• 제목/요약/키워드: Deal source

검색결과 187건 처리시간 0.026초

자연어 처리 기반 멀티 소스 이벤트 로그의 보안 심각도 다중 클래스 분류 (A Multiclass Classification of the Security Severity Level of Multi-Source Event Log Based on Natural Language Processing)

  • 서양진
    • 정보보호학회논문지
    • /
    • 제32권5호
    • /
    • pp.1009-1017
    • /
    • 2022
  • 로그 데이터는 정보 시스템의 주요 동작과 상태를 이해하고 판단하는 근거로 사용되어 왔으며, 여러 보안 분야 응용에서도 중요한 입력 데이터로 사용된다. 로그 데이터로부터 필요한 정보를 얻어 이를 근거로 의사 결정을 하고, 적절한 대응 방안을 취하는 것은 시스템을 보호하고 안정적으로 운영하는 데 있어 필수적인 요소이지만, 로그의 종류와 양이 폭발적으로 증가함에 따라 기존 도구들로는 효과적이고 효율적인 대응이 쉽지 않은 상황이다. 이에 본 연구에서는 자연어 처리 기반의 머신 러닝을 이용해 멀티 소스 이벤트 로그의 보안 심각도를 여러 단계로 분류하는 방법을 제안하였으며, 472,972건의 훈련 및 테스트 샘플을 이용하여 실험을 수행한 결과 99.59%의 정확도를 달성하였다.

사물인터넷 디바이스의 집적회로 목적물과 소스코드의 유사성 분석 및 동일성 (Similarity Evaluation and Analysis of Source Code Materials for SOC System in IoT Devices)

  • 김도현;이규대
    • 한국소프트웨어감정평가학회 논문지
    • /
    • 제15권1호
    • /
    • pp.55-62
    • /
    • 2019
  • 사물인터넷 디바이스의 소형화, 저전력화 요구는 프로그램을 단일 칩으로 구현하는 SOC 기술로 구현되고 있다. 불법 복제에 의한 저작권 분쟁은 반도체 칩에서도 증가하고 있으며, 디자인하우스의 칩 구현에서의 분쟁과 소스코드의 도용에 의한 칩 구현에 발생하고 있다. 그러나 최종 칩 구현은 디자인하우스에서 제작되기 때문에 저작권의 보호범위에서 어려움이 있다. 본 연구에서는 사물인터넷 디바이스의 집적회로에서 HDL 언어로 작성된 소스코드의 분쟁에서, 유사성을 판단하기 위한 분석방법과 유사성 판단의 기준을 설정하는 항목에 대해 다루었다. 특히 동일한 시방서를 기준으로 제작된 칩의 경우 동일한 구성과 코드 형태를 포함해야 하는 제작특성에서 유사성의 판단영역을 구분하는 내용에 대해서도 다룬다.

High-degree Cubature Kalman Filtering Approach for GPS Aided In-Flight Alignment of SDINS

  • Shin, Hyun-choel;Yu, Haesung;Park, Heung-won
    • Journal of Positioning, Navigation, and Timing
    • /
    • 제4권4호
    • /
    • pp.181-186
    • /
    • 2015
  • A High-degree Cubature Kalman Filter (CKF) is proposed to deal with the Strapdown Inertial Navigation System (SDINS) alignment problem. In-flight Alignment (IFA) is an effective method to compensate for attitude errors of the navigation system. While providing precise attitude error compensation, however, the external source aided alignment often creates a nonlinear filtering problem caused by a large misalignment angle. Introduced recently, Cubature Kalman Filter is a suitable technique for various nonlinear problems. In this paper, a higher degree CKF is applied to this accuracy-is-everything SDINS IFA problem. The simulation results show that the proposed technique outperformed a traditional nonlinear filter in terms of precision and alignment time.

Development of Intelligent Electricity Saving System Using SARIMA Algorithm

  • Heo, Jun;Kim, Kyung-Shin
    • International Journal of Advanced Culture Technology
    • /
    • 제2권2호
    • /
    • pp.19-24
    • /
    • 2014
  • Many people all over the world have been conducting a great deal of research to solve the problem of global warming since the great majority consider reduction of CO2 as the only solution for that. That is why the production and conservation of energy is thought to be highly crucial. while it is important to produce energy with the high efficiency, the efficient use of the energy is also important. This paper focused on the development of devices for the reducing electricity which is a primary energy source used in homes, shops, buildings, factories and so on. Also the objective of this paper is to develop the inference mechanism as the core component of the devices. Therefore, in this paper, we propose the inference algorithm for reducing the electricity consumption using SARIMA mode and present the feasibility of the procedure.

