Deep Learning Algorithms for Human Activity Recognition in Manual Material Handling Tasks
Sensors · 2025
DOI: 10.3390/s25216705 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Giulia Bassani und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Mechanical Intelligence, Scuola Superiore Sant'Anna, 56124 Pisa, Italy. Hauptthemen laut MEDLINE: Deep Learning, Human Activities. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union, BRIEF “Biorobotics Research and Innovation Engineering Facilities” project, Italian Ministry of University.
Abstract (Originalsprache)
Human Activity Recognition (HAR) is widely used for healthcare, but few works focus on Manual Material Handling (MMH) activities, despite their diffusion and impact on the workers’ health. We propose four Deep Learning algorithms for HAR in MMH: Bidirectional Long Short-Term Memory (BiLSTM), Sparse Denoising Autoencoder (Sp-DAE), Recurrent Sp-DAE, and Recurrent Convolutional Neural Network (RCNN). We explored different hyperparameter combinations to maximize the classification performance (F1-score,) using wearable sensors’ data gathered from 14 subjects. We investigated the best three-parameter combinations for each network using the full dataset to select the two best-performing networks, which were then compared using 14 datasets with increasing subject numerosity, 70–30% split, and Leave-One-Subject-Out (LOSO) validation, to evaluate whether they may perform better with a larger dataset. The benchmarking network DeepConvLSTM was tested on the full dataset. BiLSTM performs best in classification and complexity (95.7% 70–30% split; 90.3% LOSO). RCNN performed similarly (95.9%; 89.2%) with a positive trend with subject numerosity. DeepConvLSTM achieves similar classification performance (95.2%; 90.3%) but requires ×57.1 and ×31.3 more Multiply and ACcumulate (MAC) and ×100.8 and ×28.3 more Multiplication and Addition (MA) operations, which measure the complexity of the network’s inference process, than BiLSTM and RCNN, respectively. The BILSTM and RCNN perform close to DeepConvLSTM while being computationally lighter, fostering their use in embedded systems. Such lighter algorithms can be readily used in the automatic ergonomic and biomechanical risk assessment systems, enabling personalization of risk assessment and easing the adoption of safety measures in industrial practices involving MMH.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Mechanical Intelligence, Scuola Superiore Sant'Anna, 56124 Pisa, Italy.
- Department of Excellence in Robotics and AI, Scuola Superiore Sant'Anna, 56124 Pisa, Italy.
ORCID-Profile: Giulia Bassani, Carlo Alberto Avizzano, Alessandro Filippeschi
Förderung
- European Union
- BRIEF “Biorobotics Research and Innovation Engineering Facilities” project
- Italian Ministry of University
Zitieren
APA
Bassani, G., Avizzano, C. A., & Filippeschi, A. (2025). Deep Learning Algorithms for Human Activity Recognition in Manual Material Handling Tasks. Sensors. https://doi.org/10.3390/s25216705
Vancouver
Bassani G, Avizzano CA, Filippeschi A. Deep Learning Algorithms for Human Activity Recognition in Manual Material Handling Tasks. Sensors. 2025. doi:10.3390/s25216705
BibTeX
@article{Bassani2025,
author = {Bassani, Giulia and Avizzano, Carlo Alberto and Filippeschi, Alessandro},
title = {Deep Learning Algorithms for Human Activity Recognition in Manual Material Handling Tasks},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25216705}
}
EUVIMED