• 제목/요약/키워드: Composition Algorithm

검색결과 280건 처리시간 0.023초

하이퍼스펙트럴 영상의 무감독 변화탐지를 위한 SSS 알고리즘과 기대최대화 기법의 적용 (The Application of the Spectral Similarity Scale Algorithm and Expectation-Maximization for Unsupervised Change Detection using Hyperspectral Image)

  • 김용현;김대성;김용일;유기윤
    • 한국공간정보시스템학회:학술대회논문집
    • /
    • 한국공간정보시스템학회 2007년도 GIS 공동춘계학술대회 논문집
    • /
    • pp.139-144
    • /
    • 2007
  • Recording data in hundreds of narrow contiguous spectral intervals, hyperspectral images have provided the opportunity to detect small differences in material composition. But a limitation of a hyperspectral image is the signal to noise ratio (SNR) lower than that of a multispectral image. This paper presents the efficiency of Spectral Similarity Scale (SSS) in change detection of hyperspectral image and the experiment was performed with Hyperion data. SSS is an algorithm that objectively quantifies differences between reflectance spectra in both magnitude and direction dimensions. The thresholds for detecting the change area were determined through Expectation-Maximization (EM) algorithm. The experimental result shows that the SSS algorithm and EM algorithm are efficient enough to be applied to the unsupervised change detection of hyperspectral images.

  • PDF

무인차량의 주행성능을 고려한 장애물 격자지도 기반의 지역경로계획 (A Local Path Planning Algorithm considering the Mobility of UGV based on the Binary Map)

  • 이영일;이호주;고정호
    • 한국군사과학기술학회지
    • /
    • 제13권2호
    • /
    • pp.171-179
    • /
    • 2010
  • A fundamental technology of UGV(Unmanned Ground Vehicle) to perform a given mission with success in various environment is a path planning method which generates a safe and optimal path to the goal. In this paper, we suggest a local path-planning method of UGV based on the binary map using world model data which is gathered from terrain perception sensors. In specially, we present three core algorithms such as shortest path computation algorithm, path optimization algorithm and path smoothing algorithm those are used in the each composition module of LPP component. A simulation is conducted with M&S(Modeling & Simulation) system in order to verify the performance of each core algorithm and the performance of LPP component with scenarios.

예측알고리즘 적용을 위한 데이터세트 구성이 근적외선 분광광도계를 이용한 옥수수 품질평가에 미치는 영향 (The Effect of Representative Dataset Selection on Prediction of Chemical Composition for Corn kernel by Near-Infrared Reflectance Spectroscopy)

  • 최성원;이창석;박창희;김동희;박성권;김법균;문상호
    • 한국축산시설환경학회지
    • /
    • 제20권3호
    • /
    • pp.117-124
    • /
    • 2014
  • The objectives were to assess the use of near-infrared reflectance spectroscopy (NIRS) as a tool for estimating nutrient compositions of corn kernel, and to apply an NIRS-based indium gallium arsenide array detector to the system for collecting spectra and analyzing calibration equations using equipments designed for field application. Partial Least Squares Regression (PLSR) was employed to develop calibration equations based on representative data sets. The kennard-stone algorithm was applied to induce a calibration set and a validation set. As a result, the method for structuring a calibration set significantly affected prediction accuracy. The prediction of chemical composition of corn kernel resulted in the following (kennard-stone algorithm: relative) moisture ($R^2=0.82$, RMSEP=0.183), crude protein ($R^2=0.80$, RMSEP=0.142), crude fat ($R^2=0.84$, RMSEP=0.098), crude fiber ($R^2=0.74$, RMSEP=0.098), and crude ash ($R^2=0.81$, RMSEP=0.048). Result of this experiment showed the potential of NIRS to predict the chemical composition of corn kernel.

