Activity monitoring of workers using single wearable inertial sensor

This Activity monitoring of workers in installations such as industries, underground tunnels, sewerage lines, remote field deployments etc. is a daunting task. Due to lack of communication systems and scarce energy resources, these scenarios pose great challenges in developing a monitoring system for workers. The design of activity recognition system for workers, using a single tri-axial accelerometer is presented in this paper. Time, frequency and spatial domain features were extracted using a naturalistic dataset and were used to analyze the performance of various classifiers. FFT energy, entropy and correlation between axes showed good results in classification of 9 different activities. The various classification algorithms were tested using Weka classification tool and we have achieved up to 93.9% successful classification results using Random Forest algorithm.