Kyoung Shin Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kyoung Shin Park has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Yongjoo Cho
Department of Computer Science, Sangmyung University, 20 Hongjimoon-2gil, Jongno-gu, Seoul 03016, Republic of Korea
9 shared publications Yongjoo Cho
Department of Computer Science, College of Future Convergence Engineering, Sangmyung University, Seoul, South Korea
4 shared publicationsMinyoung Kim
SangMyung University
3 shared publicationsBin-Na-Ra Lee
1 shared publication- Chu Xin
Department of Artificial Intelligence Convergence, Dankook University, Yongin-si, Gyeonggi-do, Republic of Korea
1 shared publication - Chu Xin
Department of Artificial Intelligence Convergence, Graduate School, Dankook University, 152 Jukjeon-ro, Suji-gu, Yongin-si 16890, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 17 September 2026
- Published by MDPI AG in Electronics
- Vol. 15 (18) , 4238
Comparing Interaction Structures for User Experience in XR Cultural Heritage Learning
Extended Reality (XR) is increasingly used to support learning experiences in cultural heritage education, but how learners interact with XR content—rather than the sophistication of the underlying technology—can meaningfully shape the quality of the learning experience. This study investigates the effects of interaction structure on cultural heritage learning in XR. A HoloLens 2 XR application for Gyeongbokgung Palace was developed using three interaction conditions: Information-Presentation (Text+Image), Inquiry-Based Exploration (QA), and Assessment-Participation (Quiz). All content was pre-generated using a Large Language Model (LLM) to hold information constant across conditions, ensuring that any observed differences in user experience could be attributed to interaction structure rather than to content. Participants experienced all three interaction types in a partially counterbalanced order, and their interest, immersion, ease of use, perceived learning comprehension, intention to reuse, and perceived difficulty were assessed. The results revealed distinct strengths for each interaction structure. Quiz generated higher preference for interest and immersion, but was also rated the most cognitively demanding condition. Text+Image achieved the highest ease-of-use ratings. QA received the numerically highest preference for perceived learning comprehension, but the difference across conditions was not statistically significant, indicating that this study did not detect a reliable preference difference on this dimension. Within this single-site, single-device study, these findings indicate that interaction structure was associated with systematically different user experience profiles, even when the underlying content was held constant. The study provides design implications for structuring interaction in cultural heritage XR learning environments.
- 17 September 2026
- Published by MDPI AG in Electronics
- Vol. 15 (18) , 4238
Open AccessComparing Interaction Structures for User Experience in XR Cultural Heritage Learning
Extended Reality (XR) is increasingly used to support learning experiences in cultural heritage education, but how learners interact with XR content—rather than the sophistication of the underlying technology—can meaningfully shape the quality of the learning experience. This study investigates the effects of interaction structure on cultural heritage learning in XR. A HoloLens 2 XR application for Gyeongbokgung Palace was developed using three interaction conditions: Information-Presentation (Text+Image), Inquiry-Based Exploration (QA), and Assessment-Participation (Quiz). All content was pre-generated using a Large Language Model (LLM) to hold information constant across conditions, ensuring that any observed differences in user experience could be attributed to interaction structure rather than to content. Participants experienced all three interaction types in a partially counterbalanced order, and their interest, immersion, ease of use, perceived learning comprehension, intention to reuse, and perceived difficulty were assessed. The results revealed distinct strengths for each interaction structure. Quiz generated higher preference for interest and immersion, but was also rated the most cognitively demanding condition. Text+Image achieved the highest ease-of-use ratings. QA received the numerically highest preference for perceived learning comprehension, but the difference across conditions was not statistically significant, indicating that this study did not detect a reliable preference difference on this dimension. Within this single-site, single-device study, these findings indicate that interaction structure was associated with systematically different user experience profiles, even when the underlying content was held constant. The study provides design implications for structuring interaction in cultural heritage XR learning environments.
