Jiaqi Zhou

Maintaining prescribed joint motion while allowing for compliant responses to changing interaction is challenging in passive lower limb rehabilitation. We propose interaction error-driven adaptive admittance control (IE-AAC), which subtracts the predicted nominal-interaction difference between reference and commanded states. A soft dead zone processes the corrected residual before bounded scheduling of virtual damping, stiffness, and interaction mapping gain. We evaluate the controller using a common reference reconstructed from simulated therapist demonstrations and a phenomenological interaction model. In 100 strictly paired Monte Carlo trials, IE-AAC reduced the equally weighted hip–knee–ankle mean reference deviation RMSE by 20.26%, 32.09%, and 28.23% relative to fixed admittance and two literature-derived variable admittance comparators (Zhang-2018 and Cao-2024), respectively. All four controllers in this comparison share mismatch compensation, so the reductions quantify differences in the implemented scheduling laws; a separate ablation evaluates compensation itself. The results include knee-specific trade-offs in tracking, smoothness, and interaction residual.

Human activity recognition (HAR) based on wearable sensors is a key technology in the fields of smart sensing and health monitoring. With the rapid development of deep learning, its powerful feature extraction capabilities have significantly enhanced recognition performance and reduced reliance on traditional handcrafted feature engineering. However, current deep learning models still face challenges in effectively capturing complex temporal dependencies in long-term time-series sensor data and addressing information redundancy, which affect model recognition accuracy and generalization ability. To address these issues, this paper proposes an innovative CNN-BiGRU–Transformer hybrid deep learning model aimed at improving the accuracy and robustness of human activity recognition. The proposed model integrates a multi-branch Convolutional Neural Network (CNN) to effectively extract multi-scale local spatial features, and combines a Bidirectional Gated Recurrent Unit (BiGRU) with a Transformer hybrid module for modeling temporal dependencies and extracting temporal features in long-term time-series data. Additionally, an attention mechanism is incorporated to dynamically allocate weights, suppress redundant information, and enhance key features, further improving recognition performance. To demonstrate the capability of the proposed model, evaluations are performed on three public datasets: WISDM, PAMAP2, and UCI-HAR. The model achieved recognition accuracies of 98.41%, 95.62%, and 96.74% on the three datasets, respectively, outperforming several state-of-the-art methods. These results confirm that the proposed approach effectively addresses feature extraction and redundancy challenges in long-term sensor time-series data and provides a robust solution for wearable sensor-based human activity recognition.