Jungryul Seo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jungryul Seo has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Teemu H. Laine
Department of Digital Media, Ajou University, Suwon, Republic of Korea
5 shared publications - Kyung-Ah Sohn
Department of Artificial Intelligence, Ajou University, Suwon, Republic of Korea
2 shared publications Teemu H. Laine
University of Turku
2 shared publicationsAdil M. Khan
Innopolis University, Kazan, Russia
1 shared publicationErkki Sutinen
University of Eastern Finland
1 shared publication- Gyuhwan Oh
Department of Digital Media, Ajou University, Suwon 16499, Korea
1 shared publication
Latest Publications
- Open Access
Data Collection Framework for Context-Aware Virtual Reality Application Development in Unity: Case of Avatar Embodiment
Virtual Reality (VR) has been adopted as a leading technology for the metaverse, yet most previous VR systems provide one-size-fits-all experiences to users. Context-awareness in VR enables personalized experiences in the metaverse, such as improved embodiment and deeper integration of the real world and virtual worlds. Personalization requires context data from diverse sources. We proposed a reusable and extensible context data collection framework, ManySense VR, which unifies data collection from diverse sources for VR applications. ManySense VR was implemented in Unity based on extensible context data managers collecting data from data sources such as an eye tracker, electroencephalogram, pulse, respiration, galvanic skin response, facial tracker, and Open Weather Map. We used ManySense VR to build a context-aware embodiment VR scene where the user’s avatar is synchronized with their bodily actions. The performance evaluation of ManySense VR showed good performance in processor usage, frame rate, and memory footprint. Additionally, we conducted a qualitative formative evaluation by interviewing five developers (two males and three females; mean age: 22) after they used and extended ManySense VR. The participants expressed advantages (e.g., ease-of-use, learnability, familiarity, quickness, and extensibility), disadvantages (e.g., inconvenient/error-prone data query method and lack of diversity in callback methods), future application ideas, and improvement suggestions that indicate potential and can guide future development. In conclusion, ManySense VR is an efficient tool for researchers and developers to easily integrate context data into their Unity-based VR applications for the metaverse.
Open AccessData Collection Framework for Context-Aware Virtual Reality Application Development in Unity: Case of Avatar Embodiment
Virtual Reality (VR) has been adopted as a leading technology for the metaverse, yet most previous VR systems provide one-size-fits-all experiences to users. Context-awareness in VR enables personalized experiences in the metaverse, such as improved embodiment and deeper integration of the real world and virtual worlds. Personalization requires context data from diverse sources. We proposed a reusable and extensible context data collection framework, ManySense VR, which unifies data collection from diverse sources for VR applications. ManySense VR was implemented in Unity based on extensible context data managers collecting data from data sources such as an eye tracker, electroencephalogram, pulse, respiration, galvanic skin response, facial tracker, and Open Weather Map. We used ManySense VR to build a context-aware embodiment VR scene where the user’s avatar is synchronized with their bodily actions. The performance evaluation of ManySense VR showed good performance in processor usage, frame rate, and memory footprint. Additionally, we conducted a qualitative formative evaluation by interviewing five developers (two males and three females; mean age: 22) after they used and extended ManySense VR. The participants expressed advantages (e.g., ease-of-use, learnability, familiarity, quickness, and extensibility), disadvantages (e.g., inconvenient/error-prone data query method and lack of diversity in callback methods), future application ideas, and improvement suggestions that indicate potential and can guide future development. In conclusion, ManySense VR is an efficient tool for researchers and developers to easily integrate context data into their Unity-based VR applications for the metaverse.
- Open Access
EEG-Based Emotion Classification for Alzheimer’s Disease Patients Using Conventional Machine Learning and Recurrent Neural Network Models
As the number of patients with Alzheimer’s disease (AD) increases, the effort needed to care for these patients increases as well. At the same time, advances in information and sensor technologies have reduced caring costs, providing a potential pathway for developing healthcare services for AD patients. For instance, if a virtual reality (VR) system can provide emotion-adaptive content, the time that AD patients spend interacting with VR content is expected to be extended, allowing caregivers to focus on other tasks. As the first step towards this goal, in this study, we develop a classification model that detects AD patients’ emotions (e.g., happy, peaceful, or bored). We first collected electroencephalography (EEG) data from 30 Korean female AD patients who watched emotion-evoking videos at a medical rehabilitation center. We applied conventional machine learning algorithms, such as a multilayer perceptron (MLP) and support vector machine, along with deep learning models of recurrent neural network (RNN) architectures. The best performance was obtained from MLP, which achieved an average accuracy of 70.97%; the RNN model’s accuracy reached only 48.18%. Our study results open a new stream of research in the field of EEG-based emotion detection for patients with neurological disorders.
