• 제목/요약/키워드: Data fusion system

검색결과 588건 처리시간 0.026초

15-리드 심전계용 표준 시뮬레이터의 개발 (Development of Standard ECG Simulator for 15-Lead ECG Monitor)

  • 강유민;이진홍;최성욱
    • 대한기계학회논문집B
    • /
    • 제39권5호
    • /
    • pp.391-395
    • /
    • 2015
  • 15 리드 심전도는 12 리드 심전도가 진단하지 못하는 심장의 후벽질환 등을 진단하기 위하여 개발되었다. 그러나 15 리드 심전도를 이용한 심장질환 진단알고리즘을 개발하기 위해 필요한 15 리드 심전도 데이터가 부족하고, 기존의 심전도 시뮬레이터는 전극의 부착위치나 심장질환에 따라 달라지는 심전도의 형태를 예측할 수 없는 문제가 있다. 따라서 이러한 문제를 해결하기 위하여 심장을 전기적인 캐패시턴스를 가지는 15 개의 부분으로 나누고 전기적인 저항소자를 통하여 연결된 LPM 을 제작하였다. 심장의 전기전도기전을 모사하기 위하여 각 절점은 전류원과 연결되고 위치와 시간지연을 고려한 개별적인 전류를 인가하였다. 본 연구의 목적은 제작한 LPM 의 각 절점에 특정한 전류를 인가함으로써 심전도로서 활용 가능한 파형을 얻는데 있다.

Reviews on innovations and applications in structural health monitoring for infrastructures

  • Li, Hong-Nan;Yi, Ting-Hua;Ren, Liang;Li, Dong-Sheng;Huo, Lin-Sheng
    • Structural Monitoring and Maintenance
    • /
    • 제1권1호
    • /
    • pp.1-45
    • /
    • 2014
  • The developments and implementations of the structural health monitoring (SHM) system for large infrastructures have been gradually recognized by researchers, engineers and administrative authorities in the last decades. This paper summarizes an updated review on innovations and applications in SHM for infrastructures carried out by researchers at Dalian University of Technology. Invented sensors and data acquisition system are firstly briefly described. And then, some proposed theories and methods including the sensing technology, sensor placement method, signal processing and data fusion, system identification and damage detection are discussed in details. Following those, the activities on the standardization of SHM and several case applications on specific types of structure are reviewed. Finally, existing problems and promising research efforts in the field of SHM are given.

GUI환경을 갖는 퍼지기반 이동로봇제어 (Fuzzy Based Mobile Robot Control with GUI Environment)

  • 홍선학
    • 전자공학회논문지 IE
    • /
    • 제43권4호
    • /
    • pp.128-135
    • /
    • 2006
  • 본 논문에서는 이동로봇 주변의 자기위치인식, 광학식 엔코더의 위치 데이터 및 초음파 센서의 환경 지도를 이용하여 퍼지 기반 센서융합 제어방식을 제시하였다. 영상 카메라를 이용하여 자기위치 인식성능을 높이고 초음파 센서에서 감지한 목표물의 형태, 거리와 특징을 퍼지 기반 제어기를 통하여 처리하여 이동로봇 주변의 환경지도를 만들어 자기위치 인식능력의 개선을 실험을 통하여 구현하였다.

Mobile Robot Navigation using a Dynamic Multi-sensor Fusion

  • Kim, San-Ju;Jin, Tae-Seok;Lee, Oh-Keol;Lee, Jang-Myung
    • 한국지능시스템학회:학술대회논문집
    • /
    • 한국퍼지및지능시스템학회 2003년도 ISIS 2003
    • /
    • pp.240-243
    • /
    • 2003
  • In this study, as the preliminary step far developing a multi-purpose Autonomous robust carrier mobile robot to transport trolleys or heavy goods and serve as robotic nursing assistant in hospital wards. The aim of this paper is to present the use of multi-sensor data fusion such as sonar, IR sensor for map-building mobile robot to navigate, and presents an experimental mobile robot designed to operate autonomously within both indoor and outdoor environments. Smart sensory systems are crucial for successful autonomous systems. We will give an explanation for the robot system architecture designed and implemented in this study and a short review of existing techniques, since there exist several recent thorough books and review paper on this paper. It is first dealt with the general principle of the navigation and guidance architecture, then the detailed functions recognizing environments updated, obstacle detection and motion assessment, with the first results from the simulations run.

  • PDF

레이더, 비전, 라이더 융합 기반 자율주행 환경 인지 센서 고장 진단 (Radar, Vision, Lidar Fusion-based Environment Sensor Fault Detection Algorithm for Automated Vehicles)

  • 최승리;정용환;이명수;이경수
    • 자동차안전학회지
    • /
    • 제9권4호
    • /
    • pp.32-37
    • /
    • 2017
  • For automated vehicles, the integrity and fault tolerance of environment perception sensor have been an important issue. This paper presents radar, vision, lidar(laser radar) fusion-based fault detection algorithm for autonomous vehicles. In this paper, characteristics of each sensor are shown. And the error of states of moving targets estimated by each sensor is analyzed to present the method to detect fault of environment sensors by characteristic of this error. Each estimation of moving targets isperformed by EKF/IMM method. To guarantee the reliability of fault detection algorithm of environment sensor, various driving data in several types of road is analyzed.

