• 제목/요약/키워드: sub-goal algorithm

검색결과 32건 처리시간 0.031초

Levenberg-Marquardt 인공신경망 알고리즘을 이용한 지반공학문제의 적용성 검토 (Application of Artificial Neural Network with Levenberg-Marquardt Algorithm in Geotechnical Engineering Problem)

  • 김영수;이재호;서인식;김현동;신지섭;나윤영
    • 한국지반공학회:학술대회논문집
    • /
    • 한국지반공학회 2008년도 춘계 학술발표회 초청강연 및 논문집
    • /
    • pp.987-997
    • /
    • 2008
  • Successful design, construction and maintenance of geotechnical structure in soft ground and marine clay demands prediction, control, stability estimation and monitoring of settlement with high accuracy. It is important to predict and to estimate the compression index of soil for predicting of ground settlement. Lab. and field tests have been and are indispensable tools to achieve this goal. In this paper, Artificial Neural Networks (ANNs) model with Levenberg-Marquardt Algorithm and field database were used to predict compression index of soil in Korea. Based on soil property database obtained from more than 1800 consolidation tests from soils samples, the ANNs model were proposed in this study to estimate the compression index, using multiple soil properties. The compression index from the proposed ANN models including multiple soil parameters were then compared with those from the existing empirical equations.

  • PDF

RIS Selection and Energy Efficiency Optimization for Irregular Distributed RIS-assisted Communication Systems

  • Xu Fangmin;Fu Jinzhao;Cao HaiYan;Hu ZhiRui
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제17권7호
    • /
    • pp.1823-1840
    • /
    • 2023
  • In order to improve spectral efficiency and reduce power consumption for reconfigurable intelligent surface (RIS) assisted wireless communication systems, a joint design considering irregular RIS topology, RIS on-off switch, power allocation and phase adjustment is investigated in this paper. Firstly, a multi-dimensional variable joint optimization problem is established under multiple constraints, such as the minimum data requirement and power constraints, with the goal of maximizing the system energy efficiency. However, the proposed optimization problem is hard to be resolved due to its property of nonlinear nonconvex integer programming. Then, to tackle this issue, the problem is decomposed into four sub-problems: topology design, phase shift adjustment, power allocation and switch selection. In terms of topology design, Tabu search algorithm is introduced to select the components that play the main role. For RIS switch selection, greedy algorithm is used to turn off the RISs that play the secondary role. Finally, an iterative optimization algorithm with high data-rate and low power consumption is proposed. The simulation results show that the performance of the irregular RIS aided system with topology design and RIS selection is better than that of the fixed topology and the fix number of RISs. In addition, the proposed joint optimization algorithm can effectively improve the data rate and energy efficiency by changing the propagation environment.

스포츠 중계 방송의 구조적 특성을 이용한 축구동영상 하이라이트 생성 알고리즘 (Soccer Video Highlight Building Algorithm using Structural Characteristics of Broadcasted Sports Video)

  • 김재홍;낭종호;하명환;정병희;김경수
    • 한국정보과학회논문지:소프트웨어및응용
    • /
    • 제30권7_8호
    • /
    • pp.727-743
    • /
    • 2003
  • 본 논문에서는 축구 동영상에서 스포츠 중계방송의 구조적 특성을 이용하여 자동적으로 하이라이트(Highlight)를 추출하는 새로운 방법을 제안하고 실험을 통하여 그 유용성을 증명한다. 일반적으로 스포츠 중계 방송에서는 중요한 이벤트(골, 반칙)가 발생하면, 그 장면을 다시 느린 속도의 리플레이(Replay) 화면으로 보여주고, 리플레이가 시작되고 끝날 때 Wipe와 같은 점진적인 화면 전환 기법을 사용하는 구조적 특성을 가지고 있다. 본 논문에서는 이러한 스포츠 중계방송의 구조적 특징을 이용하여 축구동 상의 중요한 이벤트만을 추출하여 하이라이트를 생성하는 방법을 제안한다. 이를 위해 본 논문에서는 비디오의 슬라이스 이미지(Slice Image)를 이용하여 Wipe효과 장면과 줌인/아웃 장면을 검출하고, 검출된 Wipe 효과 지점을 기준으로 하여 리플레이 장면을 검출한다. 이때 이런 기본 알고리즘에 새로이 Sub-Sampling방법과 Two-Pass 방법을 더하여 보다 빠르고 정확한 Wipe검출을 하였고, 비디오의 모션 정보 및 Wipe지점의 시간간격을 이용하여 보다 정화한 리플레이 장면을 검출하였으며, 샷의 녹색영역 비율을 측정하여 보다 정화한 줌인/아웃 장면을 검출하였다. 이렇게 최종적으로 검출된 리플레이 장면과 줌인/아웃 장면을 토대로 이벤트 샷(Shot)과 선수 샷으로 구성된 하이라이트 장면을 추출하게 된다. 이러한 방법은 자동적으로 축구 중계방송을 요약해줌으로써 축구와 관련된 웹서비스나 방송용 하이라이트 제작에 유용하게 사용될 수 있을 것이다.

