{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T01:54:10Z","timestamp":1769824450285,"version":"3.49.0"},"reference-count":41,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2024,2,12]],"date-time":"2024-02-12T00:00:00Z","timestamp":1707696000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"UK EPSRC Industrial CASE","award":["2784470"],"award-info":[{"award-number":["2784470"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Parkinson\u2019s disease (PD) is the second most prevalent dementia in the world. Wearable technology has been useful in the computer-aided diagnosis and long-term monitoring of PD in recent years. The fundamental issue remains how to assess the severity of PD using wearable devices in an efficient and accurate manner. However, in the real-world free-living environment, there are two difficult issues, poor annotation and class imbalance, both of which could potentially impede the automatic assessment of PD. To address these challenges, we propose a novel framework for assessing the severity of PD patient\u2019s in a free-living environment. Specifically, we use clustering methods to learn latent categories from the same activities, while latent Dirichlet allocation (LDA) topic models are utilized to capture latent features from multiple activities. Then, to mitigate the impact of data imbalance, we augment bag-level data while retaining key instance prototypes. To comprehensively demonstrate the efficacy of our proposed framework, we collected a dataset containing wearable-sensor signals from 83 individuals in real-life free-living conditions. The experimental results show that our framework achieves an astounding 73.48% accuracy in the fine-grained (normal, mild, moderate, severe) classification of PD severity based on hand movements. Overall, this study contributes to more accurate PD self-diagnosis in the wild, allowing doctors to provide remote drug intervention guidance.<\/jats:p>","DOI":"10.3390\/s24041196","type":"journal-article","created":{"date-parts":[[2024,2,12]],"date-time":"2024-02-12T06:19:59Z","timestamp":1707718799000},"page":"1196","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Wearable-Sensor-Based Weakly Supervised Parkinson\u2019s Disease Assessment with Data Augmentation"],"prefix":"10.3390","volume":"24","author":[{"given":"Peng","family":"Yue","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Sheffield, Sheffield S10 2TN, UK"},{"name":"AntData Ltd., Liverpool L16 2AE, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziheng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Software, Yunnan University, Kunming 650106, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Menghui","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Sheffield, Sheffield S10 2TN, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xulong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Sheffield, Sheffield S10 2TN, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Po","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Sheffield, Sheffield S10 2TN, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,2,12]]},"reference":[{"key":"ref_1","first-page":"8","article-title":"Symptoms and possible causes cures for parkinsons disease","volume":"3","author":"McHenry","year":"2021","journal-title":"Brain Matters"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1212\/01.wnl.0000247740.47667.03","article-title":"Projected number of people with Parkinson disease in the most populous nations, 2005 through 2030","volume":"68","author":"Dorsey","year":"2007","journal-title":"Neurology"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1001\/archneur.56.1.33","article-title":"Diagnostic criteria for Parkinson disease","volume":"56","author":"Gelb","year":"1999","journal-title":"Arch. Neurol."},{"key":"ref_4","unstructured":"Nass, R., and Przedborski, S. (2011). Parkinson\u2019s Disease: Molecular and Therapeutic Insights from Model Systems, Elsevier."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2129","DOI":"10.1002\/mds.22340","article-title":"Movement Disorder Society-sponsored revision of the Unified Parkinson\u2019s Disease Rating Scale (MDS-UPDRS): Scale presentation and clinimetric testing results","volume":"23","author":"Goetz","year":"2008","journal-title":"Mov. Disord. Off. J. Mov. Disord. Soc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1186\/s12883-020-01996-7","article-title":"Parkinson\u2019s disease: Current assessment methods and wearable devices for evaluation of movement disorder motor symptoms-a patient and healthcare professional perspective","volume":"20","author":"AlMahadin","year":"2020","journal-title":"BMC Neurol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.pmcj.2017.06.018","article-title":"A Advanced internet of things for personalised healthcare systems: A survey","volume":"41","author":"Qi","year":"2017","journal-title":"Pervasive Mob. Comput."