• Korean Journal of Radiology
• /
• v.24 no.11
• /
• pp.1061-1080
• /
• 2023

Artificial intelligence (AI) in radiology is a rapidly developing field with several prospective clinical studies demonstrating its benefits in clinical practice. In 2022, the Korean Society of Radiology held a forum to discuss the challenges and drawbacks in AI development and implementation. Various barriers hinder the successful application and widespread adoption of AI in radiology, such as limited annotated data, data privacy and security, data heterogeneity, imbalanced data, model interpretability, overfitting, and integration with clinical workflows. In this review, some of the various possible solutions to these challenges are presented and discussed; these include training with longitudinal and multimodal datasets, dense training with multitask learning and multimodal learning, self-supervised contrastive learning, various image modifications and syntheses using generative models, explainable AI, causal learning, federated learning with large data models, and digital twins.

• International Journal of Contents
• /
• v.17 no.1
• /
• pp.61-70
• /
• 2021

As the resolution of climate change scenario data applied with regional models increased, Earth System Grid Federation (ESGF) was established around major climate-related organizations to jointly operated and manage large-scale climate data. ESGF developed standard software to provide model output, observation data management, dissemination, and analysis using Peer to Peer (P2P) computing technology. Roles of each institution were divided into index and data nodes. Therefore, ESGF data node was established at APEC Climate Center in Korea on behalf of Asia to share data on climate change scenarios of CORDEX-East Asia (CORDEX-EA) to study climate changes in Eastern Asia. Climate researchers are expected to play a large role in researching causes of global warming and responding to climate change by providing CORDEX-EA regional model data to the world through ESGF data node.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.2
• /
• pp.92.1-92.1
• /
• 2011

NASA launched Solar Dynamics Observatory (SDO) on February 2011 in order to understand the cause of solar activities and their influences on the Earth and the near-Earth space. KASI is constructing Korean Data Center for SDO based on the letter of agreement between KASI and NASA for space weather research. SDO produces about 1.5 TB a day and its raw data amounts to about 550 TB in a year. Stanford University has been already operating the data center for scientific raw data, but there is a limit to use its data for space weather research and space weather service in real time because of network environment. Korean Data Center for SDO will provide scientific data not only to Korean institutes but also to international space weather societies. KASI has designed the data transfer system by using GLORIAD in order to get higher performance and stability. After the first construction of data transfer system and storage system in this year, we will increase the storage capacity of the data center in phases considering new developments in a storage technology and drop of their prices.

• Korean Journal of Radiology
• /
• v.23 no.9
• /
• pp.847-852
• /
• 2022

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.620-624
• /
• 2007

Recently, Gonzalez-Audicana et al. proposed the substitute wavelet intensity (SWI) method which provided a solution based on the intensity-hue-saturation (IHS) method for the fusing of panchromatic (PAN) and multispectral (MS) images. Although the spectral quality of the fused MS images is enhanced, this method is not efficient enough to quickly merge massive volumes of data from satellite. To overcome this problem, we introduce a new SWI method based on a fast IHS transform to implement efficiently as an alternative procedure. In addition, we show that the method is well applicable for fusing IKONOS PAN with MS images.

• Proceedings of the KIEE Conference
• /
• 2003.07a
• /
• pp.151-153
• /
• 2003

This paper was studied on using data of the protective relay by Power Quality Monitor. The protective relay will have problem to save data for PQM(Power Qualify Monitoring) analysis because the protective relay memory is limited. So this paper was proposed new data compression of the data was get from the protective relay. The scheme is compared each cycle after DFT(Discrete Fourier Transform). And scheme is verified through simulation of protective relay data was from real distribution system.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.10
• /
• pp.932-939
• /
• 2012

Recently, data centers are being established because IT and telecommunication industries are growing. The data centers have to install emergency generators to prevent unexpected shutdown of the electrical power supply. When the data centers are located in the densely populated urban area, the operating noise of the emergency generators can be a cause of people's complaints. In this case, it is necessary to establish effective countermeasure by noise & vibration specialists. To achieve this, noise reduction measure using noise measurement data and 3D noise analysis method have been employed in this study.

• Korean Journal of Remote Sensing
• /
• v.23 no.5
• /
• pp.347-353
• /
• 2007

Recently, $Gonz\acute{a}lez-Aud\acute{i}cana$ et al. proposed the substitute wavelet intensity(SWI) method which provided a solution based on the intensity-hue-saturation(IHS) method for the fusing of panchromatic(PAN) and multispectral(MS) images. Although the spectral quality of the fused MS images is enhanced, this method is not efficient enough to quickly merge massive volumes of data from satellite. To overcome this problem, we introduce a new SWI method based on a fast IHS transform to implement efficiently as an alternative procedure. In addition, we show that the method is well applicable for fusing IKONOS PAN with MS images.

• ETRI Journal
• /
• v.41 no.2
• /
• pp.224-234
• /
• 2019

This paper proposes a new spectrum forecasting (SF) model to estimate the spectrum demands for future mobile broadband (MBB) services. The model requires five main input metrics, that is, the current available spectrum, site number growth, mobile data traffic growth, average network utilization, and spectrum efficiency growth. Using the proposed SF model, the future MBB spectrum demand for Malaysia in 2020 is forecasted based on the input market data of four major mobile telecommunication operators represented by A-D, which account for approximately 95% of the local mobile market share. Statistical data to generate the five input metrics were obtained from prominent agencies, such as the Malaysian Communications and Multimedia Commission, OpenSignal, Analysys Mason, GSMA, and Huawei. Our forecasting results indicate that by 2020, Malaysia would require approximately 307 MHz of additional spectrum to fulfill the enormous increase in mobile broadband data demands.

• Korean Institute of Interior Design Journal
• /
• no.33
• /
• pp.46-53
• /
• 2002

The development of data communication and network technology has brought a change to various communications through the internet. Regarding the stable internet service, corporations and Individuals came to require an internet data center in which there is computer equipment and network devices available 24 hours everyday. The internet data center is now on a large scale in its structure and facility, suitable for the internet environment that is under development in various dimensions, and effective for task support, stable facility, capable of space expansion and flexibility, and easiness in ease of maintenance and management, etc. The monitoring center of the data center which is one of the core facilities in the center, special space elements and functions as well as a function of task space are to be put into consideration additionally. This study was to present a proposal for the space elements and environmental design of a monitoring center, which could create an efficient and comfortable room.