• Title/Summary/Keyword: 상태 분류

Search Result 2,299, Processing Time 0.038 seconds

Facial Expression Recognition with Instance-based Learning Based on Regional-Variation Characteristics Using Models-based Feature Extraction (모델기반 특징추출을 이용한 지역변화 특성에 따른 개체기반 표정인식)

  • Park, Mi-Ae;Ko, Jae-Pil
    • Journal of Korea Multimedia Society
    • /
    • v.9 no.11
    • /
    • pp.1465-1473
    • /
    • 2006
  • In this paper, we present an approach for facial expression recognition using Active Shape Models(ASM) and a state-based model in image sequences. Given an image frame, we use ASM to obtain the shape parameter vector of the model while we locate facial feature points. Then, we can obtain the shape parameter vector set for all the frames of an image sequence. This vector set is converted into a state vector which is one of the three states by the state-based model. In the classification step, we use the k-NN with the proposed similarity measure that is motivated on the observation that the variation-regions of an expression sequence are different from those of other expression sequences. In the experiment with the public database KCFD, we demonstrate that the proposed measure slightly outperforms the binary measure in which the recognition performance of the k-NN with the proposed measure and the existing binary measure show 89.1% and 86.2% respectively when k is 1.

  • PDF

Analysis and the Conservation Treatment of the Paper Relics of the Seonwon Temple Area (선원사지(禪源寺地)출토 지류 유물의 분석 및 보존 처리 방법)

  • Lim, Ju-Hee;Park, Chi-sun
    • Journal of Conservation Science
    • /
    • v.12 no.1 s.15
    • /
    • pp.71-82
    • /
    • 2003
  • The paper relics excavated from the 4th excavation of the historical spot No.259 Seonwon temple area were analyzed and conserved. Because these works remained folded, the most important conservation treatment was a separation. This process depended on the state of the works: dry state works were separated using Gore-Tex chamber and the filtrated water, wet state works were separated through vacuum freeze drying method. Analyses of the paper relics performed were examination on the paper to find its distinction, binocular microscope and SEM on fiber, and XRF on character ingredient. This study presumed the times though C14 dating of these works. The works were able to be classified through analysis and conservation treatment. This separation made lost part of the works conserve an archetype. This study presented the application of conservation methods on the paper relics which are in the bad condition and obtained information through carbon dating of it.

  • PDF

Water Quality Assessment at Coastal Area of the East Sea of Korea (한국 동해연안의 수질 평가)

  • Kim, Young-Sug;Lee, Yong-Hwa;Choi, Hee-Gu
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.18 no.1
    • /
    • pp.15-24
    • /
    • 2012
  • This study aims to investigate characteristics of water quality factors by using survey results of national marine environmental monitoring system from 2004 to 2010 at coastal area of the East Sea of Korea. In this study, we chose statistical methods to analyze the correlation among water quality parameters and principal component analysis for characteristics of each water environment. In addition to this, we evaluated each water's pollution level based on eutrophication standard of OECD, Eutrophication Index(EI), and Organic Pollution Index(OPI). Major factors were chlorophyll a and salt according to the analysis at coastal area of the East Sea. The sea was divided into the south and the central part by Jukbyeon. Also, Jukbyeon in the central part of the East Sea and Gampo in the southern sea coastal waters have been classified separately. The nutritional status of coastal area of East Sea presented Mesotrophic to Oligotrophic level and EI showed less than 1. OPI in all of the coastal area at the East Sea represented that the water quality condition was favorable.

A Study on Development of Automatic Categorization System for Internet Documents (인터넷 문서 자동 분류 시스템 개발에 관한 연구)

  • Han, Kwang-Rok;Sun, B.K.;Han, Sang-Tae;Rim, Kee-Wook
    • The Transactions of the Korea Information Processing Society
    • /
    • v.7 no.9
    • /
    • pp.2867-2875
    • /
    • 2000
  • In this paper, we discuss the implementation of automatic internet text categorization system. A categorization algorithm is designed and the system is implemented by back propagation learning model. Internet documents are collected according to the established categories and tested by Chi-squre (χ2) for the document leaning, and the category features are extracted. The sets of learning and separating vector are productt>d by these features. As a result of experimental evaluation, we show that this system is more improved in the performance of automatic categorization than the nearest neigbor method.