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1016\/j.inffus.2019.09.002","article-title":"An overview of data fusion techniques for Internet of Things enabled 436 physical activity recognition and measure","volume":"55","author":"Qi","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1109\/JBHI.2020.3009319","article-title":"Validation of inertial sensing-based wearable device for tremor and bradykinesia quantification","volume":"25","author":"Dai","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"105099","DOI":"10.1016\/j.engappai.2022.105099","article-title":"Parkinson\u2019s disease diagnosis and stage prediction based on gait signal analysis using EMD and CNN\u2013LSTM network","volume":"114","author":"Vidya","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_11","first-page":"4007909","article-title":"Detection and Classification of Early Stages of Parkinson\u2019s Disease Through Wearable Sensors and Machine Learning","volume":"2023","author":"Shcherbak","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/TITB.2011.2182616","article-title":"Assessment of tremor activity in the Parkinson\u2019s disease using a set of wearable sensors","volume":"16","author":"Rigas","year":"2012","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2187","DOI":"10.3390\/s90302187","article-title":"Measurement and evaluation of finger tapping movements using log-linearized Gaussian mixture networks","volume":"9","author":"Shima","year":"2009","journal-title":"Sensors"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2504","DOI":"10.1002\/mds.23893","article-title":"Differential response of speed, amplitude, and rhythm to dopaminergic medications in Parkinson\u2019s disease","volume":"26","author":"Espay","year":"2011","journal-title":"Mov. Disord."},{"key":"ref_15","first-page":"1","article-title":"Validation of 24-hour ambulatory gait assessment in Parkinson\u2019s disease with simultaneous video observation","volume":"10","author":"MacDougall","year":"2011","journal-title":"Biomed. Eng. Online"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1038\/s41746-018-0071-z","article-title":"Wearable sensors for Parkinson\u2019s disease: Which data are worth collecting for training symptom detection models","volume":"1","author":"Lonini","year":"2018","journal-title":"NPJ Digit. Med."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1293","DOI":"10.1002\/mds.26718","article-title":"Free-living monitoring of Parkinson\u2019s disease: Lessons from the field","volume":"31","author":"Godfrey","year":"2016","journal-title":"Mov. Disord."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1002\/mds.870090109","article-title":"Portable device for quantifying parkinsonian wrist rigidity","volume":"9","author":"Caligiuri","year":"1994","journal-title":"Mov. Disord."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3738","DOI":"10.1109\/JSEN.2020.3027564","article-title":"Avoiding Misdiagnosis of Parkinson\u2019s Disease with the Use of Wearable Sensors and Artificial Intelligence","volume":"21","author":"Talitckii","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Sigcha, L., Dom\u00ednguez, B., Borz\u00ec, L., Costa, N., Costa, S., Arezes, P., L\u00f3pez, J.M., De Arcas, G., and Pav\u00f3n, I. (2022). Bradykinesia Detection in Parkinson\u2019s Disease Using Smartwatches\u2019 Inertial Sensors and Deep Learning Methods. Electronics, 11.","DOI":"10.3390\/electronics11233879"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1093\/nsr\/nwx106","article-title":"A brief introduction to weakly supervised learning","volume":"5","author":"Zhou","year":"2018","journal-title":"Natl. Sci. Rev."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.artint.2013.06.003","article-title":"Multiple instance classification: Review, taxonomy and comparative study","volume":"201","author":"Amores","year":"2013","journal-title":"Artif. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Pinheiro, P.O., and Collobert, R. (2015, January 7\u201312). From image-level to pixel-level labeling with convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298780"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/j.compbiomed.2018.04.004","article-title":"Mass detection in digital breast tomosynthesis data using convolutional neural networks and multiple instance learning","volume":"96","author":"Yousefi","year":"2018","journal-title":"Comput. Biol. Med."