{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:45:52Z","timestamp":1759970752240,"version":"build-2065373602"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003093","name":"Ministry of Higher Education, Malaysia","doi-asserted-by":"publisher","award":["FRGS\/1\/2023\/SKK06\/MUSM\/03\/1"],"award-info":[{"award-number":["FRGS\/1\/2023\/SKK06\/MUSM\/03\/1"]}],"id":[{"id":"10.13039\/501100003093","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>To develop applications for assisting Parkinson\u2019s disease (PD) patients, extracting Parkinsonian tremors from the raw signal is crucial; however, conventional methods such as filtering require a preset frequency range, and a poorly set frequency range may lead to the inclusion of undesired signals. AI algorithms can potentially overcome the heterogenous tremor characteristics in different patients, but they have been applied in the disease or tremor type classification rather than in tremulous-voluntary motion classification. Hence, this study presents an approach to automatically differentiate between voluntary and tremulous motions in PD patients, achieved by combining ensemble empirical mode decomposition (EEMD) and convolutional bi-directional long short-term memory (LSTM). Non-labelled raw hand-arm orientation data collected from PD patients was decomposed into sub-signals via EEMD to replace the conventional filtering techniques. A convolutional layer automatically extracted key features from these sub-signals to train the deep learning classifier, eliminating the need for manual feature engineering. The proposed method can be generalized to identify tremors from motion signals obtained during daily activities without pre-identified features. The proposed approach accurately extracted Parkinsonian tremors from raw signals across various activities, achieving low root-mean-square error and 94.2\u2009\u00b1\u20091.1% accuracy in differentiating voluntary and tremulous motions in PD patients.<\/jats:p>","DOI":"10.1038\/s41598-025-08216-7","type":"journal-article","created":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T11:09:31Z","timestamp":1759921771000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic differentiation of voluntary and tremulous motion using ensemble empirical mode decomposition and convolutional Bi-directional LSTM"],"prefix":"10.1038","volume":"15","author":[{"given":"Jie Qi","family":"Ling","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. S. M.","family":"Bakibillah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping Yi","family":"Chan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Surya G.","family":"Nurzaman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chee Pin","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,8]]},"reference":[{"key":"8216_CR1","unstructured":"Naqvi, E. Parkinson\u2019s Disease Statistics | Parkinson\u2019s News Today. https:\/\/parkinsonsnewstoday.com\/parkinsons-disease-statistics\/"},{"key":"8216_CR2","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1109\/TNSRE.2021.3097007","volume":"29","author":"A Ibrahim","year":"2021","unstructured":"Ibrahim, A., Zhou, Y., Jenkins, M. E., Trejos, A. L. & Naish, M. D. Real-Time voluntary motion prediction and parkinson\u2019s tremor reduction using deep neural networks. IEEE Trans. Neural Syst. Rehabil Eng. 29, 1413\u20131423 (2021).","journal-title":"IEEE Trans. Neural Syst. Rehabil Eng."},{"key":"8216_CR3","doi-asserted-by":"publisher","unstructured":"Widjaja, F. et al. Kalman filtering of accelerometer and electromyography (EMG) data in pathological tremor sensing system. in. IEEE International Conference on Robotics and Automation 3250\u20133255 (2008). (2008). https:\/\/doi.org\/10.1109\/ROBOT.2008.4543706","DOI":"10.1109\/ROBOT.2008.4543706"},{"key":"8216_CR4","doi-asserted-by":"publisher","first-page":"372","DOI":"10.20965\/jaciii.2023.p0372","volume":"27","author":"M Xie","year":"2023","unstructured":"Xie, M., She, J., Liu, Z. T. & Yang, Z. A Real-Time voluntary motion extraction method based on an adaptive filter. JACIII 27, 372\u2013377 (2023).","journal-title":"JACIII"},{"key":"8216_CR5","doi-asserted-by":"publisher","unstructured":"Wang, S. et al. Estimation of tremor parameters and extraction tremor from recorded signals for tremor suppression. 2016 IEEE Int. Conf. Rob. Autom. (ICRA). 3717-3722 https:\/\/doi.org\/10.1109\/ICRA.2016.7487558 (2016).","DOI":"10.1109\/ICRA.2016.7487558"},{"key":"8216_CR6","doi-asserted-by":"publisher","first-page":"201555","DOI":"10.1109\/ACCESS.2020.3035498","volume":"8","author":"D Yoon","year":"2020","unstructured":"Yoon, D., Kim, E., Choi, I., Han, S. W. & Yang, S. Prediction of voluntary motion using Decomposition-and-Ensemble framework with deep neural networks. IEEE Access. 