A Deep Learning Approach for Safety Monitoring of Sick People
G. Ramesh
Abstract
This project illustrates a method of smart recognition of human behavior to automatically recognize human actions from skeletal joint movements and integrate the skills.This is a low-cost solution and has high precision.An independent mobile app is also intended to track the condition of individuals and their environment while they are alone.The mobile application also incorporates a Notification API integration to enable the sending of warning alerts during irregular conditions.Therefore, our initiative offers a way to assist senior citizens and children with some kind of mishap and health problems.This research proposed novel Convolutional Neural Network (ConvNet/CNN) to predict the action based on human activity.Proposed model provides 3% better accuracy than the existing state of art methodologies.