Design and Development of an IoT Enabled Low-Cost Smart Hand Glove System for Gait Detection in Stroke Patients

Stroke is a non-communicable disease in human beings signifies a critical, pervasive, and widely recognized health crisis. Stroke-induced gait alterations can significantly impact a patient’s ability to perform daily activities. In the recent past, stroke became one of the primary cause of the disability in elderly people and recorded as third leading cause of death globally. According to statistics given by National Center for Disease Informatics and Research(NCDIR), stroke is India’s 3rd leading source of death and the 6th leading reason of disability. To this end, there exists different rehabilitation models to detect human gait in stroke survivors. Human gait, a complex interplay of limb (arm or leg) movements, velocity, and energy cycles, holds crucial diagnostic information for stroke patients. Most of the existing models are cost effective and intrusive type, cause discomfort while using. Thus, in this paper, a wearable low-cost hand glove based system for gait detection and analysis for stroke survivors using IoT is proposed. The system leverages MEMS accelerometer sensor (ADXL335), offers a non-intrusive means of collecting gait dynamics like motion, shock or vibration and allows continuous monitoring. Further, the MEMS sensor is integrated into an IoT enabled hand glove with Wi-Fi communication module used for wireless monitoring of gait dynamics. Later, the collected data is analyzed using MATLAB. The analysis provides a thorough understanding of post-stroke gait patterns and cautions the stroke survivors about their abnormal gait. In addition, the proposed wearable hand glove model possibly saves the patients from future injuries and may allow to tailor rehabilitation strategies for every individual.