- Open Access
- 12 January 2026
- Published by MDPI AG in Electronics
- Vol. 15 (2) , 336
A Mobile Augmented Reality Integrating KCHDM-Based Ontologies with LLMs for Adaptive Q&A and Knowledge Testing in Urban Heritage
A cultural heritage augmented reality system overlays virtual information onto real-world heritage sites, enabling intuitive exploration and interpretation with spatial and temporal contexts. This study presents the design and implementation of a cognitive Mobile Augmented Reality (MAR) system that integrates KCHDM-based ontologies with large language models (LLMs) to facilitate intelligent exploration of urban heritage. While conventional AR guides often rely on static data, our system introduces a Semantic Retrieval-Augmented Generation (RAG) pipeline anchored in a structured knowledge base modeled after the Korean Cultural Heritage Data Model (KCHDM). This architecture enables the LLM to perform dynamic contextual reasoning, transforming heritage data into adaptive question-answering (Q&A) and interactive knowledge-testing quizzes that are precisely grounded in both historical and spatial contexts. The system supports on-site AR exploration and map-based remote exploration to ensure robust usability and precise spatial alignment of virtual content. To deliver a rich, multisensory experience, the system provides multimodal outputs, integrating text, images, models, and audio narration. Furthermore, the integration of a knowledge sharing repository allows users to review and learn from others’ inquires. This ontology-driven LLM-integrated MAR design enhances semantic accuracy and contextual relevance, demonstrating the potential of MAR for socially enriched urban heritage experiences.
- 12 January 2026
- Published by MDPI AG in Electronics
- Vol. 15 (2) , 336
Open AccessA Mobile Augmented Reality Integrating KCHDM-Based Ontologies with LLMs for Adaptive Q&A and Knowledge Testing in Urban Heritage
A cultural heritage augmented reality system overlays virtual information onto real-world heritage sites, enabling intuitive exploration and interpretation with spatial and temporal contexts. This study presents the design and implementation of a cognitive Mobile Augmented Reality (MAR) system that integrates KCHDM-based ontologies with large language models (LLMs) to facilitate intelligent exploration of urban heritage. While conventional AR guides often rely on static data, our system introduces a Semantic Retrieval-Augmented Generation (RAG) pipeline anchored in a structured knowledge base modeled after the Korean Cultural Heritage Data Model (KCHDM). This architecture enables the LLM to perform dynamic contextual reasoning, transforming heritage data into adaptive question-answering (Q&A) and interactive knowledge-testing quizzes that are precisely grounded in both historical and spatial contexts. The system supports on-site AR exploration and map-based remote exploration to ensure robust usability and precise spatial alignment of virtual content. To deliver a rich, multisensory experience, the system provides multimodal outputs, integrating text, images, models, and audio narration. Furthermore, the integration of a knowledge sharing repository allows users to review and learn from others’ inquires. This ontology-driven LLM-integrated MAR design enhances semantic accuracy and contextual relevance, demonstrating the potential of MAR for socially enriched urban heritage experiences.
- Open Access
- 13 February 2024
- Published by MDPI AG in Electronics
- Vol. 13 (4) , 747
Enhancing Human Action Recognition with 3D Skeleton Data: A Comprehensive Study of Deep Learning and Data Augmentation
Human Action Recognition (HAR) is an important field that identifies human behavior through sensor data. Three-dimensional human skeleton data extracted from the Kinect depth sensor have emerged as a powerful alternative to mitigate the effects of lighting and occlusion of traditional 2D RGB or grayscale image-based HAR. Data augmentation is a key technique to enhance model generalization and robustness in deep learning while suppressing overfitting to training data. In this paper, we conduct a comprehensive study of various data augmentation techniques specific to skeletal data, which aim to improve the accuracy of deep learning models. These augmentation methods include spatial augmentation, which generates augmented samples from the original 3D skeleton sequence, and temporal augmentation, which is designed to capture subtle temporal changes in motion. The evaluation covers two publicly available datasets and a proprietary dataset and employs three neural network models. The results highlight the impact of temporal augmentation on model performance on the skeleton datasets, while exhibiting the nuanced impact of spatial augmentation. The findings underscore the importance of tailoring augmentation strategies to specific dataset characteristics and actions, providing novel perspectives for model selection in skeleton-based human action recognition tasks.
