Privacy-Preserving Deep Learning Models for Human Activity Recognition in Edge Computing Environments

The increase of wearable devices and smart sensors led to increase of human activity recognition system; this plays a vital role in various domains like healthcare and mainly we need to take further modifications on education, sports and security. Human activity recognition system raises privacy concerns, it often involves the collection of sensitive data of users, there is an approach to modernizing human activity recognition system by using machine learning techniques and data identification and lattice based methods to ensure privacy while restructuring and managing unwanted data or activities in the recognition process. Human activity recognition system involves the continuous monitoring and analyzing the individual activities. To address this, we can use machine learning approaches like deep learning models which improve the accuracy of activity recognition while minimizing the intrusion on the user privacy. Here we use machine learning for accurate the activity recognition and deepdeep learning techniques for preserving privacy and restructuring of unwanted activities. Combining these techniques we can safeguard user privacy in an increasingly data centric world. In this paper we are seeing as the negligible of human exercises from the pictures or recordings taken from the different public where the high goal can be distinguished and getting the exceptionally low goal and protection can be stowed away from such pictures or recordings.