[in Japanese]

View full abstract

[in Japanese]

View full abstract

The muscles of the lower extremities are important in baseball, and recovery methods should be　considered. AVA cooling is an effective recovery method because, unlike conventional icing, it allows cooling without decreasing blood flow. Therefore, the purpose of this study was to investigate whether AVA cooling is effective in the ecovery of muscle fatigue in the lower extremities. The results showed that AVA cooling improved muscle fatigue in the lower extremities before and after practice and improved pitching performance. This suggests that AVA cooling improves lower extremity muscle fatigue and is effective in improving pitching performance.

View full abstract

[in Japanese]

View full abstract

The purpose of this study is to Clarify the relationship between cytokinesis and calcium ion flow. It is generally known that the interactions between cytokines and receptors on the neutrophil surface are related to signaling by calcium ions. In this study, to clarify the effect of calcium ion concentration on the neutrophil propulsion mechanism, observation experiments with a microscopy are conducted. As calcium ion indicator, fura-2 is used. The time history of calcium ion concentration is obtained. As a result, it was found that both the cytokine concentration gradient on the membrane and the calcium ion concentration gradient inside the neutrophil periodically change and the frequency is almost same. It is concluded that calcium ions flow has correlation with cytokine flow.

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

In recent years, labor shortages have become a social issue, affecting even waste disposal facilities.This study proposes an affordable automated control system for cranes in waste disposal sites, aimed at lowering the barrier to automation for small and medium-sized enterprises. The system consists of two main parts: a camera-based coordinate designation unit and a joystick control for crane operation. We simulate the system using a desktop robotic arm as a crane model to verify its functionality. This paper details the camera-based coordinate designation and joystick control, as well as their key features.

View full abstract

The authors are conducting research on a programming learning support system to make it easier for beginners to learn C programming. So far, we have designed and implemented a “standard coding form” to help program ssembly and a function to present hints according to the cause of stumbling blocks, and have evaluated the system as needed. A coding sequence, a method that records keystroke information as a way to monitor learner skills, has been developed. We believe that the functions we have studied and the analysis of coding sequences and presentation of the results will contribute to maintaining learner motivation. In this paper, we report the results of a comparison experiment with a conventional learning environment regarding the maintenance of motivation, and discuss the possibility that the design of each function is effective.

View full abstract

This study investigates how calligraphic styles and viewers' expertise influence the aesthetic evaluation of apanese calligraphy. We developed a quantitative assessment method using Visual Analog Scale to analyze responses from 145 college students with varying calligraphic experience. Participants evaluated three fundamental writing styles (kaisho, gyosho, and sosho) across seven aesthetic dimensions. Statistical analysis revealed three key findings: (1) distinctive perceptual characteristics for each style, with kaisho excelling in readability (mean 0.76) while sosho demonstrated superior artistic uniqueness; (2) significant expertise-dependent evaluation differences, particularly in perceiving sosho's artistic qualities (experienced: 0.72, novice: 0.52); and (3) the formation of distinct evaluation patterns based on viewers' expertise levels. These findings provide empirical evidence for developing objective evaluation criteria in calligraphy education and automated assessment systems for traditional Japanese calligraphy.

View full abstract

Currently, there are few reports comparing the psychological factors of supporters before and after activities for children with developmental disabilities. Accordingly, this study aimed to explore the changes in awareness of coaches who provide exercise and sports instruction to children with developmental disabilities, and to examine how their teaching methods and interactions with parents change because of their involvement with children with developmental disabilities, leading to personal growth. Analysis using semi-structured interviews and KJ method showed that the coaches improved the quality of their instruction by placing emphasis on flexible teaching methods for children and creating a safe and fun environment and building relationships of trust with the children and their parents.

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

Currently, using the internet as a means of gathering tourism information has become standard practice. Traditionally, information related to travel was obtained from travel magazines, television, and travel agencies. However, with the widespread adoption of the internet, these sources have been largely replaced by online earches for tourism information. Additionally, visitors to tourist destinations often share their experiences on platforms like SNS (social networking services). To increase tourism, it has become essential to analyze online information. In this study, we collect regional information from the vast amount of data available on the web for use in tourism promotion and regional revitalization. However, the data posted on SNS varies widely, and it often includes content that differs from the intended purpose of analysis. Therefore, in this study, we focus on the frequency of posts by the same user ID to classify the collected data. We examine whether it is possible to identify valuable posts through this classification based on posting frequency.

