Deep Learning-Based Myoelectric Potential Estimation Method for Wheelchair Operation.

Wheelchair sports are recognized as an international sport, and research and support are being promoted to increase the competitiveness of wheelchair sports. For example, an electromyogram can observe muscle activity. However, it is generally used under controlled conditions due to the complexity of preparing the measurement equipment and the movement restrictions imposed by cables and measurement equipment. It is difficult to perform measurements in actual competition environments. Therefore, in this study, we developed a method to estimate myoelectric potential that can be used in competitive environments and does not limit physical movement. We developed a deep learning model that outputs surface myoelectric potentials by inputting camera images of wheelchair movements and the measured values of inertial sensors installed on wheelchairs. For seven subjects, we estimated the myoelectric potential during chair work, which is important in wheelchair sports. As a result of creating an in-subject model and comparing the estimated myoelectric potential with the myoelectric potential measured by an electromyogram, we confirmed a correlation (correlation coefficient 0.5 or greater at a significance level of 0.1%). Since this method can estimate the myoelectric potential without limiting the movement of the body, it is considered that it can be applied to the performance evaluation of wheelchair sports.

Model-based analysis on social acceptability and feasibility of a focused protection strategy against the COVID-19 pandemic.

This paper studies the social acceptability and feasibility of a focused protection strategy against coronavirus disease 2019 (COVID-19). We propose a control scheme to develop herd immunity while satisfying the following two basic requirements for a viable policy option. The first requirement is social acceptability: the overall deaths should be minimized for social acceptance. The second is feasibility: the healthcare system should not be overwhelmed to avoid various adverse effects. To exploit the fact that the disease severity increases considerably with age and comorbidities, we assume that some focused protection measures for those high-risk individuals are implemented and the disease does not spread within the high-risk population. Because the protected population has higher severity ratios than the unprotected population by definition, the protective measure can substantially reduce mortality in the whole population and also avoid the collapse of the healthcare system. Based on a simple susceptible-infected-recovered model, social acceptability and feasibility of the proposed strategy are summarized into two easily computable conditions. The proposed framework can be applied to various populations for studying the viability of herd immunity strategies against COVID-19. For Japan, herd immunity may be developed by the proposed scheme if [Formula: see text] and the severity rates of the disease are 1/10 times smaller than the previously reported value, although as high mortality as seasonal influenza is expected.