Background: Recent advancements in wearable sensor technology have shown the feasibility of remote physical therapy at home. In particular, the current COVID-19 pandemic has revealed the need and opportunity of internet-based wearable technology in future health care systems. Previous research has shown the feasibility of human activity recognition technologies for monitoring rehabilitation activities in home environments; however, few comprehensive studies ranging from development to clinical evaluation exist.Objective: This study aimed to (1) develop a home-based rehabilitation (HBR) system that can recognize and record the type and frequency of rehabilitation exercises conducted by the user using a smartwatch and smartphone app equipped with a machine learning (ML) algorithm and (2) evaluate the efficacy of the home-based rehabilitation system through a prospective comparative study with chronic stroke survivors.Methods: The HBR system involves an off-the-shelf smartwatch, a smartphone, and custom-developed apps. A convolutional neural network was used to train the ML algorithm for detecting home exercises. To determine the most accurate way for detecting the type of home exercise, we compared accuracy results with the data sets of personal or total data and accelerometer, gyroscope, or accelerometer combined with gyroscope data. From March 2018 to February 2019, we conducted a clinical study with two groups of stroke survivors. In total, 17 and 6 participants were enrolled for statistical analysis in the HBR group and control group, respectively. To measure clinical outcomes, we performed the Wolf Motor Function Test (WMFT), Fugl-Meyer Assessment of Upper Extremity, grip power test, Beck Depression Inventory, and range of motion (ROM) assessment of the shoulder joint at 0, 6, and 12 months, and at a follow-up assessment 6 weeks after retrieving the HBR system.Results: The ML model created with personal data involving accelerometer combined with gyroscope data (5590/5601, 99.80%) was the most accurate compared with accelerometer (5496/5601, 98.13%) or gyroscope data (5381/5601, 96.07%). In the comparative study, the drop-out rates in the control and HBR groups were 40% (4/10) and 22% (5/22) at 12 weeks and 100% (10/10) and 45% (10/22) at 18 weeks, respectively. The HBR group (n=17) showed a significant improvement in the mean WMFT score (P=.02) and ROM of flexion (P=.004) and internal rotation (P=.001). The control group (n=6) showed a significant change only in shoulder internal rotation (P=.03).Conclusions: This study found that a home care system using a commercial smartwatch and ML model can facilitate participation in home training and improve the functional score of the WMFT and shoulder ROM of flexion and internal rotation in the treatment of patients with chronic stroke. This strategy can possibly be a cost-effective tool for the home care treatment of stroke survivors in the future.Trial Registration: Clinical Research Information Service KCT0004818; https://tinyurl.com/y92w978t

Accumulating evidence suggests cortical circuits may contribute to control of human locomotion. Here, noninvasive electroencephalography (EEG) recorded from able-bodied volunteers during a novel treadmill walking paradigm was used to assess neural correlates of walking. A systematic processing method, including a recently developed subspace reconstruction algorithm, reduced movement-related EEG artifact prior to independent component analysis and dipole source localization. We quantified cortical activity while participants tracked slow and fast target speeds across two treadmill conditions: an active mode that adjusted belt speed based on user movements and a passive mode reflecting a typical treadmill. Our results reveal frequency specific, multi-focal task related changes in cortical oscillations elicited by active walking. Low γ band power, localized to the prefrontal and posterior parietal cortices, was significantly increased during double support and early swing phases, critical points in the gait cycle since the active controller adjusted speed based on pelvis position and swing foot velocity. These phasic γ band synchronizations provide evidence that prefrontal and posterior parietal networks, previously implicated in visuo-spatial and somotosensory integration, are engaged to enhance lower limb control during gait. Sustained μ and β band desynchronization within sensorimotor cortex, a neural correlate for movement, was observed during walking thereby validating our methods for isolating cortical activity. Our results also demonstrate the utility of EEG recorded during locomotion for probing the multi-regional cortical networks which underpin its execution. For example, the cortical network engagement elicited by the active treadmill suggests that it may enhance neuroplasticity for more effective motor training.

