A Comparative Study of the Electrodes Gels’Electrical Properties in the Measurement Issues of Intrabody Communication

Intrabody communication(IBC)technology is becoming progressively more standard-ized due to its low power consumption and high security features incorporated into the third phys-ical layer of the IEEE 802.15.6 standard.Even then,there are still many challenges in normalizing the measurement issues of IBC.A major concern that should not be overlooked is the electrodes in the IBC,especially the popular use of gel electrodes.In the channel measurements,gel electrodes are commonly employed to improve the signal-to-noise ratio and prevent electrodes from falling off.In this paper,a comparative study of the electrical properties of gel was investigated during the measurement of human channel characteristics and to clarify the differences of them.Firstly,the basis of electrostatic field pole plate measurements and electromagnetic theory were introduced to interpretate how the relative permittivity and conductivity of different gels will influence the meas-urement results.Then the in vivo experiments with different gel or dry electrodes were performed to compare the differences induced by the gel.The results indicate that the influence of the gel on the human channel measurement is mainly concentrated below 400 kHz(the attenuation is re-duced by 16.7 dB on average),and the stability of the permittivity and conductivity of the gel has a direct impact on the stability of its measurement of the human channel.This result may provide a meaningful reference for the standardization of electrode usage in IBC.

A Hybrid Model Based on ResNet and GCN for sEMG-Based Gesture Recognition

The surface electromyography(sEMG)is one of the basic processing techniques to the gesture recognition because of its inherent advantages of easy collection and non-invasion.However,limited by feature extraction and classifier selection,the adaptability and accuracy of the conventional machine learning still need to promote with the increase of the input dimension and the number of output classifications.Moreover,due to the different characteristics of sEMG data and image data,the conventional convolutional neural network(CNN)have yet to fit sEMG signals.In this paper,a novel hybrid model combining CNN with the graph convolutional network(GCN)was constructed to improve the performance of the gesture recognition.Based on the characteristics of sEMG signal,GCN was introduced into the model through a joint voting network to extract the muscle synergy feature of the sEMG signal.Such strategy optimizes the structure and convolution kernel parameters of the residual network(ResNet)with the classification accuracy on the NinaPro DBl up to 90.07%.The experimental results and comparisons confirm the superiority of the proposed hybrid model for gesture recognition from the sEMG signals.