Research Article
Assessment of Human Activity Classification Algorithms for IoT Devices
@INPROCEEDINGS{10.1007/978-3-031-28663-6_13, author={Gianluca Ciattaglia and Linda Senigagliesi and Ennio Gambi}, title={Assessment of Human Activity Classification Algorithms for IoT Devices}, proceedings={IoT Technologies for HealthCare. 9th EAI International Conference, HealthyIoT 2022, Braga, Portugal, November 16-18, 2022, Proceedings}, proceedings_a={HEALTHYIOT}, year={2023}, month={3}, keywords={Automotive radar Deep learning Human activities IoT}, doi={10.1007/978-3-031-28663-6_13} }- Gianluca Ciattaglia
Linda Senigagliesi
Ennio Gambi
Year: 2023
Assessment of Human Activity Classification Algorithms for IoT Devices
HEALTHYIOT
Springer
DOI: 10.1007/978-3-031-28663-6_13
Abstract
Human activity classification is assuming great relevance in many fields, including the well-being of the elderly. Many methodologies to improve the prediction of human activities, such as falls or unexpected behaviors, have been proposed over the years, exploiting different technologies, but the complexity of the algorithms requires the use of processors with high computational capabilities. In this paper different deep learning techniques are compared in order to evaluate the best compromise between recognition performance and computational effort with the aim to define a solution that can be executed by an IoT device, with a limited computational load. The comparison has been developed considering a dataset containing different types of activities related to human walking obtained from an automotive Radar. The procedure requires a pre-processing of the raw data and then the feature extraction from range-Doppler maps. To obtain reliable results different deep learning architectures and different optimizers are compared, showing that an accuracy of more than 97% is achieved with an appropriate selection of the network parameters.