- 13 February 2024
- Published by MDPI AG in Electronics
- Vol. 13 (4) , 747
Open AccessEnhancing Human Action Recognition with 3D Skeleton Data: A Comprehensive Study of Deep Learning and Data Augmentation
Human Action Recognition (HAR) is an important field that identifies human behavior through sensor data. Three-dimensional human skeleton data extracted from the Kinect depth sensor have emerged as a powerful alternative to mitigate the effects of lighting and occlusion of traditional 2D RGB or grayscale image-based HAR. Data augmentation is a key technique to enhance model generalization and robustness in deep learning while suppressing overfitting to training data. In this paper, we conduct a comprehensive study of various data augmentation techniques specific to skeletal data, which aim to improve the accuracy of deep learning models. These augmentation methods include spatial augmentation, which generates augmented samples from the original 3D skeleton sequence, and temporal augmentation, which is designed to capture subtle temporal changes in motion. The evaluation covers two publicly available datasets and a proprietary dataset and employs three neural network models. The results highlight the impact of temporal augmentation on model performance on the skeleton datasets, while exhibiting the nuanced impact of spatial augmentation. The findings underscore the importance of tailoring augmentation strategies to specific dataset characteristics and actions, providing novel perspectives for model selection in skeleton-based human action recognition tasks.
- Open Access
- 3 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
A Comparison of Machine Learning Models with Data Augmentation Techniques for Skeleton-based Human Action Recognition
3D skeleton motion recognition plays a crucial role in the field of human action recognition (HAR) due to its efficiency and reliability. This paper introduces data augmentation techniques applied to skeleton data with the aim of improving the accuracy of machine learning models and examining the effectiveness of different augmentation methods for different activities. Spatial transformations are applied to generate augmented samples from the original 3D skeleton sequences, while temporal augmentation techniques are employed to capture the temporal differences in motion. We evaluated the effects of spatial and temporal data augmentation at different levels on the MSR Daily Activity 3D dataset using SVM, CNN, LSTM, and CNNLSTM models. The results show that temporal augmentation significantly improves model performance, while spatial augmentation has only a limited effect on model performance. Simultaneously applying both spatial and temporal augmentation further improved model performance, highlighting the importance of temporal information in action sequence data.
- 3 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessA Comparison of Machine Learning Models with Data Augmentation Techniques for Skeleton-based Human Action Recognition
3D skeleton motion recognition plays a crucial role in the field of human action recognition (HAR) due to its efficiency and reliability. This paper introduces data augmentation techniques applied to skeleton data with the aim of improving the accuracy of machine learning models and examining the effectiveness of different augmentation methods for different activities. Spatial transformations are applied to generate augmented samples from the original 3D skeleton sequences, while temporal augmentation techniques are employed to capture the temporal differences in motion. We evaluated the effects of spatial and temporal data augmentation at different levels on the MSR Daily Activity 3D dataset using SVM, CNN, LSTM, and CNNLSTM models. The results show that temporal augmentation significantly improves model performance, while spatial augmentation has only a limited effect on model performance. Simultaneously applying both spatial and temporal augmentation further improved model performance, highlighting the importance of temporal information in action sequence data.
- Top Cited PapersOpen Access
- 7 January 2023
- Published by MDPI AG in Electronics
- Vol. 12 (2) , 315
Designing Immersive Virtual Reality Simulation for Environmental Science Education
Recently, severe environmental changes, such as global warming, climate change and environmental pollution, have become expected, and thus environmental education is becoming essential. The purpose of environmental education is to instill awareness in students to recognize and solve environmental problems. Virtual reality provides students with a spatial and temporal experience similar to reality, and it can increase their understanding of knowledge through immersion and interaction compared to traditional learning. In previous studies, virtual reality for education has mainly focused on experience, but it is difficult to find examples for environmental education. Hence, this research proposed an immersive virtual reality simulation for environmental education based on the virtual ecosystem model. It also presented two applications developed based on this simulation. This research aims at encouraging students’ active participation and motivation to solve the environmental problems while experiencing the results of interaction related to environmental factors in a virtual environment.
- 7 January 2023
- Published by MDPI AG in Electronics
- Vol. 12 (2) , 315
Top Cited PapersOpen AccessDesigning Immersive Virtual Reality Simulation for Environmental Science Education
Recently, severe environmental changes, such as global warming, climate change and environmental pollution, have become expected, and thus environmental education is becoming essential. The purpose of environmental education is to instill awareness in students to recognize and solve environmental problems. Virtual reality provides students with a spatial and temporal experience similar to reality, and it can increase their understanding of knowledge through immersion and interaction compared to traditional learning. In previous studies, virtual reality for education has mainly focused on experience, but it is difficult to find examples for environmental education. Hence, this research proposed an immersive virtual reality simulation for environmental education based on the virtual ecosystem model. It also presented two applications developed based on this simulation. This research aims at encouraging students’ active participation and motivation to solve the environmental problems while experiencing the results of interaction related to environmental factors in a virtual environment.