사례 기반 추론을 이용한 서비스 컴포지션 연구 (A Study on Service Composition Using Case-Based Reasoning)

  • 김건수;이동훈;박두경;이지형
    • 한국지능시스템학회논문지
    • /
    • 제18권2호
    • /
    • pp.175-182
    • /
    • 2008
  • 웹서비스와 상황인식서비스는 사용자의 요구에 따라 많은 종류의 서비스를 제공할 수 있어야 한다. 사용자의 요구는 날로 다양해지고 있고 그에 발맞추어 다양한 종류의 서비스들이 서비스 제공 업체에 의해 새롭게 시장에 등장하고 있다. 하지만 사용자의 새로운 요청에 맞추어 새로운 서비스를 생산하거나 일부 사용자의 요구 때문에 새로운 서비스를 만드는 것은 비효율적이다. 그래서 최근에는 유저의 다양한 요청에 보다 유연하게 대응할 수 있는 기술들에 대한 연구가 이루어지고 있다. 그 중 단일 서비스의 조합을 통해 복합서비스를 제공할 수 있는 서비스 컴포지션이라는 기술이 주목을 받고 있다. 하지만, 기존 연구들은 다소 늦은 처리속도로 인해 빠른 응답이 필요한 실시간 상황인식서비스에는 부적합하다. 그래서 본 논문은 사례기반추론을 이용하여 기존 방법보다 빠른 서비스 컴포지션을 구현하는 방법을 제안한다. 그리고 제안하는 알고리즘을 검증하기 위해 사용자에게 이동서비스와 구매정보서비스를 이용하여 사용자의 이동 및 구매 요구를 만족하는 조합을 찾아주는 물건 구매 서비스 서비스를 구현하고 이 구현된 물건 구매 도우미 서비스에 제안하는 알고리즘과 기존 서비스 컴포지션 기법을 적용하여 각 알고리즘의 성능을 비교분석 한다.

Neural Network Modeling of PECVD SiN Films and Its Optimization Using Genetic Algorithms

  • Han, Seung-Soo
    • International Journal of Fuzzy Logic and Intelligent Systems
    • /
    • 제1권1호
    • /
    • pp.87-94
    • /
    • 2001
  • Silicon nitride films grown by plasma-enhanced chemical vapor deposition (PECVD) are useful for a variety of applications, including anti-reflecting coatings in solar cells, passivation layers, dielectric layers in metal/insulator structures, and diffusion masks. PECVD systems are controlled by many operating variables, including RF power, pressure, gas flow rate, reactant composition, and substrate temperature. The wide variety of processing conditions, as well as the complex nature of particle dynamics within a plasma, makes tailoring SiN film properties very challenging, since it is difficult to determine the exact relationship between desired film properties and controllable deposition conditions. In this study, SiN PECVD modeling using optimized neural networks has been investigated. The deposition of SiN was characterized via a central composite experimental design, and data from this experiment was used to train and optimize feed-forward neural networks using the back-propagation algorithm. From these neural process models, the effect of deposition conditions on film properties has been studied. A recipe synthesis (optimization) procedure was then performed using the optimized neural network models to generate the necessary deposition conditions to obtain several novel film qualities including high charge density and long lifetime. This optimization procedure utilized genetic algorithms, hybrid combinations of genetic algorithm and Powells algorithm, and hybrid combinations of genetic algorithm and simplex algorithm. Recipes predicted by these techniques were verified by experiment, and the performance of each optimization method are compared. It was found that the hybrid combinations of genetic algorithm and simplex algorithm generated recipes produced films of superior quality.

  • PDF

Effective Design of Inference Rule for Shape Classification

  • Kim, Yoon-Ho;Lee, Sang-Sock;Lee, Joo-Shin
    • 한국지능시스템학회:학술대회논문집
    • /
    • 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
    • /
    • pp.417-422
    • /
    • 1998
  • This paper presents a method of object classification from dynamic image based on fuzzy inference algorithm which is suitable for low speed such as, conveyor, uninhabited transportation. At first, by using feature parameters of moving object, fuzzy if - then rule that can be able to adapt the wide variety of surroundings is developed. Secondly, implication function for fuzzy inference are compared with respect the proposed algorithm. Simulation results are presented to testify the performance and applicability of the proposed system.

