8","author":"D Xiong","year":"2021","unstructured":"Xiong, D., Zhang, D., Zhao, X. & Zhao, Y. Deep learning for emg-based human-machine interaction: A review. IEEE\/CAA J. Automatica Sinica 8, 512\u2013533. https:\/\/doi.org\/10.1109\/JAS.2021.1003865 (2021).","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"key":"30716_CR35","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1109\/TNSRE.2019.2896269","volume":"27","author":"U C\u00f4t\u00e9-Allard","year":"2019","unstructured":"C\u00f4t\u00e9-Allard, U. et al. Deep learning for electromyographic hand gesture signal classification using transfer learning. IEEE Trans. Neural Syst. Rehabil. Eng. 27, 760\u2013771. https:\/\/doi.org\/10.1109\/TNSRE.2019.2896269 (2019).","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"30716_CR36","doi-asserted-by":"publisher","unstructured":"Soroushmojdehi, R., Javadzadeh, S., Pedrocchi, A. & Gandolla, M. Transfer learning in hand movement intention detection based on surface electromyography signals. Front. Neurosci.16, https:\/\/doi.org\/10.3389\/fnins.2022.977328 (2022).","DOI":"10.3389\/fnins.2022.977328"},{"key":"30716_CR37","unstructured":"Lundberg, S.\u00a0M. & Lee, S.-I. A unified approach to interpreting model predictions. In Guyon, I. et\u00a0al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030 (Curran Associates, Inc., 2017)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-30716-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-30716-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-30716-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T22:29:41Z","timestamp":1729117781000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-30716-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,23]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["30716"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-30716-7","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,23]]},"assertion":[{"value":"25 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"4730"}}