• 제목/요약/키워드: generating function method

검색결과 308건 처리시간 0.034초

HMM을 기반으로 한 자율이동로봇의 음성명령 인식시스템의 개발 (Development of Autonomous Mobile Robot with Speech Teaching Command Recognition System Based on Hidden Markov Model)

  • 조현수;박민규;이현정;이민철
    • 제어로봇시스템학회논문지
    • /
    • 제13권8호
    • /
    • pp.726-734
    • /
    • 2007
  • Generally, a mobile robot is moved by original input programs. However, it is very hard for a non-expert to change the program generating the moving path of a mobile robot, because he doesn't know almost the teaching command and operating method for driving the robot. Therefore, the teaching method with speech command for a handicapped person without hands or a non-expert without an expert knowledge to generate the path is required gradually. In this study, for easily teaching the moving path of the autonomous mobile robot, the autonomous mobile robot with the function of speech recognition is developed. The use of human voice as the teaching method provides more convenient user-interface for mobile robot. To implement the teaching function, the designed robot system is composed of three separated control modules, which are speech preprocessing module, DC servo motor control module, and main control module. In this study, we design and implement a speaker dependent isolated word recognition system for creating moving path of an autonomous mobile robot in the unknown environment. The system uses word-level Hidden Markov Models(HMM) for designated command vocabularies to control a mobile robot, and it has postprocessing by neural network according to the condition based on confidence score. As the spectral analysis method, we use a filter-bank analysis model to extract of features of the voice. The proposed word recognition system is tested using 33 Korean words for control of the mobile robot navigation, and we also evaluate the performance of navigation of a mobile robot using only voice command.

사건중심 뉴스기사 자동요약을 위한 사건탐지 기법에 관한 연구 (A Study on an Effective Event Detection Method for Event-Focused News Summarization)

  • 정영미;김용광
    • 정보관리학회지
    • /
    • 제25권4호
    • /
    • pp.227-243
    • /
    • 2008
  • 이 연구에서는 사건중심 뉴스기사 요약문을 자동생성하기 위해 뉴스기사들을 SVM 분류기를 이용하여 사건 주제범주로 먼저 분류한 후, 각 주제범주 내에서 싱글패스 클러스터링 알고리즘을 통해 특정한 사건 관련 기사들을 탐지하는 기법을 제안하였다. 사건탐지 성능을 높이기 위해 고유명사에 가중치를 부여하고, 뉴스의 발생시간을 고려한 시간벌점함수를 제안하였다. 또한 일정 규모 이상의 클러스터를 분할하여 적절한 크기의 사건 클러스터를 생성하도록 수정된 싱글패스 알고리즘을 사용하였다. 이 연구에서 제안한 사건탐지 기법의 성능은 단순 싱글패스 클러스터링 기법에 비해 정확률, 재현율, F-척도에서 각각 37.1%, 0.1%, 35.4%의 성능 향상률을 보였고, 오보율과 탐지비용에서는 각각 74.7%, 11.3%의 향상률을 나타냈다.

누가차분법을 통한 가뭄 빈도유입량 산정에 관한 이론적 고찰 (Theoretical analysis of quantification of drought frequency inflow series via K-water cumulative difference method)

  • 김지흔;이재황;김영오
    • 한국수자원학회논문집
    • /
    • 제55권9호
    • /
    • pp.701-705
    • /
    • 2022
  • 이상기후로 가뭄이 빈번해짐에 따라 수자원 시설의 가뭄대응력 산정에 대한 필요성이 커지고 있다. 이를 위해서는 신뢰할 수 있는 갈수빈도 유입량 추정 연구가 선행되어야 한다. 본 연구는 기존 K-water의 가뭄 빈도유입량 추정방법인 누가차분법의 세 가지 한계, 즉 음의 값과 역전현상, 그리고 평년 이상으로 과대 산정되는 문제의 발생조건에 대해 각각 2변수 log-normal 분포와 Gumbel 분포를 적용하여 이론적 고찰을 실시하였다. 그 결과, 음의 값은 누가 과정에서 scale parameter보다 location parameter의 변화가 커지는 경우 발생함을 확인하였고, 역전현상 및 평년보다 큰 가뭄유입량은 누가 과정에서 표준편차가 감소하는 경우 발생하는 것으로 분석되었다.

KOMPSAT-2 MSC 전처리시스템을 위한 RPC(Rational Polynomial Coefficient)생성 기법에 관한 연구 (A Study on the Method of Generating RPC for KOMPSAT-2 MSC Pre-Processing System)

  • 서두천;임효숙
    • 한국측량학회:학술대회논문집
    • /
    • 한국측량학회 2003년도 추계학술발표회 논문집
    • /
    • pp.417-422
    • /
    • 2003
  • The KOMPSAT-2 MSC(Multi-Spectral Camera), with high spatial resolution, is currently under development and will be launched in the end of 2004. A sensor model relates a 3-D ground position to the corresponding 2-D image position and describes the imaging geometry that is necessary to reconstruct the physical imaging process. The Rational Function Model (RFM) has been considered as a generic sensor model. form. The RFM is technically applicable to all types of sensors such as frame, pushbroom, whiskbroom and SAR etc. With the increasing availability of the new generation imaging sensors, accurate and fast rectification of digital imagery using a generic sensor model becomes of great interest to the user community. This paper describes the procedure to generation of the RPC (Rational Polynomial Coefficients) for KOMPSAT-2 MSC.