Open AccessEEG-Based Emotion Classification for Alzheimer’s Disease Patients Using Conventional Machine Learning and Recurrent Neural Network Models
As the number of patients with Alzheimer’s disease (AD) increases, the effort needed to care for these patients increases as well. At the same time, advances in information and sensor technologies have reduced caring costs, providing a potential pathway for developing healthcare services for AD patients. For instance, if a virtual reality (VR) system can provide emotion-adaptive content, the time that AD patients spend interacting with VR content is expected to be extended, allowing caregivers to focus on other tasks. As the first step towards this goal, in this study, we develop a classification model that detects AD patients’ emotions (e.g., happy, peaceful, or bored). We first collected electroencephalography (EEG) data from 30 Korean female AD patients who watched emotion-evoking videos at a medical rehabilitation center. We applied conventional machine learning algorithms, such as a multilayer perceptron (MLP) and support vector machine, along with deep learning models of recurrent neural network (RNN) architectures. The best performance was obtained from MLP, which achieved an average accuracy of 70.97%; the RNN model’s accuracy reached only 48.18%. Our study results open a new stream of research in the field of EEG-based emotion detection for patients with neurological disorders.
- Open Access
An Exploration of Machine Learning Methods for Robust Boredom Classification Using EEG and GSR Data
In recent years, affective computing has been actively researched to provide a higher level of emotion-awareness. Numerous studies have been conducted to detect the user’s emotions from physiological data. Among a myriad of target emotions, boredom, in particular, has been suggested to cause not only medical issues but also challenges in various facets of daily life. However, to the best of our knowledge, no previous studies have used electroencephalography (EEG) and galvanic skin response (GSR) together for boredom classification, although these data have potential features for emotion classification. To investigate the combined effect of these features on boredom classification, we collected EEG and GSR data from 28 participants using off-the-shelf sensors. During data acquisition, we used a set of stimuli comprising a video clip designed to elicit boredom and two other video clips of entertaining content. The collected samples were labeled based on the participants’ questionnaire-based testimonies on experienced boredom levels. Using the collected data, we initially trained 30 models with 19 machine learning algorithms and selected the top three candidate classifiers. After tuning the hyperparameters, we validated the final models through 1000 iterations of 10-fold cross validation to increase the robustness of the test results. Our results indicated that a Multilayer Perceptron model performed the best with a mean accuracy of 79.98% (AUC: 0.781). It also revealed the correlation between boredom and the combined features of EEG and GSR. These results can be useful for building accurate affective computing systems and understanding the physiological properties of boredom.
Open AccessAn Exploration of Machine Learning Methods for Robust Boredom Classification Using EEG and GSR Data
In recent years, affective computing has been actively researched to provide a higher level of emotion-awareness. Numerous studies have been conducted to detect the user’s emotions from physiological data. Among a myriad of target emotions, boredom, in particular, has been suggested to cause not only medical issues but also challenges in various facets of daily life. However, to the best of our knowledge, no previous studies have used electroencephalography (EEG) and galvanic skin response (GSR) together for boredom classification, although these data have potential features for emotion classification. To investigate the combined effect of these features on boredom classification, we collected EEG and GSR data from 28 participants using off-the-shelf sensors. During data acquisition, we used a set of stimuli comprising a video clip designed to elicit boredom and two other video clips of entertaining content. The collected samples were labeled based on the participants’ questionnaire-based testimonies on experienced boredom levels. Using the collected data, we initially trained 30 models with 19 machine learning algorithms and selected the top three candidate classifiers. After tuning the hyperparameters, we validated the final models through 1000 iterations of 10-fold cross validation to increase the robustness of the test results. Our results indicated that a Multilayer Perceptron model performed the best with a mean accuracy of 79.98% (AUC: 0.781). It also revealed the correlation between boredom and the combined features of EEG and GSR. These results can be useful for building accurate affective computing systems and understanding the physiological properties of boredom.
