[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

We aim to predict highly accurate Extracorporeal Shock Wave Lithotripsy (ESWL) outcome predictions by introducing complex machine learning models. To interpret these complex models, factor importance evaluation by Shapley Additive Explanations (SHAP) value was performed. In this study, the data was collected from 214 subjects. Three machine learning algorithms were performed to predict ESWL outcomes, and factor importance was evaluated by SHAP. The results showed that the two ensemble tree models provided superior accuracy compared to a simple determination. These results encourage the usage of complex models that are difficult to interpret and allow for more accurate prediction of ESWL outcomes.

View full abstract

We are developing a life support robot for caregivers. In order to provide daily life support, the robot needs to run autonomously. The purpose of this research is to develop a control method for autonomous motion that matches the living environment. For instance, the robot should move slowly near a bed or in a narrow corridor to avoid colliding with people. In this work, we start by recognizing the size of the area, and adjust the speed of the robot depending on the size. We also verify the effectiveness of the system through simulation.

View full abstract

In this study, we aimed to develop a system that uses machine learning to evaluate the performance of musical instruments. The system was designed to run on a web browser in order to run on a variety of devices. We conducted an evaluation experiment with five university students who had experience playing musical instruments, and obtained a certain level of evaluation of the system's performance evaluation results and feedback. We believe that the system was able to evaluate and visualize the performance of musical instruments. In the future, it will be necessary to study the evaluation of performances other than pitch.

View full abstract

 Some characteristics of the mental map were investigated using the in-vehicle cameras and the following results were obtained. 1 The memory of the branch points by the left camera is about 48% and it by the ,forward one is about 89%, 2 The memory of the locations by the left camera is about 67.5% and it by the forward one is 79.2%.

View full abstract

In this study, we examined whether the effects of applying a skin stimulation tool during high-intensity exercise, which were verified in previous studies, could occur under conditions similar to those of daily activities using physiological indices. We measured autonomic nerve activity, brain activity, and eye movements during a 5-minute desk work task using a skin stimulation tool applied to both mastoid processes of the temporal bone. The results showed no statistically significant differences in any of the indices. When the skin stimulation tool was applied to the mastoid process of the temporal bone, the effect on the physiological index was small.

View full abstract

 People living in modern society feel relatively high mental stresses in the workplace and daily life, and these stresses are a critical topic because of causing serious illness in the future. With such a background, the research about comfort aiming to get rid of mental stresses draw attention recently. However, one of the problems is difficult to find a common solution for it, because each person has his/her own vague sensations to comfort. Some specific methods to quantitatively assess comfort level will be needed from now on. To sustain comfort is defined as subjective insensitivity, it is basically difficult to detect it as a physiological response. There is one strategy of assessment comfort level that whether the difference in a physiological response to mental stress appears in a comfortable environment and uncomfortable environment. If a stress reduction effect in a certain comfort environment exists, it is expected to detect specific physiological responses in both environments with the load.
 In this study, we fulfill an experiment to assess the sustainable comfort feelings using the objective index. If we are able to quantitatively assess the comfort level by some physiological response, it is possible to apply it to various products to accurately evaluate more than now. The result of comfort assessment with cerebral blood flow we experimented with NIRS equipment is reported this time.

View full abstract

There is a high possibility that it will be difficult to make a precise judgment of programming skills only by static analysis of the created source programs. In the process of coding a source program, it is thought that characteristic operations such as the timing of keystrokes and differences in notation and expressions depending on the programming style can be seen. In this paper, we will consider on an experiment whether it is possible to evaluate programming skills based on the recorded data of the coding sequence.

View full abstract

In this study, to investigate the phenomenon that neutrophils generate pseudopods near the wall, the distance between the neutrophils and the wall is measured. As the result, it is found that the neutrophil velocity decreased near the wall. The geometrical characteristics of the neutrophils are asymmetrical at a distance from the wall, but no extreme peaks such as pseudopods appeared on the membrane. In addition, the relationship between the shape of neutrophils and the propulsion mechanism is investigated by calculating the velocity of neutrophil movement and the concentration gradient on the membrane of neutrophils stimulated by shock waves, evaluating the membrane function of neutrophils, and comparing it with the geometric characteristics. The results show that shock wave stimulation improved the membrane function of neutrophils. Besides, it is found that the arithmetic mean roughness and root mean square roughness of the neutrophils decrease for the shock wave stimulus. The changes in skewness and kurtosis indicated that the surface roughness of the neutrophil membrane increased. In the future, it will be investigated that the further factors that affect the propulsion of neutrophils and the driving principle in detail.

View full abstract

Land-based aquaculture systems for fishes cause lots of stress. It is challenging to cultivate fish stably in such a condition, so we need stress-analyzing methods for fish. We have conducted experiments on flounders to give them high-temperature saltwater as a factor of stress cause and investigated the possibility of fast and easy fish stress analysis using Poincaré plot by calculating stress evaluation indexes such as RMSSD and sd2/sd1. As a result, we observed that flounders under a stress state come back to a relaxed state to weaken sympathetic nerve activity after giving the factor of stress cause as mentioned above.