Vehicle Image Recognition Using Deep Convolution Neural Network and Compressed Dictionary Learning

  • Zhou, Yanyan
    • Journal of Information Processing Systems
    • /
    • 제17권2호
    • /
    • pp.411-425
    • /
    • 2021
  • In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

Monte Carlo analysis of LWR spent fuel transmutation in a fusion-fission hybrid reactor system

  • Sahin, Sumer;Sahin, Haci Mehmet;Tunc, Guven
    • Nuclear Engineering and Technology
    • /
    • 제50권8호
    • /
    • pp.1339-1348
    • /
    • 2018
  • The aim of this paper is to determine neutronic performances of the light water reactor (LWR) spent fuel mixed with fertile thorium fuel in a FFHR. Time dependent three dimensional calculations for major technical data, such as blanket energy multiplication, tritium breeding ratio, cumulative fissile fuel enrichment and burnup have been performed by using Monte Carlo Neutron-Particle Transport code MCNP5 1.4, coupled with a novel interface code MCNPAS, which is developed by our research group. A self-sustaining tritium breeding ratio (TBR>1.05) has been kept throughout the calculations. The study has shown that the fissile fuel quality will be improved in the course of the transmutation of the LWR spent in the FFHR. The latter has gained the reusable fuel enrichment level conventional LWRs between one and two years. Furthermore, LWR spent fuel - thorium mixture provides higher burn-up values than in light water reactors.

다중 융합 기반 심층 교차 도메인 추천 (Multiple Fusion-based Deep Cross-domain Recommendation)

  • 홍민성;이원진
    • 한국멀티미디어학회논문지
    • /
    • 제25권6호
    • /
    • pp.819-832
    • /
    • 2022
  • Cross-domain recommender system transfers knowledge across different domains to improve the recommendation performance in a target domain that has a relatively sparse model. However, they suffer from the "negative transfer" in which transferred knowledge operates as noise. This paper proposes a novel Multiple Fusion-based Deep Cross-Domain Recommendation named MFDCR. We exploit Doc2Vec, one of the famous word embedding techniques, to fuse data user-wise and transfer knowledge across multi-domains. It alleviates the "negative transfer" problem. Additionally, we introduce a simple multi-layer perception to learn the user-item interactions and predict the possibility of preferring items by users. Extensive experiments with three domain datasets from one of the most famous services Amazon demonstrate that MFDCR outperforms recent single and cross-domain recommendation algorithms. Furthermore, experimental results show that MFDCR can address the problem of "negative transfer" and improve recommendation performance for multiple domains simultaneously. In addition, we show that our approach is efficient in extending toward more domains.

통행시간과 점유율 기반의 실시간 신호운영 알고리즘 (A Real-time Traffic Signal Control Algorithm based on Travel Time and Occupancy Rate)

  • 박순용;정영제
    • 한국콘텐츠학회논문지
    • /
    • 제16권8호
    • /
    • pp.671-680
    • /
    • 2016
  • 본 연구에서는 통행시간과 점유율의 융합 정보를 이용하는 새로운 실시간 신호제어 알고리즘을 제시하였다. 교통정보시스템의 통행시간 정보를 신호운영에 적용하였으며, 통행시간으로 부터 산정한 포화도를 신호제어에 이용하기 위한 프로세스를 개발하였다. 결정적 지체모형을 이용해 통행시간으로부터 대기행렬 길이를 생성하고, 대기행렬 길이를 다시 포화도로 변환하는 과정이 적용되었다. 또한 통행시간 기반 포화도와 루프검지기 포화도를 융합해 신호시간이 산정되도록 하였다. 신호제어 알고리즘의 효과평가를 위해 미시적 시뮬레이션 분석을 시행하였으며, 과포화 상태에서 기존 루프검지기 기반 실시간 신호제어 대비 최대 27%의 지체 감소 효과를 확인하였다. 또한 과포화 및 검지기 고장상황에 대한 효과적이고, 유용한 대응이 가능함을 확인하였다. 본 연구에서는 교통신호제어시스템과 교통정보시스템의 교통정보 통합이용 방안을 제시하였다는데 의의가 있겠다.

3D 공간정보와 비디오 융합에 의한 X3D기반 웹 가시화 (X3D Based Web Visualization by Data Fusion of 3D Spatial Information and Video Sequence)

  • 손홍규;김성삼;유병현;김상민
    • 대한공간정보학회지
    • /
    • 제17권4호
    • /
    • pp.95-103
    • /
    • 2009
  • 전세계적으로 다양한 관측 센서 및 자료처리 기술개발을 통하여 현실 세계에 대한 3차원 공간정보 구축에 관한 관심이 높아지고 있으며, 사생활 침해 논란에도 불구하고 도시지역 곳곳에 설치된 CCTV가 교통관리나 범죄 예방 및 재난 모니터링을 위한 핵심 관측장비로서 활용되고 있다. 도시지역의 안전 확보와 각종 재난 예방을 위해 기구축된 3차원 공간정보에 CCTV 영상이나 비디오 자료를 연계시켜 유사시 발생한 상황을 실시간적으로 인터렉티브하게 파악하고 모니터링할 수 있는 감시 시스템의 필요성이 제기되고 있다. 따라서, 본 연구에서는 웹 가시화의 국제표준인 X3D를 기반으로 3차원 공간정보와 비디오 융합을 통하여 인터넷 상에서 실시간으로 인터렉티브하게 가시화할 수 있는 프로토타입 시스템을 개발하여 그 활용가능성을 제시하고자 하였다.

  • PDF