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"8004","DOI":"10.1038\/srep08004","article-title":"MBSTAR: Multiple instance learning for predicting specific functional binding sites in microRNA targets","volume":"5","author":"Bandyopadhyay","year":"2015","journal-title":"Sci. Rep."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1109\/RBME.2017.2651164","article-title":"Multiple-instance learning for medical image and video analysis","volume":"10","author":"Quellec","year":"2017","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, A., Cebulla, A., Panev, S., Hodgins, J., and De la Torre, F. (2017, January 11\u201315). Weakly-supervised learning for Parkinson\u2019s disease tremor detection. Proceedings of the 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jeju Island, Repbulic of Korea.","DOI":"10.1109\/EMBC.2017.8036782"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Um, T.T., Pfister, F.M., Pichler, D., Endo, S., Lang, M., Hirche, S., Fietzek, U., and Kuli\u0107, D. (2017, January 13\u201317). Data augmentation of wearable sensor data for parkinson\u2019s disease monitoring using convolutional neural networks. Proceedings of the 19th ACM International Conference on Multimodal Interaction, Glasgow, UK.","DOI":"10.1145\/3136755.3136817"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"12819","DOI":"10.1038\/s41598-022-16741-y","article-title":"EMD-based data augmentation method applied to handwriting data for the diagnosis of Essential Tremor using LSTM networks","volume":"12","author":"Otero","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1097\/00004691-199909000-00010","article-title":"Using frequency domain characteristics to discriminate physiologic and parkinsonian tremors","volume":"16","author":"Beuter","year":"1999","journal-title":"J. Clin. Neurophysiol."},{"key":"ref_31","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chandrasekaran, K., Gerych, W., Buquicchio, L., Alajaji, A., Agu, E., and Rundensteiner, E. (2021, January 23\u201327). CARTMAN: Complex Activity Recognition Using Topic Models for Feature Generation from Wearable Sensor Data. Proceedings of the 2021 IEEE International Conference on Smart Computing (SMARTCOMP), Irvine, CA, USA.","DOI":"10.1109\/SMARTCOMP52413.2021.00026"},{"key":"ref_33","unstructured":"Frank, E., and Xu, X. (2003). Applying Propositional Learning Algorithms to Multi-Instance Data, University of Waikato."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1931","DOI":"10.1109\/TPAMI.2006.248","article-title":"MILES: Multiple-instance learning via embedded instance selection","volume":"28","author":"Chen","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_35","unstructured":"Csurka, G., Dance, C., Fan, L., Willamowski, J., and Bray, C. (2004, January 15). Visual categorization with bags of keypoints. Proceedings of the Workshop on Statistical Learning in Computer Vision, ECCV, Prague, Czech Republic."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1007\/s11263-013-0636-x","article-title":"Image classification with the fisher vector: Theory and practice","volume":"105","author":"Perronnin","year":"2013","journal-title":"Int. J. Comput. Vis."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Yuan, L., Zhao, L., and Xu, H. (2015, January 27\u201330). Multi-instance learning via instance-based and bag-based representation transformations. Proceedings of the 2015 IEEE International Conference on Image Processing (ICIP), Quebec City, QC, Canada.","DOI":"10.1109\/ICIP.2015.7351307"},{"key":"ref_38","unstructured":"Song, H., Zhu, Z., and Wang, X. (2015). Bag reference vector for multi-instance learning. arXiv."},{"key":"ref_39","unstructured":"Dong, L. (2006). A Comparison of Multi-Instance Learning Algorithms. [Ph.D. Thesis, The University of Waikato]."},{"key":"ref_40","unstructured":"Zhou, M., Zhang, Y., Yang, Y., Liu, T., and Yang, P. (2023, January 7\u201314). Robust Temporal Smoothness in Multi-Task Learning. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zhou, M., and Yang, P. (2023, January 6\u201310). Automatic temporal relation in multi-task learning. Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Long Beach, CA, USA.","DOI":"10.1145\/3580305.3599261"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/4\/1196\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:58:54Z","timestamp":1760104734000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/4\/1196"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,12]]},"references-count":41,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["s24041196"],"URL":"https:\/\/doi.org\/10.3390\/s24041196","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,12]]}}}