A DATA COMPRESSION METHOD USING ADAPTIVE BINARY ARITHMETIC CODING AND FUZZY LOGIC

  • Jou, Jer-Min;Chen, Pei-Yin
    • 한국지능시스템학회:학술대회논문집
    • /
    • 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
    • /
    • pp.756-761
    • /
    • 1998
  • This paper describes an in-line lossless data compression method using adaptive binary arithmetic coding. To achieve better compression efficiency , we employ an adaptive fuzzy -tuning modeler, which uses fuzzy inference to deal with the problem of conditional probability estimation. The design is simple, fast and suitable for VLSI implementation because we adopt the table -look-up approach. As compared with the out-comes of other lossless coding schemes, our results are good and satisfactory for various types of source data.

  • PDF

실내공간의 이미지 표현에 있어서 자연성 적용에 관한 연구 (A Study on the Application of Natural Characteristics in Image Expression of interior Design)

  • 나인영
    • 한국실내디자인학회논문집
    • /
    • 제17호
    • /
    • pp.52-59
    • /
    • 1998
  • In the modern ages when the surroundings of a city has become firm and monotonous this study designed to suggest an direction towards creative approaches to space planning by analyzing the images of interior space with the introduction of natural expressions as an alternative to create original space in order to give vitality to the previous standardized space and to satisfy human beings psychological desire. The results of the analysis as a way of expressing direct indirect and eclectic images using nature a source of arts read that most of the natural expressions show perceptive images strongly that natural elements can become the elements of design in any form and that nature's images are expressed by not only natural and artificial materials. In conclusion natural expression in interior space does not have any fixed form of expression but gives a great deal of vocabulary to the image formation of interior space by stimulating being's sentiment with the spatial restructure of nature's own particular order of form.

  • PDF

조명디자인 교육연구 (A Study on Lighting Design Education)

  • 안희영
    • 한국실내디자인학회논문집
    • /
    • 제17호
    • /
    • pp.128-135
    • /
    • 1998
  • The first issue was concerning the subject to provide students with an understanding of the principle of light its concept mental factors etc and with the observation and analysis of the light of an object and its form which is the process for designers to be able to deal with the deeper design concept by complementing the setting of necessary concept. The second issue was concerning the process of basic learning about basic electricity and lighting that lighting designers or interior decoration and architecture designer should have such as the introduction of light in kind of light source lighting system and so forth. The third issue was focused on practical affairs such as design and expression techniques the calculation of illumination using the computer simulation and so on. In addition such issues as the history of lighting photograph and its linkage with the field of engineering about new material ware addressed.

  • PDF

모르터와 콘크리트의 균열검출을 위한 음향방출기법의 적용 (Application of Acoustic Emission Technique for Detection of Crack in Mortar and Concrete)

  • 진치섭;신동익;장종철
    • 한국콘크리트학회:학술대회논문집
    • /
    • 한국콘크리트학회 2000년도 가을 학술발표회논문집(I)
    • /
    • pp.739-744
    • /
    • 2000
  • Concrete structures generally have cracks, so for the safety and durability of structures, studies to detect cracks using nondestructive tests have been treated in great deal. In order to assure the reliability of concrete structure, microscopic fracture behavior and internal damage progress of concrete under the loading should be fully understood. The purpose of this study predicts location of initial crack and measures direction of crack propagation for on-line monitoring before the crack really grows in structures by using two-dimensional Acoustic Emission(AE) source location based on rectangular method with three-point bending test. This will allow efficient maintenance of concrete structure through monitoring of internal cracking based on AE method.

  • PDF

전문가 시스템에서의 system matrix를 이용한 정전 및 비정전구간 인식 (The Recognition of Energized & Deenergized System Using System Matrix in Expert system)

  • 함완균;추진부;김건중;심국진;조한형
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1989년도 하계종합학술대회 논문집
    • /
    • pp.237-240
    • /
    • 1989
  • This paper deals with the expert system for power system recognition of energized and deenergized system using circuit breaker information. The basic idea is isolating the system with the system matrix representing the system configuration and the states of the circuit breakers. The knowledge base is composed of these isolated systems and decision rules. The isolated system with the sources is recognized as the energized system and the system without the source as the deenergized system. The rules use the system matrix and the the inference scheme is simplified in a great deal. Above all, the overall searching labor of the rules is independent on the system size and it is possible to expand into the real system and the real time restoration can be carried out easily. The expert system is written in PROLOG.

  • PDF

미활용에너지의 열 포텐셜 평가 수법에 관한 연구 (Study on Evaluation Method of Thermal Potential of Unused Energy)

  • 정용현
    • 한국환경과학회지
    • /
    • 제15권5호
    • /
    • pp.493-501
    • /
    • 2006
  • The increase in environmental loads and energy consumptions has resulted in the need of developed new forms of energy for a sustainable use for the society. Recently, the viability of using unused energy has attracted a great deal of attention. From the view point of using unused energy, the most critical problem can be referred to as the distance between the heat source/sink and heat demand area. The water resource in the city water system was used to solve this distance problem with unused energy. The calculation method of the potential use unit was used to survey the potential of the water resource in the city water system. The amount of theoretical unused energy and energy savings in the model city were estimated using this method. It is estimated that the amounts of energy savings and $CO_2$ reduction correspond to 131.3 GWh and 29280[t-C], respectively, per annual basis.