Background: Wearable sensor technology can facilitate diagnostics and monitoring of people with upper extremity (UE) paresis after stroke. The purpose of this study is to investigate the perspectives of clinicians, people living with stroke, and their caregivers on an interactive wearable system that detects UE movements and provides feedback. Methods: This qualitative description study used semi-structured interviews relating to the perspectives of a prospective interactive wearable system including a wearable sensor to capture UE movement and a user interface to provide feedback as the means of data collection. Ten rehabilitation therapists, 9 people with stroke, and 2 caregivers participated in this study.Results: Four themes were identified (1) “Everyone is different” highlighted the need for addressing individual user’s rehabilitation goal and personal preference; (2) “The wearable system should identify UE and trunk movements” emphasized that in addition to arm, hand, and finger movements, detecting compensatory trunk movements during UE movements is also of interest; (3) “Both quality and amount of movements are necessary to measure” described the parameters related to how well and how much the user is using their affected UE that participants envisioned the system to monitor; (4) “Functional activities should be practiced by the users” outlined UE movements and activities that are of priority in designing the system.Conclusions: Narratives from clinicians, people with stroke, and their caregivers offer insight into the design of interactive wearable systems. Future studies examining the experience and acceptability of existing wearable systems from end-users are warranted to guide the adoption of this technology.

Background Wearable sensor technology can facilitate diagnostics and monitoring of people with upper extremity (UE) paresis after stroke. The purpose of this study is to investigate the perspectives of clinicians, people living with stroke, and their caregivers on an interactive wearable system that detects UE movements and provides feedback. Methods This qualitative study used semi-structured interviews relating to the perspectives of a future interactive wearable system including a wearable sensor to capture UE movement and a user interface to provide feedback as the means of data collection. Ten rehabilitation therapists, 9 people with stroke, and 2 caregivers participated in this study. Results Four themes were identified (1) “Everyone is different” highlighted the need for addressing individual user’s rehabilitation goal and personal preference; (2) “The wearable system should identify UE and trunk movements” emphasized that in addition to arm, hand, and finger movements, detecting compensatory trunk movements during UE movements is also of interest; (3) “Both quality and amount of movements are necessary to measure” described the parameters related to how well and how much the user is using their affected UE that participants envisioned the system to monitor; (4) “Functional activities should be practiced by the users” outlined UE movements and activities that are of priority in designing the system. Conclusions Narratives from clinicians, people with stroke, and their caregivers offer insight into the design of interactive wearable systems. Future studies examining the experience and acceptability of existing wearable systems from end-users are warranted to guide the adoption of this technology.

Recent advances in wearable devices and Internetof-Things (IoT) have led to massive growth in sensor data generated in edge devices. Labeling such massive data for classification tasks has proven to be challenging. In addition, data generated by different users bear various personal attributes and edge heterogeneity, rendering it impractical to develop a global model that adapts well to all users. Concerns over data privacy and communication costs also prohibit centralized data accumulation and training. We propose SemiPFL that supports edge users having no label or limited labeled datasets and a sizable amount of unlabeled data that is insufficient to train a well-performing model. In this work, edge users collaborate to train a Hypernetwork in the server, generating personalized autoencoders for each user. After receiving updates from edge users, the server produces a set of base models for each user, which the users locally aggregate them using their own labeled dataset. We comprehensively evaluate our proposed framework on various public datasets from a wide range of application scenarios, from wearable health to IoT, and demonstrate that SemiPFL outperforms state-of-art federated learning frameworks under the same assumptions regarding user performance, network footprint, and computational consumption. We also show that the solution performs well for users without label or having limited labeled datasets and increasing performance for increased labeled data and number of users, signifying the effectiveness of SemiPFL for handling data heterogeneity and limited annotation. We also demonstrate the stability of SemiPFL for handling user hardware resource heterogeneity in three real-time scenarios.