Surface electromyography (sEMG) is a non-invasive and straightforward way to allow the user to actively control the prosthesis. However, results reported by previous studies on using sEMG for hand and wrist movement classification vary by a large margin, due to several factors including but not limited to the number of classes and the acquisition protocol. The objective of this paper is to investigate the deep neural network approach on the classification of 41 hand and wrist movements based on the sEMG signal. The proposed models were trained and evaluated using the publicly available database from the Ninapro project, one of the largest public sEMG databases for advanced hand myoelectric prosthetics. Two datasets, DB5 with a low-cost 16 channels and 200 Hz sampling rate setup and DB7 with 12 channels and 2 kHz sampling rate setup, were used for this study. Our approach achieved an overall accuracy of 93.87 ± 1.49 and 91.69 ± 4.68% with a balanced accuracy of 84.00 ± 3.40 and 84.66 ± 4.78% for DB5 and DB7, respectively. We also observed a performance gain when considering only a subset of the movements, namely the six main hand movements based on six prehensile patterns from the Southampton Hand Assessment Procedure (SHAP), a clinically validated hand functional assessment protocol. Classification on only the SHAP movements in DB5 attained an overall accuracy of 98.82 ± 0.58% with a balanced accuracy of 94.48 ± 2.55%. With the same set of movements, our model also achieved an overall accuracy of 99.00% with a balanced accuracy of 91.27% on data from one of the amputee participants in DB7. These results suggest that with more data on the amputee subjects, our proposal could be a promising approach for controlling versatile prosthetic hands with a wide range of predefined hand and wrist movements.

Glucose is a key biomarker for both type 1 and type 2 diabetes [2] and an effective approach for glucose monitoring is essential for diabetes management. Commonly, glucose levels have been measured by blood drawing requiring a painful sample collection. Alternatively, glucose can be detected in other biofluids such as tears, saliva, and sweat. [3] To avoid pain and infection risk arising from traditional invasive diagnosis, noninvasive methods have been explored. Sweat can be collected continuously and may be less prone to contamination than other biofluids. [4] Glucose level in sweat has been reported to be in a range of 0.01-1.11 × 10 −3 m and it is correlated well with blood glucose levels. [5] Likewise, lactate is an important biomarker for pressure ischemia, and hypoxia. [6] It has been reported that the increase of lactate level is directly related with DKA which is a serious complication of diabetes. [7] Wearable sensors play an important role for self-health monitoring. [8] However, the commercial wearable sensors such as Fitbit, Garmin, and Apple watch provide only physical information, such as heart rate without chemical information of the wearer. Since the electrochemistry is a simple, rapid, and portable analytical technique, the researchers have attempted to develop noninvasive wearable chemical sensors based on electrochemical An electrochemical sensing device based on a cotton-thread electrode for real-time and simultaneous detection of sweat glucose and sweat lactate is reported. The cotton thread surfaces are simply modified by cellulose nanofibers/carbon nanotube ink-Prussian blue/chitosan to enhance liquid adsorption, bioreceptor immobilization, and sensor performance in addition to minimize potential irritation and allergies on the wearer's skin. The modified thread surfaces are characterized by laser scanning confocal microscopy, scanning electron microscopy, and Fourier transform Raman spectroscopy. Amperometry is carried out via hydrogen peroxide detection for electrochemical characterization of the modified thread electrodes. A circuit and digital readout of this wearable sensor are customized designed to be integrated with thread electrodes for real-time and simultaneous detection of sweat glucose and sweat lactate. The wristwatch sensing device provides a linear range of 0.025-3 × 10 −3 m with a detection limit of 0.025 × 10 −3 m for glucose and a linear range of 0.25-35 × 10 −3 m with a detection limit of 0.25 × 10 −3 m for lactate. This device can effectively determine the cut-off levels of both glucose and lactate, which can distinguish between a normal individual and one with a diabetic condition. This platform opens a new avenue for noninvasive and real-time detection of other sweat biomarkers.

A goniometer is currently the gold standard for range of motion (ROM) measurements. However, trained staff are required for accurate measurements. The objective of this study is to assess an agreement between the proposed standalone inertial measurement unit glove, smartphone device, and a standard goniometer for the measurement of wrist range of motion. Twenty participants performed wrist flexion, wrist extension, pronation, supination, ulnar deviation, and radial deviation movements with three operators measuring the movements with three devices. Average measurements from the three approaches had within 1.5 degrees of difference from each other for all of the movements. Both the proposed IMU glove and smartphone showed a strong correlation to the goniometer in most of the movements, with an intraclass correlation coefficient (ICC) between 0.914 and 0.961, and between 0.929 and 0.951, respectively. Only wrist supination using the smartphone has an ICC of 0.828. In comparison with a standard goniometer, a smartphone device is a more convenient method and readily available. The proposed IMU glove requires additional hardware but is easier to use and is more suitable for measuring and monitoring dynamic motion than a smartphone or a goniometer. These patient-friendly approaches could be used by the patients at home and provide remote quantitative monitoring during the wrist rehabilitation process.

No abstract

No abstract