Significant functional impairment of the hand is common among stroke survivors and restoration of hand function should be prioritized during post-stroke rehabilitation. The goal of this study was to develop a novel biomimetic device to assist patients in producing complex hand movements with a limited number of actuators. The Biomimetic Hand Exoskeleton Device (BiomHED) is actuated by exotendons that mimic the geometry of the major tendons of the hand. Ten unimpaired subjects and four chronic stroke survivors participated in experiments that tested the efficacy of the system. The exotendons reproduced distinct spatial joint coordination patterns similar to their target muscle-tendon units for both subject groups. In stroke survivors, the exotendon-produced joint angular displacements were smaller, but not significantly different, than those of unimpaired subjects (\mbi p = 0.15-0.84). Even with limited use of the BiomHED, the kinematic workspace of the index finger increased by 63%-1014% in stroke survivors. The device improved the kinematics of the tip-pinch task in stroke survivors and resulted in a significant reduction in the fingertip-thumb tip distance ( 17.9 ±15.3 mm). This device is expected to enable effective “task-oriented” training of the hand post-stroke.

Brain-Computer Interface (BCI) technology enables users to operate external devices without physical movement. Electroencephalography (EEG) based BCI systems are being actively studied due to their high temporal resolution, convenient usage, and portability. However, fewer studies have been conducted to investigate the impact of high spatial resolution of EEG on decoding precise body motions, such as finger movements, which are essential in activities of daily living. Low spatial sensor resolution, as found in common EEG systems, can be improved by omitting the conventional standard of EEG electrode distribution (the international 10–20 system) and ordinary mounting structures (e.g., flexible caps). In this study, we used newly proposed flexible electrode grids attached directly to the scalp, which provided ultra-high-density EEG (uHD EEG). We explored the performance of the novel system by decoding individual finger movements using a total of 256 channels distributed over the contralateral sensorimotor cortex. Dense distribution and small-sized electrodes result in an inter-electrode distance of 8.6 mm (uHD EEG), while that of conventional EEG is 60 to 65 mm on average. Five healthy subjects participated in the experiment, performed single finger extensions according to a visual cue, and received avatar feedback. This study exploits mu (8–12 Hz) and beta (13–25 Hz) band power features for classification and topography plots. 3D ERD/S activation plots for each frequency band were generated using the MNI-152 template head. A linear support vector machine (SVM) was used for pairwise finger classification. The topography plots showed regular and focal post-cue activation, especially in subjects with optimal signal quality. The average classification accuracy over subjects was 64.8 (6.3)%, with the middle versus ring finger resulting in the highest average accuracy of 70.6 (9.4)%. Further studies are required using the uHD EEG system with real-time feedback and motor imagery tasks to enhance classification performance and establish the basis for BCI finger movement control of external devices.

The human hand is one of the most complex and compact grippers that has arisen as a product of natural genetic engineering; it is highly versatile, as it handles power and precision tasks. Since proper contact points and force directions are required to ensure versatility and secure a stable grip on an object, there must be a large workspace and controllable tip force directions for the digits. Although they are important, many individuals with neuromuscular diseases experience loss of these features. Thus, we propose a high-degree-of-freedom (DOF) soft robotic glove inspired by the anatomical features of human hands. The mechanism for adjusting the position and force direction of each tip is based on the structure of the extrinsic and intrinsic muscle–tendon units. The large thumb workspace was achieved by assisting opposition/reposition and flexion/extension to enable various grasping postures. A bidirectional actuation control mechanism with a cable-actuated agonist and an elastomer antagonist increased the assisted DOF and maintained compactness. The kinematic and kinetic performances of our device were evaluated by performing tests with eight stroke survivors. The thumb workspace increased by 43%, 207%, and 248% in the distal–proximal, dorsal–palmar, and radial–ulnar directions, respectively. The pinching shear force decreased by 54% and 45% for the nonthumb digits and thumb, respectively. These device-assisted improvements allowed objects to be stably grasped and manipulated in various postures. The novel device can assist individuals with impaired hand function to improve their grasping performance. Clinical Research Information Service (CRIS) Registration Number: KCT0004855.

Hydraulic actuating system exhibits potential for legged robots to achieve highly agile dynamic movement because of their high power-to-weight ratio. However, the low energy efficiency of the hydraulic system can reduce the operating time and cause heat dissipation. In this article, an optimal control framework based on the model predictive control (MPC) is proposed to improve energy efficiency and provide robust supply of pressure required for robot tasks. The MPC includes the power loss function and supply pressure regularization term as the cost function and limitation on the pump speed and acceleration as the constraints. When implemented to the hydraulic biped robot, LIGHT, the proposed method allows legged robots to achieve the commanded motion without losing balance while minimizing energy consumption. The energy saving performance of the proposed method with MPC is also validated via simulation and experiment.