• 제목/요약/키워드: Feature Parameter

검색결과 530건 처리시간 0.032초

동영상 컷 검출을 위한 가변형 동적 임계값 기법 (Variable Dynamic Threshold Method for Video Cut Detection)

  • 염성주;김우생
    • 한국통신학회논문지
    • /
    • 제27권4A호
    • /
    • pp.356-363
    • /
    • 2002
  • 컷 검출은 내용기반 검색에 필요한 인덱싱을 위해 수행되어야 하는 기초 작업으로 이를 위한 매우 다양한 기법들이 제안된바 있다. 그러나 기존의 연구에서는 대부분 고정된 하나의 임계값을 사용하기 때문에 통영상의 종류나 내용에 따라 최적의 임계값을 정해야만 하는 문제점을 갖는다. 본 논문에서는 컷 검출 간격의 확률적인 분포에 따라 임계값을 조절하며 컷이 발생하면 이전 컷과의 간격과 특징값 차이를 다음 컷 검출을 위한 임계값 설정에 반영하는 가변형 동적 임계값 방법을 제안한다. 이를 위해 임계값 조절에 필요한 인자 값들을 실행시간에 구하는 방법과 이를 사용한 컷 검출 알고리즘을 제시한다. 또한 실험을 통해 제안하는 방법이 기존의 방법에 비해 오 검출율을 줄일 수 있어 효율적임을 보인다.

반도체 공정 신호의 이상탐지 및 분류를 위한 자기구상지도 기반 기법에 관한 연구

  • 윤재준;박정술;백준걸
    • 한국진공학회:학술대회논문집
    • /
    • 한국진공학회 2011년도 제40회 동계학술대회 초록집
    • /
    • pp.36-36
    • /
    • 2011
  • 반도체 공정 신호는 주기 신호와 비주기 신호로 구분된다. 특정 패턴을 가지는 주기 신호는 해당 파라미터(parameter)에 대해서 패턴 매칭을 수행하여 관리하는 연구가 진행되고 있다. 반면 비주기 신호 데이터의 경우에는 패턴 매칭 방법을 수행할 수 없다. 또한 반도체 공정에서 얻을 수 있는 두 개 타입의 데이터는 그 파라미터가 방대하기 때문에 현재 실제 공정에 적용되고 있는 방식인 각각 하나의 파라미터에 대해 관리도(control chart)를 구성해 관리하는 것은 많은 비용과 시간의 낭비를 초래한다. 따라서 두 타입 데이터의 여러 개의 파라미터를 동시에 관측할 수 있고 파라미터간의 내재된 상관관계를 고려할 수 있는 장점을 가진 분석 기법에 대한 연구가 필요하다. 주기 신호의 이상탐지를 위한 기존 연구는 신호를 구간으로 나누어 구간별로 SPC 차트적용 시키는 방법, 각 시점 마다 측정되는 값을 하나의 변수로 고려하여 Hotelling's T square, PCA, PLS 등과 같은 다변량 통계 분석을 적용 시키는 방법들이 제시되어 왔다. 이러한 방법들은 다양한 특성을 가지는 주기신호를 분석하고 이상을 탐지 하는데 많은 한계점을 가진다. 이에 본 논문은 다양한 형태를 가지는 신호의 특성을 반영하여 자기구상지도를 기반으로 신호의 분류와 공정의 이상을 탐지하는 기법을 제안한다. 제안하는 기법은 자기구상지도를 이용하여 복잡한(고차원, 시계열) 신호를 2차원 상의 노드로 맵핑시킴으로써 신호의 특질(feature)을 추출하고 새로 표현된 신호의 특질을 기반으로 Logistic regression을 적용시켜 이상을 탐지 한다. 다양한 이상 상황을 가진 반도체 공정 신호를 사용하여 제안한 이상탐지 성능을 평가하였다.

  • PDF

Development of Audio Melody Extraction and Matching Engine for MIREX 2011 tasks

  • 송재종;장달원;이석필;박호종
    • 한국방송∙미디어공학회:학술대회논문집
    • /
    • 한국방송공학회 2012년도 하계학술대회
    • /
    • pp.164-166
    • /
    • 2012
  • In this paper, we proposed a method for extracting predominant melody of polyphonic music based on harmonic structure. Harmonic structure is an important feature parameter of monophonic signal that has spectral peaks at the integer multiples of its fundamental frequency. We extract all fundamental frequency candidates contained in the polyphonic signal by verifying the required condition of harmonic structure. Then, we combine those harmonic peaks corresponding to each extracted fundamental frequency and assign a rank to each after calculating its harmonic average energy. We run pitch tracking based on the rank of extracted fundamental frequency and continuity of fundamental frequency, and determine the predominant melody. For the query by singing/humming (QbSH) task, we proposed Dynamic Time Warping (DTW) based matching engine. Our system reduces false alarm by combining the distances of multiple DTW processes. To improve the performance, we introduced the asymmetric sense, pitch level compensation, and distance intransitiveness to DTW algorithm.

