Wearable Sensors-based Assistive Technologies for Patient Health Monitoring

Nouf Abdullah Almujally¹Danyal Khan²Naif Al Mudawi³Mohammed Alonazi⁴Asaad Algarni⁵Ahmad Jalal^2*Hui Liu^6*

• ¹Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia
• ²Air University, Islamabad, Pakistan
• ³Najran University, Najran, Saudi Arabia
• ⁴Prince Sattam Bin Abdulaziz University, Al-Kharj, Saudi Arabia
• ⁵Northern Border University, Arar, Northern Borders, Saudi Arabia
• ⁶University of Bremen, Bremen, Bremen, Germany

With the advancement of handheld devices, patient health monitoring using wearable or handheld devices plays a vital role in overall health monitoring. In this article, we have integrated multi-model bio-signals to monitor patient health data during daily life activities continuously. Two well-known datasets from ScientISST MOVE and mHealth have been analyzed, the purpose of this study is to explore possibilities of using advanced bio-signals for monitoring patient vital signs during daily life activities and predict favorable and more accurate health-related solutions based on body current health-related real-time measurements. With the help of machine learning algorithms, we have observed classification accuracy of up to 94.67 % using the mHealth dataset and 95.12 % on the ScientISST MOVE dataset. Other performance indicators such as recall, precision, and F1 score also performed well. Overall, integrating a machine learning model, with bio-signals provides an enhanced ability to interpret complex real-time patient health monitoring for personalized care and overall smart health care.