View full abstract

We are developing a new gait trainer that adjusts trunk posture to the symptoms of gait training for gait trainers with standing muscle deficits. In previous studies, the bimodality of vertical ground reaction forces was found to maintain and improve walking ability. With reference to this experiment, this report focuses on a gait trainee whose posture was corrected by a novel gait trainer. During the training of this trainee, we will verify if gait can be improved by long-term gait training using surface EMG.

View full abstract

This paper describes the novel treatment for ablation of dermal affected tissue without scar. It employs a sporting cold spray which is commonly used for the treatment for stremma and bruise. A cold spray is much cheaper and easier to handle and keep in storage rather than liquid nitrogen because of its higher boiling temperature. The developed device was examined and evaluated for verruca vulgaris, seborreic keratosis (verruca senilis), pigmented macule and milium. The pigmented patch ceased to exist without leaving the scar. This device must play an important role in dermatologic surgery in the near future.

View full abstract

We introduced the addition of a traditional medicine chapter to ICD-11 at the BMFSA 2018. In May 2019, the traditional medicine chapter of East Asian Traditional Medicine was added to ICD-11 as a supplementary chapter. Currently, the use of the traditional medicine chapter of ICD-11 in Japan is in the research stage. In the field of acupuncture and moxibustion in Japan, if we can accumulate the data of the ICD-11 traditional medicine chapter, the actual situation of acupuncture and moxibustion treatment in Japan will be clarified. If we can accumulate the data of the traditional medicine chapter in acupuncture and moxibustion in Japan, we are convinced that it will be an important information to convey the value of traditional medicine to the Japanese people.

View full abstract

Membership function can be constructed by confidence intervals of a probability distribution. From the relation we consider an equivalence between fuzzy numbers and random variables and its application to analysis of fuzzy systems.

View full abstract

In 1975, Zadeh proposed the concept of type-2 fuzzy sets for modeling imprecision and uncertainty. type-2 fuzzy sets are fuzzy sets whose membership grades are type-1 fuzzy sets. The type-2 fuzzy numbers are the extension of this concept to real numbers, and many researchers have devoted their efforts to this research. In this paper, we would propose a new triangular type-2 fuzzy number and discuss its application to simultaneous differential equations.

View full abstract

The first author taught mathematics at a high school and administered a test. Fuzzy theory and Rough set theory were used to analyze the structure of teaching materials. As a result, it became clear how the students understand the teaching materials and what are the important factors for solving a certain applied problem.

View full abstract

The professional career of female medical doctors is influenced by various life events that can lead to early retirement: marriage, childbirth, childcare, nursing, mammy track etc. In recent years, efforts have been launched to have female doctors resume their clinical practice. In order to find clues to solve the problem, we used survey data from doctors who became mothers and identified their motivation using the spherical SOM, Residual Sum of Squares(RSS) and Significant degree.

View full abstract

The problems of overlearning and optimal learning, which have been problems in SOM learning for a long time, were investigated using the significance data of irises and animals in the learning process of the significance index of 1,0. The method has been extended to general data. It was estimated that about 5000 times were close to optimal learning. This method was applied to the significance analysis of fatigue degree data and well-known benchmark problems.

View full abstract

This paper proposed a new method of grouping after principal component analysis. First, we argued that normalized principal component scores should be used in order to compare many results with each other. Using these scores, we also proposed two ways in grouping of the members in two-dimensional maps: box plots and ellipse plots. This method is an excellent way to classify all people according to their tendencies or to select extreme people based on rules. The advantage of this method is that no one is left out in the classification. Also, the percentage can be freely decided, and the classification is calculated automatically. The nine classified areas can be given meaning.

View full abstract

Recently, AI technology called deep learning has been attracting attention. Deep learning is a kind of neural network. It is a method of machine learning using a hierarchical neural network with a multi-layer structure. Deep learning has shown great results in image recognition. In this study, we consider the classification of unearthed coins using deep learning. There are many types of unearthed coins to be excavated from a ruin. One of the most famous coins is Kanei-tsuho coins. There are many subdivisions of Kanei-tsuho coins. However, the classification of unearthed coins is even difficult task for numismatics experts. The purpose of this study is to improve the accuracy of identification of unearthed coin images using deep learning.

View full abstract

This paper discusses the effectiveness of Visual Analog Scale (VAS) for subjective survey by using SWEMWBS. SWEMWBS is a mental health scale to confirm the degree of mental health by asking 7 questions using Likert Scale (LS). Since it is easy to investigate and has a low burden, SWEMWBS is one of the methods used worldwide as a method of investigating the degree of mental health. The survey in this paper was conducted with the same questionnaire using VAS instead of LS as the survey conducted by the International Labor Organization (ILO). The results show the analysis of using VAS with univariate scatter plot and so on is able to better visualize the situations of the examinees. Thus, it is implied that applying VAS to SWEMWBS is effective.

View full abstract

In recent years, research has advanced on the use of robots that effect healing through voice and touch capabilities. This study examines the customer ratings that are made on different communication toy robots in order to determine how to introduce such robots effectively in early childhood education in the future. The target of this study is the 12 types of robots with 20 or more customer reviews, which rank within the top 100 selling communication toy robots on Amazon.co.jp as of December 2019. For each robot, not only the “rating level” judged by the customer reviewer but also his/her comment is considered. These comments are analyzed using text mining software.

View full abstract