Keisuke Utsu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Keisuke Utsu has a total of 60 co-authors. Here are the top co-authors by number of shared publications:
- Osamu Uchida
Tokai University
22 shared publications Hiroshi Ishii
Dept. of Communication and Network Engineering, Sch. of Information and Telecommunication Engineering, Tokai University, Minato, Tokyo, Japan
18 shared publications- Hiroshi Ishii
Tokai University, Minato City, Japan
6 shared publications Ayami Manaka
Dept. of Communication and Network Engineering, Sch. of Info. and Telecommunication Eng., Tokai Univ. Minato, Tokyo, Japan
5 shared publicationsKei Kobayashi
Tokai University, Minato City, Japan
5 shared publicationsSachi Tajima
Center for Liberal Arts, Tokai Univ., Hiratsuka, Japan
4 shared publications
Latest Publications
- Open Access
- 10 August 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (16) , 8140
Enhancing Urban Disaster Resilience for Foreign Tourists in Japan: A Smartphone-Based, SLAM-Enabled Augmented Reality System for Inclusive Flood Risk Communication
Disaster-prone urban areas must support transient and vulnerable populations, including foreign tourists who may face language barriers and difficulty interpreting conventional 2D hazard information. This study developed a smartphone-based augmented reality (AR) system designed to support flood-risk interpretation by foreign tourists in Japan. The system integrates four live external APIs providing location, weather forecast, hazard, and designated emergency evacuation site information, and retrieves these data on demand. Its core function converts hazard map-derived flood-inundation category data into 1:1-scale AR flood visualizations using simultaneous localization and mapping (SLAM) and inertial measurement unit (IMU) data. The system also provides a multilingual interface in English, Japanese, and Thai, weather forecast display, and nearby designated emergency evacuation site identification within a 1500 m radius. This study is positioned as a technical feasibility study. The evaluation comprised a verification of the AR height-placement mechanism against a physical reference at the five display heights used by the system, including the smallest category at 0.3 m (21.5 mm mean absolute alignment error, 1.0–2.3% of the target height); a quantitative SLAM drift evaluation under three movement patterns (at most 1.6 cm mean horizontal and 0.7 cm mean vertical drift after 180 s, within a priori thresholds); and an API response time evaluation under 5G and Wi-Fi (50 measurements per API per network; summed per-API means of approximately 3.99 s and 3.89 s at the endpoint level). The results support technical feasibility under the tested conditions, while effects on comprehension, preparedness, and evacuation decision-making remain for future user studies.
- 10 August 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (16) , 8140
Open AccessEnhancing Urban Disaster Resilience for Foreign Tourists in Japan: A Smartphone-Based, SLAM-Enabled Augmented Reality System for Inclusive Flood Risk Communication
Disaster-prone urban areas must support transient and vulnerable populations, including foreign tourists who may face language barriers and difficulty interpreting conventional 2D hazard information. This study developed a smartphone-based augmented reality (AR) system designed to support flood-risk interpretation by foreign tourists in Japan. The system integrates four live external APIs providing location, weather forecast, hazard, and designated emergency evacuation site information, and retrieves these data on demand. Its core function converts hazard map-derived flood-inundation category data into 1:1-scale AR flood visualizations using simultaneous localization and mapping (SLAM) and inertial measurement unit (IMU) data. The system also provides a multilingual interface in English, Japanese, and Thai, weather forecast display, and nearby designated emergency evacuation site identification within a 1500 m radius. This study is positioned as a technical feasibility study. The evaluation comprised a verification of the AR height-placement mechanism against a physical reference at the five display heights used by the system, including the smallest category at 0.3 m (21.5 mm mean absolute alignment error, 1.0–2.3% of the target height); a quantitative SLAM drift evaluation under three movement patterns (at most 1.6 cm mean horizontal and 0.7 cm mean vertical drift after 180 s, within a priori thresholds); and an API response time evaluation under 5G and Wi-Fi (50 measurements per API per network; summed per-API means of approximately 3.99 s and 3.89 s at the endpoint level). The results support technical feasibility under the tested conditions, while effects on comprehension, preparedness, and evacuation decision-making remain for future user studies.
