• Database Research
• /
• v.34 no.3
• /
• pp.58-68
• /
• 2018

Distributed computing helps to efficiently store and process large data on a cluster of multiple machines. The performance of distributed computing is greatly influenced depending on the state of the servers constituting the distributed system. In this paper, we propose a self-diagnosis system that collects log data in a distributed system, detects anomalies and visualizes the results in real time. First, we divide the self-diagnosis process into five stages: collecting, delivering, analyzing, storing, and visualizing stages. Next, we design a real-time self-diagnosis system that meets the goals of real-time, scalability, and high availability. The proposed system is based on Apache Flume, Apache Kafka, and Apache Storm, which are representative real-time distributed techniques. In addition, we use simple but effective moving average and 3-sigma based anomaly detection technique to minimize the delay of log data processing during the self-diagnosis process. Through the results of this paper, we can construct a distributed real-time self-diagnosis solution that can diagnose server status in real time in a complicated distributed system.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.258-261
• /
• 2002

최근 네트워크 취약점 검색 방법을 이용한 침입 공격이 증가하는 추세이며 이런 공격에 대하여 적절하게 실시간 탐지 및 대응 처리하는 침입방지시스템(IPS: Intrusion Prevention System)에 대한 연구가 지속적으로 이루어지고 있다. 본 논문에서는 시스템에 허락을 얻지 않은 서비스거부 공격(Denial of Service Attack) 기술 중 TCP의 신뢰성 및 연결 지향적 전송서비스로 종단간에 이루어지는 3-Way Handshake를 이용한 Syn Flooding Attack에 대하여 침입시도패킷 정보를 수집, 분석하고 퍼지인식도(FCM : Fuzzy Cognitive Maps)를 이용한 침입시도여부결정 및 대응 처리하는 네트워크 기반의 실시간 탐지 및 방지 모델(Network based Real Time Scan Detection & Prevention Model)을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.955-957
• /
• 2017

감시 카메라 환경에서 돈사 내 돼지들을 탐지 및 추적에 관한 연구는 효율적인 돈사 관리측면에서 중요한 이슈로 떠오르고 있다. 그러나 깊이 정보 내 노이즈와 돈방 내 돼지와 배경의 깊이 정보 값이 유사하여 개별 돼지만을 탐지하기란 쉽지 않다. 특히 천장에 설치된 센서로부터 획득된 벽과 바닥 경계에 위치한 돼지를 탐지하기 위한 방법이 요구된다. 본 논문에서는 노이즈에 덜 민감한 바닥 배경을 이용하여 바닥에 위치한 돼지의 부분을 먼저 탐지한 후, 벽에 위치한 돼지의 나머지 부분을 수퍼픽셀과 영역확장 기법으로 탐지하는 방법을 제안한다. 실험 결과 돈방 내 벽과 바닥 경계에 위치한 돼지를 정확히 탐지하였으며, 영상 1장 당 수행시간이 5msec로 실시간 처리에 문제가 없음을 확인하였다.

• 한국IT서비스학회:학술대회논문집
• /
• 2009.05a
• /
• pp.361-364
• /
• 2009

침입의 방법이 점차 치밀해지고 다양해짐에 따라 새로운 방식의 침입 탐지 기법 역시 지속적으로 요구되어진다. 기존의 오용 탐지 방법론은 탐지율은 뛰어나지만 새로운 침입형태에 대한 대응 능력이 부족하다. 이러한 단점을 보완하고자 등장한 것이 비정상 행위 탐지 방법론이다. 하지만 현재까지의 연구는 네트워크나 서버 OS, 데이터베이스 등 각 개별 분야에 대해서만 진행되고 있어 그 탐지 능력에 한계가 있다. 본 논문에서는 이러한 한계를 극복하고자 사용자의 네트워크 및 운영체제 로그를 통합 하고, 데이터마이닝 기법 중 빈발 패턴 마이닝 기법을 이용한 보다 정확한 비정상 행위 탐지 기술을 제안한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.306-308
• /
• 2018

This paper proposes a variant malicious code detection algorithm in a mobile environment using a deep learning algorithm. In order to solve the problem of malicious code detection method based on Android, we have proved high detection rate through signature based malicious code detection method and realtime malicious file detection algorithm using machine learning method.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.621-623
• /
• 2023

