• Title/Summary/Keyword: 통계적 유사성

Search Result 378, Processing Time 0.033 seconds

PCA-Based MPEG Video Retrieval in Compressed Domain (PCA에 기반한 압축영역에서의 MPEG Video 검색기법)

  • 이경화;강대성
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.40 no.1
    • /
    • pp.28-33
    • /
    • 2003
  • This paper proposes a database index and retrieval method using the PCA(Principal Component Analysis). We perform a scene change detection and key frame extraction from the DC Image constructed by DCT DC coefficients in the compressed video stream that is video compression standard such as MPEG. In the extracted key frame, we use the PCA, then we can make codebook that has a statistical data as a codeword, which is saved as a database index. We also provide retrieval image that are similar to user's query image in a video database. As a result of experiments, we confirmed that the proposed method clearly showed superior performance in video retrieval and reduced computation time and memory space.

The Stabilization Model of Receive Sensitivity of Thick Film Oscillation Circuit for Air Explosion Shell (공중폭발 탄용 후막 발진회로의 수신감도 안정화 모델)

  • Lim, Young-Cheol;Kim, Kwan-Woo;Choi, Jin-Bong;Jung, Young-Gook
    • The Transactions of the Korean Institute of Power Electronics
    • /
    • v.15 no.1
    • /
    • pp.17-26
    • /
    • 2010
  • This paper proposes the stabilization modelling method of receive sensitivity of thick film oscillation circuit for air explosion shell. The proposed method minimizes the errors of the thick film oscillator which uses air explosion shell for military and it is very similar to the simulation for maximizing the efficiency. Firstly, the proposed method gets the equation of new form through statistical analysis from the data which shows always fixed and stabilized output from the real model. Secondly, the simulation is designed which is possible to predict the output, after optimization that is a model to match the each electronic component output by the equation. In a conclusion, the usefulness, the accuracy and the precision are proved as compared with the output data of real model.

Preliminary Research on Domestic Application of Vegetation Drought Response Index (VegDRI) (식생가뭄반응지수(VegDRI) 국내 적용방안 기초연구)

  • Park, Junehyeong;Ji, Hee-sook;Lim, Yoon-Jin;Kim, Baek-Jo
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2017.05a
    • /
    • pp.248-248
    • /
    • 2017
  • 최근 가뭄 모니터링을 위해 과거에 비하여 고해상도의, 물리적으로 기반을 두는 정보가 요구되고 있다. 기존에 주로 활용하고 있는 통계적 방법론 기반의 가뭄지수들은 지니고 있는 한계에 대해 여러 개선과정을 거치고 있으나, 기상변수로부터 지표상의 식생 관련 변수로의 전파 과정에 대한 개별 통계적 가뭄지수 간의 관계 설명이 매우 어렵다. 이와 같은 관계로, 국내 유역에서의 물리적 기반을 둔 고해상도 가뭄 판단방법에 대한 시도가 필요한 시점이다. Brown et al. (2008)은 위성기반 식생정보, 기상학적 가뭄지수, 지형학적 조건을 고려한 식생가뭄반응지수(Vegetation Drought Response Index; 이하 VegDRI)를 개발하였다. 학습자료에 대해 CART 기반의 경험적 모델을 구축하여, 격자마다 근-실시간 자료를 적용한 VegDRI를 산출하여 고해상도의 지도를 산출하는 방식을 제시하였다. VegDRI는 NCDC의 U.S. Drought Monitoring에 활용되고 있으며, NOAA의 Drought Task Force Assessment Protocol에서는 가뭄 모니터링의 기준으로 설정되어 있다. 본 연구에서는 국내에 VegDRI를 적용하고자 필요한 자료수집 및 전처리 과정을 거쳐 결과를 도출하였다. 기상청 ASOS 기상관측소에서 얻은 기상변수, MODIS 위성으로부터 추출된 정규식생지수(Normalized Difference Vegetation Index; NDVI), 지형학적 정보와 기상학적 가뭄지수(SPI, PDSI)를 기계학습으로 모델링하여 VegDRI를 산출하였다. 산출된 VegDRI 공간분포도에 대하여 기존에 활용되던 유관기관의 가뭄 판단방법과의 유사성과 차이점을 비교 검토하여 적용성을 평가하였다.