  • PDF

Optimal Thresholds from Non-Normal Mixture (비정규 혼합분포에서의 최적분류점)

  • Hong, Chong-Sun;Joo, Jae-Seon
    • The Korean Journal of Applied Statistics
    • /
    • v.23 no.5
    • /
    • pp.943-953
    • /
    • 2010
  • From a mixture distribution of the score random variable for credit evaluation, there are many methods of estimating optimal thresholds. Most the research news is based on the assumption of normal distributions. In this paper, we extend non-normal distributions such as Weibull, Logistic and Gamma distributions to estimate an optimal threshold by using a hypotheses test method and other methods maximizing the total accuracy and the true rate. The type I and II errors are obtained and compared with their sums. Finally we discuss their e ciency and derive conclusions for non-normal distributions.

A Study of Efficient Rock Mass Rating for Tunnel Using Multivariate Analysis (다변량분석을 이용한 터널에서의 효율적인 암반분류에 관한 연구)

  • Wye, Yong-Gon;No, Sang-Lim;Yoon, Ji-Son
    • Journal of Korean Tunnelling and Underground Space Association
    • /
    • v.2 no.2
    • /
    • pp.41-49
    • /
    • 2000
  • Rock Mass Rating has been widely applied to the underground tunnel excavation and many other practical problems in rock engineering. However, Rock Mass Rating is hard, even by the experts of tunnel assessment owing to lack of investigation system. In this study, using multivariate analysis we presented rock mass rating system that is objective and easy to use. The constituents of RMR are decided to RQD, condition of discontinuities, groundwater conditions, intact rock strength, orientation of discontinuities, spacing of discontinuities in important order. In each step, we proposed the best multiple regression model for RMR system.

  • PDF

Generation and Analysis of Pattern Classifier based on LFSRs (LFSR 기반의 패턴분류기의 생성 및 분석)

  • Kwon, Sook-Hee;Cho, Sung-Jin;Choi, Un-Sook;Kong, Gil-Tak;Kim, Doo-Han
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.19 no.7
    • /
    • pp.1577-1584
    • /
    • 2015
  • In this paper, we propose a method for generating pattern classifier based on LFSR. The proposed pattern classifier bosed on LFSR is easy to see non-reachable state, and we can obtain dependency vector by using the 0-basic path. Also, we propose a method for generating pattern classifiers based on LFSR which correspond to given dependency vector.

A Particle Filter Based Classification of Human Mobile State (파티클 필터에 기반한 인간 이동 상태 분류)

  • Song, Ha Yoon;Baik, Ji Hyun
    • KIPS Transactions on Computer and Communication Systems
    • /
    • v.4 no.4
    • /
    • pp.125-134
    • /
    • 2015
  • In this paper, we present an algorithm based on particle filter to determine the state of human movement. We calculate speed from consecutive positioning data with time, latitude and longitude. The speed values are averaged with previous speed values and thus act as basis for particle filter. We use the fact that human speed distribution follows exponential distribution approximately. An algorithm based on particle filter has been developed and utilized. Human movement state are probabilistically described in this research, and the probability is to determine whether a person is in moving state or in stable state. The experimental results are provided in various ways.

Target State Analysis Based on a Single Ping in Active Sonar (능동소나에서 단일 핑에의한 표적상태분석)

  • Kim, Jea-Soo
    • The Journal of the Acoustical Society of Korea
    • /
    • v.15 no.4
    • /
    • pp.65-69
    • /
    • 1996
  • In this paper, the techniques for target state analysis based on a single ping in the ocean environment are proposed and discussed. The first method utilizes the relationship between range and bearing in order to determine the aspect angle of target. The second method uses the Range-Doppler Map. The former method requires the multi-channel data, while the latter uses single channel data. It is concluded, from the simulation, that the target state analysis is quite possible and the techniques mentioned should be used simultaneously to get the improved results.

  • PDF

State Transition Fault Diagnosis in Brushless DC Motor Based on Fuzzy System (퍼지를 이용한 BLDC 모터의 상태천이 고장진단)

  • Baek, Gyeong-Dong;Kim, Youn-Tae;Kim, Sung-Shin
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.18 no.3
    • /
    • pp.367-372
    • /
    • 2008
  • In this paper we proposed a model of a fault diagnosis expert system with high reliability to compare identical well-functioning motors. The purpose of the survey was to determine if any differences exit among these identical motors and to identify exactly what these differences were, if in fact they were found. Using measured data for many identical brushless dc motors, this study attempted to find out whether normal and fault can be classified by each other. Measured data was analyzed using the State Transition Model (STM). Based on a proposed STM method, the effect of a different normal state is minimized and the detection of fault is improved in identical motor system. Experimental results are presented to prove that STM method could be a useful tool for diagnosing the condition of identical BLDE motors.