A Robust Recession Detective Analysis System using IoT Smart Sensor Devices

Abstract

This study suggests a wearable gadget with an autonomous fall detector that can lower risks by identifying falls and notifying care takers right away. This research study combines a heart-rate sensor and an accelerometer to create a user-adaptive fall detection system based on cluster analysis. The suggested fall detector seeks to achieve high accuracy using a simple model under a variety of circumstances. Additionally, this research study tests the efficiency of the cluster-analysis-based anomaly identification as well as the performance improvement of combining a heart rate sensor and an accelerometer. This study also demonstrates the utility of the user-adaptive approach when using both acceleration and heart rate inputs. The system will alert the carer through GSM if the user's orientation data values become aberrant in any way. The system design takes into account a straightforward, inexpensive, and power-efficient design.