Experimental Classification of Movements Using IoT for the Study of Tremors Associated with Parkinson's Disease
DOI:
https://doi.org/10.5281/zenodo.23193092Keywords:
Enfermedad del Parkinson, ESP32, IoT, Machine Learning.Abstract
Parkinson’s disease is a progressive neurodegenerative disorder that primarily affects the motor system, causing symptoms such as tremor, rigidity, and difficulty controlling movements. In this context, a TinyML- and IoT-based system was developed to monitor and classify motor symptoms using an MPU6050 sensor and an EMG sensor integrated into an ESP32 microcontroller. The acquired signals were preprocessed and categorized into three classes: no tremor, mild tremor, and severe tremor. Different machine learning models were trained and compared, with Random Forest achieving the best performance, obtaining 96% accuracy, precision, recall, and F1-score. Finally, the selected model was implemented on the ESP32 to perform real-time classification and monitoring, demonstrating the potential of a low-cost, low-latency, and scalable solution for monitoring motor symptoms associated with Parkinson’s disease.
References
Advancer Technologies. (2013). Muscle Sensor v3 user’s manual.
Antonini, A., et al. (2023). Toward objective monitoring of Parkinson's disease motor symptoms using a wearable device: wearability and performance evaluation of PDMonitor®. Frontiers in Neurology, 14, Article 1080752. https://doi.org/10.3389/fneur.2023.1080752
Balestrino, R., & Schapira, A. H. V. (2020). Parkinson disease. European Journal of Neurology, 27(1), 27–42. https://doi.org/10.1111/ene.14108
Bloem, B. R., Okun, M. S., & Klein, C. (2021). Parkinson’s disease. The Lancet, 397(10291), 2284–2303. https://doi.org/10.1016/S0140-6736(21)00218-X
Bougea, A. (2025). Application of Wearable Sensors in Parkinson’s Disease: State of the Art. Journal of Sensor and Actuator Networks, 14(2), Article 23. https://doi.org/10.3390/jsan14020023
di Biase, L., et al. (2024). Machine learning and wearable sensors for automated Parkinson’s disease diagnosis aid: a systematic review. Journal of Neurology, 271, 6452–6470. https://doi.org/10.1007/s00415-024-12611-x
Elhanashi, A., Dini, P., Saponara, S., & Zheng, Q. (2024). Advancements in TinyML: Applications, Limitations, and Impact on IoT Devices. Electronics, 13(17), Article 3562. https://doi.org/10.3390/electronics13173562
Giannakopoulou, K. M., Roussaki, I., & Demestichas, K. (2022). Internet of Things Technologies and Machine Learning Methods for Parkinson's Disease Diagnosis, Monitoring and Management: A Systematic Review. Sensors, 22(5), Article 1799. https://doi.org/10.3390/s22051799
Gigante, A. F., et al. (2017). Rest tremor in Parkinson’s disease: Body distribution and time of appearance. Journal of the Neurological Sciences, 375, 215–219. https://doi.org/10.1016/j.jns.2016.12.057
Gokul, H., Suresh, P., Hari Vignesh, B., Pravin Kumaar, R., & Vijayaraghavan, V. (2020). Gait Recovery System for Parkinson’s Disease using Machine Learning on Embedded Platforms. In 2020 IEEE International Systems Conference (SysCon) (pp. 1–8). IEEE. https://doi.org/10.1109/SysCon47679.2020.9275930
Hercog, D., Lerher, T., Truntič, M., & Težak, O. (2023). Design and Implementation of ESP32-Based IoT Devices. Sensors, 23(15), Article 6739. https://doi.org/10.3390/s23156739
Heydari, S., & Mahmoud, Q. H. (2025). Tiny Machine Learning and On-Device Inference: A Survey of Applications, Challenges, and Future Directions. Sensors, 25(10), Article 3191. https://doi.org/10.3390/s25103191
InvenSense Inc. (2013). MPU-6000 and MPU-6050 register map and descriptions (Rev. 4.2). https://www.invensense.com
Kehnemouyi, Y. M., Coleman, T. P., & Tass, P. A. (2024). Emerging wearable technologies for multisystem monitoring and treatment of Parkinson's disease: a narrative review. Frontiers in Network Physiology, 4, Article 1354211. https://doi.org/10.3389/fnetp.2024.1354211
Ministerio de Salud y Protección Social. (2023). Gobierno de Colombia. https://www.minsalud.gov.co
Ou, R., et al. (2021). Facial tremor in patients with Parkinson's disease: prevalence, determinants and impacts on disease progression. BMC Neurology, 21(1), Article 86. https://doi.org/10.1186/s12883-021-02105-y
Rasool, M., Maqsood, S., & Azam, M. A. (2025). Machine Learning Strategies for Parkinson Tremor Classification Using Wearable Sensor Data (arXiv:2501.18671). arXiv. https://doi.org/10.48550/arXiv.2501.18671
Rincon-Montana, A. G., Pantoja, C., Torres, J. F., Tamayo Torres, C. S., & Rosselli, D. (2025). Prevalence, demographic characteristics of Parkinson disease and associated comorbidities: An analysis of the Colombian Ministry of Health official registry. Acta Neurológica Colombiana, 41(1). https://doi.org/10.22379/anc.v41i1.1927
Rodriguez, F., et al. (2024). Continuous and Unconstrained Tremor Monitoring in Parkinson’s Disease Using Supervised Machine Learning and Wearable Sensors. Parkinson's Disease, 2024, Article 5787563. https://doi.org/10.1155/2024/5787563
Tang, L., et al. (2024). A multimodal fusion network based on a cross-attention mechanism for the classification of Parkinsonian tremor and essential tremor. Scientific Reports, 14, Article 28050. https://doi.org/10.1038/s41598-024-79111-w
Weiss, A., Herman, T., Giladi, N., & Hausdorff, J. M. (2014). Objective Assessment of Fall Risk in Parkinson's Disease Using a Body-Fixed Sensor Worn for 3 Days. PLOS ONE, 9(5), Article e96675. https://doi.org/10.1371/journal.pone.0096675
Downloads
Published
How to Cite
Conference Proceedings Volume
Section
License
Copyright (c) 2026 Andres Felipe Orduz Pérez, Cesar Augusto Romero Molano, Luis Ángel Lavado Matias
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
