Seongchan Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Seongchan Kim has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
Keejun Han
KAIST, Daejeon, South Korea
3 shared publicationsJae-Gil Lee
Graduate School of Knowledge Service Engineering, Korea Advanced Institute of Science and Technology, Republic of Korea
2 shared publicationsMun Y. Yi
KAIST, Daejeon, South Korea
2 shared publications- Mun Yong Yi
Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea
2 shared publications Sung-Hyon Myaeng
2 shared publicationsYing Liu
KAIST, Daejeon, South Korea
2 shared publications
Latest Publications
- Open Access
- 16 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-3
AI-Assisted Object Detection and Information Extraction from Statistical Reports for Enhanced Digital Services
- 16 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessAI-Assisted Object Detection and Information Extraction from Statistical Reports for Enhanced Digital Services
- Open Access
- 11 January 2024
- Published by Elsevier in Computers & Geosciences
- Vol. 184
Improvements in deep learning-based precipitation nowcasting using major atmospheric factors with radar rain rate
- 11 January 2024
- Published by Elsevier in Computers & Geosciences
- Vol. 184
Open AccessImprovements in deep learning-based precipitation nowcasting using major atmospheric factors with radar rain rate
- 9 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 18 (12) , 2137-2141
Rain-Type Classification From Microwave Satellite Observations Using Deep Neural Network Segmentation
The understanding of different characteristics of the stratiform and convective system is important for meteorological research, including precipitation retrievals from satellite observations, precipitation parameterization in numerical prediction models, and precipitation climatology. In this study, the possibility of discriminating rain types using deep learning techniques is examined using satellite microwave observation data. Herein, we build two types of deep neural networks for rain type classification, i.e., U-net (RTC-U-net) and fully connected neural network (RTC-fcNN). Experiments are performed with the data obtained from two sensors onboard the global precipitation measurement (GPM) satellite. The brightness temperatures observed from the GPM microwave imager (GMI) are used as input features, whereas rain types retrieved by dual-frequency precipitation radar (DPR) are used as labels. We generated the merged 40- $\times $ -40 pixel data for training and testing the data set by cropping the GMI observed fields overlapping the DPR observations. Overall, the proposed RTC-U-net and RTC-fcNN effectively classify four rain types, i.e., no-rain, stratiform, convective, and others. The total accuracy for the four rain types is 0.95, and the weighted mean of precision, recall, and f-score for stratiform and convective are 0.76, 0.68, and 0.71, respectively. Results show that the proposed techniques can extract the characteristics of each rain type from the data itself. To the best of our knowledge, this study is the first to apply a segmentation method with U-net for rain type classification.
- 9 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 18 (12) , 2137-2141
Rain-Type Classification From Microwave Satellite Observations Using Deep Neural Network Segmentation
The understanding of different characteristics of the stratiform and convective system is important for meteorological research, including precipitation retrievals from satellite observations, precipitation parameterization in numerical prediction models, and precipitation climatology. In this study, the possibility of discriminating rain types using deep learning techniques is examined using satellite microwave observation data. Herein, we build two types of deep neural networks for rain type classification, i.e., U-net (RTC-U-net) and fully connected neural network (RTC-fcNN). Experiments are performed with the data obtained from two sensors onboard the global precipitation measurement (GPM) satellite. The brightness temperatures observed from the GPM microwave imager (GMI) are used as input features, whereas rain types retrieved by dual-frequency precipitation radar (DPR) are used as labels. We generated the merged 40- $\times $ -40 pixel data for training and testing the data set by cropping the GMI observed fields overlapping the DPR observations. Overall, the proposed RTC-U-net and RTC-fcNN effectively classify four rain types, i.e., no-rain, stratiform, convective, and others. The total accuracy for the four rain types is 0.95, and the weighted mean of precision, recall, and f-score for stratiform and convective are 0.76, 0.68, and 0.71, respectively. Results show that the proposed techniques can extract the characteristics of each rain type from the data itself. To the best of our knowledge, this study is the first to apply a segmentation method with U-net for rain type classification.