- Open Access
- 27 September 2022
- Published by MDPI AG in Electronics
- Vol. 11 (19) , 3086
Effects of Exercise Type and Gameplay Mode on Physical Activity in Exergame
Exercise games (exergames) that combine both exercise and video gaming train people in a fun and competitive manner to lead a healthy lifestyle. Exergames promote more physical exertion and help users exercise more easily and independently in any place. Many studies have been conducted to evaluate the positive effects of exergames. However, in most studies, heart rate was mainly used to measure the effect of exercise. In this study, we evaluate the effects of exercise according to the exercise type (rest, walking, tennis, and running) and gameplay mode (single, competition, and cooperation) of exergaming via quantitative measurements using electrocardiogram (ECG) and Kinect. The multiple comparison results reveal that physical activity measured with Kinect was statistically significant even in exergames that did not show statistically significant differences according to ECG. Running was statistically significant compared to other exercise types, and there was a significant difference in competition compared to other gameplay modes.
- 27 September 2022
- Published by MDPI AG in Electronics
- Vol. 11 (19) , 3086
Open AccessEffects of Exercise Type and Gameplay Mode on Physical Activity in Exergame
Exercise games (exergames) that combine both exercise and video gaming train people in a fun and competitive manner to lead a healthy lifestyle. Exergames promote more physical exertion and help users exercise more easily and independently in any place. Many studies have been conducted to evaluate the positive effects of exergames. However, in most studies, heart rate was mainly used to measure the effect of exercise. In this study, we evaluate the effects of exercise according to the exercise type (rest, walking, tennis, and running) and gameplay mode (single, competition, and cooperation) of exergaming via quantitative measurements using electrocardiogram (ECG) and Kinect. The multiple comparison results reveal that physical activity measured with Kinect was statistically significant even in exergames that did not show statistically significant differences according to ECG. Running was statistically significant compared to other exercise types, and there was a significant difference in competition compared to other gameplay modes.
- Open Access
- 18 August 2020
- Published by MDPI AG in Multimodal Technologies and Interaction
- Vol. 4 (3) , 56
The Chongchong Step Master Game for Gait and Balance Training
Exercise can help to improve health, strengthen vitality and prevent brain disease, especially for the elderly. Exercise games, or exergames, which combine both exercise and video gaming, train people in a fun and competitive manner to lead a healthy lifestyle. Exergames promote more physical effort and have the potential to contribute to physical education. This research presents a full-body virtual reality exercise game called the Chongchong Step Master, which is designed to improve gait and balance function and prevent dementia in the elderly. This system used Kinect sensors to accurately recognize the user’s body movements and the stepping board mat to recognize and guide the user’s walking motion. It aims to help the elderly exercise more easily and independently with the virtual physical trainer.
- 18 August 2020
- Published by MDPI AG in Multimodal Technologies and Interaction
- Vol. 4 (3) , 56
Open AccessThe Chongchong Step Master Game for Gait and Balance Training
Exercise can help to improve health, strengthen vitality and prevent brain disease, especially for the elderly. Exercise games, or exergames, which combine both exercise and video gaming, train people in a fun and competitive manner to lead a healthy lifestyle. Exergames promote more physical effort and have the potential to contribute to physical education. This research presents a full-body virtual reality exercise game called the Chongchong Step Master, which is designed to improve gait and balance function and prevent dementia in the elderly. This system used Kinect sensors to accurately recognize the user’s body movements and the stepping board mat to recognize and guide the user’s walking motion. It aims to help the elderly exercise more easily and independently with the virtual physical trainer.