  • PDF

Effect of Fermented Brown Seaweed Waste (FBSW) on Milk Production, Composition and Physiological Responses in Holstein Dairy Cows (발효미역부산물의 첨가가 Holstein 비유우의 비유성적 및 생리반응에 미치는 영향)

  • Hong, Zhong-Shan;Lee, Zhe-Hu;Xu, Cheng-Xiong;Yin, Jin-Long;Jin, Young-Cheng;Lee, Hyun-Jun;Lee, Sang-Bum;Choi, Yun-Jaie;Lee, Hong-Gu
    • Journal of Animal Science and Technology
    • /
    • v.52 no.4
    • /
    • pp.287-296
    • /
    • 2010
  • This study was conducted to determine effects of fermented brown seaweed waste (FBSW) on milk production, composition and physiological responses as functional feed for 60 days in Holstein dairy cows. A total of 24 Holstein dairy cows (average age 49.33 months, average lactation days 175, Reproduction 2.0) were randomly allocated into control(basal diet), 1% FBSW (180g in basal diet) and 2% FBSW (360g in basal diet) groups with 8 replications for 60 days. Daily milk yield and composition (fat, protein, SNF, MUN) were not affected by FBSW supplementation, but Ca level in milk was significantly increased 4.29 mg/dl and 2.91 mg/dl in 1% and 2% groups compared to control group (p<0.05) at the end of the experiment, respectively. The somatic cell count (SCC) in milk was not significant. The plasma $T_4$ level (concentration) were increased in 1% and 2% FBSW compared to control group at the end of the experiment (p<0.05), but between triiodothyronine ($T_3$) and thyroxin ($T_4$) levels were not significant. Concentrations of plasma glucose in control, 1% FBSW and 2% FBSW groups were 64. 37mg/dl, 66.15mg/dl and 73.02 mg/dl and plasma NEFA level was 0.30~0.32 mEq/dl. Concentrations of BUN tended to be higher for FBSW group than control group. Although WBC, RBC, Hb, Hct, T-B, ALP, and GPT levels were not affected by FBSW supplementation, GOT level was significantly decreased in cows fed 1% FBSE diet compared to control group (P<0.05). Therefore we strongly suggest that the 1% FBSW supplementation in basal diet increases the milk yield and Ca level in Holstein dairy cows.

A Study on the Oceanic Diffusion of Liquid Radioactive Effluents based on the Statistical Method (통계적 방법을 이용한 방사성 물질의 해양 확산 평가)

  • Kim, Soong-Pyung;Lee, Goung-Jin
    • Journal of Radiation Protection and Research
    • /
    • v.23 no.1
    • /
    • pp.1-6
    • /
    • 1998
  • A diffusion model of radioactive liquid effluents is developed and applied for YGN NPP's site, based on the Gaussian plume type model. Due to the complexity of oceanic diffusion characteristics of YGN site, a simple and reliable statistical model based on Reg. Guide 1.113 is developed. Also, a computer code package to calculate dilution factors as a function of plant operation conditions and pathway of radioactive materials. A liquid effluents diffusion model is developed by dividing the diffusion range into two categories, i. e, a near field mixing region and a far field mixing region. In the near field, the initial mixing is affected by a buoyance force, a high initial turbulence and momentum which is characterized by a plant operation condition and environmental conditions. The far field mixing is similar to gaseous effluents diffusion. So, beyond the near field region, wellknown Gaussian plume model was adopted. A different area averages of Gaussian plume equation was taken for each radioactive exposure pathway. As a result, we can get different dilution factors for different pathways. Results shows that present dilution factors used for YGN ODCM is too much overestimated compared with dilution factors calculated with the developed model.

  • PDF

Audio Fingerprint Extraction Method Using Multi-Level Quantization Scheme (다중 레벨 양자화 기법을 적용한 오디오 핑거프린트 추출 방법)

  • Song Won-Sik;Park Man-Soo;Kim Hoi-Rin
    • The Journal of the Acoustical Society of Korea
    • /
    • v.25 no.4
    • /
    • pp.151-158
    • /
    • 2006
  • In this paper, we proposed a new audio fingerprint extraction method, based on Philips' music retrieval algorithm, which uses the energy difference of neighboring filter-bank and probabilistic characteristics of music. Since Philips method uses too many filter-banks in limited frequency band, it may cause audio fingerprints to be highly sensitive to additive noises and to have too high correlation between neighboring bands. The proposed method improves robustness to noises by reducing the number of filter-banks while it maintains the discriminative power by representing the energy difference of bands with 2 bits where the quantization levels are determined by probabilistic characteristics. The correlation which exists among 4 different levels in 2 bits is not only utilized in similarity measurement. but also in efficient reduction of searching area. Experiments show that the proposed method is not only more robust to various environmental noises (street, department, car, office, and restaurant), but also takes less time for database search than Philips in the case where music is highly degraded.

