In this paper, input-oriented virtual internal model tuning is expanded to non-minimum phase systems. Proposed method can tune the feedback controller and the desired transfer function. Compared to FRIT, the proposed method can realize good controllers even when the time constant of the desired transfer function is small. The validity of the proposed method is verified via numerical simulation.

In the medical field, accidents involving the fall of inpatients around beds have become an increasing problem. To prevent such accidents, nurses record the condition of inpatients using a check sheet referred to as the Fall Assessment Score Sheet (Fall AS). These sheets are utilized for each inpatient and provide useful information for daily clinical judgment. However, compiling these sheets adds to the excessive workload of nurses, as the Fall AS contains numerous items to be checked and assessments frequently necessitate revision. We sought to model the clinical judgment of nurses using Lasso regression, with the aim of reducing the number items of the Fall AS. Three nurses were assigned a questionnaire that included 200 patterns of Fall AS and seven patterns of patient posture, and were requested to fill in the fall risk (0% to 100%) for all 1400 pattern combinations. The clinical judgment model was constructed based Lasso regression, adopting each fall risk and Fall AS as objective and explanatory variables, respectively. The proposed model succeeded in reducing the number of Fall AS items from 50 to 25. Moreover, the mean error of estimated values for the clinical judgment increased by only 3.44% compared with the general least-squares method.

In deep learning (hereinafter referred to as DL) education, universities, research institutes and large companies are promoting education by fostering educators and creating curriculums based on national policies. However, especially small and medium-sized enterprises and companies in industries that are not good at IT cannot prepare their own educational environment, and it is considered that the educational environment for improving the added value of products and services by DL is not sufficient. Furthermore, the neural network, which is a component of DL, has a feature that it is difficult to determine the feasibility for the realization target. This feature is an issue in educational methods. Based on the above situation, we proposed an educational method that combines online live lectures, reviews, and homework as DL applied education, and confirmed its practice and educational effect.

The purpose of this study was to advance our understanding on the autonomic effects of electric fields, and to investigate the usage of electric fields for self-care by identifying the conditions under which electric field treatment causes changes in heart rate variability. The results have indicated that heart rate variability, related to both sympathetic and parasympathetic activities, increases after a 60Hz 9,000V electric field treatment of 15-minute. These findings suggest that heart rate variability can be used as a biomarker for monitoring the biological effects.

The application of Doppler radar to classify the motion differences related to the differences of pants is presented. The deep learning of the Doppler radar spectrogram using a convolutional neural network achieved a 90% of the accuracy for the classification of whether the participants wore denim pants or trekking pants while ascending a step.