Development of a Wearable IoT and Artificial Neural Network-Based Gait Screening System for Parkinson’s Disease
Keywords:
Parkinson’s Disease, Wearable IMU, IoT Healthcare, Artificial Neural Network, Gait ScreeningAbstract
Parkinson’s Disease affects gait, balance, and mobility, while conventional assessment methods rely on brief clinical observation and specialist interpretation. This study develops a wearable IoT and Artificial Neural Network-based gait screening system for early Parkinson-like movement detection. The proposed innovation, GaitAI, integrates bilateral knee-mounted MPU6050 IMU sensors, ESP32 wireless communication, Blynk monitoring, Google Sheets cloud logging, ANN-based classification, and a web-based reporting platform. The system collects lower-limb acceleration data during walking, extracts gait features, and classifies gait patterns as either Normal or Parkinson-like. The prototype demonstrates wearable data acquisition, IoT transmission, cloud-based storage, machine learning integration, analytics visualization, and report generation. This innovation provides a practical, low-cost screening platform that may assist early awareness, user monitoring, and healthcare research. Although not intended to replace clinical diagnosis, the system shows potential as a digital healthcare support tool for Parkinson’s gait screening.
References
Mi, T.-M., et al. (2020). Repetitive transcranial magnetic stimulation improves Parkinson's freezing of gait via normalising brain connectivity. npj Parkinson's Disease, 6, 16. https://doi.org/10.1038/s41531-020-0118-0
Atrsaei, A., et al. (2021). Gait speed in clinical and daily living assessments in Parkinson's disease patients: Performance versus capacity. npj Parkinson's Disease, 7(1). https://doi.org/10.1038/s41531-021-00171-0
Warmerdam, E., et al. (2021). Arm swing responsiveness to dopaminergic medication in Parkinson's disease depends on task complexity. npj Parkinson's Disease, 7(1). https://doi.org/10.1038/s41531-021-00235-1
Oftedal, L., et al. (2023). Seed amplification assay as a diagnostic tool in newly-diagnosed Parkinson's disease. Journal of Parkinson's Disease, 13(5), 841–844. https://doi.org/10.3233/jpd-230065
Pedersen, C. C., et al. (2024). Serum neurofilament light at diagnosis: A prognostic indicator for accelerated disease progression in Parkinson's disease. npj Parkinson's Disease, 10(1). https://doi.org/10.1038/s41531-024-00768-1
Yang, B., et al. (2022). Intelligent wearable system with accurate detection of abnormal gait and timely cueing for mobility enhancement of people with Parkinson's disease. Wearable Technologies, 3. https://doi.org/10.1017/wtc.2022.9
Chan, H.-L., et al. (2024). Laser-light cueing shoes with integrated foot pressure and inertial sensing for investigating the impact of visual cueing on gait characteristics in Parkinson's disease individuals. Frontiers in Bioengineering and Biotechnology, 12, 1334403. https://doi.org/10.3389/fbioe.2024.1334403
Zhang, W., et al. (2022). Multimodal data for the detection of freezing of gait in Parkinson's disease. Scientific Data, 9(1). https://doi.org/10.1038/s41597-022-01713-8
Bikias, T., et al. (2021). DeepFoG: An IMU-based detection of freezing of gait episodes in Parkinson's disease patients via deep learning. Frontiers in Robotics and AI, 8. https://doi.org/10.3389/frobt.2021.537384
Bülbül, E. (2024). Wearable sensor-based gait analysis and robotic exoskeleton control for Parkinson's patients. ECSA-11, 83. https://doi.org/10.3390/ecsa-11-20456
Faisal, A. I., et al. (2021). A simple, low-cost multi-sensor-based smart wearable knee monitoring system. IEEE Sensors Journal, 21(6), 8253–8266. https://doi.org/10.1109/jsen.2020.3044784