An assessment of statistical errors of articles in the Journal of Korean Academy of Prosthodontics: Comparison between Korean version and English version (대한치과보철학회지에 게재된 논문의 통계적 오류: 국문논문과 영문논문의 비교)

  • Park, Dong-Gyu;Choi, Yong-Geun;Kim, Young-Su;Shin, Sang-Wan
    • The Journal of Korean Academy of Prosthodontics
    • /
    • v.47 no.3
    • /
    • pp.273-285
    • /
    • 2009
  • Statement of problem: The aim of dental research is to advance scientific knowledge and leads to improvement in the treatment and prevention of dental disease. Utilizing an effective research design and adequate statistical methods are essential procedures ensuring that the results of researches are based on evidences. A research should utilize proper statistical methods without statistical errors; Otherwise, it could adversely affect clinical practice and future research. Purpose: This study was made to investigate the statistical methods used in the Journal of Korean Academy of Prosthodontics (JKAP) and then to assess them for the statistical errors. Material and methods: Among the total of 399 articles in the JKAP published from 2000 to 2006, 292 articles using statistics were reviewed. The validity of the statistical methods used in them were assessed using a checklist based on the guideline for statistical reporting in the uniform requirements for manuscripts submitted to biomedical journals by International Committee of Medical Journal Editors. The checklist consisted of three categories of statistical errors: 1) Unspecified computer statistical packages, 2) Inadequate description of statistical methods, 3) Misuse of statistical terms. Then, the results were compared between the Korean version and the English version in the JKAP. Results: Among the 212 articles using statistics in the Korean version, 115 articles (54%) and among the 80 articles using statistics in the English version, 47 articles (59%) were shown to have unspecified computer statistical packages without statistically significant difference (P = .66). Likewise, 101 articles (48%) in the Korean version and 25 articles (31%) in the English version were shown to have the inadequate description of statistical methods without statistically significant difference (P = .09). However, 114 articles (54%) in the Korean version and 19 articles (24%) in the English version were shown to have the misuse of statistical terms with statistically significant difference (P = .01). Conclusion: Some of the articles in the JKAP had inadequate statistical validity, given the statistical errors identified in this assessment. Hence, dental researchers should be more careful when it comes to describing and applying statistical methods.

Consideration of Patient Position on Posteroanterior Chest Projection (흉부 후·전 검사 시 검사자세에 관한 고찰)

  • Joo, young-cheol;Lim, cheong-hwan;Lim, woo-taek;Kim, hee-jin;Lee, seung-hwan
    • Proceedings of the Korea Contents Association Conference
    • /
    • 2015.05a
    • /
    • pp.161-162
    • /
    • 2015
  • 본 연구는 chest PA 검사 시 교과서에서 권고하는 검사자세와 임상에서 주로 이용되고 있는 검사자세의 폐야와 견갑골의 겹침 정도 차이를 비교 고찰함으로써, 임상에서 사용되고 있는 자세의 유용성을 알아보고자 진행한 연구이다. 연구 결과 세 자세 모두 견갑골을 폐야에서 제거하는데 유사한 결과를 보였으며, 연령에 따른 겹침의 차이는 통계적 유의성이 없었으나, 임상에서 현재 임상에서 사용 중인 검사자세가 성별에 따른 겹침 면적에는 차이를 보였으며, 통계적으로도 유용한 결과는 보였다.

  • PDF

Generation of Roughness Using the Random Midpoint Displacement Method and Its Application to Quantification of Joint Roughness (랜덤중점변위법에 의한 거칠기의 생성 및 활용에 관한 연구)

  • Seo, Hyeon-Kyo;Um, Jeong-Gi
    • Tunnel and Underground Space
    • /
    • v.22 no.3
    • /
    • pp.196-204
    • /
    • 2012
  • Quantification of roughness plays an important role in modeling strength deformability and fluid flow behaviors of rock joints. A procedure was suggested to simulate joint roughness, and characteristics of the roughness was investigated in this study. Stationary fractional Brownian profiles with known input values of the fractal parameter and other profile properties were generated based on random midpoint displacement method. Also, a procedure to simulate three dimensional roughness surface was suggested using the random midpoint displacement method. Selected statistical roughness parameters were calculated for the generated self-affine profiles to investigate the attribute of roughness. Obtained results show that statistical parameters applied in this study were able to consider correlation structure and amplitude of the profiles. However, effect of data density should be tackled to use statistical parameters for roughness quantification.

Statistical Modeling of Joint Distribution Functions for Reliability Analysis (신뢰성 해석을 위한 결합분포함수의 통계모델링)

  • Noh, Yoojeong;Lee, Sangjin
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.15 no.5
    • /
    • pp.2603-2609
    • /
    • 2014
  • Reliability analysis of mechanical systems requires statistical modeling of input random variables such as distribution function types and statistical parameters that affect the performance of the mechanical systems. Some random variables are correlated, but considered as independent variables or wrong assumptions on input random variables have been used. In this paper, joint distributions were modeled using copulas and Bayesian method from limited number of data. To verify the proposed method, statistical simulation tests were carried out for various number of samples and correlation coefficients. As a result, the Bayesian method selected the most probable copula types among candidate copulas even though the candidate copula shapes are similar for low correlations or the number of data is limited. The most probable copulas also yielded similar reliabilities with the true reliability obtained from a true copula, so that it can be concluded that the Bayesian method provides accurate statistical modeling for the reliability analysis.