  • PDF

소음 저감을위한 피치 배열에 관한 연구 (A study on the Pitch Array for reducing Noise)

  • 추권철;최승일;이홍진
    • 한국소음진동공학회:학술대회논문집
    • /
    • 한국소음진동공학회 2009년도 추계학술대회 논문집
    • /
    • pp.575-577
    • /
    • 2009
  • Traditionally, tire made a role of function, which is supporting vehicle load, making brake, transferring, traction etc. So, there are a lot of studying for the tire. especially, tire noise is one of the most important parameter in the car noise. this thesis shows the method how to reduce the tire noise by using the optimal pitch sequence. Because the optimal pitch sequence prevents tire from generating the pure tone while driving the car on the ground.

  • PDF

선수부 선체형상 모델링을 위한 스키닝 연구 (Skinning for Ship Forebody Modeling)

  • 정형배;김찬석
    • 대한조선학회논문집
    • /
    • 제43권3호
    • /
    • pp.375-383
    • /
    • 2006
  • This paper presents NURBS skinning for the forebody of ship. NURBS skinning is guessed as a good method to generate the faired surface of ship forebody, but it is very problematic in real ship design to generate resonable surface of ship forbody using skinning, because there are lot of problem to apply skinning and to get reasonable surface. One of main problem is data arrangement with design data. Irregular serial contour data arise so serious compatibility problem of knot vector This paper suggests a whole process using skinning successfully in generating hull form of ship forebody This process includes how to make the data set for skinning and how to execute compatibility procedure.

A Matrix Method for the Analysis of Two - Dimensional Markovian Queues

  • Kim, Sung-Shick
    • 대한산업공학회지
    • /
    • 제8권2호
    • /
    • pp.15-21
    • /
    • 1982
  • This paper offers an alternative to the common probability generating function approach to the solution of steady state equations when a Markovian queue has a multivariate state space. Identifying states and substates and grouping them into vectors appropriately, we formulate a two - dimensional Markovian queue as a Markov chain. Solving the resulting matrix equations the transition point steady state probabilities (SSPs) are obtained. These are then converted into arbitrary time SSPs. The procedure uses only probabilistic arguments and thus avoids a large and cumbersome state space which often poses difficulties in the solution of steady state equations. For the purpose of numerical illustration of the approach we solve a Markovian queue with one server and two classes of customers.

  • PDF

FINITE ELEMENT ANALYSIS FOR DISCONTINUOUS MAPPED HEXA MESH MODEL WITH IMPROVED MOVING LEAST SQUARES SCHEME

  • Tezuka, Akira;Oishi, Chihiro;Asano, Naoki
    • 한국시뮬레이션학회:학술대회논문집
    • /
    • 한국시뮬레이션학회 2001년도 The Seoul International Simulation Conference
    • /
    • pp.373-379
    • /
    • 2001
  • There is a big issue to generate 3D hexahedral finite element (FE) model, since a process to divide the whole domain into several simple-shaped sub-domains is required before generating a continuous mesh with mapped mesh generators. In general, it is nearly impossible to set up proper division numbers interactively to keep mesh connectivity between sub-domains on a complicated arbitrary-shaped domain. If mesh continuity between sub-domains is not required in an analysis, this complicated process can be omitted. Element-free Galerkin method (EFGM) can accept discontinuous meshes, which only requires nodal information. However it is difficult to choose a reasonable influenced domain in moving least squares scheme with non-uniformly distributed nodes in discontinuous FE models. A new FE scheme fur discontinuous mesh is proposed in this paper by applying improved EFGM with some modification to derive FE approximated function in discontinuous parts. Its validity is evaluated on linear elastic problems.

  • PDF

결정 다이아그램에 의한 다치조합논리시스템 구성에 관한 연구 (A Study on Constructing the Multiple-Valued Combinational Logic Systems by Decision Diagram)

  • 김이한;김성대
    • 전자공학회논문지B
    • /
    • 제32B권6호
    • /
    • pp.868-875
    • /
    • 1995
  • This paper presents a method of constructing the multiple-valued combinational logic systems(MVCLS) by decision diagram. The switching function truth table of MVCLS is transformed into canonical normal form of sum-of-products(SOP) with literals at first. Next, the canonical normal form of SOP is transfered into multiple-valued logic decision diagram(MVLDD). The selecting of variable ordering is very important in this stage. The MVLDDs are quite different from each other according to the variable ordering. Sometimes the inadequate variable ordering produces a very large size of MVLDD means the large size of circuit implementation. An algorithm for generating the proper variable ordering produce minimal MVLDD and an example shows the verity of the algorithm. The circuits are realized with T-gate acceording to the minimal MVLDD.

  • PDF

Procedure of drawing fragility curve as a function of material parameters

  • 김장호;이정;박정호;홍종석
    • 한국콘크리트학회:학술대회논문집
    • /
    • 한국콘크리트학회 2006년도 춘계학술발표회 논문집(I)
    • /
    • pp.334-337
    • /
    • 2006
  • Generally, fragility curve has been used in predicting failure of structures due to seismic actions. In this research, the method of drawing fragility curve has been applied to evaluating success/failure of structures and satisfactory/unsatisfactory of concrete mixture performance based on material parameters. In the paper, a detailed explanation of the procedure of drawing fragility curve based on material parameter has been introduced. Fragility curve generating procedure includes generation of virtual data points from limited number of actual data points by bell curve implementation, determination of success/failure status of each data point by assigned criterion, and completion of final fragility curve. For practical applications, workability of concrete mixture content based on "unit water" has been used to obtain fragility curve. Detailed explanation of fragility curve drawing procedure for material parameters is presented.

  • PDF