• 제목/요약/키워드: Mixed Noise

검색결과 341건 처리시간 0.019초

3-D 텐서와 recurrent neural network기반 심층신경망을 활용한 수동소나 다중 채널 신호분리 기술 개발 (Sources separation of passive sonar array signal using recurrent neural network-based deep neural network with 3-D tensor)

  • 이상헌;정동규;유재석
    • 한국음향학회지
    • /
    • 제42권4호
    • /
    • pp.357-363
    • /
    • 2023
  • 다양한 신호가 혼합된 수중 신호로부터 각각의 신호를 분리하는 기술은 오랫동안 연구되어왔지만, 낮은 품질의 수중 신호의 특성 상 쉽게 해결되지 않는 문제이다. 현재 주로 사용되는 방법은 Short-time Fourier transform을 사용하여 수신된 음향신호의 스펙트로그램을 얻은 뒤, 주파수의 특성을 분석하여 신호를 분리하는 기술이다. 하지만 매개변수의 최적화가 까다롭고, 스펙트로그램으로 변환하는 과정에서 위상 정보들이 손실되는 한계점이 지적되었다. 본 연구에서는 이러한 문제를 해결하기 위해 긴 시계열 신호 처리에서 좋은 성능을 보인 Dual-path Recurrent Neural Network을 기반으로, 다중 채널 센서로부터 생성된 입력신호인 3차원 텐서를 처리할 수 있도록 변형된 Tripple-path Recurrent Neural Network을 제안한다. 제안하는 기술은 먼저 다중 채널 입력 신호를 짧은 조각으로 분할하고 조각 내 신호 간, 구성된 조각간, 그리고 채널 신호 간의 각각의 관계를 고려한 3차원 텐서를 생성하여 로컬 및 글로벌 특성을 학습한다. 제안된 기법은, 기존 방법에 비해 개선된 Root Mean Square Error 값과 Scale Invariant Signal to Noise Ratio을 가짐을 확인하였다.

혼합 편광빔과 원주면렌즈를 사용한 SPPCM의 성능 개선 (Improvement of the performance of SPPCM using mixed polarized beam and cylindrical lens)

  • 이은형;김성완;김철수;김종윤;이승희;이수중
    • 전자공학회논문지D
    • /
    • 제36D권9호
    • /
    • pp.56-63
    • /
    • 1999
  • Cat형 SPPCM(selfpumped phase conjugate mirror)의 응답시간을 개선시키기 위한 기존의 방법은 원주면 렌즈를 사용하여 패팅 (fanning) 빔을 증가시키는 방법이었다. 그러나, 이 경우에 SPPCM의 특성들을 개선시키기 위해서는 패닝빔을 제어해 주어야 한다. 본 논문에서는 원주면 렌즈를 사용하여 입력빔을 선형으로 광굴절 결정에 접속시켜 SPPCM의 반사율을 증가시키고 응답시간을 감소시키며, 순수한 이상 편광빔 대신 혼합 편광빔을 입사시킴으로써 출력빔의 시간 불안정도를 감소시키는 방법을 제안하였다. 광실험을 통하여 제안한 SPPCM의 반사율이 2배로 증가하고 응답시간은 1/15로 감소함을 확인하였다. 또한, 혼합 편광빔의 편광 각을 $10^{\circ}$에서 $30^{\circ}$ 사이의 각도로 하였을 때 시간 불안정도가 감소함을 확인하였다. 광실험에서 전기광학 계수가 매우 큰 $45^{\circ}-cut\;BaTiO_3$ 결정을 사용하였다.

  • PDF

SIFT 알고리즘을 이용한 혼합형 모바일 교육 시스템 (Mixed Mobile Education System using SIFT Algorithm)

  • 홍광진;정기철;한은정;양종열
    • 한국산업정보학회논문지
    • /
    • 제13권2호
    • /
    • pp.69-79
    • /
    • 2008
  • 무선 인터넷과 모바일 기기의 보급으로 언제 어디서나 원하는 정보를 얻을 수 있는 유비쿼터스 환경을 위한 인프라가 구축되면서 교육을 포함한 다양한 분야에서 오프라인과 온라인 컨텐츠를 동시에 이용함으로써 정보 전달의 효율성을 높일 수 있는 방법에 대한 연구가 활발하게 이루어지고 있다. 본 논문은 사용자에게 모바일 기기를 이용하여 오프라인과 온라인 컨텐츠를 함께 제공하여 교육의 효과를 높일 수 있는 혼합형 모바일 교육 시스템(Mixed Mobile Education System: MME)을 제안한다. 제안된 시스템은 기존의 연구와 달리 사용자에게 자연스러운 환경을 제공하기 위해서 부가적인 태그를 사용하지 않는다. 태그를 사용하는 시스템의 경우 새로운 데이터의 등록이 어렵고 유사한 내용의 오프라인 컨텐츠 사용이 불가능하기 때문이다. 본 논문에서 우리는 저화질의 카메라를 통해 입력받은 영상에서 잡음 색상 왜곡, 크기 및 기울기 변화에 영향을 적게 받는 특징점을 추출하고 오프라인 컨텐츠를 인식하기 위해 Scale Invariant Feature Transform(SIFT) 알고리즘을 사용하였다. 또한 클라이언트-서버 구조를 사용함으로써 모바일 장치의 제한적인 저장 능력 문제를 해결하고 데이터의 등록 및 수정이 용이하도록 하였다. 실험을 통해 기존의 흔합형 교육 시스템과의 성능을 비교하고 제안된 시스템의 장단점을 확인하였으며, 시스템을 실생활에 적용하였을 경우 다양한 상황에서도 사용자에게 만족할만한 성능을 제공함을 확인하였다.