- 16 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 58 (3) , 2212-2224
MCSIP Net: Multichannel Satellite Image Prediction via Deep Neural Network
Satellite image prediction is important in weather nowcasting. In this article, we propose a novel multichannel satellite image prediction network (MCSIP Net) for predicting satellite images. The proposed MCSIP Net consists of three parts such as the satellite image predictor, the spatio-temporal 3-D discriminators, and the domain knowledge critic networks. The satellite image predictor takes a multichannel satellite image as an input and predicts a multichannel satellite image by learning spatio-temporal characteristics of each input channel. The spatio-temporal 3-D discriminators are trained to distinguish whether the input satellite image consists of a real satellite image or predicted image. By learning the spatio-temporal 3-D discriminator to distinguish and the satellite image predictor to deceive, the satellite image predictor can generate satellite image more similar to real satellite image distribution. The domain knowledge critic networks take the satellite image and the corresponding analysis data (which is obtained from a meteorological model) as an input and learn to distinguish whether the input satellite image is real or predicted on the basis of the analysis data. By utilizing the analysis data, the proposed MCSIP Net could take the meteorological knowledge into account efficiently. For the purpose of verification of the proposed method, ablation study and qualitative evaluation were conducted. Experimental results demonstrated that the proposed MCSIP Net could be learned efficiently and predict a multichannel satellite image with remarkable quality.
- 16 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 58 (3) , 2212-2224
MCSIP Net: Multichannel Satellite Image Prediction via Deep Neural Network
Satellite image prediction is important in weather nowcasting. In this article, we propose a novel multichannel satellite image prediction network (MCSIP Net) for predicting satellite images. The proposed MCSIP Net consists of three parts such as the satellite image predictor, the spatio-temporal 3-D discriminators, and the domain knowledge critic networks. The satellite image predictor takes a multichannel satellite image as an input and predicts a multichannel satellite image by learning spatio-temporal characteristics of each input channel. The spatio-temporal 3-D discriminators are trained to distinguish whether the input satellite image consists of a real satellite image or predicted image. By learning the spatio-temporal 3-D discriminator to distinguish and the satellite image predictor to deceive, the satellite image predictor can generate satellite image more similar to real satellite image distribution. The domain knowledge critic networks take the satellite image and the corresponding analysis data (which is obtained from a meteorological model) as an input and learn to distinguish whether the input satellite image is real or predicted on the basis of the analysis data. By utilizing the analysis data, the proposed MCSIP Net could take the meteorological knowledge into account efficiently. For the purpose of verification of the proposed method, ablation study and qualitative evaluation were conducted. Experimental results demonstrated that the proposed MCSIP Net could be learned efficiently and predict a multichannel satellite image with remarkable quality.
- 1 September 2016
- Published by SAGE Publications in Journal of Information Science
- Vol. 43 (6) , 742-768
Developing information quality assessment framework of presentation slides
Computerized presentation slides have become essential for many occasions such as business meetings, classroom discussions, multipurpose talks and public events. Given the tremendous increases in online resources and materials, locating high-quality slides relevant to a given task is often a formidable challenge, particularly when a user looks for superior quality slides. This study proposes a new, comprehensive framework for information quality (IQ) developed specifically for computerized presentation slides and explores the possibility of automatically detecting the IQ of slides. To determine slide-specific IQ criteria as well as their relative importances, we carried out a user study, involving 60 participants from two universities, and conducted extensive coding analysis. Further, we subsequently conducted a series of multiple experiments to examine the validity of the IQ features developed on the basis of the selected criteria from the user study. The study findings contribute to identifying key dimensions and related features that can improve effective IQ assessments of computerized presentation slides.
- 1 September 2016
- Published by SAGE Publications in Journal of Information Science
- Vol. 43 (6) , 742-768
Developing information quality assessment framework of presentation slides
Computerized presentation slides have become essential for many occasions such as business meetings, classroom discussions, multipurpose talks and public events. Given the tremendous increases in online resources and materials, locating high-quality slides relevant to a given task is often a formidable challenge, particularly when a user looks for superior quality slides. This study proposes a new, comprehensive framework for information quality (IQ) developed specifically for computerized presentation slides and explores the possibility of automatically detecting the IQ of slides. To determine slide-specific IQ criteria as well as their relative importances, we carried out a user study, involving 60 participants from two universities, and conducted extensive coding analysis. Further, we subsequently conducted a series of multiple experiments to examine the validity of the IQ features developed on the basis of the selected criteria from the user study. The study findings contribute to identifying key dimensions and related features that can improve effective IQ assessments of computerized presentation slides.
- Open Access
- 3 November 2014
- Published by Association for Computing Machinery (ACM)
- p. 1847-1850
Exploiting Knowledge Structure for Proximity-aware Movie Retrieval Model
Current movie title retrieval models, such as IMDB, mainly focus on utilizing structured or semi-structured data. However, user queries for searching a movie title are often based on the movie plot, rather than its metadata. As a solution to this problem, our movie title retrieval model proposes a new way of elaborately utilizing associative relations between multiple key terms that exist in the movie plot, in order to improve search performance when users enter more than one keyword. More specifically, the proposed model exploits associative networks of key terms, called knowledge structures, derived from the movie plots. Using the search query terms entered by Amazon Mechanical Turk users as the golden standard, experiments were conducted to compare the proposed retrieval model with the extant state-of-the-art retrieval models. The experiment results show that the proposed retrieval model consistently outperforms the baseline models. The findings have practical implications for semantic search of movie titles particularly, and of online entertainment contents in general.
