Hand Gesture Recognition Using Compact CNN Via Surface Electromyography Signals.

By training the deep neural network model, the hidden features in Surface Electromyography(sEMG) signals can be extracted. The motion intention of the human can be predicted by analysis of sEMG. However, the models recently proposed by researchers often have a large number of parameters. Therefore, we designed a compact Convolution Neural Network (CNN) model, which not only improves the classification accuracy but also reduces the number of parameters in the model. Our proposed model was validated on the Ninapro DB5 Dataset and the Myo Dataset. The classification accuracy of gesture recognition achieved good results.

All-Fabric Capacitive Pressure Sensors with Piezoelectric Nanofibers for Wearable Electronics and Robotic Sensing.

Flexible pressure sensors are increasingly sought after for applications ranging from physiological signal monitoring to robotic sensing; however, the challenges associated with fabricating highly sensitive, comfortable, and cost-effective sensors remain formidable. This study presents a high-performance, all-fabric capacitive pressure sensor (AFCPS) that incorporates piezoelectric nanofibers. Through the meticulous optimization of conductive fiber electrodes and P(VDF-TrFE) nanofiber dielectric layers, the AFCPS exhibits exceptional attributes such as high sensitivity (4.05 kPa-1), an ultralow detection limit (0.6 Pa), an extensive detection range (∼100 kPa), rapid response time (<26 ms), and robust stability (>14,000 cycles). The sensor's porous structure enhances its compressibility, while its piezoelectric properties expedite charge separation, thereby increasing the interface capacitance and augmenting overall performance. These features are elucidated further through multiphysical field-coupling simulations and experimental testing. Owing to its comprehensive superior performance, the AFCPS has demonstrated its efficacy in monitoring human activity and physiological signals, as well as in discerning soft robotic grasping movements. Additionally, we have successfully implemented multiple AFCPS units as pressure sensor arrays to ascertain spatial pressure distribution and enable intelligent robotic gripping. Our research underscores the promising potential of the AFCPS device in wearable electronics and robotic sensing, thereby contributing significantly to the advancement of high-performance fabric-based sensors.

Finger Gesture Recognition Using Sensing and Classification of Surface Electromyography Signals With High-Precision Wireless Surface Electromyography Sensors.

Finger gesture recognition (FGR) plays a crucial role in achieving, for example, artificial limb control and human-computer interaction. Currently, the most common methods of FGR are visual-based, voice-based, and surface electromyography (EMG)-based ones. Among them, surface EMG-based FGR is very popular and successful because surface EMG is a cumulative bioelectric signal from the surface of the skin that can accurately and intuitively represent the force of the fingers. However, existing surface EMG-based methods still cannot fully satisfy the required recognition accuracy for artificial limb control as the lack of high-precision sensor and high-accurate recognition model. To address this issue, this study proposes a novel FGR model that consists of sensing and classification of surface EMG signals (SC-FGR). In the proposed SC-FGR model, wireless sensors with high-precision surface EMG are first developed for acquiring multichannel surface EMG signals from the forearm. Its resolution is 16 Bits, the sampling rate is 2 kHz, the common-mode rejection ratio (CMRR) is less than 70 dB, and the short-circuit noise (SCN) is less than 1.5 µV. In addition, a convolution neural network (CNN)-based classification algorithm is proposed to achieve FGR based on acquired surface EMG signals. The CNN is trained on a spectrum map transformed from the time-domain surface EMG by continuous wavelet transform (CWT). To evaluate the proposed SC-FGR model, we compared it with seven state-of-the-art models. The experimental results demonstrate that SC-FGR achieves 97.5% recognition accuracy on eight kinds of finger gestures with five subjects, which is much higher than that of comparable models.

Flexible, Tunable, and Ultrasensitive Capacitive Pressure Sensor with Microconformal Graphene Electrodes.

High-performance flexible pressure sensors are highly desirable in health monitoring, robotic tactile, and artificial intelligence. Construction of microstructures in dielectrics and electrodes is the dominating approach to improving the performance of capacitive pressure sensors. Herein, we have demonstrated a novel three-dimensional microconformal graphene electrode for ultrasensitive and tunable flexible capacitive pressure sensors. Because the fabrication process is controllable, the morphologies of the graphene that is perfectly conformal with the electrode are controllable consequently. Multiscale morphologies ranging from a few nanometers to hundreds of nanometers, even to tens of micrometers, have been systematically investigated, and the high-performance capacitive pressure sensor with high sensitivity (3.19 kPa-1), fast response (30 ms), ultralow detection limit (1 mg), tunable-sensitivity, high flexibility, and high stability was obtained. Furthermore, an ultrasensitivity of 7.68 kPa-1 was successfully achieved via symmetric double microconformal graphene electrodes. The finite element analysis indicates that the microstructured graphene electrode can enhance large deformation and thus effectively improve the sensitivity. Additionally, the proposed pressure sensors are demonstrated with practical applications including insect crawling detection, wearable health monitoring, and force feedback of robot tactile sensing with a sensor array. The microconformal graphene may provide a new approach to fabricating controllable microstructured electrodes to enhance the performance of capacitive pressure sensors and has great potential for innovative applications in wearable health-monitoring devices, robot tactile systems, and human-machine interface systems.