Junhyeong Baek
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Junhyeong Baek has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Ki Jun Yu
School of Electrical and Electronic Engineering, Yonsei University, Seoul, Republic of Korea
2 shared publications - Kyowon Kang
Department of Biomedical Engineering, Hankuk University of Foreign Studies, Yongin 17035, Republic of Korea
2 shared publications - Byunghwan Jeon
Department of Computer Engineering, Hankuk University of Foreign Studies, Seoul 02450, Republic of Korea
1 shared publication - Doohyun J. Lee
Functional Bio-integrated Electronics and Energy Management Lab, School of Electrical and Electronic Engineering, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, Seoul 03722, Republic of Korea
1 shared publication - Dosik Hwang
Yonsei University
1 shared publication Doyun Kim
Department of Chemistry, Hankuk University of Foreign Studies (HUFS), Yongin 17035, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 1 May 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 12 (18) , eaec8995
An AI-driven, wearable, conformal ring system for real-time and user-independent sign language interpretation
Sign language translation systems have long aimed to bridge the communication between signers and nonsigners. However, preliminary systems rely on glove-type wearables or wired sensor arrays, which constrain hand movement, reduce comfort, and require nonpersonalized sensor positions that limit adaptability across users. Here, we introduce a wirelessly connected, ring-type sign language translator (WRSLT) designed to overcome these limitations by enabling full finger mobility through independent sensor rings and multilink communication. The system supports static and dynamic gesture detection using selected fingers via quantitative relevance analysis and achieves robust user-independent performance without per-user calibration. WRSLT demonstrated high recognition accuracy on large-scale datasets comprising 100 American Sign Language and 100 International Sign Language words, achieving 88.3 and 88.5% accuracy, respectively, under unseen-user conditions (i.e., test users not included in model training). Furthermore, a custom sequential word detection framework enables sentence-level translation from continuous signing input without requiring separate training on entire sentence structures.
- 1 May 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 12 (18) , eaec8995
Open AccessAn AI-driven, wearable, conformal ring system for real-time and user-independent sign language interpretation
Sign language translation systems have long aimed to bridge the communication between signers and nonsigners. However, preliminary systems rely on glove-type wearables or wired sensor arrays, which constrain hand movement, reduce comfort, and require nonpersonalized sensor positions that limit adaptability across users. Here, we introduce a wirelessly connected, ring-type sign language translator (WRSLT) designed to overcome these limitations by enabling full finger mobility through independent sensor rings and multilink communication. The system supports static and dynamic gesture detection using selected fingers via quantitative relevance analysis and achieves robust user-independent performance without per-user calibration. WRSLT demonstrated high recognition accuracy on large-scale datasets comprising 100 American Sign Language and 100 International Sign Language words, achieving 88.3 and 88.5% accuracy, respectively, under unseen-user conditions (i.e., test users not included in model training). Furthermore, a custom sequential word detection framework enables sentence-level translation from continuous signing input without requiring separate training on entire sentence structures.
- Open Access
- 1 June 2024
- Published by AIP Publishing in Applied Physics Reviews
- Vol. 11 (2)
Biomimic and bioinspired soft neuromorphic tactile sensory system
The progress in flexible and neuromorphic electronics technologies has facilitated the development of artificial perception systems. By closely emulating biological functions, these systems are at the forefront of revolutionizing intelligent robotics and refining the dynamics of human–machine interactions. Among these, tactile sensory neuromorphic technologies stand out for their ability to replicate the intricate architecture and processing mechanisms of the brain. This replication not only facilitates remarkable computational efficiency but also equips devices with efficient real-time data-processing capability, which is a cornerstone in artificial intelligence evolution and human–machine interface enhancement. Herein, we highlight recent advancements in neuromorphic systems designed to mimic the functionalities of the human tactile sensory system, a critical component of somatosensory functions. After discussing the tactile sensors which biomimic the mechanoreceptors, insights are provided to integrate artificial synapses and neural networks for advanced information recognition emphasizing the efficiency and sophistication of integrated system. It showcases the evolution of tactile recognition biomimicry, extending beyond replicating the physical properties of human skin to biomimicking tactile sensations and efferent/afferent nerve functions. These developments demonstrate significant potential for creating sensitive, adaptive, plastic, and memory-capable devices for human-centric applications. Moreover, this review addresses the impact of skin-related diseases on tactile perception and the research toward developing artificial skin to mimic sensory and motor functions, aiming to restore tactile reception for perceptual challenged individuals. It concludes with an overview of state-of-the-art biomimetic artificial tactile systems based on the manufacturing–structure–property–performance relationships, from devices mimicking mechanoreceptor functions to integrated systems, underscoring the promising future of artificial tactile sensing and neuromorphic device innovation.
- 1 June 2024
- Published by AIP Publishing in Applied Physics Reviews
- Vol. 11 (2)
Open AccessBiomimic and bioinspired soft neuromorphic tactile sensory system
The progress in flexible and neuromorphic electronics technologies has facilitated the development of artificial perception systems. By closely emulating biological functions, these systems are at the forefront of revolutionizing intelligent robotics and refining the dynamics of human–machine interactions. Among these, tactile sensory neuromorphic technologies stand out for their ability to replicate the intricate architecture and processing mechanisms of the brain. This replication not only facilitates remarkable computational efficiency but also equips devices with efficient real-time data-processing capability, which is a cornerstone in artificial intelligence evolution and human–machine interface enhancement. Herein, we highlight recent advancements in neuromorphic systems designed to mimic the functionalities of the human tactile sensory system, a critical component of somatosensory functions. After discussing the tactile sensors which biomimic the mechanoreceptors, insights are provided to integrate artificial synapses and neural networks for advanced information recognition emphasizing the efficiency and sophistication of integrated system. It showcases the evolution of tactile recognition biomimicry, extending beyond replicating the physical properties of human skin to biomimicking tactile sensations and efferent/afferent nerve functions. These developments demonstrate significant potential for creating sensitive, adaptive, plastic, and memory-capable devices for human-centric applications. Moreover, this review addresses the impact of skin-related diseases on tactile perception and the research toward developing artificial skin to mimic sensory and motor functions, aiming to restore tactile reception for perceptual challenged individuals. It concludes with an overview of state-of-the-art biomimetic artificial tactile systems based on the manufacturing–structure–property–performance relationships, from devices mimicking mechanoreceptor functions to integrated systems, underscoring the promising future of artificial tactile sensing and neuromorphic device innovation.