Zobrazeno 1 - 10
of 300
pro vyhledávání: '"Chan-Hyun Youn"'
Publikováno v:
IEEE Access, Vol 12, Pp 148201-148215 (2024)
Source-Free Domain Adaptation (SFDA) is an important research topic in domains with data privacy concerns. Existing SFDA studies have successfully achieved domain adaptation without revealing source domain data, significantly reducing the possibility
Externí odkaz:
https://doaj.org/article/a539888449b74d39b342dac3531c03c2
Publikováno v:
IEEE Access, Vol 11, Pp 7043-7055 (2023)
In the constrained computing environments such as mobile device or satellite on-board system, various computational factors of hardware resource can restrict the processing of deep learning (DL) services. Recent DL models such as satellite image anal
Externí odkaz:
https://doaj.org/article/0911917156584c4698133466144fe258
Publikováno v:
IEEE Access, Vol 11, Pp 4306-4321 (2023)
In some DL applications such as remote sensing, it is hard to obtain the high task performance (e.g. accuracy) using the DL model on image analysis due to the low resolution characteristics of the imagery. Accordingly, several studies attempted to pr
Externí odkaz:
https://doaj.org/article/7046a5535a06437d9de0c73ad352347c
Publikováno v:
IEEE Access, Vol 10, Pp 117315-117333 (2022)
With advances in NanoSat (CubeSat) and high-resolution sensors, the amount of raw data to be analyzed by human supervisors has been explosively increasing for satellite image analysis. To reduce the raw data, the satellite onboard AI processing with
Externí odkaz:
https://doaj.org/article/d4bcbf2aab644f2aa9e4d14b04acbec4
Autor:
Yungi Ha, Chan-Hyun Youn
Publikováno v:
IEEE Access, Vol 10, Pp 112776-112788 (2022)
Due to the black-box nature of deep networks, making explanations of their decision-making is extremely challenging. A solution is using post-hoc attention mechanisms with the deep network to verify the decision basis. However, those methods have pro
Externí odkaz:
https://doaj.org/article/0d33f9e43ada4dfb93df756afc335e48
Publikováno v:
IEEE Access, Vol 10, Pp 37164-37180 (2022)
We propose a new low-diameter interconnection network called FleX, which offers high flexibility when installing interconnections in a HPC system. FleX consists of multiple layers with only connections between neighboring layers and not within each l
Externí odkaz:
https://doaj.org/article/eeb6deef77d94a55b4db66a5d7e335d9
Publikováno v:
IEEE Access, Vol 9, Pp 62332-62346 (2021)
Recently, satellite image analytics based on convolutional neural networks have been vigorously investigated; however, in order for the artificial intelligence systems to be applied in practice, there still exists several challenges: (a) model explan
Externí odkaz:
https://doaj.org/article/346579d7d7694732bf2bb4a5a2aa204c
Autor:
Kyung-No Joo, Chan-Hyun Youn
Publikováno v:
IEEE Access, Vol 9, Pp 52601-52618 (2021)
The scale of model parameters and datasets is rapidly growing for high accuracy in various areas. To train a large-scale deep neural network (DNN) model, a huge amount of computation and memory is required; therefore, a parallelization technique for
Externí odkaz:
https://doaj.org/article/ae8f4659d785456e87859b9661883953
Autor:
Woo-Joong Kim, Chan-Hyun Youn
Publikováno v:
IEEE Access, Vol 8, Pp 116881-116899 (2020)
Video Analytics System has emerged as a promising technology to realize deep neural network based intelligent applications for video streams. Its objective is to maximize the video analytics performance of video streams, such as accuracy, while utili
Externí odkaz:
https://doaj.org/article/c1155edf91df4496b3533e6905827ab5
Publikováno v:
IEEE Access, Vol 8, Pp 195341-195358 (2020)
As smart metering technology evolves, power suppliers can make low-cost, low-risk estimation of customer-side power consumption by analyzing energy demand data collected in real-time. With advances network infrastructure, smart sensors, and various m
Externí odkaz:
https://doaj.org/article/0e0ea54c139742bc9bf4ca795e13b88d