An Extensive Study on HAR Systems to Recognize Daily Activities using Deep Learning Approaches
Gayathri Tippani, Veerraju Gampala · 2022 International Conference on Automation, Computing and Renewable Systems (ICACRS) · 2022
"Human Activity Recognition" (HAR) refers to the ability to recognise human physical movements using wearable devices or IoT sensors. In this epidemic, the majority of patients, particularly the elderly and those who are extremely ill, are placed in isolation units. Because of the quick development of COVID, it's tough for caregivers or others to keep an eye on them when they're in the same room. People are fitted with wearable gadgets to monitor them and take required precautions, and IoT-based video capturing equipment is installed in the isolation ward. The existing systems are designed to record and categorise six common actions, including walking, jogging, going upstairs, downstairs, sitting, and standing, using multi-class classification algorithms. This paper discussed the advantages and limitations associated with developing the model using deep learning approaches on the live streaming data through sensors using different publicly available datasets.