- Open Access
- 4 July 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (13) , 6821
Estimated Population Exposure Within Designated Hazard Zones Across Walkability-Based Urban Spatial Characteristics in Japan: A Nationwide Analysis of Postcode-Level Population Core Cells
While Japan’s population is declining overall, some areas remain densely populated within designated hazard zones. Understanding how these spatial patterns vary across urban contexts is important for sustainable and resilient urban development. This study presents a nationwide analysis of hazard-specific estimated population exposure at postcode-level population core cells across walkability-based urban spatial characteristics in Japan. We integrated designated hazard-zone layers from the Geospatial Information Authority of Japan (GSI) with 250 m census population grids and linked the resulting dataset to the Japan Postcode-level Walkability Index using these core cells as a common spatial unit. This analysis used postcode-level population core cells and was not designed to estimate total hazard-zone-based exposure within entire postcode areas. The four hazard-zone layers were analyzed separately to characterize hazard-specific patterns, not to assess simultaneous or compound hazard events, cumulative exposure, or compound risk. Population core cells in higher-JPWI strata generally overlapped more frequently with flood, storm surge, and tsunami inundation zones, whereas lower-JPWI population core cells overlapped more frequently with designated landslide warning zones. Where hazard-zone overlap was identified, estimated exposed populations tended to be larger in higher-JPWI core cells. The pattern should be interpreted descriptively because the estimate is partly influenced by cell population and JPWI includes a population-density component. Overall, the results show hazard-specific differences in how walkability-based urban spatial characteristics coincide with hazard-zone-based estimated population exposure, providing a transparent and nationally consistent baseline for characterizing designated hazard-zone overlap and estimated exposed population at population core cells in Japan.
- 4 July 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (13) , 6821
Open AccessEstimated Population Exposure Within Designated Hazard Zones Across Walkability-Based Urban Spatial Characteristics in Japan: A Nationwide Analysis of Postcode-Level Population Core Cells
While Japan’s population is declining overall, some areas remain densely populated within designated hazard zones. Understanding how these spatial patterns vary across urban contexts is important for sustainable and resilient urban development. This study presents a nationwide analysis of hazard-specific estimated population exposure at postcode-level population core cells across walkability-based urban spatial characteristics in Japan. We integrated designated hazard-zone layers from the Geospatial Information Authority of Japan (GSI) with 250 m census population grids and linked the resulting dataset to the Japan Postcode-level Walkability Index using these core cells as a common spatial unit. This analysis used postcode-level population core cells and was not designed to estimate total hazard-zone-based exposure within entire postcode areas. The four hazard-zone layers were analyzed separately to characterize hazard-specific patterns, not to assess simultaneous or compound hazard events, cumulative exposure, or compound risk. Population core cells in higher-JPWI strata generally overlapped more frequently with flood, storm surge, and tsunami inundation zones, whereas lower-JPWI population core cells overlapped more frequently with designated landslide warning zones. Where hazard-zone overlap was identified, estimated exposed populations tended to be larger in higher-JPWI core cells. The pattern should be interpreted descriptively because the estimate is partly influenced by cell population and JPWI includes a population-density component. Overall, the results show hazard-specific differences in how walkability-based urban spatial characteristics coincide with hazard-zone-based estimated population exposure, providing a transparent and nationally consistent baseline for characterizing designated hazard-zone overlap and estimated exposed population at population core cells in Japan.
- Open Access
- 8 January 2026
- Published by MDPI AG in Information
- Vol. 17 (1) , 59
Analysis of Japanese Twitter Posts Related to COVID-19 Vaccination Focusing on Frequently Occurring Words and Emotional Expressions
The Coronavirus Disease 2019 (COVID-19) pandemic and its prolonged effects have been widely discussed on social media, and these discussions have been analyzed in various studies. A long-term analysis of Twitter (now “X”) posts regarding COVID-19 vaccination is essential for informing policy and improving public health communication strategies. In addition, to prevent the spread of infectious diseases, it is crucial to rapidly promote vaccination while mitigating the impact of negative sentiment toward vaccination on social media platforms. Therefore, identifying the key factors behind negative discussions is important for guiding policy decisions and shaping responses. In this study, we collected Japanese tweets (posts) containing the words “Corona” and “vaccine” that were posted from February 2021 to December 2022. The results indicate that negative sentiment was primarily driven by concerns about adverse reactions and general fear and anxiety, which were particularly prominent before vaccination for the general public began, as well as mentions of pain during and after vaccination. While concerns about adverse reactions persisted throughout the analysis period, their prominence decreased over time as positive reactions became more frequent. Our findings provide insights into the characteristics and key factors behind negative discussions on COVID-19 vaccination in the Japanese context and may help improve public health communication strategies.