  • PDF

Quality Enhancement for Hybrid 3DTV with Mixed Resolution Using Conditional Replenishment Algorithm

  • Jung, Kyeong-Hoon;Bang, Min-Suk;Kim, Sung-Hoon;Choo, Hyon-Gon;Kang, Dong-Wook
    • ETRI Journal
    • /
    • 제36권5호
    • /
    • pp.752-760
    • /
    • 2014
  • This paper proposes a conditional replenishment algorithm (CRA) to improve the visual quality (where spatial resolutions of the left and right views are mismatched) of a hybrid stereoscopic 3DTV that is based on the ATSC-M/H standard. So as to generate an enhanced view, the CRA is to choose the better substitute among a disparity-compensated view with high quality and a simply interpolated view. The CRA generates a disparity map that includes modes and disparity vectors as additional information. It also employs a quad-tree structure with variable block size by considering the spatial correlation of disparity vectors. In addition, it takes advantage of the disparity map used in a previous frame to keep the amount of additional information as small as possible. The simulation results show that the proposed CRA can successfully improve the peak signal-to-noise ratio of a poor-quality view and consequently have a positive effect on the subjective quality of the resulting 3D view.

자기 조직화 지도를 이용한 다중 평면영역 검출 (Multiple Plane Area Detection Using Self Organizing Map)

  • 김정현;등죽;강동중
    • 제어로봇시스템학회논문지
    • /
    • 제17권1호
    • /
    • pp.22-30
    • /
    • 2011
  • Plane detection is very important information for mission-critical of robot in 3D environment. A representative method of plane detection is Hough-transformation. Hough-transformation is robust to noise and makes the accurate plane detection possible. But it demands excessive memory and takes too much processing time. Iterative randomized Hough-transformation has been proposed to overcome these shortcomings. This method doesn't vote all data. It votes only one value of the randomly selected data into the Hough parameter space. This value calculated the value of the parameter of the shape that we want to extract. In Hough parameters space, it is possible to detect accurate plane through detection of repetitive maximum value. A common problem in these methods is that it requires too much computational cost and large number of memory space to find the distribution of mixed multiple planes in parameter space. In this paper, we detect multiple planes only via data sampling using Self Organizing Map method. It does not use conventional methods that include transforming to Hough parameter space, voting and repetitive plane extraction. And it improves the reliability of plane detection through division area searching and planarity evaluation. The proposed method is more accurate and faster than the conventional methods which is demonstrated the experiments in various conditions.

A Low-power High-resolution Band-pass Sigma-delta ADC for Accelerometer Applications

  • Cao, Tianlin;Han, Yan;Zhang, Shifeng;Cheung, Ray C.C.;Chen, Yaya
    • JSTS:Journal of Semiconductor Technology and Science
    • /
    • 제17권3호
    • /
    • pp.438-445
    • /
    • 2017
  • This paper presents a low-power high-resolution band-pass ${\Sigma}{\Delta}$ ADC for accelerometer applications. The proposed band-pass ${\Sigma}{\Delta}$ ADC consists of a high-performance 6-th order feed-forward ${\Sigma}{\Delta}$ modulator with 1-bit quantization and a low-power, area-efficient digital filter. The ADC is fabricated in 180 nm 1P6M mixed-signal CMOS process with a die area of $5mm^2$. This high-resolution ADC got 90 dB peak signal to noise plus distortion ratio (SNDR) and 96 dB dynamic range (DR) over 4 kHz bandwidth, while the intermediate frequency (IF) is shifting from 100 KHz to 200 KHz. The power dissipation of the chip is 5.6 mW under 1.8 V (digital)/3.3 V (analog) power supply.