DESIGN AND ANALYSIS FOR THE SPECIAL SERIAL MANIPULATOR

  • Kim, Woo-Sub;Park, Jae-Hong;Kim, Jung-Ha
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 2004년도 ICCAS
    • /
    • pp.1396-1401
    • /
    • 2004
  • In recent years, robot has been used widely in industrial field and has been expanded as a result of continous research and development for high-speed and miniaturization. The goal of this paper is to design the special serial manipulator through the understanding of the structure, mobility, and analysis of serial manipulator. Thereafter we control the position and orientation of end-effector with respect to time. In general, a structure of industrial robot consists of several links connected in series by various types of joints. Typically revolute and prismatic joints. The movement of these joints is determined in inverse kinematic analysis. Compared to the complicated structure of parallel and hybrid robot, open loop system retains the characteristic that each link is independent and is controlled easily by AC servomotor that is used to place the robot end-effector toward the accurate point with the desired speed and power while it is operated by position control algorithm. The robot end-effector should trace the given trajectory within the appropriate time. The trajectory of 3D end-effector model made by OpenGL can be displayed on the monitor program simultaneously

  • PDF

Automated Feature-Based Registration for Reverse Engineering of Human Models

  • Jun, Yong-Tae;Choi, Kui-Won
    • Journal of Mechanical Science and Technology
    • /
    • 제19권12호
    • /
    • pp.2213-2223
    • /
    • 2005
  • In order to reconstruct a full 3D human model in reverse engineering (RE), a 3D scanner needs to be placed arbitrarily around the target model to capture all part of the scanned surface. Then, acquired multiple scans must be registered and merged since each scanned data set taken from different position is just given in its own local co-ordinate system. The goal of the registration is to create a single model by aligning all individual scans. It usually consists of two sub-steps: rough and fine registration. The fine registration process can only be performed after an initial position is approximated through the rough registration. Hence an automated rough registration process is crucial to realize a completely automatic RE system. In this paper an automated rough registration method for aligning multiple scans of complex human face is presented. The proposed method automatically aligns the meshes of different scans with the information of features that are extracted from the estimated principal curvatures of triangular meshes of the human face. Then the roughly aligned scanned data sets are further precisely enhanced with a fine registration step with the recently popular Iterative Closest Point (ICP) algorithm. Some typical examples are presented and discussed to validate the proposed system.

Tree-Pattern-Based Clone Detection with High Precision and Recall

  • Lee, Hyo-Sub;Choi, Myung-Ryul;Doh, Kyung-Goo
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제12권5호
    • /
    • pp.1932-1950
    • /
    • 2018
  • The paper proposes a code-clone detection method that gives the highest possible precision and recall, without giving much attention to efficiency and scalability. The goal is to automatically create a reliable reference corpus that can be used as a basis for evaluating the precision and recall of clone detection tools. The algorithm takes an abstract-syntax-tree representation of source code and thoroughly examines every possible pair of all duplicate tree patterns in the tree, while avoiding unnecessary and duplicated comparisons wherever possible. The largest possible duplicate patterns are then collected in the set of pattern clusters that are used to identify code clones. The method is implemented and evaluated for a standard set of open-source Java applications. The experimental result shows very high precision and recall. False-negative clones missed by our method are all non-contiguous clones. Finally, the concept of neighbor patterns, which can be used to improve recall by detecting non-contiguous clones and intertwined clones, is proposed.

Advanced Navigation Technology Development Trend as an Unmanned Vehicle Core Technology

  • Seok, Hyo-Jeong;Hwang, In Seong;Kang, Wanggu
    • Journal of Positioning, Navigation, and Timing
    • /
    • 제10권4호
    • /
    • pp.235-242
    • /
    • 2021
  • Unmanned Aerial Vehicles (UAVs), which were used for military purposes, are gradually expanding their application fields under the influence of electrification and digitalization. Starting from the field of aerial imaging and Intelligence Surveillance and Reconnaissance (ISR) mission, nowadays the possibility of Urban Air Mobility (UAM), which transports passengers and cargo with drones, is widely under discussion. In order to occupy the rapidly growing global unmanned aerial vehicle market in advance, it is necessary to secure core technologies and develop key UAVs components based on the new technologies. In the navigation field, it is necessary to secure a precise position with guaranteed reliability and continuity, unrelated to the operating environments. The reliability and continuity should be secured in the algorithm level and in the H/W component levels also. In order to achieve this technical goal, the Ministry of Science and ICT has launched the 'Unmanned Vehicle Core Technology Research and Development Program' in 2019 to support the R&D on the unmanned vehicle technologies. In this paper, authors introduce the unmanned vehicle core technology research and development program to the related researchers. The authors summarize the backgrounds of the program and show the technological tasks and objectives on the sub-programs in the unmanned vehicle navigation program. We present the program schedules especially focused on the test and evaluation of the developed technologies and components.