8, 201555\u2013201565 (2020).","journal-title":"IEEE Access."},{"key":"8216_CR7","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1080\/00207454.2018.1450253","volume":"128","author":"Q Sun","year":"2018","unstructured":"Sun, Q. et al. A feature extraction method for adaptive DBS using an improved EMD. Int. J. Neurosci. 128, 975\u2013986 (2018).","journal-title":"Int. J. Neurosci."},{"key":"8216_CR8","doi-asserted-by":"publisher","first-page":"104147","DOI":"10.1016\/j.bspc.2022.104147","volume":"79","author":"B Kara Gulay","year":"2023","unstructured":"Kara Gulay, B., Demirel, N., Vahaplar, A. & Guducu, C. A novel feature extraction method using chemosensory EEG for parkinson\u2019s disease classification. Biomed. Signal Process. Control. 79, 104147 (2023).","journal-title":"Biomed. Signal Process. Control"},{"key":"8216_CR9","doi-asserted-by":"publisher","first-page":"22547","DOI":"10.1038\/s41598-022-26644-7","volume":"12","author":"M Aljalal","year":"2022","unstructured":"Aljalal, M., Aldosari, S. A., Molinas, M., AlSharabi, K. & Alturki, F. A. Detection of parkinson\u2019s disease from EEG signals using discrete wavelet transform, different entropy measures, and machine learning techniques. Sci. Rep. 12, 22547 (2022).","journal-title":"Sci. Rep."},{"key":"8216_CR10","doi-asserted-by":"publisher","first-page":"103883","DOI":"10.1016\/j.bspc.2022.103883","volume":"78","author":"R Zhang","year":"2022","unstructured":"Zhang, R., Jia, J. & Zhang, R. EEG analysis of parkinson\u2019s disease using time\u2013frequency analysis and deep learning. Biomed. Signal Process. Control. 78, 103883 (2022).","journal-title":"Biomed. Signal Process. Control"},{"key":"8216_CR11","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1007\/s11517-008-0369-0","volume":"46","author":"SM Rissanen","year":"2008","unstructured":"Rissanen, S. M. et al. Surface EMG and acceleration signals in parkinson\u2019s disease: feature extraction and cluster analysis. Med. Biol. Eng. Comput. 46, 849\u2013858 (2008).","journal-title":"Med. Biol. Eng. Comput."},{"key":"8216_CR12","doi-asserted-by":"publisher","first-page":"283","DOI":"10.3390\/bioengineering9070283","volume":"9","author":"K Safi","year":"2022","unstructured":"Safi, K. et al. EMD-Based method for supervised classification of parkinson\u2019s disease patients using balance control data. Bioengineering 9, 283 (2022).","journal-title":"Bioengineering"},{"key":"8216_CR13","doi-asserted-by":"publisher","unstructured":"Ghassemi, N. H. et al. Combined accelerometer and EMG analysis to differentiate essential tremor from Parkinson\u2019s disease. in. 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 672\u2013675 (IEEE, Orlando, FL, USA, 2016). (2016). https:\/\/doi.org\/10.1109\/EMBC.2016.7590791","DOI":"10.1109\/EMBC.2016.7590791"},{"key":"8216_CR14","unstructured":"Bhoi, A. K. Classification and Clustering of Parkinson\u2019s and Healthy Control Gait Dynamics Using LDA and K-means. (2017)."},{"key":"8216_CR15","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1123\/jab.2019-0400","volume":"36","author":"Y Li","year":"2020","unstructured":"Li, Y., Zhang, S. & Odeh, C. Automated classification of postural control for individuals with parkinson\u2019s disease using a machine learning approach: A preliminary study. J. Appl. Biomech. 36, 334\u2013339 (2020).","journal-title":"J. Appl. Biomech."},{"key":"8216_CR16","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/978-981-15-1451-7_5","volume-title":"Cognitive Informatics and Soft Computing","author":"R Subba","year":"2020","unstructured":"Subba, R. & Bhoi, A. K. Feature extraction and classification between control and parkinson\u2019s using EMG signal. In Cognitive Informatics and Soft Computing Vol. 1040 (eds Mallick, P. K. et al.) 45\u201352 (Springer Singapore, 2020)."},{"key":"8216_CR17","doi-asserted-by":"publisher","unstructured":"Ouhmida, A., Raihani, A., Cherradi, B. & Lamalem, Y. Parkinson\u2019s disease classification using machine learning algorithms: performance analysis and comparison. in 2nd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) 1\u20136 (IEEE, Meknes, Morocco, 2022). 