Special Issue

Preface to the Special Issue

View more >>

Special Issue Information Sciences

Fundamental Study on Detection of Dangerous Objects on the Road Surface Leading to Motorcycle Accidents Using a 360-Degree Camera

In recent years, the number of fatalities in traffic accidents involving motorcyclists has remained almost unchanged, with single-vehicle accidents accounting for 37.2% of all accidents by accident type in the past five years. In the development of overturn prevention devices for motorcycles, problems remain in post-mounting of the device as well as its downsizing. On the other hand, an existing study using deep learning has proposed a method for detecting dangerous objects on the road surface leading motorcycles to overturn, though this method still needs verification under different conditions. In this study, we apply a method for detecting dangerous objects on the road surface from video images using YOLO to two types of 360-degree cameras and verify that this method is versatile under different conditions.

View more >>

Special Issue Agriculture Electrical and Electronic Engineering Food Sciences Information Sciences

Wildlife Approach Detection Using a Custom-Built Multimodal IoT Camera System with Environmental Sound Analysis

This paper presents a custom-built IoT camera system designed for recognizing wild animal approaches, where data transmission and power consumption are critical concerns in resource-constrained outdoor settings. The proposed method involves the spectral analysis on both infrared and environmental sound data before uploading images and videos to the remote server. Experiments, including battery endurance tests and wildlife monitoring, were conducted to validate the system. These results showed that the system minimized false positives caused by environmental factors such as wind or vegetation movement. Importantly, adding frequency features from audio waveforms that capture sounds including wind noise and footsteps led to an improvement in detection accuracy, which increased the AUC from 0.894 to 0.990 in Random Forest (RF) and from 0.900 with infrared sensor data alone to 0.987 in Logistic Regression (LR). These findings contribute to applications in wildlife conservation, agricultural protection, and ecosystem monitoring.

View more >>

Special Issue Information Sciences

Research on Indoor Self-Location Estimation Technique Using Similar Image Retrieval Considering Environmental Changes

In Japan, the shortage of human resources due to the declining birthrate and aging population is becoming a social problem. Particularly in the security industry, the irregular working hours and associated risks are making it increasingly challenging to secure workers. This has led to a rise in use of security systems that utilize security cameras and drones. However, in factories and other buildings with a lot of equipment and intricate structures, there is the problem of blind spots caused by occlusion. This situation necessitates the use of automated drone patrols, and a problem arises when self-position estimation fails in areas where acquiring feature points is difficult, such as corridors. To solve these problems, in a previous study, we devised a technique for position estimation using a method that can calculate similarity based on changes in the distribution of color information across the entire image. In this study, we propose a method that can cope with environmental changes caused by object movement while combining feature point-based methods.

View more >>

Special Issue Engineering in General Information Sciences Others

A Study on the Development of a Traffic Volume Counting Method by Vehicle Type and Direction Using Deep Learning

The turning movement count is investigated to understand the traffic conditions at intersections and identify bottleneck locations. In recent years, methods utilizing probe data and AI-based analysis of video images have been developed to streamline the survey process. Existing methods can count vehicles as they pass but struggle to classify vehicle types. Therefore, the objective of this study is to develop a method for counting turning movement count by vehicle type using deep learning. In this method, YOLOv8 is used to detect cars, buses, and trucks in video images, and BoT-SORT is used for tracking. When a vehicle being tracked crosses the cross-sectional lines and auxiliary lines at the intersection captured in the video images, it is counted by class. In this case, the entry direction of vehicles that cannot be determined upon entering the intersection is estimated based on accurately counted vehicles. Additionally, the entry direction is inferred from a series of vector information within the detection bounding boxes. The results of the verification experiment showed that the proposed method can count the directional traffic volume with an accuracy of over 95.0% and classify the three vehicle classes—car, bus, and truck—with an accuracy of over 90.0%.

View more >>

Special Issue Engineering in General Information Sciences Others

Detecting Near-Miss Actions and Estimating Physical Fatigue among Construction Workers Using Wearable Sensors

Labor shortages in the construction industry have become a serious issue in developed countries, particularly in Japan, where workforce aging and declining recruitment of young workers are significant challenges. In this context, ensuring worker safety has become increasingly critical. While occupational accidents in Japan's construction industry have decreased annually due to proper safety measures, the construction industry still has the highest number of fatalities among all industries. Falls from height and falls on the same level are the leading causes of injuries and fatalities. Therefore, detecting near-miss incidents (such as tripping and slipping) that precede falls, along with physical fatigue, could help prevent occupational accidents. This study investigated the feasibility of detecting near-miss incidents and estimating fatigue levels using wearable sensors suitable for continuous monitoring at construction sites. We conducted validation experiments simulating near-miss actions and fatigue conditions. Results showed that applying a Convolutional Neural Network (CNN) to data collected from an iPhone® placed in workers' trouser pockets achieved an F1-score of 0.95 in detecting near-miss actions. Additionally, by comparing body sway magnitudes before and after fatigue, we confirmed the potential for estimating physical fatigue.

