Surface electromyography signal plays an important role in hand function recovery training. In this paper, an IoT-enabled stroke rehabilitation system was introduced which was based on a smart wearable armband (SWA), machine learning (ML) algorithms, and a 3-D printed dexterous robot hand. User comfort is one of the key issues which should be addressed for wearable devices. The SWA was developed by integrating a low-power and tiny-sized IoT sensing device with textile electrodes, which can measure, pre-process, and wirelessly transmit bio-potential signals. By evenly distributing surface electrodes over user's forearm, drawbacks of classification accuracy poor performance can be mitigated. A new method was put forward to find the optimal feature set. ML algorithms were leveraged to analyze and discriminate features of different hand movements, and their performances were appraised by classification complexity estimating algorithms and principal components analysis. According to the verification results, all nine gestures can be successfully identified with an average accuracy up to 96.20%. In addition, a 3-D printed five-finger robot hand was implemented for hand rehabilitation training purpose. Correspondingly, user's hand movement intentions were extracted and converted into a series of commands which were used to drive motors assembled inside the dexterous robot hand. As a result, the dexterous robot hand can mimic the user's gesture in a real-time manner, which shows the proposed system can be used as a training tool to facilitate rehabilitation process for the patients after stroke.

Facial expressions are among behavioral signs of pain that can be employed as an entry point to develop an automatic human pain assessment tool. Such a tool can be an alternative to the self-report method and particularly serve patients who are unable to self-report like patients in the Intensive Care Unit and minors. In this paper, a wearable device with a bio-sensing facial mask is proposed to monitor pain intensity of a patient by utilizing facial surface electromyogram (sEMG). The wearable device works as a wireless sensor node and is integrated into an Internet of Things system for remote pain monitoring. In the sensor node, up to eight channels of sEMG can be each sampled at 1000 Hz, to cover its full frequency range, and transmitted to the cloud server via the gateway in real-time. In addition, both low energy consumption and wearing comfort are considered throughout the wearable device design for long-term monitoring. To remotely illustrate real-time pain data to caregivers, a mobile web application is developed for real-time streaming of high-volume sEMG data, digital signal processing, interpreting, and visualization. The cloud platform in the system act as a bridge between the sensor node and web browser, managing wireless communication between the server and the web application. In summary, this study proposes a scalable IoT system for real-time biopotential monitoring and a wearable solution for automatic pain assessment via facial expressions.

Current acute pain intensity assessment tools are mainly based on self-reporting by patients, which is impractical for non-communicative, sedated or critically ill patients. In previous studies, various physiological signals have been observed qualitatively as a potential pain intensity index. On the basis of that, this study aims at developing a continuous pain monitoring method with the classification of multiple physiological parameters. Heart rate (HR), breath rate (BR), galvanic skin response (GSR) and facial surface electromyogram were collected from 30 healthy volunteers under thermal and electrical pain stimuli. The collected samples were labelled as no pain, mild pain or moderate/severe pain based on a self-reported visual analogue scale. The patterns of these three classes were first observed from the distribution of the 13 processed physiological parameters. Then, artificial neural network classifiers were trained, validated and tested with the physiological parameters. The average classification accuracy was 70.6%. The same method was applied to the medians of each class in each test and accuracy was improved to 83.3%. With facial electromyogram, the adaptivity of this method to a new subject was improved as the recognition accuracy of moderate/severe pain in leave-one-subject-out cross-validation was promoted from 74.9 ± 21.0 to 76.3 ± 18.1%. Among healthy volunteers, GSR, HR and BR were better correlated to pain intensity variations than facial muscle activities. The classification of multiple accessible physiological parameters can potentially provide a way to differentiate among no, mild and moderate/severe acute experimental pain.

Atrial fibrillation (AF) is a serious medical condition of the heart potentially leading to stroke, which can be diagnosed by analyzing electrocardiograms (ECG). Technologies of Artificial Intelligence of Things (AIoT) enable smart abnormality detection by analyzing streaming healthcare data from the sensor end of users. Analyzing streaming data in the cloud leads to challenges of response latency and privacy issues, and local inference by a model deployed on the user end brings difficulties in model update and customization. Therefore, we propose an AIoT Platform with AF recognition neural networks on the sensor edge with model retraining ability on a resource-constrained embedded system. To this aim, we proposed to combine simple but effective neural networks and an ECG feature selection strategy to reduce computing complexity while maintaining recognition performance. Based on the platform, we evaluated and discussed the performance, response time, and requirements for model retraining in the scenario of AF detection from ECG recordings. The proposed lightweight solution was validated with two public datasets and an ECG data stream simulation on an ATmega2560 processor, proving the feasibility of analysis and training on edge.

Automatic pain assessment is an application in healthcare serving personalized pain care, and patients cannot self-report pain. Pain at the present is inferred from physiological dynamics at the present and in the near past. However, heterogeneous pain responses cross-subject and cross-type hinder accurate recognition of pain. This work solves the adaptive pain recognition problem across pain types. We concrete the adaptivity problem into recognizing both phasic/short and tonic/long pain from the physiological sequences of the same length. The adaptivity of the proposed solution (TCAtt-PainNet) was ensured by hybrid temporal-channel attention when fusing multivariate time-series of electrocardiogram (ECG) and galvanic skin response (GSR) features. The attention was obtained by learning the dependencies between the point at present and the sequence in the near past, where sequence point temporal attention was constructed via modified self-attention, and the following feature channel attention was constructed by squeeze-and-excitation temporal attention weighted deep feature sequence. The proposed solution successfully enhanced recognition adaptivity by addressing relevant information only from long input sequences when testing with tonic and phasic pain databases, making progress towards automatic pain assessment for real application scenarios with attributes unknown pain.