Design and Performance Evaluation of a Smart Helmet System for Human Activity Recognition in Worker Safety Applications

Human activity recognition (HAR) is gaining importance in the development of smart personal protective equipment (PPE). Yet, most solutions rely on body-worn devices or invasive helmet modifications, limiting adoption in industrial settings. We propose a non-invasive smart helmet with embedded motion and environmental sensors, fully integrated into a certification-compliant shell. To explore its applicability in realistic industrial conditions, we focused on constrained acquisition scenarios—characterized by low sampling rates, limited storage, and processing capacity. A multimodal dataset was collected using embedded tri-axial accelerometers and barometric pressure sensors during operational tasks. Four classification pipelines were evaluated: Random Forest (RF), Extreme Gradient Boosting (XGBoost), a wavelet-based RF (using Horizontal Concatenation of Continuous Wavelet Transforms, HC-CWT), and a deep learning pipeline combining a Convolutional Autoencoder with LSTM (ConvAE-LSTM). Among these, XGBoost achieved the highest accuracy (up to 87.4%) and the most favorable balance between latency and computational efficiency, particularly with 8–15 s windows. This best-performing model was then deployed on the resource-constrained helmet system, confirming its suitability for on-board HAR in scalable occupational safety applications.