전자금융거래 시장이 활발해지며 이에 따라 신용 카드 이상 거래가 증가하고 있다. 따라서 많은 금융 기관은 신용 카드 이상 거래 탐지 시스템을 사용하여 신용 카드 이상 거래를 탐지하고 개인 피해를 줄이는 등 소비자를 보호하기 위해 큰 노력을 하고 있으며, 이에 따라 높은 정확도로 신용 카드 이상 거래를 탐지할 수 있는 실시간 자동화 시스템에 대한 개발이 요구되었다. 이에 본 논문에서는 머신러닝 기법 중 부스팅 알고리즘을 사용하여 더욱 정확한 신용 카드 이상 거래 탐지 시스템을 제안하고자 한다. XGBoost, LightGBM, CatBoost 부스팅 알고리즘을 사용하여 보다 정확한 신용 카드 이상 거래 탐지 시스템을 개발하였으며, 실험 결과 평균적으로 정밀도 99.95%, 재현율 99.99%, F1-스코어 99.97%를 취득하여 높은 신용 카드 이상 거래 탐지 성능을 보여주는 것을 확인하였다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.4
• /
• pp.102-110
• /
• 2009

In this paper, we propose an object detection method for real-time in infrared (IR) images and PowerPC (PPC) and H/W design based on field programmable gate array (FPGA). An open H/W architecture has the advantages, such as easy transplantation of HW and S/W, support of compatibility and scalability for specification of current and previous versions, common module design using standardized design, and convenience of management and maintenance. Proposed background modeling for an open H/W architecture design decreases size of search area to construct a sparse block template of search area in IR images. We also apply to compensate for motion compensation when image moves in previous and current frames of IR sensor. Separation method of background and objects apply to adaptive values through time analysis of pixel intensity. Method of clutter reduction to appear near separated objects applies to median filter. Methods of background modeling, object detection, median filter, labeling, merge in the design embedded system execute in PFC processor. Based on experimental results, proposed method showed real-time object detection through global motion compensation and background modeling in the proposed embedded system.

• The KIPS Transactions:PartA
• /
• v.8A no.4
• /
• pp.331-338
• /
• 2001

With the general use of network, cyber terror rages throughout the world. However, IP Fragmentation isn\`t free from its security problem yet, even though it guarantees effective transmission of the IP package in its network environment. Illegal invasion could happen or disturb operation of the system by using attack mechanism such as IP Spoofing, Ping of Death, or ICMP taking advantage of defectiveness, if any, which IP Fragmentation needs improving. Recently, apart from service refusal attack using IP Fragmentation, there arises a problem that it is possible to detour packet filtering equipment or network-based attack detection system using IP Fragmentation. In the paper, we generate the real time access log file to make the system manager help decision support and to make the system manage itself in case that some routers or network-based attack detection systems without packet reassembling function could not detect or suspend illegal invasion with divided datagrams of the packet. Through the implementation of the self-managing system we verify its validity and show its future effect.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.561-568
• /
• 2021

In recent years, autonomous driving technologies have become a high-value-added technology that attracts attention in the fields of science and industry. For smooth Self-driving, it is necessary to accurately detect an object and estimate its movement speed in real time. CNN-based deep learning algorithms and conventional dense optical flows have a large consumption time, making it difficult to detect objects and estimate its movement speed in real time. In this paper, using a single camera image, fast object detection was performed using the YOLOv5 algorithm, a deep learning algorithm, and fast estimation of the speed of the object was performed by using a local dense optical flow modified from the existing dense optical flow based on the detected object. Based on this algorithm, we present a system that can predict the collision time and probability, and through this system, we intend to contribute to prevent tram accidents.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.468-474
• /
• 2022

In this paper, we propose a method to implement a real-time fire alarm system using deep learning. The deep learning image dataset for fire alarms acquired 1,500 sheets through the Internet. If various images acquired in a daily environment are learned as they are, there is a disadvantage that the learning accuracy is not high. In this paper, we propose a fire image data expansion method to improve learning accuracy. The data augmentation method learned a total of 2,100 sheets by adding 600 pieces of learning data using brightness control, blurring, and flame photo synthesis. The expanded data using the flame image synthesis method had a great influence on the accuracy improvement. A real-time fire detection system is a system that detects fires by applying deep learning to image data and transmits notifications to users. An app was developed to detect fires by analyzing images in real time using a model custom-learned from the YOLO V4 TINY model suitable for the Edge AI system and to inform users of the results. Approximately 10% accuracy improvement can be obtained compared to conventional methods when using the proposed data.