- 8 January 2026
- Published by MDPI AG in Information
- Vol. 17 (1) , 59
Open AccessAnalysis of Japanese Twitter Posts Related to COVID-19 Vaccination Focusing on Frequently Occurring Words and Emotional Expressions
The Coronavirus Disease 2019 (COVID-19) pandemic and its prolonged effects have been widely discussed on social media, and these discussions have been analyzed in various studies. A long-term analysis of Twitter (now “X”) posts regarding COVID-19 vaccination is essential for informing policy and improving public health communication strategies. In addition, to prevent the spread of infectious diseases, it is crucial to rapidly promote vaccination while mitigating the impact of negative sentiment toward vaccination on social media platforms. Therefore, identifying the key factors behind negative discussions is important for guiding policy decisions and shaping responses. In this study, we collected Japanese tweets (posts) containing the words “Corona” and “vaccine” that were posted from February 2021 to December 2022. The results indicate that negative sentiment was primarily driven by concerns about adverse reactions and general fear and anxiety, which were particularly prominent before vaccination for the general public began, as well as mentions of pain during and after vaccination. While concerns about adverse reactions persisted throughout the analysis period, their prominence decreased over time as positive reactions became more frequent. Our findings provide insights into the characteristics and key factors behind negative discussions on COVID-19 vaccination in the Japanese context and may help improve public health communication strategies.
- 30 June 2024
- Published by Springer Nature
- p. 133-147
Location Extraction in Disaster Tweets with a Model Trained on Past Data: Diverse Analysis
- 30 June 2024
- Published by Springer Nature
- p. 133-147
Location Extraction in Disaster Tweets with a Model Trained on Past Data: Diverse Analysis
- 14 April 2022
- Published by Springer Nature
- p. 107-120
Analysis of Quote Retweets for COVID-19 State of Emergency Related Tweets Posted from Prefectural Governors’ Accounts in Japan
- 14 April 2022
- Published by Springer Nature
- p. 107-120
Analysis of Quote Retweets for COVID-19 State of Emergency Related Tweets Posted from Prefectural Governors’ Accounts in Japan
- 1 November 2020
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E103.A (11) , 1319-1323
Analysis of Rescue Request and Damage Report Tweets Posted during 2019 Typhoon Hagibis
The 2019 Typhoon Hagibis (No. 19) caused widespread destruction in eastern Japan. During the disaster, many tweets including rescue request hashtags such as #救助(meaning #Rescue) and #救助要請(meaning #Rescue_request) were posted on Twitter. An official disaster information account of the Nagano Prefectural Government asked the public to provide information in the form of damage reports and rescue requests using the hashtag #台風19号長野県被害(#Typhoon_No.19_Nagano_Prefecture_damage). As a result, many tweets were posted using this hashtag. Moreover, the account contacted the posters of tweets requesting rescue and delivered the information to the Fire Department. In this study, we analyze the circumstances of the above tweets.
- 1 November 2020
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E103.A (11) , 1319-1323
Analysis of Rescue Request and Damage Report Tweets Posted during 2019 Typhoon Hagibis
The 2019 Typhoon Hagibis (No. 19) caused widespread destruction in eastern Japan. During the disaster, many tweets including rescue request hashtags such as #救助(meaning #Rescue) and #救助要請(meaning #Rescue_request) were posted on Twitter. An official disaster information account of the Nagano Prefectural Government asked the public to provide information in the form of damage reports and rescue requests using the hashtag #台風19号長野県被害(#Typhoon_No.19_Nagano_Prefecture_damage). As a result, many tweets were posted using this hashtag. Moreover, the account contacted the posters of tweets requesting rescue and delivered the information to the Fire Department. In this study, we analyze the circumstances of the above tweets.
- Open Access
- 16 January 2020
- Published by MDPI AG in Future Internet
- Vol. 12 (1) , 14
Twitter-Based Safety Confirmation System for Disaster Situations
In the aftermath of disastrous events in Japan, safety information and rescue requests, as well as emergency alerts and damage situations, have been shared on Twitter. However, even victims who are familiar with smartphones or similar devices and social media cannot easily share detailed information, such as the coordinates or address of their current location, which are essential components of safety information and rescue requests. Moreover, local governments and rescue experts have difficulty in gathering such tweets from Twitter. In this paper, we propose a novel system to enable the victims to share their safety information, make rescue requests, and enable quick information gathering for decision making by local government staff or rescue experts. The proposed system is a Twitter-based safety confirmation system named T-@npi. Using the proposed application, the users can easily submit their safety information and send rescue requests on Twitter. The users who want to confirm the safety information can check it quickly on Twitter or via this system. Furthermore, the registered safety information is displayed on an online map to support rescue and assistance activities by local governments and rescue experts.