- Open Access
- 22 May 2018
- Published by Springer Nature in Human-centric Computing and Information Sciences
- Vol. 8 (1) , 15
Comparative analysis of affective and physiological responses to emotional movies
In this research, we investigated on user’s affective and physiological responses to the emotional movies. The emotional movies provide continuous feedback such as changes in saturation, brightness and contrast of the movie in response to users’ emotional states. In the user study, the subjects watched the emotional movies, edited by fearful and joyful scenes, and presented in 2D and 3D formats. The subject’s self-reported emotion responses and their physiological signals were analyzed. The results highlight the importance of scenes (such as, the color, tone, and brightness of the scene) than 2D or 3D format in understanding the impact of users’ emotional responses. More physiological emotional changes, positive user responses and higher correlation rate between physiological and subjective responses were evident for joyful scene than fearful scene when presented in 3D format.
- 22 May 2018
- Published by Springer Nature in Human-centric Computing and Information Sciences
- Vol. 8 (1) , 15
Open AccessComparative analysis of affective and physiological responses to emotional movies
In this research, we investigated on user’s affective and physiological responses to the emotional movies. The emotional movies provide continuous feedback such as changes in saturation, brightness and contrast of the movie in response to users’ emotional states. In the user study, the subjects watched the emotional movies, edited by fearful and joyful scenes, and presented in 2D and 3D formats. The subject’s self-reported emotion responses and their physiological signals were analyzed. The results highlight the importance of scenes (such as, the color, tone, and brightness of the scene) than 2D or 3D format in understanding the impact of users’ emotional responses. More physiological emotional changes, positive user responses and higher correlation rate between physiological and subjective responses were evident for joyful scene than fearful scene when presented in 3D format.
- 31 January 2015
- Published by Korea Institute of Information and Communication Engineering (Nurimedia) in The Journal of the Korean Institute of Information and Communication Engineering
- Vol. 19 (1) , 127-135
Study on the Methods of Enhancing the Quality of DIBR-based Multiview Intermediate Images using Depth Expansion and Mesh Construction
- 31 January 2015
- Published by Korea Institute of Information and Communication Engineering (Nurimedia) in The Journal of the Korean Institute of Information and Communication Engineering
- Vol. 19 (1) , 127-135
Study on the Methods of Enhancing the Quality of DIBR-based Multiview Intermediate Images using Depth Expansion and Mesh Construction
- 1 January 2015
- Published by SAGE Publications in Journal of Ambient Intelligence and Smart Environments
- Vol. 7 (1) , 99-113
Mediating individual affective experience through the emotional photo frame
A photograph is considered a medium with emotional legibility and a means of expressing and exchanging emotional experience. This research presents the interactive emotional photo frame system focusing on mediating individual affective experience among close relationships. This emotional photo frame system dynamically controls the photograph based on a user's affective states and user-specified emotion reaction rules. It is designed for helping users recognize and experience the same emotions with others. The system consists of an emotion recognition system, an emotion share server and an emotional digital picture frame. The emotion recognition system analyzes photoplethysmography, skin temperature and galvanic skin response signals to recognize user's emotional states and transmits the results to the server in real-time. The server stores user emotional data with individual emotion reaction rules that define how the picture frame should affect the photo in response to individual affective states. The emotional picture frame renders personalized visual and aural elements on the photograph according to the feedback of emotions. This paper presents an empirical exploration of the effectiveness of this system. The results revealed that most participants were influenced by their partner's emotion presented in this system. There was a strong relation of emotion sharing between the partners.
- 1 January 2015
- Published by SAGE Publications in Journal of Ambient Intelligence and Smart Environments
- Vol. 7 (1) , 99-113
Mediating individual affective experience through the emotional photo frame
A photograph is considered a medium with emotional legibility and a means of expressing and exchanging emotional experience. This research presents the interactive emotional photo frame system focusing on mediating individual affective experience among close relationships. This emotional photo frame system dynamically controls the photograph based on a user's affective states and user-specified emotion reaction rules. It is designed for helping users recognize and experience the same emotions with others. The system consists of an emotion recognition system, an emotion share server and an emotional digital picture frame. The emotion recognition system analyzes photoplethysmography, skin temperature and galvanic skin response signals to recognize user's emotional states and transmits the results to the server in real-time. The server stores user emotional data with individual emotion reaction rules that define how the picture frame should affect the photo in response to individual affective states. The emotional picture frame renders personalized visual and aural elements on the photograph according to the feedback of emotions. This paper presents an empirical exploration of the effectiveness of this system. The results revealed that most participants were influenced by their partner's emotion presented in this system. There was a strong relation of emotion sharing between the partners.