View full abstract

[in Japanese]

View full abstract

Continuous authentication is used to detect identity theft and to confirm the identity of a person. Continuous authentication using keystroke information, a type of biometrics, is a stress-free method that does not cause interruption of the work of the person being authenticated. In this paper, we present a model of continuous multimodal authentication using features obtained from a keyboard, a microphone, and a webcam, which are commonly used for external devices. This paper discusses the processing model we have built with the goal of realizing a processing model for the Enter key operation in free text input .

View full abstract

In Japan, the rapid aging of the population has led to a critical shortage of caregiving staff, necessitating the urgent improvement of efficiency in care environments. Traditional video surveillance systems pose privacy concerns and have limitations in effectively monitoring elderly patients. In this study, we propose a non-contact, privacy-preserving system for monitoring and recognizing the Actions of elderly patients using depth cameras and human pose estimation techniques. Specifically, we employ depth cameras to collect data and utilize bounding box detection (BB) and human pose estimation (Keypoint) methods to analyze elderly Actions. To achieve detailed action recognition, we compare the effectiveness of the BB method with the Keypoint method and apply a Graph Convolutional Network (GCN) to model the relationships between body joints. Furthermore, we use a Transformer model for action recognition and compare two preprocessing methods—standardization and Min-Max scaling—to develop a more accurate action estimation model.

View full abstract

We conducted an experiment in which subjects were asked to watch a drive recorder video, draw a map from memory, and at the same time answer the distance traveled, straight line distance, and direction of the end point as seen from the start point. The subjects were asked to watch two courses, "Course with sound " and "Course without sound ". Six courses of video were used in the experiment. The correct response rates for direction, distance, and change of course were compared with and without sound.

View full abstract

The number of samples on the horizontal axis was normalized to 0-1 using data in which uric acid　values were arranged in ascending order. The data points were compared from A, B, and C of 3 data sets. In　each data, there are differences in uric acid levels between men and women. Also, based on the values on the　horizontal axis where the normal value falls, it was possible to compare which region was healthier using three　data points, A, B, and C.

View full abstract

Using benchmark data, we investigated its accuracy using a spherical SOM．The following six data types were used: iris data, wine data, glass data, liver disease data, diabetes data, and breast cancer data. Each calculation was performed by normalizing the data to 0-1. For each method, each data was projected onto a spherical SOM, and the accuracy was judged by determining which group the boundary of each group of each data belonged to. As a result, the accuracy was highest for irises, wine, and breast cancer in that order. The rest had poor accuracy and many misclassifications.

View full abstract

We examined the distribution status and characteristics of the cherry blossoms in the western part of　Tottori Prefecture. Here, we investigated the case of the Someiyoshino cherry treess on their triage of the diagnosis and their tree management by using the spherical SOM and the significance method.

View full abstract

In the Traveling Salesman Problem (TSP), when the number of cities increases from hundreds to thousands, the number of trials itself is limited due to the increase in calculation time, and it becomes impossible to even get the correct solution. In the SOM method, the calculation time increases on the order of N2. This N2 factor etermines the limit of SOM. In this study, we focused on the function of neighborhood radius, one of the parameters, and attempted to reduce the number of learning cycles.

View full abstract

The authors have defined a fuzzy contingency table (type-1/type-2 fuzzy contingency table) by applying　t-norm. Then, this enabled the fuzzification of typical similarity indices in general set theory into type-1/type-2　fuzzy contingency tables. In this paper, we propose a vector similarity calculation method using fuzzy　contingency table and a similarity evaluation method using MDS and multiple regression analysis, and evaluate　the similarity of correlated simulated data as its simulation.

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

This paper provides an overview of the author's studies of subjective evaluation measurements using visual analog scales (VAS). They have previously conducted studies into subjective evaluation measurement using VAS and Likert Scale, the correlation between subjective evaluation measurements and biosignal analysis values, and visualizing methods for subjective evaluation values. As a result, the usefulness of subjective evaluation measurement using VAS has been demonstrated. Meanwhile, the authors have also proposed a visualizing method for trends in small samples. Based on these results, it will be important to conduct studies into subjective valuation measurement using VAS in a wider range of fields.

View full abstract

[in Japanese]

View full abstract

In recent years, predictive maintenance for equipment in the manufacturing industry has gained significant attention. This study presents the development of a system that utilizes Wi-Fi sensing technology to non-invasively measure the vibration of machine tools and assess their operating conditions. By analyzing the channel state information (CSI) from Wi-Fi signals, the aim is to differentiate between various states, such as machine stoppage, idling, and cutting. Experimental results have confirmed that high-precision identification is achievable under controlled conditions. However, accuracy can be adversely affected by environmental changes, leading to fluctuations. To mitigate the impact of surrounding factors, a new CSI measurement system was designed to obtain more stable data. The findings from this research are expected to enhance the efficiency of equipment management within the manufacturing industry.

