Elderly monitoring tag

• Main Author: Lie, Thomas Alison
• Other Authors: Oh Hong Lye
• Format: Final Year Project
• Language: English
• Published: 2019
• Subjects: DRNTU::Engineering::Computer science and engineering
• Online Access: http://hdl.handle.net/10356/77050
• Institution: Nanyang Technological University

This project described an implementation of the elderly monitoring tag system. It is implemented on sensor tag CC2650 by Texas Instrument and featured fall detection and step detection algorithm with the purpose of sending a warning if a medical hazard is detected while reducing power consumption by minimizing Radio Frequency communication. Additional algorithms are also implemented to further enhance the system such as single point calibration for temperature detection, signal strength detection which will regulate the connection between the Sensor Tag devices and the listening servers, and average activity level functionality which keeps track of how active a person compared to his/her peers. The data was collected from the sensor tag by using raspberry pi, which acts as the listening servers and processes the data sent by Sensor Tag devices. The algorithms were found to be working within the objective requirement. All simulated falls were detected with approximately 20 times reduced power consumption. Various results were obtained for simulated steps with an error of ±1 for 5 steps and ±2 for 20 steps. However, rare occurrences of 1 or 2 additional steps resulting in 23 or 24 steps were observed.