Obtaining robust feature representations from multi-position wearable sensory data is challenging in human activity recognition (HAR) since data from different positions can have unordered implicit correlations. Graph neural networks (GNNs) represent data as structured graphs by mining complex relationships and interdependency via message passing between the nodes of graphs. This paper proposes a novel framework (MhaGNN) that combines GNNs and the multi-head attention mechanism, aiming to learn more informative representations for multi-position HAR tasks. The MhaGNN framework takes the sensor channels from multiple wearing positions as nodes to construct graph-structured data from the spatial dimension. Besides, the multi-head attention mechanism is introduced to complete the message passing and aggregation of the graphs for spatial-temporal feature extraction. The MhaGNN learns correlations among sensor channels that can be used as compensatory features together with the captured features from each single sensor channel to enhance HAR. Experimental evaluations on three publicly available HAR datasets and a ground-truth dataset demonstrate that our proposed MhaGNN achieves state-of-the-art recognition performance with the captured rich features, including PAMAP2, OPPORTUNITY, MHAEATH and MPWHAR.
15 July 2025 in Biomedical Signal Processing and Control
This article proposes a robust adaptive fuzzy pseudoinverse control strategy for hysteretic nonlinear systems subject to strict state constraints, specifically targeting giant magnetostrictive actuators (GMA). To address physical constraints and uncertain control gains, an improved integral barrier Lyapunov function (IBLF) is employed, enabling direct enforcement of state constraints without feasibility condition verification. Furthermore, a command-filtered backstepping framework combined with a fixed-time compensation mechanism is developed. This approach not only circumvents the explosion of complexity inherent in traditional backstepping but also effectively attenuates filtering errors to enhance robustness. To mitigate severe hysteresis nonlinearity, a fuzzy pseudoinverse control scheme is constructed to compensate for hysteresis effects without requiring an explicit inverse model. Comprehensive experimental validations on a GMA platform—covering single-frequency, composite-frequency, square wave, and triangular wave trajectory tracking—demonstrate the superiority of the proposed method. Experimental results confirm that the strategy achieves high-precision motion control with minimal tracking error and strictly satisfies system constraints under various dynamic conditions.