Special Issue Education Information Sciences Psychology and Education Sociology

Development of Gamified VR Content to Enhance Indoor Disaster Preparedness and Risk Perception

In Japan, natural disasters such as earthquakes and floods are frequent. However, many citizens view such disasters as impersonal events rather than imminent personal threats. This has led to low participation rates in local disaster drills and poor retention of disaster prevention knowledge, posing significant challenges. Against this backdrop, existing research has reported the effectiveness of disaster prevention education utilizing gamification and VR. However, when applying existing approaches to VR-based disaster prevention education, it is necessary to consider the potential psychological burden of highly realistic depictions, opportunities for self-directed hazard identification, and replay-oriented design. Therefore, this study developed VR disaster prevention learning content incorporating gamification. The content was designed to foster a sense of crisis about disasters and interest in replay while considering psychological burden. The proposed content employs a "spot-the-difference" game mechanic, requiring users to actively identify deficiencies in indoor disaster preparedness measures. As a proof of concept, a questionnaire survey was conducted immediately after the experience with 123 participants, including high school students. Many participants reported an increased sense of crisis regarding disasters and an intention to replay the game.

View more >>

Special Issue Information Sciences Psychology and Education Sociology

Development of a VR Vertical Evacuation Simulator for Schools Integrating Conformity Bias for Disaster Preparedness Education

In recent years, Japan has experienced frequent water-related disasters, including earthquake-induced tsunamis and flooding caused by heavy rainfall, increasing the importance of disaster preparedness measures. However, participation in disaster drills remains low, indicating that many citizens do not regard disaster preparedness as a personally relevant issue. In addition, conventional drills often require participants to follow predetermined routes and therefore make it difficult to experience unexpected situations, such as blocked routes or collective behavior during panic. Although disaster simulators using virtual reality (VR) have advanced, few studies have focused on indoor flooding while also considering the influence of other evacuees’ incorrect evacuation behavior. This study therefore developed a simulator that enables users to experience vertical evacuation during indoor flooding in school facilities, which are often designated as evacuation sites. By placing non-player characters (NPCs) that exhibit incorrect evacuation behavior, the simulator makes it possible to examine how the behavior of others may affect participants’ evacuation decisions, subjective difficulty, and sense of urgency. An empirical evaluation clarified the simulator’s potential value for disaster preparedness education and awareness raising, as well as issues requiring further verification.

View more >>

Article Agriculture Food Sciences Information Sciences Psychology Psychology and Education

Why do you recall that smelly food? Effects of childhood residence region and potential reinforcing effect of marriage

Little is known about why smelly foods have been maintained for long periods of time despite their unpleasant smell. Previous research suggests that regional background and family environment during upbringing influence food selection. Based on those findings, we hypothesized that living in a region where traditional smelly foods are produced and consumed during one's childhood would enhance the recall of such foods in adulthood. Additionally, we proposed that this childhood experience would positively influence the effect of marriage on an individual’s recall of smelly foods. We selected *kusaya* as the chosen smelly food and examined how, as the main effect, living in the Kanto region of Japan until the age of 20 impacts an individual’s *kusaya* recall. Furthermore, we explored the moderating effect of this upbringing on *kusaya* recall and marital status by sequentially inputting variables into a logistic regression model. Both effects were confirmed. This study contributes to the understanding of how characteristic smelly foods can be preserved by clarifying the factors that enhance their recall, using *kusaya* as an example.

View more >>

Technical Article Engineering in General Information Sciences Others

An attempt to realize digital transformation in local governments by utilizing the IT skills of information science students

Division of Business Improvement and Digital Transformation of Iizuka City Hall in Fukuoka Prefecture and students from Faculty of Computer Science and Systems Engineering at Kyushu Institute of Technology collaborated to attempt to use IT to improve various aspects of Iizuka City Hall's operations. First, Division of the Business Improvement and Digital Transformation solicited themes from divisions in Iizuka City Hall, selected around 10 from these and assigned university students to the themes to be solved. The information science students had a range of skill levels. They solved the problems in a variety of ways, including using automated processing, using cloud services, and developing software for tablet devices. While some of these methods have actually been used, there are also cases where they are not. This is thought to be because the system was created without sufficient consideration of how it would be used in the real case.

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 >>

Special Issue Information Sciences

Study on Automatic Detection of Dust Mask Wearing Status in Factories

In construction and industrial work environments, workers are mandated to wear dust masks to ensure their health and safety. However, in actual field conditions, many workers neglect this requirement due to breathing discomfort and the heat and humidity within the factory. To address this issue, it is necessary to detect workers who are not wearing masks in real time and prompt them to put them on. Therefore, this study proposes a method to determine the wearing status of dust masks using deep learning based on video footage captured within the factory.

View more >>

Article Education Information Sciences Psychology and Education

An Inquiry-Based Learning Support System for Children in Sports Acquisition Processes

This study examined an inquiry-based learning support system for children in sports acquisition processes and describes the characteristics of a case study on the long-term collaborative process of children’s forward and backward cycle practices on horizontal bars. We analyzed 18 horizontal-bar practices for two elementary schoolchildren who had not succeeded in their backward cycle for approximately half a year. They were required to make practice plans collaboratively to succeed in their forward and backward cycles. To support their practices, we provided them with “HDMi (HDMi is the name of a system we developed in the past.),” which was developed to support reflecting on one’s physical movements using movies. The movies were also used for discourse analysis to determine where the children focused, and OpenPose software was used for motion analysis to examine how the children’s actions improved on a horizontal bar. Both the HDMi and the discourse analysis suggested that two children selected their focusing points for their practice and they gradually became referring to “move toes toward opposite side of the bar” in the periods of practices. However, the motion analysis revealed that the focused points and actual movement of the body did not match completely.

View more >>