• 한국통신학회논문지
• /
• 제22권2호
• /
• pp.344-352
• /
• 1997

This paper proposes an efficient lossless coding scheme for tree structured vector quantization (TSVQ) system which efficiently exploits inter-block correlation. The TSVQ index of the current block is adaptively arithmeticencoded depending on the indices of the previous blocks. This paper also presents a reductio method, which effectively resolve the memory problem which usually arises in many conditional entropy coding schemes. Simulation results show that the proposed scheme provides remarkable bitrate reduction by effectively exploiting not only linear but also non-linear inter-block correlation.

• 한국통신학회논문지
• /
• 제28권2C호
• /
• pp.100-109
• /
• 2003

가변길이 나무구조 벡터양자화기(VLTSVQ : variable-length tree-structured vector quantizer)를 기반으로 하는 영상 부호화 방식인 차분 인덱스(DI : Differential index) 할당기법을 제안하였다. 각 소스벡터는 VLTSVQ의 단말 노드로 양자화가 되어지고, 각 단말 노드는 유일한 이진 벡터로 표현된다. 제안한 방법은 영상의 화질은 유지하면서 압축률을 개선하기 위해 이웃하는 영상 블록들간의 상관성을 이용하였다. 모의실험을 통하여 제안한 방법이 기존 방법들에 비해 매우 높은 압축률을 보였으며, 화소간의 상관성이 높은 영상에 대해서는 63.2%의 발생 비트율 감소를 확인하였다. 그리고 영상내의 이웃블록들간 상관성이 커질수록 더 큰 비트율이 감소됨을 보였다. 제안한 부호화 기법은 일반적으로 이웃된 화소들간에 높은 상관성을 가진 MR(magnetic resonance)영상 부호화에 효율적으로 사용될 수 있다.

• Journal of information and communication convergence engineering
• /
• 제9권6호
• /
• pp.747-752
• /
• 2011

The position detection of overlapping area in the interframe for image stitching using auto and cross correlation function (ACCF) and compounding one image with the stitching algorithm is presented in this paper. ACCF is used by autocorrelation to the featured area to extract the filter mask in the reference (previous) image and the comparing (current) image is used by crosscorrelation. The stitching is detected by the position of high correlation, and aligns and stitches the image in shifting the current image based on the moving vector. The ACCF technique results in a few computations and simplicity because the filter mask is given by the featuring block, and the position is enabled to detect a bit movement. Input image captured from CMOS is used to be compared with the performance between the ACCF and the window correlation. The results of ACCF show that there is no seam and distortion at the joint parts in the stitched image, and the detection performance of the moving vector is improved to 12% in comparison with the window correlation method.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.4102-4102
• /
• 2001

In multivariate analysis, absorbance spectrum is measured over a band of wavelengths. One does not often pay attention to the size of this wavelength band. However, it is desirable that spectrum is measured at only necessary wavelengths as long as the acceptable accuracy of prediction can be met. In this paper, the method of selecting an optimal band of wavelengths based on the loading vector analysis was proposed and applied for determining total protein in human serum using near-infrared transmission spectroscopy and PLSR. Loading vectors in the full spectrum PLSR were used as reference in selecting wavelengths, but only the first loading vector was used since it explains the spectrum best. Absorbance spectra of sera from 97 outpatients were measured at 1530∼1850 nm with an interval of 2 nm. Total protein concentrations of sera were ranged from 5.1 to 7.7 g/㎗. Spectra were measured by Cary 5E spectrophotometer (Varian, Australia). Serum in the 5 mm-pathlength cuvette was put in the sample beam and air in the reference beam. Full spectrum PLSR was applied to determine total protein from sera. Next, the wavelength region of 1672∼1754 nm was selected based on the first loading vector analysis. Standard Error of Cross Validation (SECV) of full spectrum (1530∼l850 nm) PLSR and selected wavelength PLSR (1672∼1754 nm) was respectively 0.28 and 0.27 g/㎗. The prediction accuracy between the two bands was equal. Wavelength selection based on loading vector in PLSR seemed to be simple and robust in comparison to other methods based on correlation plot, regression vector and genetic algorithm. As a reference of wavelength selection for PLSR, the loading vector has the advantage over the correlation plot since the former is based on multivariate model whereas the latter, on univariate model. Wavelength selection by the first loading vector analysis requires shorter computation time than that by genetic algorithm and needs not smoothing.

• Journal of the Korean Data and Information Science Society
• /
• 제17권4호
• /
• pp.1129-1139
• /
• 2006

Pearson's correlation coefficient and vector similarity are generally applied to The users' similarity weight of user based recommender system. This study is needed to find that the correlation coefficient of similarity weight is effected by the number of pair response and significance probability. From the classified correlation coefficient by the significance probability test on the correlation coefficient and pair of response, the change of MAE is studied by comparing the predicted precision of the two. The results are experimentally related with the change of MAE from the significant correlation coefficient and the number of pair response.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.677-680
• /
• 1998

In this paper, we proposed a lwo bit rate subband coding with adaptive vector quantization using the correlation between motion vector and block energy in subband. In this method, the difference between the input signal and the motion compensated interframe prediction signal is decomposed into several narrow bands using quadrature mirror filter (QMF) structure. The subband signals are then quantized by adaptive vector quantizers. In the codebook generating process, each classified region closer to the block value in the same region after the classification of region by the magnitude of motion vector and the variance values of subband block. Because codebook is genrated considering energy distribution of each region classified by motion vector and variance of subband block, this technique gives a very good visual quality at low bit rate coding.