반용융 재료의 물성치 평가에 관한 연구(II) -모델재료의 후방압출 실험과 상계해석을 통한 반용융 재료의 유동응력식 결정- (A Study on Material Characterization of Semi-Solid Materials(II) -Determination of Flow Stress For Semi-Solid Materials Using Backward Extrusion Experiment with Model Material and Upper Bound Analysis-)

  • 이주영;김낙수
    • 소성∙가공
    • /
    • 제8권4호
    • /
    • pp.374-383
    • /
    • 1999
  • To determine the flow stress of semi-solid materials, a new combined method has been studied by experimental and analytic technique in the current approach. Using backward extrusion experiment and its numerical analysis, the characterization scheme of semi-solid materials according to the change of initial solid volume fraction has been proposed. Because that solid volume fraction is sensitive to temperature change, it is required to precisely control the temperature setting. Model materials can guarantee the establishment of material characterization technique from the noise due to temperature change. Thus, clay mixed with bonded abrasives was used for experiment and the change of initial solid fraction was copied out through the variation of mixing ratio. Upper bound method was adapted to increase in efficiency of the calculation in numerical analysis and new kinematically admissible velocity field was employed to improve the accuracy of numerical solution. It is thought that the material characterization scheme proposed in this study can be applied to not only semi-solid materials, but also other materials that is difficult to obtain the simple stress state.

  • PDF

자동 목표물 인식 시스템을 위한 클러스터 기반 투영기법과 혼합 전문가 구조 (Cluster-based Linear Projection and %ixture of Experts Model for ATR System)

  • 신호철;최재철;이진성;조주현;김성대
    • 대한전자공학회논문지SP
    • /
    • 제40권3호
    • /
    • pp.203-216
    • /
    • 2003
  • In this paper a new feature extraction and target classification method is proposed for the recognition part of FLIR(Forwar Looking Infrared)-image-based ATR system. Proposed feature extraction method is "cluster(=set of classes)-based"version of previous fisherfaces method that is known by its robustness to illumination changes in face recognition. Expecially introduced class clustering and cluster-based projection method maximizes the performance of fisherfaces method. Proposed target image classification method is based on the mixture of experts model which consists of RBF-type experts and MLP-type gating networks. Mixture of experts model is well-suited with ATR system because it should recognizee various targets in complexed feature space by variously mixed conditions. In proposed classification method, one expert takes charge of one cluster and the separated structure with experts reduces the complexity of feature space and achieves more accurate local discrimination between classes. Proposed feature extraction and classification method showed distinguished performances in recognition test with customized. FLIR-vehicle-image database. Expecially robustness to pixelwise sensor noise and un-wanted intensity variations was verified by simulation.

주차장 바닥용 표면 마감재의 안전성 평가 및 성능기준에 관한 연구 (A Experiment Study for the Standard Performance and Test of Surface Finishing Material for Parking Slab)

  • 김귀태;권시원;곽규성;오상근
    • 한국건축시공학회:학술대회논문집
    • /
    • 한국건축시공학회 2005년도 춘계 학술기술논문발표대회 논문집
    • /
    • pp.125-131
    • /
    • 2005
  • Recently, to improve condition car park, using surface finishing material for variety color and property epoxy resin, urethane, cement mixed resin mortar or polymeric resin, and so on. However, it is frequent noise and wear out of tier and waterproofing materials, when the car slip or stop in car park, To minimize these cases, It is necessary that reduction of repair cost through performance long term durability of surface finishing material, improvement inside condition such as reduce dirty and car accident and ensurance the expected life of concrete slab in car park. Especially, we have not any tech for quality control, construction tech, production technology for car park surface materials, that's why park slab is not safety and suffer a loss. For this problems, this paper is to test surface finishing materials and as that result, suggest quality standard in the car park.

  • PDF

PEM 연료전지용 복합재 분리판의 제작비용 비교: 압축성형과 기계식 가공 (Comparison of fabrication cost of composite bipolar plates for PEM fuel cell: compression molding and machining)

  • 이희섭;추원식;강윤철;강혁진;안성훈
    • 한국신재생에너지학회:학술대회논문집
    • /
    • 한국신재생에너지학회 2006년도 추계학술대회
    • /
    • pp.105-108
    • /
    • 2006
  • The fuel cell is one of the promising environment-friendly energy sources for the next generation. The fuel cell provides good energy efficiency above 40% without pollution or noise. Different fuel cell types are usually distinguished by the kind of electrolyte. Among these, the proton exchange membrane fuel cell (PEMFC) has advantages of high power density. low operating temperature, relatively quick start-up, and rapid response to varying loads. The bipolar plate is a major component of the PEM fuel cell stack, and it takes a large portion of stack volume, weight and cost. In this study, as alternative materials for bipolar plate of PEM fuel cells, graphite composites were fabricated by compression molding and by machining. Graphite particles mixed with epoxy resin were used as the main substance to provide electric conductivity. Flow channels were fabricated by compression molding with design of experiments (DOE) to evaluate moldability. The cost for compression molding of graphite-composite bipolar plate was compared with machining cost to make the same bipolar plate.

  • PDF