Muscle strength training for stroke patients is of vital importance for helping survivors to progressively restore muscle strength and improve the performance of their activities in daily living (ADL). An adaptive hierarchical therapy control framework which integrates the patient's real biomechanical state estimation with task-performance quantitative evaluation is proposed. Firstly, a high-level progressive resistive supervisory controller is designed to determine the resistive force base for each training session based on the patient's online task-performance evaluation. Then, a low-level adaptive resistive force triggered controller is presented to further regulate the interactive resistive force corresponding to the patient's real-time biomechanical state -characterized by the patient's bio-damping and bio-stiffness in the course of one training session, so that the patient is challenged in a moderate but engaging and motivating way. Finally, a therapeutic robot system using a Barrett WAM TM compliant manipulator is set up. We recruited eighteen inpatient and outpatient stroke participants who were randomly allocated in experimental (robot-aided) and control (conventional physical therapy) groups and enrolled for sixteen weeks of progressive resistance training. The preliminary results show that the proposed therapy control strategies can enhance the recovery of strength and motor control ability.
Person re-identification (re-ID) continues to pose a significant challenge, particularly in scenarios involving occlusions. Prior approaches aimed at tackling occlusions have predominantly focused on aligning physical body features through the utilization of external semantic cues. However, these methods tend to be intricate and susceptible to noise. To address the aforementioned challenges, we present an innovative end-toend solution known as the Dynamic Patch-aware Enrichment Transformer (DPEFormer). This model effectively distinguishes human body information from occlusions automatically and dynamically, eliminating the need for external detectors or precise image alignment. Specifically, we introduce a dynamic patch token selection module (DPSM). DPSM utilizes a label-guided proxy token as an intermediary to identify informative occlusionfree tokens. These tokens are then selected for deriving subsequent local part features. To facilitate the seamless integration of global classification features with the finely detailed local features selected by DPSM, we introduce a novel feature blending module (FBM). FBM enhances feature representation through the complementary nature of information and the exploitation of part diversity. Furthermore, to ensure that DPSM and the entire DPEFormer can effectively learn with only identity labels, we also propose a Realistic Occlusion Augmentation (ROA) strategy. This strategy leverages the recent advances in the Segment Anything Model (SAM) [1]. As a result, it generates occlusion images that closely resemble real-world occlusions, greatly enhancing the subsequent contrastive learning process. Experiments on occluded and holistic re-ID benchmarks signify a substantial advancement of DPEFormer over existing state-ofthe-art approaches. The code will be made publicly available.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.