- 3 November 2014
- Published by Association for Computing Machinery (ACM)
- p. 1847-1850
Open AccessExploiting Knowledge Structure for Proximity-aware Movie Retrieval Model
Current movie title retrieval models, such as IMDB, mainly focus on utilizing structured or semi-structured data. However, user queries for searching a movie title are often based on the movie plot, rather than its metadata. As a solution to this problem, our movie title retrieval model proposes a new way of elaborately utilizing associative relations between multiple key terms that exist in the movie plot, in order to improve search performance when users enter more than one keyword. More specifically, the proposed model exploits associative networks of key terms, called knowledge structures, derived from the movie plots. Using the search query terms entered by Amazon Mechanical Turk users as the golden standard, experiments were conducted to compare the proposed retrieval model with the extant state-of-the-art retrieval models. The experiment results show that the proposed retrieval model consistently outperforms the baseline models. The findings have practical implications for semantic search of movie titles particularly, and of online entertainment contents in general.
- 1 January 2014
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 638-643
Quality-Based Automatic Classification for Presentation Slides
- 1 January 2014
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 638-643
Quality-Based Automatic Classification for Presentation Slides
- Open Access
- 4 September 2012
- Published by Association for Computing Machinery (ACM)
- p. 133-136
Scientific table type classification in digital library
- 4 September 2012
- Published by Association for Computing Machinery (ACM)
- p. 133-136
Open AccessScientific table type classification in digital library
- 1 September 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1364-1368
Functional-Based Table Category Identification in Digital Library
Better understanding the document logical components is crucial to many applications, e.g., document classification or data integration. As the development of digital libraries, more people realize the importance of the scientific tables, which contain valuable information concisely. Although tons of previous table works focus on table data extraction, few concrete works on understanding and utilizing the extracted table data exist. Based on a large-scaled quantitative study on scientific papers, we believe that identifying the original purpose of the table authors can improve the table data comprehension and facilitate the table data reusability. In this paper, scientific document tables are classified into three topical categories: background, system/method, and experimental, and two functional categories: commentary and comparison. We apply machine learning based methods to implement the table classification task. Our results demonstrate that the proposed features are effective in the classification performance and our proposed method outperforms the rule-based baseline significantly.
- 1 September 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1364-1368
Functional-Based Table Category Identification in Digital Library
Better understanding the document logical components is crucial to many applications, e.g., document classification or data integration. As the development of digital libraries, more people realize the importance of the scientific tables, which contain valuable information concisely. Although tons of previous table works focus on table data extraction, few concrete works on understanding and utilizing the extracted table data exist. Based on a large-scaled quantitative study on scientific papers, we believe that identifying the original purpose of the table authors can improve the table data comprehension and facilitate the table data reusability. In this paper, scientific document tables are classified into three topical categories: background, system/method, and experimental, and two functional categories: commentary and comparison. We apply machine learning based methods to implement the table classification task. Our results demonstrate that the proposed features are effective in the classification performance and our proposed method outperforms the rule-based baseline significantly.
- 1 January 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
Personal Information Access Using Proactive Search and Mobile Hypertext Framework
Mobile search has inherent difficulties with a small screen and an inconvenient input method. As such, deploying a conventional search engine and its user-system interaction method presents problems. Considering the constraints and new opportunities associated with a mobile phone, we propose a novel interaction method with the notion of Mobile Hypertext that encompasses proactive search. Both dynamic and static parts of Mobile Hypertext are created automatically for a variety of personal information stored in a mobile phone. Our experiment shows that the interaction mode provided by Mobile Hypertext can save a significant amount of searching and browsing efforts as the number of information objects to be browsed through is reduced significantly.
- 1 January 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
Personal Information Access Using Proactive Search and Mobile Hypertext Framework
Mobile search has inherent difficulties with a small screen and an inconvenient input method. As such, deploying a conventional search engine and its user-system interaction method presents problems. Considering the constraints and new opportunities associated with a mobile phone, we propose a novel interaction method with the notion of Mobile Hypertext that encompasses proactive search. Both dynamic and static parts of Mobile Hypertext are created automatically for a variety of personal information stored in a mobile phone. Our experiment shows that the interaction mode provided by Mobile Hypertext can save a significant amount of searching and browsing efforts as the number of information objects to be browsed through is reduced significantly.