View full abstract

[in Japanese]

View full abstract

This paper introduces research on building multimodal AI. Multimodal AI is an AI that can uniformly handle images, voice, text, and other environmental information. To build a multimodal AI, it is necessary to build a database and interface that can uniformly handle multimodal data. Multimodal data includes voice, text, and other environmental information data. Multimodal AI has experiences like humans and can make the same judgments and take the same actions as humans. Multimodal AI can make autonomous decisions in accordance with environmental conditions and objectives and makes decisions based on experience. To realize human multimodal AI, it is first necessary to create a database that can handle multimodal data.

View full abstract

Idiopathic interstitial pneumonia (IIP) is one kind of designated diseases of Japan, because there is no way of treatment with western medicine. The attempt was made to adopt the acupuncture/moxibustion treatment for working out the IIP. The blood test shows the temporal decrease of sialylated carbohydrate antigen (KL-6), which is a serum marker to diagnose and monitor IIP. It implies that the activity of IIP is significantly reduced.

View full abstract

[in Japanese]

View full abstract

Humans often use colors to judge situations well in their daily lives. Therefore, it is important to consider how colors are perceived in order to facilitate social life. In this study, we discuss improving the visibility of digital images based on color enhancement in color vision diversity, especially in dichromatic vision. The LMS color space is convenient for considering dichromatic vision. Meanwhile, digital images often employ the RGB color space to represent colors. We investigate color enhancement by mapping the coordinates of the LMS color space to the RGB color space. The performance of color enhancement is discussed in experiments.

View full abstract

Soft tissue sarcoma (STS), which is a rare cancer, arise in soft tissues in the body, and it is difficult to diagnose and treat in general hospitals. This study focuses on obtaining a quantitative index that supports doctors building a treatment plan for STS based on the patient's risk of experiencing clinical events in the future. This index is expected to reduce the burden on doctors to make decision and realizing the tailored treatment considering the patient's condition. This paper proposes a survival period prediction method using convolutional neural network (CNN) and pathological images. The number of subjects is not enough to train a complex CNN model for regression because the STS is one of the rare cancers. We employ the mean-variance loss to perform the regression using a classification CNN called ResNet18. Furthermore, we propose the fit-label to efficiently train the classification CNN for the regression task. Experiments on 44 whole slide images of 44 patients showed that the proposed fit-label outperformed hard- and soft-labels, achieving the lowest mean absolute error of 6.5 months and the highest concordance index of 0.893. These results suggested that the proposed method can be used to evaluate the risk level of STS patients.

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

[in Japanese]

View full abstract

This paper presents a comparative study evaluating the effectiveness of the Visual Analog Scale (VAS) and ikert Scale (LS) for assessing AI-generated emotional responses to short stories. We conducted experiments with technical college students majoring in information systems (n=20-22/group) and AI responses (using　ChatGPT GPT-3.5, with five ifferent personality settings per evaluation method) to analyze four basic　emotions: interest, surprise, sadness, and anger. Three short Japanese stories were selected as stimuli, focusing　on their potential to elicit subtle emotional responses. The results revealed that VAS demonstrated superior performance in capturing AI-generated emotional responses, particularly in terms of precision and sensitivity to subtle variations. Our findings indicate that AI consistently overestimated positive emotions (interest and surprise) compared with human responses, while showing varying degrees of accuracy in recognizing negative emotions (sadness and anger). Additionally, VAS exhibited higher consistency and smaller standard deviations in AI response measurements than LS, especially with limited data points. This research contributes to the methodology of evaluating AI's emotional intelligence and provides insights into the development of more empathetic AI systems. Furthermore, we discuss future research directions, including multimodal emotional assessment and cross-cultural comparative studies, to enhance our nderstanding of AI's emotional recognition capabilities of AI.

View full abstract

We have made concerted efforts to support the smooth implementation of programming education, focusing on preparation and practical application. While our aim is to utilize programming education materials effectively, we recognize that varying teacher competencies and subject-specific characteristics can pose challenges. Our research investigates how teachers can optimally use programming education materials and adapt their approaches based on specific circumstances. We are developing methods to flexibly present the same materials across different contexts and subjects. Additionally, we have identified key features of effective programming education materials. In this study, we will present our findings to date and discuss our future plans in this field, emphasizing the importance of adaptable strategies in programming education.

View full abstract

[in Japanese]

View full abstract