  • PDF

가변구성비 추정기법과 이를 이용한 무효전력 축약모델의 오차보정기법 개발 (Estimation Method of Variable Composition Rate and Error Compensation Method of Aggregative Model for Reactive Power by Variable Composition Rate)

  • 이대종;이종필;임재윤;지평식
    • 전기학회논문지P
    • /
    • 제60권4호
    • /
    • pp.186-192
    • /
    • 2011
  • Recently, due to the expansion of electric power demands, nonlinear load such as converters and inverters connected to the electric power distribution system, and extensive application of harmonic generation sources with power electric devices, disturbance of the electric power system and its influences on industries have been continuously increasing. In this research, we develop a novel aggregation algorithm by considering the harmonics characteristics for residential loads. Using data sets acquired from various experiments, we analyzed load characteristics according to harmonics and presented the results obtained the proposed method.

내장형 소프트웨어 컴포넌트의 상향식 합성과 검증 (Bottom-up Composition and Verification of Embedded Software)

  • 최윤자
    • 정보처리학회논문지D
    • /
    • 제17D권6호
    • /
    • pp.415-422
    • /
    • 2010
  • 본 논문은 단위 컴포넌트가 제공하는 서비스를 중심으로 컴포넌트 행위모델을 합성하고 상위수준의 추상적 행위모델을 추출하는 서비스기반 합성과 검증기법을 제안한다. 이를 위하여, 상향식 행위양식 추상화의 기초가 되는 추상 컴포넌트를 정의하고, 포트기반 동기화 알고리즘과 서비스기반 투영을 통한 추상화기법을 제안하였다. 또한, 제안된 기법을 적용한 모델검증 프레임워크를 개발하고, 사례연구를 통하여 제안된 방식이 검증비용을 절감함을 입증하였다.

Identification and Determination of Oil Pollutants Based on 3-D Fluorescence Spectrum Combined with Self-weighted Alternating Trilinear Decomposition Algorithm

  • Cheng, Pengfei;Wang, Yutian;Chen, Zhikun;Yang, Zhe
    • Journal of the Optical Society of Korea
    • /
    • 제20권1호
    • /
    • pp.204-211
    • /
    • 2016
  • Oil pollution seriously endangers the biological environment and human health. Due to the diversity of oils and the complexity of oil composition, it is of great significance to identify the oil contaminants. The 3-D fluorescence spectrum combined with a second order correction algorithm was adopted to measure an oil mixture with overlapped fluorescence spectra. The self-weighted alternating trilinear decomposition (SWATLD) is a kind of second order correction, which has developed rapidly in recent years. Micellar solutions of #0 diesel, #93 gasoline and ordinary kerosene in different concentrations were made up. The 3-D fluorescence spectra of the mixed oil solutions were measured by a FLS920 fluorescence spectrometer. The SWATLD algorithm was applied to decompose the spectrum data. The predict concentration and recovery rate obtained by the experiment show that the SWATLD algorithm has advantages of insensitivity to component number and high resolution for mixed oils.

문서화상에 대한 차분부호장 혼합 합성 알고리즘 (A Study On Runlength Distance Mixing Algorithm For Document Image)

  • 박일남
    • 정보학연구
    • /
    • 제5권1호
    • /
    • pp.1-12
    • /
    • 2002
  • 본 논문에서는 문서화상에 대한 차분 부호장 혼합 알고리즘을 제안한다. 본 알고리즘을 사용할 경우 RL과 DM 알고리즘에 비해 동일 문서에 2배의 정보를 합성할 수 있다. 본 알고리즘을 사용할 경우 비 보안 문서상에 디지털 서명 뿐 아니라 보안 문서도 합성 가능하다. 이 경우 제 3자가 보안 전송 사실을 감지 할 수 없어 문서의 보안 전송이 구현된다.

  • PDF