A Multiple Data Source Framework for the Identification of Activities of Daily Living Based on Mobile Device Data

TL;DR

This paper presents a multi-source data framework using mobile device sensors and neural networks to accurately recognize daily activities and environments, demonstrating high recognition rates and robustness.

Contribution

It introduces a comprehensive framework combining data acquisition, fusion, and neural network classification for ADL recognition using off-the-shelf mobile sensors.

Findings

Recognition accuracy of 85.89% for standard ADL

100% recognition rate for some activities with DNN

86.50% accuracy for environment identification

Abstract

Most mobile devices include motion, magnetic, acoustic, and location sensors. They allow the implementation of a framework for the recognition of Activities of Daily Living (ADL) and its environments, composed by the acquisition, processing, fusion, and classification of data. This study compares different implementations of artificial neural networks, concluding that the obtained results were 85.89% and 100% for the recognition of standard ADL. Additionally, for the identification of standing activities with Deep Neural Networks (DNN) respectively, and 86.50% for the identification of the environments with Feedforward Neural Networks. Numerical results illustrate that the proposed framework can achieve robust performance from the data fusion of off-the-shelf mobile devices.