Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Mooseop Kim"'
Publikováno v:
IEEE Access, Vol 12, Pp 90501-90510 (2024)
Recent studies have revealed that visual-auditory sensory substitution devices (SSDs) can effectively convey visual information to visually impaired or blind individuals through sound. However, SSDs are still not widely available to the visually impa
Externí odkaz:
https://doaj.org/article/7ad74dacc14f4f5490ae754bdca2fc3a
Publikováno v:
IEEE Access, Vol 11, Pp 14169-14180 (2023)
Visual–auditory sensory substitution systems can aid visually impaired people in traveling to various places and recognizing their own environments without help from others. Although several such systems have been developed, they are either not wid
Externí odkaz:
https://doaj.org/article/2747be9951cd4086bb98172417981b20
Publikováno v:
Sensors, Vol 23, Iss 15, p 6893 (2023)
Numerous deep learning methods for acoustic scene classification (ASC) have been proposed to improve the classification accuracy of sound events. However, only a few studies have focused on continual learning (CL) wherein a model continually learns t
Externí odkaz:
https://doaj.org/article/ef2dc4d43eff4ef390b18bf3d1329155
Publikováno v:
Journal of Korean Institute of Intelligent Systems. 32:117-126
Publikováno v:
Journal of Real-Time Image Processing. 20
Image dehazing methods can restore clean images from hazy images and are popularly used as a preprocessing step to improve performance in various image analysis tasks. In recent times, deep learning-based methods have been used to sharply increase th
Publikováno v:
Sensors, Vol 21, Iss 7, p 2364 (2021)
Recent studies have applied the superior performance of deep learning to mobile devices, and these studies have enabled the running of the deep learning model on a mobile device with limited computing power. However, there is performance degradation
Externí odkaz:
https://doaj.org/article/8d014274c5454809a52ff2bf20a09690
Publikováno v:
2022 13th International Conference on Information and Communication Technology Convergence (ICTC).
Publikováno v:
2022 13th International Conference on Information and Communication Technology Convergence (ICTC).
Publikováno v:
Multimedia Tools and Applications. 80:20991-21009
Human activity recognition (HAR) using an accelerometer can provide valuable information for understanding user context. Therefore, several studies have been conducted using deep learning to increase the recognition rate of activity classification. H
Autor:
Chi Yoon Jeong, Mooseop Kim
Publikováno v:
Sensors, Vol 19, Iss 17, p 3688 (2019)
Human activity recognition (HAR), which is important in context awareness services, needs to occur continuously in daily life, owing to which an energy-efficient method is needed. However, because human activities have a longer cycle than HAR methods
Externí odkaz:
https://doaj.org/article/b80c8cf9e0ad4d3dbd70e8c6461c8a2f