S
Sa-Kwang Song
Researcher at Korea Institute of Science and Technology Information
Publications - 110
Citations - 1016
Sa-Kwang Song is an academic researcher from Korea Institute of Science and Technology Information. The author has contributed to research in topics: Information extraction & Big data. The author has an hindex of 17, co-authored 109 publications receiving 867 citations. Previous affiliations of Sa-Kwang Song include Korea Institute of Science and Technology & Electronics and Telecommunications Research Institute.
Papers
More filters
Posted Content
DeepRain: ConvLSTM Network for Precipitation Prediction using Multichannel Radar Data.
TL;DR: This study introduces a brand-new data-driven precipitation prediction model called DeepRain, which predicts the amount of rainfall from weather radar data, which is three-dimensional and four-channel data, using convolutional LSTM (ConvLSTM).
Journal ArticleDOI
Computer Vision in Precipitation Nowcasting: Applying Image Quality Assessment Metrics for Training Deep Neural Networks
Quang-Khai Tran,Sa-Kwang Song +1 more
TL;DR: A new sequence-to-sequence neural network structure to leverage convolutional recurrent neural network models in a realistic data context and was more tolerant to increasing uncertainty in the data, and the use of image quality metrics can significantly reduce the blurry image issue.
Journal ArticleDOI
Media-aware quantitative trading based on public Web information
TL;DR: A media-aware quantitative trading strategy utilizing sentiment information of Web media is proposed, achieved by capturing public mood from interactive behaviors of investors in social media and studying the impact of firm-specific news sentiment on stocks along with such public mood.
Patent
Smart footwear and operating method thereof
TL;DR: In this paper, a film type insole sensor measuring a change of force applied by a user's foot, as a resistance value, was used to estimate the user's current condition and the quantity of motion based on the resistance value and the acceleration value.
Proceedings ArticleDOI
Toward real time detection of the basic living activity in home using a wearable sensor and smart home sensors
TL;DR: In this article, a triaxial accelerometer sensor and environment sensors indicating contact with subject in home are used to infer activities of daily living (ADL) for maintaining healthy life and recognizing emergency.