- 16 January 2020
- Published by MDPI AG in Future Internet
- Vol. 12 (1) , 14
Open AccessTwitter-Based Safety Confirmation System for Disaster Situations
In the aftermath of disastrous events in Japan, safety information and rescue requests, as well as emergency alerts and damage situations, have been shared on Twitter. However, even victims who are familiar with smartphones or similar devices and social media cannot easily share detailed information, such as the coordinates or address of their current location, which are essential components of safety information and rescue requests. Moreover, local governments and rescue experts have difficulty in gathering such tweets from Twitter. In this paper, we propose a novel system to enable the victims to share their safety information, make rescue requests, and enable quick information gathering for decision making by local government staff or rescue experts. The proposed system is a Twitter-based safety confirmation system named T-@npi. Using the proposed application, the users can easily submit their safety information and send rescue requests on Twitter. The users who want to confirm the safety information can check it quickly on Twitter or via this system. Furthermore, the registered safety information is displayed on an online map to support rescue and assistance activities by local governments and rescue experts.
- Open Access
- 16 August 2019
- Published by Association for Computing Machinery (ACM)
- p. 29-36
Analysis of Rescue Request Tweets in the 2018 Japan Floods
- 16 August 2019
- Published by Association for Computing Machinery (ACM)
- p. 29-36
Open AccessAnalysis of Rescue Request Tweets in the 2018 Japan Floods
- Open Access
- 7 July 2019
- Published by MDPI AG in Future Internet
- Vol. 11 (7) , 150
Town-Watching Workshop Using Disaster Information Tweeting and Mapping System
Self- and mutual-help by citizens are important as well as social-help from the local governments, for disaster prevention and mitigation. Then, town watching and disaster prevention map-making workshops are held to review the town and promote self- and mutual-help by citizens. On the other hand, the use of social media for information sharing during and after disasters has been gaining attention. To facilitate information sharing in disasters, we developed a web system, Disaster Information Tweeting and Mapping System (DITS/DIMS). From the above background, we organized a town-watching workshop using DITS/DIMS in October 2018 in Minami Ward, Sapporo City, Hokkaido, Japan; affected area of the Hokkaido Eastern Iburi Earthquake in September 2018. In this paper, we explain the workshop procedure, outcome, questionnaire survey results, and post-meeting. The questionnaire survey result shows that the workshop educated the participants about posting useful information on social media during a disaster. In addition, at the post-meeting, the participants recognized that they had reviewed the town only from the perspective of “daily life” convenience before the earthquake, and they had not evaluated the “emergency viewpoint.” Therefore, the workshop was a meaningful opportunity for the participants to review the town in terms of disaster prevention and mitigation.
- 7 July 2019
- Published by MDPI AG in Future Internet
- Vol. 11 (7) , 150
Open AccessTown-Watching Workshop Using Disaster Information Tweeting and Mapping System
Self- and mutual-help by citizens are important as well as social-help from the local governments, for disaster prevention and mitigation. Then, town watching and disaster prevention map-making workshops are held to review the town and promote self- and mutual-help by citizens. On the other hand, the use of social media for information sharing during and after disasters has been gaining attention. To facilitate information sharing in disasters, we developed a web system, Disaster Information Tweeting and Mapping System (DITS/DIMS). From the above background, we organized a town-watching workshop using DITS/DIMS in October 2018 in Minami Ward, Sapporo City, Hokkaido, Japan; affected area of the Hokkaido Eastern Iburi Earthquake in September 2018. In this paper, we explain the workshop procedure, outcome, questionnaire survey results, and post-meeting. The questionnaire survey result shows that the workshop educated the participants about posting useful information on social media during a disaster. In addition, at the post-meeting, the participants recognized that they had reviewed the town only from the perspective of “daily life” convenience before the earthquake, and they had not evaluated the “emergency viewpoint.” Therefore, the workshop was a meaningful opportunity for the participants to review the town in terms of disaster prevention and mitigation.