- 9 November 2018
- Published by SAGE Publications in Journal of Ambient Intelligence and Smart Environments
- Vol. 10 (6) , 481-495
Accurate position and orientation independent step counting algorithm for smartphones
Step counting (SC) algorithms can be applied to different areas such as well-being applications, games, and indoor navigation. Many existing SC algorithms for smartphones use data from inertial sensors to infer the number of steps taken, but their us
- 9 November 2018
- Published by SAGE Publications in Journal of Ambient Intelligence and Smart Environments
- Vol. 10 (6) , 481-495
Accurate position and orientation independent step counting algorithm for smartphones
Step counting (SC) algorithms can be applied to different areas such as well-being applications, games, and indoor navigation. Many existing SC algorithms for smartphones use data from inertial sensors to infer the number of steps taken, but their us
- 1 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 136-138
Designing a Game for Learning Math by Composing: A Finnish Primary School Case
Music is filled with mathematical relations. When creating music, the composer must keep in mind the rhythm, the notes, and how well they ring with each other. Our aim was to design an application that teaches these relationships and allows users to compose their own songs using numbers. Our work follows the design science research method, and we have co-designed the application together with elementary school students and teachers in Finland. This paper demonstrates the design process and provides an analysis on our design based on data collected from the participants in two separate sessions.
- 1 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 136-138
Designing a Game for Learning Math by Composing: A Finnish Primary School Case
Music is filled with mathematical relations. When creating music, the composer must keep in mind the rhythm, the notes, and how well they ring with each other. Our aim was to design an application that teaches these relationships and allows users to compose their own songs using numbers. Our work follows the design science research method, and we have co-designed the application together with elementary school students and teachers in Finland. This paper demonstrates the design process and provides an analysis on our design based on data collected from the participants in two separate sessions.
- 20 April 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Learning Technologies
- Vol. 9 (4) , 328-341
Enhancing Physical Education with Exergames and Wearable Technology
Increases in the numbers of obese and overweight children are a major issue in post-industrial societies because obesity can lead to severe health-related problems. In addition, many challenges affect the quantity and quality of physical education (PE) provided by schools. Exergames that combine exercise with gaming have been recognized as a possible method for motivating children to become physically active and to make PE more fun. Furthermore, exergames that utilize wearable sensors devices allow players' movements to be tracked for estimating the efficiency of exercise. In this study, we developed the Running Othello 2 (RO2) exergame, where players wear a smartphone and a smart wrist band to compete in a board game enhanced with physical and pedagogical missions. In physical missions, the game uses inertial sensors and a heart rate meter to detect the physical activities of players. The pedagogical part of the game is based on the South Korean PE curriculum. We evaluated RO2 with 61 South Korean third grade elementary school students, 32 of whom learned curriculum topics by playing the game. The other 29 students comprised a control group who studied the pedagogical content using handouts. The results indicated that learning with RO2 was more efficient, the players were engaged, and their heart rates increased. Based on the evaluation, we identified several issues to be addressed in future research. Finally, we discussed how RO2 supports the educational affordances of wearables and we explained how exergames using wearables can overcome some of the challenges faced by PE.
- 20 April 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Learning Technologies
- Vol. 9 (4) , 328-341
Enhancing Physical Education with Exergames and Wearable Technology
Increases in the numbers of obese and overweight children are a major issue in post-industrial societies because obesity can lead to severe health-related problems. In addition, many challenges affect the quantity and quality of physical education (PE) provided by schools. Exergames that combine exercise with gaming have been recognized as a possible method for motivating children to become physically active and to make PE more fun. Furthermore, exergames that utilize wearable sensors devices allow players' movements to be tracked for estimating the efficiency of exercise. In this study, we developed the Running Othello 2 (RO2) exergame, where players wear a smartphone and a smart wrist band to compete in a board game enhanced with physical and pedagogical missions. In physical missions, the game uses inertial sensors and a heart rate meter to detect the physical activities of players. The pedagogical part of the game is based on the South Korean PE curriculum. We evaluated RO2 with 61 South Korean third grade elementary school students, 32 of whom learned curriculum topics by playing the game. The other 29 students comprised a control group who studied the pedagogical content using handouts. The results indicated that learning with RO2 was more efficient, the players were engaged, and their heart rates increased. Based on the evaluation, we identified several issues to be addressed in future research. Finally, we discussed how RO2 supports the educational affordances of wearables and we explained how exergames using wearables can overcome some of the challenges faced by PE.
- Open Access
- 8 January 2015
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Step counting on smartphones using advanced zero-crossing and linear regression
- 8 January 2015
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessStep counting on smartphones using advanced zero-crossing and linear regression