1\u20136 (IEEE, Meknes, Morocco, 2022). (2022). https:\/\/doi.org\/10.1109\/IRASET52964.2022.9738264","DOI":"10.1109\/IRASET52964.2022.9738264"},{"key":"8216_CR18","doi-asserted-by":"publisher","first-page":"1395","DOI":"10.3390\/diagnostics11081395","volume":"11","author":"SJ Priya","year":"2021","unstructured":"Priya, S. J. et al. Local pattern transformation based feature extraction for recognition of parkinson\u2019s disease based on gait signals. Diagnostics 11, 1395 (2021).","journal-title":"Diagnostics"},{"key":"8216_CR19","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.1007\/s00521-016-2756-z","volume":"30","author":"R Yuvaraj","year":"2018","unstructured":"Yuvaraj, R., Rajendra Acharya, U. & Hagiwara, Y. A novel parkinson\u2019s disease diagnosis index using higher-order spectra features in EEG signals. Neural Comput. Applic. 30, 1225\u20131235 (2018).","journal-title":"Neural Comput. Applic"},{"key":"8216_CR20","doi-asserted-by":"publisher","first-page":"7338","DOI":"10.1016\/j.eswa.2012.01.084","volume":"39","author":"SH Lee","year":"2012","unstructured":"Lee, S. H. & Lim, J. S. Parkinson\u2019s disease classification using gait characteristics and wavelet-based feature extraction. Expert Syst. Appl. 39, 7338\u20137344 (2012).","journal-title":"Expert Syst. Appl."},{"key":"8216_CR21","doi-asserted-by":"publisher","first-page":"107946","DOI":"10.1016\/j.compeleceng.2022.107946","volume":"101","author":"JJ Hathaliya","year":"2022","unstructured":"Hathaliya, J. J. et al. Parkinson and essential tremor classification to identify the patient\u2019s risk based on tremor severity. Comput. Electr. Eng. 101, 107946 (2022).","journal-title":"Comput. Electr. Eng."},{"key":"8216_CR22","doi-asserted-by":"publisher","first-page":"101683","DOI":"10.1016\/j.bspc.2019.101683","volume":"56","author":"AB Oktay","year":"2020","unstructured":"Oktay, A. B. & Kocer, A. Differential diagnosis of Parkinson and essential tremor with convolutional LSTM networks. Biomed. Signal Process. Control. 56, 101683 (2020).","journal-title":"Biomed. Signal Process. Control"},{"key":"8216_CR23","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.1007\/s13246-023-01284-x","volume":"46","author":"H G\u00f6ker","year":"2023","unstructured":"G\u00f6ker, H. Automatic detection of parkinson\u2019s disease from power spectral density of electroencephalography (EEG) signals using deep learning model. Phys. Eng. Sci. Med. 46, 1163\u20131174 (2023).","journal-title":"Phys. Eng. Sci. Med."},{"key":"8216_CR24","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1109\/TNSRE.2017.2782361","volume":"26","author":"PY Chan","year":"2018","unstructured":"Chan, P. Y. et al. An In\u2013Laboratory validity and reliability tested system for quantifying Hand\u2013Arm tremor in motions. IEEE Trans. Neural Syst. Rehabil Eng. 26, 460\u2013467 (2018).","journal-title":"IEEE Trans. Neural Syst. Rehabil Eng."},{"key":"8216_CR25","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s40734-020-00086-7","volume":"7","author":"EMJ van Brummelen","year":"2020","unstructured":"van Brummelen, E. M. J. et al. Quantification of tremor using consumer product accelerometry is feasible in patients with essential tremor and parkinson\u2019s disease: a comparative study. J. Clin. Mov. Disorders. 7, 4 (2020).","journal-title":"J. Clin. Mov. Disorders"},{"key":"8216_CR26","doi-asserted-by":"publisher","first-page":"808","DOI":"10.1152\/japplphysiol.01041.2020","volume":"131","author":"CM Germer","year":"2021","unstructured":"Germer, C. M. et al. Surface EMG cross talk quantified at the motor unit population level for muscles of the hand, thigh, and calf. J. Appl. Physiol. (1985). 131, 808\u2013820 (2021).","journal-title":"J. Appl. Physiol. (1985)"},{"key":"8216_CR27","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1038\/s41597-024-03740-z","volume":"11","author":"CK Perera","year":"2024","unstructured":"Perera, C. K. et al. A motion capture dataset on human sitting to walking transitions. Sci. Data. 11, 878 (2024).","journal-title":"Sci. Data"},{"key":"8216_CR28","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1007\/s11517-006-0065-x","volume":"44","author":"ER De Lima","year":"2006","unstructured":"De Lima, E. R., Andrade, A. O., Pons, J. L., Kyberd, P. & Nasuto, S. J. Empirical mode decomposition: a novel technique for the study of tremor time series. Med. Bio Eng. Comput. 44, 569\u2013582 (2006).","journal-title":"Med. Bio Eng. Comput."