• 방송공학회논문지
• /
• 제10권4호통권29호
• /
• pp.621-631
• /
• 2005

다시점 동영상 부호화기의 성능을 향상시키기 위해서 본 논문에서는 평행식 카메라 구조에서의 효율적인 변이 벡터 예측을 이용한 부호화 방식을 제안한다 변이 벡터는 움직임 벡터와는 달리 다시점 카메라 구조 정보로부터 예측이 가능하다. 이러한 성질을 이용하여 예측하여 구한 예측 벡터와 직접 추정한 변이 벡터와의 차이값을 부호화한다. 그러므로 변이 벡터 부호화의 성능을 향상시키기 위해서 정교한 변이 벡터의 예측이 필요하다. 기존의 벡터 예측 방식은 미리 부호화된 주위 블록의 변이 벡터를 이용하여 현재 블록의 변이 벡터를 예측하지만 제안 알고리듬은 다시점 영상간의 상관성을 이용한다. 본 논문에서는 5시점 동영상에 대해서 차벡터의 엔트로피와 절대 평균값을 구하는 실험을 수행하였다. 실험 결과를 통해서 기존의 공간적인 상관성만을 이용하여 변이 벡터를 부호화하는 방식보다 제안 알고리듬이 우수한 성능을 보임을 확인하였다. 제안 알고리듬은 기존알고리듬과 비교하여 영상의 화질을 유지하면서 $30{\~}40\%$의 부호화 효율을 증가시킨다.

• Journal of the Korean Data and Information Science Society
• /
• 제24권2호
• /
• pp.401-408
• /
• 2013

Soil moisture is a very important variable in various area of hydrological processes. We predict the soil moisture using a support vector regression. The model is trained and tested using the soil moisture data observed in five sites in the Yongdam dam basin. With respect to soil moisture data of of four sites-Jucheon, Bugui, Sangieon and Ahncheon which are used to train the model, the correlation coefficient between the esimtates and the observed values is about 0.976. As the result of the application to Cheoncheon2 for validating the model, the correlation coefficient between the estimates and the observed values of soil moisture is about 0.835. We compare those results with those of artificial neural network models.

• The Korean Journal of Ecology
• /
• 제9권3호
• /
• pp.135-147
• /
• 1986

The simplification and the searching trends of complex data which assumed relationship between predictor variables and object variables are one of primary objective of ecological research. This study was aimed to apply cononical analysis consisting of canonical correlation analysis and canonical variate analysis related to lichen vegetation and several environmental variables which are elevation, height on grond, exposure side and cover values. Data collected from the Duckyoo National Park in August 1985. Lichen species was ranked by eqivocation information theory with cover values. Canonical correlation analysis was applied to one data set both set both environmental variables and lichem family. In order to make two sets of data matrix the scale of position vector ordination was calculated from the vector scalar product for lichen species. Canonical variate analysis was applied to rearranged data which was made by interval class code for environmental variables. The sharpness values was calculated in frequency of cotingency tables and the dispersion profiles of each species in classes of environmental variables was designed to extract component values based on the decomposition of expected frequencies in contingency table. The results of canonical correlation analysis revealed canonical first correlation value 0.815(89%), and second correlation value 0.083(11%). Significance test showed that the hypothesis of joint mutuallity of canonical correlation is accepted (P>0.05). The relation between canonical score of vegetation variables and that of environmental variable indicated linear tendency.

• 대한의용생체공학회:의공학회지
• /
• 제23권2호
• /
• pp.101-107
• /
• 2002

이 논문에서는 자기공명심장영상에서 내벽과 외벽의 추출을 위한 반자동 분할 알고리즘을 제안하였다. 이 알고리즘은 Generalized gradient vector flow snake와 초기 윤곽선 예측 과정을 기반으로 한다. 특히 이 알고리즘은 내벽과 외벽의 공간적인 특설을 이용하며 Cross profile correlation matching (CPCM)을 사용한다. 현재 공간에서의 이전 시간에 관계된 영상과 현재 시간에서의 공간에 관계된 영상을 사용하여 초기 윤곽선 예측을 더욱 효과적으로 수행하였다. Multislice와 multiphase의 Siemens와 GE. Medinus 자기공명심장영상을 사용하여 실험하였고 많은 영상들에 대해 충분히 만족할만한 결과를 얻었다. 그리고 분할한 결과로 quantitative analysis를 수행하였고 시각적으로 보여주었다. 개발된 소프트웨어는 Visual C++을 사용하여 windows 환경의 응용프로그램으로 개발되었다.