LDPC를 이용한 예측 기반 워터마킹 알고리듬 (Estimation-based Watermarking Algorithm with Low Density Parity Check (LDPC) Codes)

  • 임재혁;원치선
    • 대한전자공학회논문지SP
    • /
    • 제44권1호
    • /
    • pp.76-84
    • /
    • 2007
  • 본 논문에서는 워터마크 예측과 LDPC 코드를 이용하여 워터마크의 성능을 향상시키는 알고리듬을 제안한다. 워터마크 추출의 경우 삽입된 워터마크의 파워(power)가 원본 영상의 파워에 비해 아주 작기 때문에 워터마크의 추출 성능을 높이기 위해서는 워터마크의 예측이 필수적이다. 본 논문에서는 웨이블릿 영역에서 잡음 제거 필터를 사용하여 워터마크의 예측을 수행하였다. 이렇게 예측된 워터마크에 에러가 발생할 경우 LDPC 코드를 사용하여 수정하였다. 에러 수정 시 삽입된 워터마크의 통계적인 특성을 사용하여 기존의 LDPC 코드의 성능보다 우수한 실험 결과를 도출하였다.

Endpoint Detection in Semiconductor Etch Process Using OPM Sensor

  • Arshad, Zeeshan;Choi, Somang;Jang, Boen;Hong, Sang Jeen
    • 한국진공학회:학술대회논문집
    • /
    • 한국진공학회 2014년도 제46회 동계 정기학술대회 초록집
    • /
    • pp.237.1-237.1
    • /
    • 2014
  • Etching is one of the most important steps in semiconductor manufacturing. In etch process control a critical task is to stop the etch process when the layer to be etched has been removed. If the etch process is allowed to continue beyond this time, the material gets over-etched and the lower layer is partially removed. On the other hand if the etch process is stopped too early, part of the layer to be etched still remains, called under-etched. Endpoint detection (EPD) is used to detect the most accurate time to stop the etch process in order to avoid over or under etch. The goal of this research is to develop a hardware and software system for EPD. The hardware consists of an Optical Plasma Monitor (OPM) sensor which is used to continuously monitor the plasma optical emission intensity during the etch process. The OPM software was developed to acquire and analyze the data to perform EPD. Our EPD algorithm is based on the following theory. As the etch process starts the plasma generated in the vacuum is added with the by-products from the etch reactions on the layer being etched. As the endpoint reaches and the layer gets completely removed the plasma constituents change gradually changing the optical intensity of the plasma. Although the change in optical intensity is not apparent, the difference in the plasma constituents when the endpoint has reached leaves a unique signature in the data gathered. Though not detectable in time domain, this signature could be obscured in the frequency spectrum of the data. By filtering and analysis of the changes in the frequency spectrum before and after the endpoint we could extract this signature. In order to do that, first, the EPD algorithm converts the time series signal into frequency domain. Next the noise in the frequency spectrum is removed to look for the useful frequency constituents of the data. Once these useful frequencies have been selected, they are monitored continuously in time and using a sub-algorithm the endpoint is detected when significant changes are observed in those signals. The experiment consisted of three kinds of etch processes; ashing, SiO2 on Si etch and metal on Si etch to develop and evaluate the EPD system.

  • PDF

Computational Thinking역량 계발을 위한 수업 설계 및 평가 루브릭 개발 (Developing Lessons and Rubrics to Promote Computational Thinking)

  • 최형신
    • 정보교육학회논문지
    • /
    • 제18권1호
    • /
    • pp.57-64
    • /
    • 2014
  • 본 연구의 목적은 최근에 큰 주목을 받고 있는 Computational Thinking(CT) 개념과 세부 역량에 대해 문헌연구를 수행하고 CT역량을 계발하기 위한 초등예비교사를 위한 수업 내용과 평가 방법을 고안하는 것이다. 이를 위해 CT관련 문헌, 프로그래밍 효과성 관련 문헌, 스크래치 교육용 프로그래밍 언어 2.0버전의 기능을 분석하여 예비초등교사를 위한 6개의 CT세부 요소(절차 및 알고리즘, 병행화 및 동기화, 자료 표현, 추상화, 문제 분해, 시뮬레이션)를 도출하였다. 도출된 6개의 CT세부 역량의 계발을 위해 교원양성기관에서 한 학기에 진행할 수 있는 수업을 설계하고 각 차시의 수업내용과 CT요소와의 관련성을 분석하여 제시하였다. 또한 PECT(Progression of Early Computational Thinking)모형과 CT평가 프레임워크를 분석하여 학습자의 산출물에 나타난 CT역량 습득 정도를 기초, 발달, 능숙 세 단계로 평가할 수 있는 루브릭을 고안하였다. 본 연구의 결과는 향후 실증적 효과성 검증을 통해 교원양성기관에서 CT역량 계발 프로그램으로 활용될 수 있을 것으로 기대한다.