},{"key":"8216_CR29","doi-asserted-by":"publisher","first-page":"8550","DOI":"10.3390\/s150408550","volume":"15","author":"Z Ma","year":"2015","unstructured":"Ma, Z., Wen, G. & Jiang, C. EEMD independent extraction for mixing features of rotating machinery reconstructed in phase space. Sensors 15, 8550\u20138569 (2015).","journal-title":"Sensors"},{"key":"8216_CR30","doi-asserted-by":"crossref","unstructured":"Gao, Y., Ge, G., Sheng, Z. & Sang, E. Analysis and Solution to the Mode Mixing Phenomenon in EMD. in 2008 Congress on Image and Signal Processing vol. 5 223\u2013227 (2008).","DOI":"10.1109\/CISP.2008.193"},{"key":"8216_CR31","doi-asserted-by":"publisher","DOI":"10.1142\/S1793536909000047","author":"Z Wu","year":"2011","unstructured":"Wu, Z. & Huang, N. E. Ensemble Empirical Mode Decomposition: A Noise-assisted Data Analysis Method. Adv. Adapt. Data Anal. https:\/\/doi.org\/10.1142\/S1793536909000047 (2011).","journal-title":"Adv. Adapt. Data Anal."},{"key":"8216_CR32","doi-asserted-by":"crossref","unstructured":"Huang, N. E. Hilbert-Huang Transform and its Applications (World Scientific, 2014).","DOI":"10.1142\/8804"},{"key":"8216_CR33","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1016\/j.bspc.2013.10.004","volume":"10","author":"S Wang","year":"2014","unstructured":"Wang, S., Gao, Y., Zhao, J. & Cai, H. Adaptive sliding bandlimited multiple fourier linear combiner for Estimation of pathological tremor. Biomed. Signal Process. Control. 10, 260\u2013274 (2014).","journal-title":"Biomed. Signal Process. Control"},{"key":"8216_CR34","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/S0165-0270(97)02263-2","volume":"74","author":"CN Riviere","year":"1997","unstructured":"Riviere, C. N., Reich, S. G. & Thakor, N. V. Adaptive fourier modeling for quantification of tremor1. J. Neurosci. Methods. 74, 77\u201387 (1997).","journal-title":"J. Neurosci. Methods"},{"key":"8216_CR35","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1016\/j.cmpb.2010.03.018","volume":"99","author":"LZ Popovi\u0107","year":"2010","unstructured":"Popovi\u0107, L. Z., \u0160ekara, T. B. & Popovi\u0107, M. B. Adaptive band-pass filter (ABPF) for tremor extraction from inertial sensor data. Comput. Methods Programs Biomed. 99, 298\u2013305 (2010).","journal-title":"Comput. Methods Programs Biomed."},{"key":"8216_CR36","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/j.dsp.2011.01.010","volume":"21","author":"L Ai","year":"2011","unstructured":"Ai, L., Wang, J. & Yao, R. Classification of parkinsonian and essential tremor using empirical mode decomposition and support vector machine. Digit. Signal Proc. 21, 543\u2013550 (2011).","journal-title":"Digit. Signal Proc."},{"key":"8216_CR37","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.compbiomed.2018.02.007","volume":"95","author":"HB Kim","year":"2018","unstructured":"Kim, H. B. et al. Wrist sensor-based tremor severity quantification in parkinson\u2019s disease using convolutional neural network. Comput. Biol. Med. 95, 140\u2013146 (2018).","journal-title":"Comput. Biol. Med."},{"key":"8216_CR38","doi-asserted-by":"publisher","unstructured":"Tang, S. Y., Hoang, N. S., Chui, C. K., Lim, J. H. & Chua, M. C. H. Development of Wearable Gait Assistive Device Using Recurrent Neural Network. in IEEE\/SICE International Symposium on System Integration (SII) 626\u2013631 (2019). 626\u2013631 (2019). (2019). https:\/\/doi.org\/10.1109\/SII.2019.8700415","DOI":"10.1109\/SII.2019.8700415"},{"key":"8216_CR39","doi-asserted-by":"publisher","first-page":"102459","DOI":"10.1016\/j.artmed.2022.102459","volume":"135","author":"L Borz\u00ec","year":"2023","unstructured":"Borz\u00ec, L., Sigcha, L., Rodr\u00edguez-Mart\u00edn, D. & Olmo, G. Real-time detection of freezing of gait in parkinson\u2019s disease using multi-head convolutional neural networks and a single inertial sensor. Artif. Intell. Med. 135, 102459 (2023).","journal-title":"Artif. Intell. Med."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-08216-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-08216-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-08216-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T11:09:33Z","timestamp":1759921773000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-08216-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,8]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["8216"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-08216-7","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,8]]},"assertion":[{"value":"4 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2025","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 declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"The research primarily took place at the Neurology Clinic of Penang General Hospital, following the National Institutes of Health guidelines. It received approval from the Medical Research Ethics Committee within the National Institutes of Health, Malaysia.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"35064"}}