A Novel Framework Based on Deep Learning Architecture for Continuous Human Activity Recognition with Inertial Sensors

Abstract

Frameworks for human activity recognition (HAR) can be applied in the clinical environment for monitoring patients’ motor and functional abilities either remotely or within a rehabilitation program. Deep Learning (DL) models can be exploited to perform HAR by means of raw data, thus avoiding time-demanding feature engineering operations. Most works targeting HAR with DL-based architectures have tested the workflow performance on data related to a separate execution of the tasks. Hence, a paucity in the literature has been found with regard to frameworks aimed at recognizing continuously executed motor actions. In this article, the authors present the design, development, and testing of a DL-based workflow targeting continuous human activity recognition (CHAR). The model was trained on the data recorded from ten healthy subjects and tested on eight different subjects. Despite the limited sample size, the authors claim the capability of the proposed framework to accurately classify motor actions within a feasible time, thus making it potentially useful in a clinical scenario.

Deep Residual Network with a CBAM Mechanism for the Recognition of Symmetric and Asymmetric Human Activity Using Wearable Sensors

“…It is essential to highlight that the k-CV approach can require considerable computational resources, particularly with large datasets or when using high k values. Utilizing the k-CV technique aims to guarantee a just and impartial assessment of the model [47]. In our investigation, we opted for a 5-fold cross-validation (k = 5) to find a compromise between computational efficiency and accurate performance estimation.…”