Poleur, M., et al. (2025). Wearable inertial device for monitoring Parkinson's disease symptoms: A pilot study in a controlled environment. Scientific Reports, 15(1), 45479. https://doi.org/10.1038/s41598-025-28927-1
Saez, Y., et al. (2025). A wearable Internet of Things-based device for the quantitative assessment of hand tremors in Parkinson's disease: The ELENA project. Sensors, 25(9), 2763. https://doi.org/10.3390/s25092763
Franco, T., et al. (2022). Motion sensors for knee angle recognition in muscle rehabilitation solutions. Sensors, 22(19), 7605. https://doi.org/10.3390/s22197605
Sáez, Y., et al. (2025). Precision analysis and calibration of the MPU6050 sensor for tremor measurement in Parkinson's disease. Proceedings of LACCEI 2025. https://doi.org/10.18687/laccei2025.1.1.848
Trabassi, D., et al. (2022). Machine learning approach to support the detection of Parkinson's disease in IMU-based gait analysis. Sensors, 22(10), 3700. https://doi.org/10.3390/s22103700
Aich, S., et al. (2020). Design of a machine learning-assisted wearable accelerometer-based automated system for studying the effect of dopaminergic medicine on gait characteristics of Parkinson's patients. Journal of Healthcare Engineering, 2020, 1–11. https://doi.org/10.1155/2020/1823268
Zhang, X., et al. (2025). Evaluation of Parkinson's disease motor symptoms via wearable inertial measurements units and surface electromyography sensors. Bioengineering, 12(10), 1116. https://doi.org/10.3390/bioengineering12101116
Gutowski, T., et al. (2025). Machine learning-based assessment of Parkinson's disease symptoms using wearable and smartphone sensors. Sensors, 25(16), 4924. https://doi.org/10.3390/s25164924
Tanim, S. A. (2021). PD-BIOSTAMPRC21: Parkinson’s disease accelerometry [Dataset]. Kaggle. https://www.kaggle.com/datasets/arfintanim/hamster-is-a-small-rat-which-help-you-to-be-cat
Johnson, S., Kantartjis, M., Severson, J., Dorsey, R., Adams, J. L., Kangarloo, T., Kostrzebski, M. A., Best, A., Merickel, M., Amato, D., Severson, B., Jezewski, S., Polyak, S., Keil, A., Cosman, J., & Anderson, D. (2024). Wearable sensor-based assessments for remotely screening early-stage Parkinson’s disease. Sensors, 24(17), 5637. https://doi.org/10.3390/s24175637
Khalil, R. M., Shulman, L. M., Gruber-Baldini, A. L., Reich, S. G., Savitt, J. M., Hausdorff, J. M., von Coelln, R., & Cummings, M. P. (2025). Applying wearable sensors and machine learning to the diagnostic challenge of distinguishing Parkinson’s disease from other forms of parkinsonism. Biomedicines, 13(3), 572. https://doi.org/10.3390/biomedicines13030572
Ma, L., Lin, S., Jin, J., Wang, Z., Wang, X., Chen, Z., Ling, Y., Zhang, F., Ren, K., & Feng, T. (2025). Objective assessment of gait and posture symptoms in Parkinson’s disease using wearable sensors and machine learning. Frontiers in Aging Neuroscience, 17, Article 1618764. https://doi.org/10.3389/fnagi.2025.1618764
Yang, P. K., Filtjens, B., Ginis, P., Goris, M., Nieuwboer, A., Gilat, M., Slaets, P., & Vanrumste, B. (2024). Freezing of gait assessment with inertial measurement units and deep learning: Effect of tasks, medication states, and stops. Journal of NeuroEngineering and Rehabilitation, 21(1), Article 24. https://doi.org/10.1186/s12984-024-01320-1
Zhang, W., Ling, Y., Chen, Z., Ren, K., Chen, S., Huang, P., & Tan, Y. (2024). Wearable sensor-based quantitative gait analysis in Parkinson’s disease patients with different motor subtypes. npj Digital Medicine, 7, Article 169. https://doi.org/10.1038/s41746-024-01163-z
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Guan Chengg Wong, Muhammad Fitri Rosle, Shankari Nair Murali, Zunuwanas Mohamad
This work is licensed under a Creative Commons Attribution 4.0 International License.
