• Proceedings of the Korean Information Science Society Conference
• /
• 2010.11a
• /
• pp.127-128
• /
• 2010

본 논문에서는 CCTV 감시 영상에서 취득한 얼굴 이미지를 이용하여, 범죄자 감시목록에 등록된 범죄 용의자를 탐지 식별하는 시스템을 설계 및 구현하였다. 특히 본 논문에서 제안한 SVDD와 SRC를 혼합한 계층적 구조의 범죄 용의자 식별 모듈은 다음과 같은 특성을 갖는다: 1) 먼저 SVDD를 이용하여 범죄 용의자만을 빠르게 인식함으로써, 일반인에 대한 불필요한 범죄자 식별 연산을 수행하지 않는다; 2) 다양한 식별 성능을 저해하는 환경에서도 이미 강인한 성능이 검증된 SRC를 범죄 용의자 식별과정에 적용함으로써 안정적이고 정확한 식별 시스템을 보장한다; 3) 동일 생체 특정의 반복적 사용을 통한 다수결 투표전략을 취함으로써 시스템의 신뢰도를 보장한다; 4) 점증적 갱신의 학습 능력으로 인하여 범죄 용의자 감시목록 데이터베이스의 변화에도 능동적으로 적응한다 실제 KUFD(Korea University Face Database)를 자체 제작하고 캠퍼스 내에서 CCTV 환경의 얼굴 인식 기반 범죄 용의자 탐지 및 식별 시스템 환경을 모의 구축하여 실험적으로 제안된 시스템의 성능을 검증한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06a
• /
• pp.174-178
• /
• 2008

P2P를 포함하는 인터넷 애플리케이션 트래픽의 보다 빠르고 정확한 분류는 최근 학계의 중요한 이슈 중 하나이다. 본 논문에서는 기존의 전통적인 분류방법으로 대표되는 port 번호 및 payload 정보를 이용하는 방법론의 구조적 한계점을 극복하는 새로운 대안으로써, 이진 분류기인 SVM과 단일클래스 SVM을 계층적으로 결합한 다중 클래스 SVM을 구축하여 인터넷 애플리케이션 트래픽 분류를 수행하였다. 제안된 시스템은 이진 분류기인 SVM으로 P2P 트래픽과 non-P2P 트래픽을 빠르게 분류하는 첫 번째 계층, 3개의 단일클래스 SVM을 기반으로 P2P 트래픽들을 파일공유, 메신저, TV로 분류하는 두 번째 계층, 그리고 전체 16가지의 애플리케이션 트래픽별로 세분화 분류하는 세 번째 계층으로 구성된다. 제안된 시스템은 flow 기반의 트래픽 정보를 수집하여 인터넷 애플리케이션 트래픽을 coarse 혹은 fine하게 분류함으로써 효율적인 시스템의 자원 관리, 안정적인 네트워크 환경의 지원, 원활한 bandwidth의 사용, 그리고 적절한 QoS를 보장하였다. 또한, 새로운 애플리케이션 트래픽이 추가되더라도 전체 시스템을 재학습 시킬 필요 없이 새로운 애플리케이션 트래픽만을 추가 학습함으로써 시스템의 점증적 갱신 및 확장성에도 기여하였다. 평가항목인 recall과 precision에서 만족스러운 수치 등을 실험을 통하여 확인함으로써 제안된 시스템의 성능을 검증하였다.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.4
• /
• pp.477-486
• /
• 1995

This paper describes and constructs object-oriented analysis models using Galois-lattices that we are always studying in discrete mathematics, shows fundamental approaches to maintain the models, analyzes the construction of object-oriented analysis models through good examples. Also, we define several properties of Galois-lattices that have binary relations between class objects, propose the incremental updating algorithms that can update the Galois-lattice whenever new classes are added. This proposal shows that in case of adding new class nodes the results from simulations can implement in constant time and have linearly the incremental structures in worst cases, and in that the growth rate of lattices is proportioned to class nodes in time complexity. This results can achieve the high understandability of object-oriented analysis models and the high traceability of maintenance models. Furthermore it is possible to make more efficient performances of class reusability in advantages of object-oriented systems and support truly the class hierarchical maintenances.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.3
• /
• pp.282-288
• /
• 2005

