Jaegwang Kim
Sungkyunkwan University · Computer Science
About the Lab
Professor Jaegwang Kim's research lab specializes in intelligent systems and data-driven solutions for critical infrastructure and network security. The lab focuses on water resource management using advanced predictive modeling, particularly for large-scale dams under climate change impacts, while also advancing cybersecurity through anomaly detection in network traffic using fuzzy logic and policy-based traffic control. Additionally, the lab explores energy-efficient routing in wireless sensor networks and develops explainable AI-driven recommendation systems for business-to-business e-commerce using knowledge graphs. The integration of real-time sensing, machine learning, and intelligent decision-making defines the lab’s interdisciplinary approach.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
15The Soyang Dam, the largest multipurpose dam in Korea, faces water resource management challenges due to global warming. Global warming increases the duration and frequency of days with high temperatures and extreme precipitation events. Therefore, it is crucial to accurately predict the inflow rate for water resource management because it helps plan for flood, drought, and power generation in the Seoul metropolitan area. However, the lack of hydrological data for the Soyang River Dam causes a p
The slow port scan attack detection is the one of the important topics in the network security. We suggest an abnormal traffic control framework to detect slow port scan attacks using fuzzy rules. The abnormal traffic control framework acts as an intrusion prevention system to suspicious network traffic. It manages traffic with a stepwise policy: first decreasing network bandwidth and then discarding traffic. In this paper, we show that our abnormal traffic control framework effectively detects
In wireless sensor networks (WSNs), routing algorithms are one of the important research topics because low energy consumption is strongly needed. In comparison with single hop and cluster routing scheme, virtual backbone tree schemes have recently attracted considerable attention in WSN routing algorithms as they offer energy-efficient transmission based on multi-hop routing approaches. The Energy-aware Virtual Backbone Tree (EVBT) is the pioneer of this concept which considers the energy-aware
The adoption of recommender systems in business-to-business (B2B) can make the management of companies more efficient. Although the importance of recommendation is increasing with the expansion of B2B e-commerce, not enough studies on B2B recommendations have been conducted. Due to several differences between B2B and business-to-consumer (B2C), the B2B recommender system should be defined differently. This paper presents a new perspective on the explainable B2B recommender system using the knowl
In recent years, fusion camera systems that consist of color cameras and Time-of-Flight (TOF) depth sensors have been popularly used due to its depth sensing capability at real-time frame rates. However, captured depth maps are limited in low resolution compared to the corresponding color images due to physical limitation of the TOF depth sensor. Although many algorithms have been proposed, they still yield erroneous results, especially when boundaries of the depth map and the color image are no
In this paper, an approach is proposed to evaluate and rearrange web pages, based on the query-related web context. The contexts we focus on are the terms co-occurring with queries in microblogs. The proposed approach is based on the retrieved result by a search engine. If a query is given, it retrieves the search results, and checks whether the query is on a burst state or not. If the query is on a burst state (or popular state), our method applies the query-related context to the search result
The virtual backbone concept is a method of efficient communication in wireless sensor networks. A recent variant is the energy-aware virtual backbone tree (EVBT) algorithm which applies a tree structure to the backbone. This algorithm can minimize the energy consumed in a data transfer between a sensor node and a tree node, but cannot minimize the energy consumption throughout the routing process. In this paper, we propose a modified-EVBT (m-EVBT) algorithm which consumes less energy than the E
Clickstreams in users' navigation logs have various data which are related to users' web surfing. Those are visit counts, stay times, product types, etc. When we observe these data, we can divide clickstreams into sub-clickstreams so that the pages in a sub-clickstream share more contexts with each other than with the pages in other sub-clickstreams. In this paper, we propose a method which extracts more informative rules from clickstreams for web page recommendation based on genetic programming
근래 들어 개인 적응형 서비스에 대한 관심이 높아지고 있으나 아직 음악에 관련된 서비스는 보편화되어 있지 않다. 그 이유는 음악의 관련 정보를 분석하는 것이 텍스트 기반의 자료에 비해 어렵기 때문이다. 이에 본 논문은 사용자가 선택했던 음악을 분석해서 사용자의 성향을 파악하고 그와 유사한 음악을 추천해주는 시스템을 제안한다. 음악의 속성을 추출하는 방법으로 음파 분석 기법을 사용한다. 음파에서 세 가지의 수치화된 속성을 추출하여 이를 특성 공간에 나타낸다. 이 때 사용자가 선택한 음악이 많이 모여 있는 군집을 분석한다면, 사용자의 취향을 파악할 수 있다. 하지만 몇 개의 군집이 형성될 것인지를 예측하기란 쉽지 않다. 이를 해결하기 위하여 군집의 수를 상황에 따라 유동적으로 변경할 수 있는 가변형 -means 기법을 제시한다. 이 기법은 군집의 직경 크기를 제한하여, 일정치 이상일 때 군집의 수를 늘리는 방법으로 데이터의 범위를 알고 있을 때 매우 효율적으로 적용할 수 있다. 이 방법
근래 들어 개인 적응형 서비스에 대한 관심이 높아지고 있으나 아직 음악에 관련된 서비스는 보편화되어 있지 않다. 그 이유는 음악의 관련 정보를 분석하는 것이 텍스트 기반의 자료에 비해 어렵기 때문이다. 이에 본 논문은 사용자가 선택했던 음악을 분석해서 사용자의 성향을 파악하고 그와 유사한 음악을 추천해주는 시스템을 제안한다. 음악의 속성을 추출하는 방법으로 음파 분석 기법을 사용한다. 음파에서 세 가지의 수치화된 속성을 추출하여 이를 특성 공간에 나타낸다. 이 때 사용자가 선택한 음악이 많이 모여 있는 군집을 분석한다면, 사용자의 취향을 파악할 수 있다. 하지만 몇 개의 군집이 형성될 것인지를 예측하기란 쉽지 않다. 이를 해결하기 위하여 군집의 수를 상황에 따라 유동적으로 변경할 수 있는 가변형 K-means 기법을 제시한다. 이 기법은 군집의 직경 크기를 제한하여, 일정치 이상일 때 군집의 수를 늘리는 방법으로 데이터의 범위를 알고 있을 때 매우 효율적으로 적용할 수 있다. 이 방
Spam detection is one of the important problems in these days. Many spam detection methods were proposed, but fax spam detection is not popular. It not easy to directly use existing content-based spam detection methods for fax documents because the documents are processed as image rather than text. In this paper, we propose a fax spam detection framework which is based on keyword patterns by using an Optical Character Recognition (OCR) technique. To demonstrate how effective the proposed framewo
In this paper, we present a method for extracting video objects efficiently by using the modified graph cut algorithm based on contour information. First, we extract objects at the first frame by an automatic object extraction algorithm or the user interaction. To estimate the objects' contours at the current frame, motion information of objects' contour in the previous frame is analyzed. Block-based histogram back-projection is conducted along the estimated contour point. Each color model of ob
Research Areas
Dive deeper into Jaegwang Kim's research on Nubint
Open this lab's papers in the app to read with AI, summarize, and cite in your writing.