Most mobile devices include motion, magnetic, acoustic, and location sensors. These sensors can be used in the development of a framework for activities of daily living (ADL) and environment recognition. This framework is composed of the acquisition, processing, fusion, and data classification features. This study compares different implementations of artificial neural networks. The obtained results were 85.89% and 100% for the recognition of standard ADL and standing activities with Deep Neural Networks, respectively. Furthermore, the results present 86.50% for identification of the environments using Feedforward Neural Networks. Numerical results illustrate that the proposed framework can achieve robust performance from the incorporation of data fusion methods using mobile devices.
Recognition of Activities of Daily Living Based on a Mobile Data Source Framework
Spinsante, SusannaMembro del Collaboration Group
2021-01-01
Abstract
Most mobile devices include motion, magnetic, acoustic, and location sensors. These sensors can be used in the development of a framework for activities of daily living (ADL) and environment recognition. This framework is composed of the acquisition, processing, fusion, and data classification features. This study compares different implementations of artificial neural networks. The obtained results were 85.89% and 100% for the recognition of standard ADL and standing activities with Deep Neural Networks, respectively. Furthermore, the results present 86.50% for identification of the environments using Feedforward Neural Networks. Numerical results illustrate that the proposed framework can achieve robust performance from the incorporation of data fusion methods using mobile devices.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