In this paper, we propose a new intrusion detection model, which keeps advantages of existing misuse detection model and anomaly detection model and resolves their problems. This new intrusion detection system, named to MMIDS, was designed to satisfy all the following requirements : 1) Fast detection of new types of attack unknown to the system; 2) Provision of detail information about the detected types of attack; 3) cost-effective maintenance due to fast and efficient learning and update; 4) incrementality and scalability of system. The fast and efficient training and updating faculties of proposed novel multi-class SVM which is a core component of MMIDS provide cost-effective maintenance of intrusion detection system. According to the experimental results, our method can provide superior performance in separating similar patterns and detailed separation capability of MMIDS is relatively good.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.7-14
• /
• 2010

In this paper, we introduce a hierarchical internet application traffic classification system based on SVM as an alternative overcoming the uppermost limit of the conventional methodology which is using the port number or payload information. After selecting an optimal attribute subset of the bidirectional traffic flow data collected from the campus, the proposed system classifies the internet application traffic hierarchically. The system is composed of three layers: the first layer quickly determines P2P traffic and non-P2P traffic using a SVM, the second layer classifies P2P traffics into file-sharing, messenger, and TV, based on three SVDDs. The third layer makes specific classification of the entire 16 application traffics. By classifying the internet application traffic finely or coarsely, the proposed system can guarantee an efficient system resource management, a stable network environment, a seamless bandwidth, and an appropriate QoS. Also, even a new application traffic is added, it is possible to have a system incremental updating and scalability by training only a new SVDD without retraining the whole system. We validate the performance of our approach with computer experiments.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.6
• /
• pp.183-190
• /
• 2011

In this paper, we propose a prototype system for abnormal sound detection and identification which detects and recognizes the abnormal situations by means of analyzing audio information coming in real time from CCTV cameras under surveillance environment. The proposed system is composed of two layers: The first layer is an one-class support vector machine, i.e., support vector data description (SVDD) that performs rapid detection of abnormal situations and alerts to the manager. The second layer classifies the detected abnormal sound into predefined class such as 'gun', 'scream', 'siren', 'crash', 'bomb' via a sparse representation classifier (SRC) to cope with emergency situations. The proposed system is designed in a hierarchical manner via a mixture of SVDD and SRC, which has desired characteristics as follows: 1) By fast detecting abnormal sound using SVDD trained with only normal sound, it does not perform the unnecessary classification for normal sound. 2) It ensures a reliable system performance via a SRC that has been successfully applied in the field of face recognition. 3) With the intrinsic incremental learning capability of SRC, it can actively adapt itself to the change of a sound database. The experimental results with the qualitative analysis illustrate the efficiency of the proposed method.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.14 no.2
• /
• pp.7-16
• /
• 1986

This study was carried out to investigate the effects of such erosion control measures as sowing, planting and small earth structures on the soil and vegetation. In order to study the changes in soil and vegetation, 36 plots were surveyed from 1981 to 1982 in the large erosion control area which is restored last 20 years. The factors which were measured included vegetation coverage, tree growth, number of species, soil depth, soil consistancy, and Chemical properties of soil. The results were as follows; 1) Maximum coverage of the overstory and understory was attained 7 years after the initiation of erosion control. So the overstory need to be tended and pruned. 2) Diversity of species increased until age 6 after which it began to decrease. 3) In order of tree growth, black locust was the fastest, followed by siberian alder and pitch pine. The initial growth of black locust, though the best among the 3 tree stop., decreased rapidly year by year. At the same time, siberian alder and pitch pine grew well until 12 and 6 years after the initiation of erosion control respectively. 4) Fifty percent of the initially planted trees died within 8 yeard. The mortality of siberian alder occurred until the 20th year while the mortality of pitch pine stopped after 10 years. Thereafter 500 trees per hectare were maintained. 5) The soil depth in A and B horision increased by 2cm annually during 20 years. The soil consistency also decreased rapidly until 7th year. The physical soil properties of the rehabilitated areas were improved after the 14th year. 6) The soil pH tend to decrease from 5.3 during the first year to 5.1 during the twentieth year. 7) The organic matter and nitrogen content in the soil were increased by fertilization but after 20 years these nutrients are still deficient for normal tree growth. 8) The phosphorous content in the soil was high in the first year but the longer the period after the initiation of erosion control the lese the content of phosphorous. 9) The biomass of black locust was the highest and increased continuously. The biomass of siberian alder on the contrary decreased from the 15th year because the number of trees in this place was very low. The total biomass in the twentieth year after erosion control initiation was 105.7 ton per hectare.