Junyong Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Junyong Park has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Sungho Jo
School of Computing, KAIST, Daejeon, Republic of Korea
3 shared publications - Sejoon Huh
School of Computing, Korea Advanced Institute of Science and Technology, Daejeon, South Korea
2 shared publications - Daekyum Kim
School of Mechanical Engineering Korea University Seoul Republic of Korea
1 shared publication - Jin Woo Choi
Department of Neurology & Neurological Sciences, Stanford University School of Medicine, Stanford, USA
1 shared publication - Saelyne Yang
Carnegie Mellon University, Pittsburgh, USA
1 shared publication
Latest Publications
- Open Access
- 11 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Silent Impact: Tracking Tennis Shots from the Passive Arm
Wearable technology has transformed sports analytics, offering new dimensions in enhancing player experience. Yet, many solutions involve cumbersome setups that inhibit natural motion. In tennis, existing products require sensors on the racket or dominant arm, causing distractions and discomfort. We propose Silent Impact, a novel and user-friendly system that analyzes tennis shots using a sensor placed on the passive arm. Collecting Inertial Measurement Unit sensor data from 20 recreational tennis players, we developed neural networks that exclusively utilize passive arm data to detect and classify six shots, achieving a classification accuracy of 88.2% and a detection F1 score of 86.0%, comparable to the dominant arm. These models were then incorporated into an end-to-end prototype, which records passive arm motion through a smartwatch and displays a summary of shots on a mobile app. User study (N=10) showed that participants felt less burdened physically and mentally using Silent Impact on the passive arm. Overall, our research establishes the passive arm as an effective, comfortable alternative for tennis shot analysis, advancing user-friendly sports analytics.
- 11 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Open AccessSilent Impact: Tracking Tennis Shots from the Passive Arm
Wearable technology has transformed sports analytics, offering new dimensions in enhancing player experience. Yet, many solutions involve cumbersome setups that inhibit natural motion. In tennis, existing products require sensors on the racket or dominant arm, causing distractions and discomfort. We propose Silent Impact, a novel and user-friendly system that analyzes tennis shots using a sensor placed on the passive arm. Collecting Inertial Measurement Unit sensor data from 20 recreational tennis players, we developed neural networks that exclusively utilize passive arm data to detect and classify six shots, achieving a classification accuracy of 88.2% and a detection F1 score of 86.0%, comparable to the dominant arm. These models were then incorporated into an end-to-end prototype, which records passive arm motion through a smartwatch and displays a summary of shots on a mobile app. User study (N=10) showed that participants felt less burdened physically and mentally using Silent Impact on the passive arm. Overall, our research establishes the passive arm as an effective, comfortable alternative for tennis shot analysis, advancing user-friendly sports analytics.
- 5 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (14) , 16252-16263
Asynchronous Motor Imagery BCI and LiDAR-Based Shared Control System for Intuitive Wheelchair Navigation
Mapping drivers’ thoughts directly to mobility system control would make driving more intuitive as if the mobility system is an extension of their own body. Such a system would allow patients with motor disabilities to drive, as it would not require any physical movement. In this paper, we therefore propose a brain-controlled mobility system that analyzes real-time neural signals elicited from motor imagery, an imagination of different body movements. As such asynchronous brain-computer interfaces (BCIs) are prone to error, our system contains shared control capabilities that take into consideration continuously updated information of the surrounding environment along with electroencephalogram (EEG) signals to improve navigating performance without precise and accurate control from the driver. With our shared control method that uses a wheelchair with light detection and ranging (LiDAR) and inertial measurement unit (IMU) sensors, we held a comparative study in which participants drove our wheelchair with and without our shared control approach using either our brain-controlled system or a keyboard in a physical environment. The experimental results show that among the five participants, the three participants that failed the driving task with the asynchronous BCI-based system could also successfully complete it using our shared control approach. Furthermore, our approach narrows the gap between driving with neural signals and driving with a widely used interface in terms of both elapsed time and safety. These results show not only the potential of brain signals for driving, but also the applicability of BCIs to real-life situations.
- 5 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (14) , 16252-16263
Asynchronous Motor Imagery BCI and LiDAR-Based Shared Control System for Intuitive Wheelchair Navigation
Mapping drivers’ thoughts directly to mobility system control would make driving more intuitive as if the mobility system is an extension of their own body. Such a system would allow patients with motor disabilities to drive, as it would not require any physical movement. In this paper, we therefore propose a brain-controlled mobility system that analyzes real-time neural signals elicited from motor imagery, an imagination of different body movements. As such asynchronous brain-computer interfaces (BCIs) are prone to error, our system contains shared control capabilities that take into consideration continuously updated information of the surrounding environment along with electroencephalogram (EEG) signals to improve navigating performance without precise and accurate control from the driver. With our shared control method that uses a wheelchair with light detection and ranging (LiDAR) and inertial measurement unit (IMU) sensors, we held a comparative study in which participants drove our wheelchair with and without our shared control approach using either our brain-controlled system or a keyboard in a physical environment. The experimental results show that among the five participants, the three participants that failed the driving task with the asynchronous BCI-based system could also successfully complete it using our shared control approach. Furthermore, our approach narrows the gap between driving with neural signals and driving with a widely used interface in terms of both elapsed time and safety. These results show not only the potential of brain signals for driving, but also the applicability of BCIs to real-life situations.
- 2 May 2022
- Published by Elsevier in Pattern Recognition
- Vol. 129
Maximization and restoration: Action segmentation through dilation passing and temporal reconstruction
- 2 May 2022
- Published by Elsevier in Pattern Recognition
- Vol. 129
Maximization and restoration: Action segmentation through dilation passing and temporal reconstruction