  • PDF

A Study Personal 2D Color Feature Image Interpolation

  • Jo, Nam-Chul;Ku, Ja-Hyo;Kim, Hwi-Won;Lee, Ki-Dong
    • 한국정보컨버전스학회:학술대회논문집
    • /
    • 한국정보컨버전스학회 2008년도 International conference on information convergence
    • /
    • pp.177-180
    • /
    • 2008
  • Surveillance Cameras such as CCTV easily found in places requiring security and the prevention of crimes such as public institutions, banks, etc. play an important role as they prevent all sorts of crimes, and provide a decisive clue fix settling a criminal case. But, in case that a far-off person is photographed, an original image should be enlarged to identify the person. And as for the technique of enlarging an image, it is important to enlarge and restore it close to its original image rather than to merely magnify it. For the enlargement and restoration of an image, techniques called interpolation are used; as for interpolation methods known hitherto, however, the higher the magnifying power is, the more deteriorated the quality of an image becomes to the extent that the image cannot be identified. Therefore, in this paper, we are going to propose a new technique whereby the face outline in an image is vectorized and restored by means of FDP(Facial Definition Parameter) standardized by the MPEG-4 SNHC FBA group, and an image is restored to have better quality than images restored with the existing interpolation.

  • PDF

음향음성학 파라메터를 이용한 이중모음의 분류 (Classification of Diphthongs using Acoustic Phonetic Parameters)

  • 이석명;최정윤
    • 한국음향학회지
    • /
    • 제32권2호
    • /
    • pp.167-173
    • /
    • 2013
  • 본 논문은 이중모음을 분류하기 위한 음향음성학적 파라메터를 연구하였다. 음향음성학적 파라메터는 성도를 통해 음성이 발성될 때 나타나는 특징을 기반으로 하여 분산분석(ANOVA) 방법을 통해 선별한 모음의 길이, 에너지 궤적, 그리고 포먼트의 차이를 이용하였다. TIMIT 데이터 베이스를 사용하였을 때, 단모음과 이중모음만을 구분하는 실험에서는 17.8% 의 밸런스 에러율(BER)을 얻을 수 있었고, /aw/, /ay/, 그리고 /oy/를 단모음과 분류하는 실험에서는 각각 32.9%, 29.9%, 그리고 20.2%의 에러율을 얻을 수 있었다. 추가적으로 진행한 실험에서, 음향음성학적 파라메터와 음성인식에 널리 쓰이고 있는 MFCC를 함께 사용하였을 경우 역시 성능향상이 나타나는 것을 확인하였다.

THEORETICAL ANALYSIS FOR STUDYING THE FRETTING WEAR PROBLEM OF STEAM GENERATOR TUBES IN A NUCLEAR POWER PLANT

  • LEE CROON YEOL;CHAI YOUNG SUCK;BAE JOON WOO
    • Nuclear Engineering and Technology
    • /
    • 제37권2호
    • /
    • pp.201-206
    • /
    • 2005
  • Fretting, which is a special type of wear, is defined as small amplitude relative motion along the contacting interface between two materials. The structural integrity of steam generators in nuclear power plants is very much dependent upon the fretting wear characteristics of Inconel 690 U-tubes. In this study, a finite element model that can simulate fretting wear on the secondary side of the steam generator was developed and used for a quantitative investigation of the fretting wear phenomenon. Finite element modeling of elastic contact wear problems was performed to demonstrate the feasibility of applying the finite element method to fretting wear problems. The elastic beam problem, with existing solutions, is treated as a numerical example. By introducing a control parameter s, which scaled up the wear constant and scaled down the cycle numbers, the algorithm was shown to greatly reduce the time required for the analysis. The work rate model was adopted in the wear model. In the three-dimensional finite element analysis, a quarterly symmetric model was used to simulate cross tubes contacting at right angles. The wear constant of Inconel 690 in the work rate model was taken as $K=26.7{\times}10^{-15}\;Pa^{-1}$ from experimental data obtained using a fretting wear test rig with a piezoelectric actuator. The analyses revealed donut-shaped wear along the contacting boundary, which is a typical feature of fretting wear.