View more >>

Article Others

A practical evaluation method using item response theory to evaluate children’s form of Jumping-over and crawling-under

In order to develop the test battery evaluating the movement of Jumping-over and crawling-under for young children, we measured and videotaped it performed by 350 kindergarten children. After that, 16 movements by body part were assess using three categories of “possible,” “no idea” and “impossible.” Since the change of eigenvalues derived from this data represented a one-dimensional structure having a high homogeneous each other, successively, the parameters of step difficulty and samples were computed using IRT. Among various IRT models, this study used Partial Credit model because obtained data is ordinal and the sample size is few. Then we found the outcomes as follows: 1) The correlation between the two sets of parameters of step difficulty computed from two sets of randomly divided samples was high, so that it can be concluded that the difficulty parameters are not depended on any ability level of samples. Again, the correlation between the two sets of sample parameters calculated from two groups of randomly grouped item parameters was also significant. This fact allowed us to conclude the obtained sample parameters did not depend on any difficulty level of items. 2) As significant difference between ages in obtained thetas was found, it is considered that thetas reflect motor ability that advances with maturity. There was also high correlation between thetas and measurements of Jumping-over and crawling-under. 3) Judging from information function consisting of 16 items, this test is suitable to determine the ability with from middle to a little low level because the information reached around there. 4) A practical estimation and evaluation sheet utilizing thetas by total score based on Zhu and Cole (1996) was developed and the application examples were represented. 5) As a result that the relationship between strictly computed indexes of fitness and the number of aberrant patterns detected in the practical method in this study was examined, the high correlation was found. Judging from this fact, it can be concluded that IRT is useful to estimate and evaluate the movement of Jumping-over and crawling-under.

View more >>

Technical Article Business & Management Economics Psychology and Education

A Survey on BeReal among University Students: Focus on Learning Motivation and Privacy Consciousness

The purpose of this study was to determine university students' thoughts on the use of BeReal. After clarifying these ideas, we compared and examined the differences in learning motivation and privacy consciousness by use, non-use, and differences in thinking. The survey population consisted of 368 university students. The survey included “items on thoughts about using BeReal”, “Learning Motivation Scale”, and “Privacy Consciousness Scale”. The results of this study indicated that BeReal is becoming more common among university students, and that many of them are willing to contribute during class.Also, It revealed that university students who use BeReal tend to be less learning motivation than those who do not use BeReal. Furthermore, the group that posts BeReal during class tends to have lower awareness of and behavior to maintain their own privacy than the group that does not post BeReal during class.

View more >>

Review Article Others

Methodological examination of methods for analyzing factors that affect home team advantage: from univariate analysis to multivariate correlation models and causal models

While most researchers agree that home advantage (HA) exists in soccer, baseball, field hockey, basketball, and other sports regardless of whether they are collegiate or professional, there is no common view on the relationship between “travel,” “familiarity with the game environment,” and “spectator effect” and the factors derived from them and home advantage. However, there is no common view on the relationship between “travel,” “familiarity with the game environment,” “spectator effect,” and their derived factors, and HA. In other words, unless there are new factors that are not addressed here, it is more appropriate to think of the factors that affect HA, which clearly exists, as “multiple factors that relate to each other and affect it comprehensively,” rather than as “factors that affect it independently. Therefore, a possible methodology for examining HA factors is the use of multivariate analysis, such as multiple regression analysis or logistic regression analysis. Then, when illustrating the findings obtained from correlation analysis, one-way arrows are used to show the relationship between the factors, and the focus shifts from the correlation relationship to the search for causal relationships. When the scope of correlation analysis is extended to include causal relationships, path analysis is used to examine not only direct effects but also indirect effects. Furthermore, as a natural development of the methodology of causal analysis, a new direction is considered to be the analysis of covariance structure, which examines the causal relationships between factors, rather than only the observed variables.

View more >>

Article Engineering in General

Evaluation of Revitalization Measures for Central City Areas Considering Changes in Human Flows

In recent years, a declining population and an aging and decline have led to a reduction in the vibrancy and economic activity of the city. Various regional cities have taken measures to revitalize their central city areas. However, they have yet to develop a method to quantify the effects of these measures. In this study, using a device equipped with Internet of Things (IoT), we obtained basic data on the number of visitors before the COVID-19 to quantify pedestrian traffic along Kokusai Street. Our findings revealed that the implementation of revitalization strategies led to a notable increase in the number of individuals visiting the area, as well as in the average duration of their stay. This suggests that the implemented measures have the potential to contribute to the revitalization of the area, thereby fostering the creation of a vibrant town center.

View more >>