Gait Monitoring System for Stroke Prediction of Aging Adults
Health has become a major concern nowadays. People pass significant amount of time of daily life on walking, moving here and there and so on. Some health complexity happens during walking like heart problem, stroke etc. Stroke patient has unbalanced gait pattern compared to normal person. The Internet of Things (IoT) plays an important role in the development of connected people, which offers cloud connectivity, smartphone integration, safety, security, and healthcare services. Insole Foot Pressure sensor and accelerometer will be attached to the foot for gait speed, foot pressure and other gait pattern. Gait parameters of 68 Stroke patients and 208 Elderly healthy persons have been gathered in Chungnam National University Hospital Rehabilitation Center, Daejeon, South Korea. Gait parameters are foot pressure, gait acceleration etc. Dynafoot2 Insole sensor used for data acquisition. Subjects walked and perform activities like walking, sitting, standing, doing some regular activities during gait data acquisition. Area under curve (AUC) of performance curve for C4.5, SVM, Random Tree, Logistic Regression, LSVM, CART algorithms are 0.98, 0.976, 0.935, 0.909 and 0.906, 0.87 respectively. A gait monitoring system has been proposed for stroke onset prediction for stroke patient. IoT sensors are used to gather gait data and machine learning algorithms are used to classify gait pattern of stroke patient group and normal healthy group. In future, sensors such as EEG, EMG will be used to improve system reliability.
KeywordsStroke Gait Health monitoring Classification algorithms
This work was supported by the National Research Council of Science & Technology (NST) grant by the Korea government (MSIP) (No. CRC-15-05-ETRI).
- 2.Clark, D.J., Ting, L.H., Zajac, F.E., Neptune, R.R., Kautz, S.A.: Merging of healthy motor modules predicts reduced locomotor performance and muscle coordination complexity post-stroke 103(2), 844–857 (2010)Google Scholar
- 5.Lakhan, S.E., Kirchgessner, A., Hofer, M.: Inflammatory mechanisms in ischemic stroke: therapeutic approaches (in eng). J. Transl. Med. 7, 97 (2009)Google Scholar
- 7.Balaban, B., Tok, F.: Gait disturbances in patients with stroke. PM&R 6(7), 635–642 (2014)Google Scholar
- 10.Ponikowski, P., et al.: 2016 ESC guidelines for the diagnosis and treatment of acute and chronic heart failure. 18(8), 891–975 (2016)Google Scholar
- 11.Benson, L.C., Clermont, C.A., Bošnjak, E., Ferber, R.: The use of wearable devices for walking and running gait analysis outside of the lab: a systematic review. Gait & Posture 63, 124–138 (2018)Google Scholar
- 13.Hassanalieragh, M., et al.: Health monitoring and management using internet-of-things (IoT) sensing with cloud-based processing: opportunities and challenges. In: 2015 IEEE International Conference on Services Computing, pp. 285–292 (2015)Google Scholar
- 14.Park, S.J., Hong, S., Kim, D., Hussain, I., Seo, Y.: Intelligent In-Car Health Monitoring System for Elderly Drivers in Connected Car, Cham, pp. 40–44. Springer International Publishing (2019)Google Scholar
- 15.Park, S.J., et al.: Development of a real-time stroke detection system for elderly drivers using quad-chamber air cushion and IoT devices (2018). https://doi.org/10.4271/2018-01-0046