A consistent FEM-Vlasov model for hyperbolic cooling towers on layered soil under unsymmetrical wind load

  • Karakas, Ali I.;Ozgan, Korhan;Daloglu, Ayse T.
    • Wind and Structures
    • /
    • 제22권6호
    • /
    • pp.617-633
    • /
    • 2016
  • In this paper, the analysis of hyperbolic cooling tower on elastic subsoil exposed to unsymmetrical wind loading is presented. Modified Vlasov foundation model is used to determine the soil parameters as a function of vertical deformation profile within subsoil. The iterative parameter updating procedure involves the use of Open Application Programming Interface (OAPI) feature of SAP2000 to provide two way data flow during execution. A computing tool coded in MATLAB employing OAPI is used to perform the analysis of hyperbolic cooling tower with supporting columns over a hollow annular raft founded on elastic subsoil. The analysis of such complex soil-structure system is investigated under self-weight and unsymmetrical wind load. The response of the cooling tower on elastic subsoil is compared with that of a tower that its supporting raft foundation is treated as fixed at the base. The results show that the effect of subsoil on the behavior of cooling tower is considerable at the top and bottom of the wall as well as supporting columns and raft foundation. The application of a full-size cooling tower has demonstrated that the procedure is simple, fast and can easily be implemented in practice.

A statistical framework with stiffness proportional damage sensitive features for structural health monitoring

  • Balsamo, Luciana;Mukhopadhyay, Suparno;Betti, Raimondo
    • Smart Structures and Systems
    • /
    • 제15권3호
    • /
    • pp.699-715
    • /
    • 2015
  • A modal parameter based damage sensitive feature (DSF) is defined to mimic the relative change in any diagonal element of the stiffness matrix of a model of a structure. The damage assessment is performed in a statistical pattern recognition framework using empirical complementary cumulative distribution functions (ECCDFs) of the DSFs extracted from measured operational vibration response data. Methods are discussed to perform probabilistic structural health assessment with respect to the following questions: (a) "Is there a change in the current state of the structure compared to the baseline state?", (b) "Does the change indicate a localized stiffness reduction or increase?", with the latter representing a situation of retrofitting operations, and (c) "What is the severity of the change in a probabilistic sense?". To identify a range of normal structural variations due to environmental and operational conditions, lower and upper bound ECCDFs are used to define the baseline structural state. Such an approach attempts to decouple "non-damage" related variations from damage induced changes, and account for the unknown environmental/operational conditions of the current state. The damage assessment procedure is discussed using numerical simulations of ambient vibration testing of a bridge deck system, as well as shake table experimental data from a 4-story steel frame.

DS-CDMA 셀룰라 시스템에서 호 차단률 개선을 위한 채널 할당 방식 (A channel assignment scheme for reducing call blocking rate in DS-CDMA cellular systems)

  • 전형구;황선호;권수근;강창언
    • 한국통신학회논문지
    • /
    • 제22권5호
    • /
    • pp.1075-1082
    • /
    • 1997
  • In this paper, we propose a channel assignment scheme for reducing call blocking rate in a base station(BS) of DS-CDMA cellular systems. The proposed scheme can e applied to the case where the capacity of reverse radio link is enough, but not are the available traffic channels performing the digital modulation and demodulation functions between a mobile station and the base station. The proposed scheme takes advantage of the feature of soft handoff in which a mobile station keeps its communication link even if one of the two communication links is released. The scheme estimates the mean and variance of the received power level measured at the base station before assigning a traffic channel for a new call request. The BS makes decision based on the estimated balues whether the new call request will be accepted or not. If it is decided that the capacity of reverse radio link is enough, but all traffic channels are not available, then the BS increases the soft handoff parameter T_DROP to release the traffic channels of mobile stations loactedin soft handoff area. The BS assigns the released traffic channel to anew call or a handoff call. The performance of the proposed channel assignment scheme is evaluated by computer simulation. The results show that the call blocking rate for new calls and handoff calls is reduced.

  • PDF

Hybrid Fuzzy PI-Control Scheme for Quasi Multi-Pulse Interline Power Flow Controllers Including the P-Q Decoupling Feature

  • Vural, Ahmet Mete;Bayindir, Kamil Cagatay
    • Journal of Power Electronics
    • /
    • 제12권5호
    • /
    • pp.787-799
    • /
    • 2012
  • Real and reactive power flows on a transmission line interact inherently. This situation degrades power flow controller performance when independent real and reactive power flow regulation is required. In this study, a quasi multi-pulse interline power flow controller (IPFC), consisting of eight six-pulse voltage source converters (VSC) switched at the fundamental frequency is proposed to control real and reactive power flows dynamically on a transmission line in response to a sequence of set-point changes formed by unit-step reference values. It is shown that the proposed hybrid fuzzy-PI commanded IPFC shows better decoupling performance than the parameter optimized PI controllers with analytically calculated feed-forward gains for decoupling. Comparative simulation studies are carried out on a 4-machine 4-bus test power system through a number of case studies. While only the fuzzy inference of the proposed control scheme has been modeled in MATLAB, the power system, converter power circuit, control and calculation blocks have been simulated in PSCAD/EMTDC by interfacing these two packages on-line.