Non-Parametric Learning Technique for Activity Recognition in Elderly Patients
Nimisha Ghosh, Satyabrata Maity, Krishanu Maity, Sayantan Saha · 2019
To improve the generic lifestyle of a patient, remote monitoring has become an essential part of patient assistance in any health care services. Patient falls in nursing homes and hospitals are a major source of concern in any health care services. To mitigate this problem and to reduce falls, improved surveillance system which helps in activity recognition in a patient is the need of the day. This work proposes an activity recognition system using Grey Relational Analysis which considers readings from lightweight wearable sensors to detect activities in patients. To verify the feasibility of the proposed work, it has been applied on a real life data. It can be seen from the simulation results that the proposed methodology shows competitively improved results than some of the existing contemporary machine learning techniques.