• 한국연초학회지
• /
• 제20권2호
• /
• pp.183-190
• /
• 1998

This study was conducted to analyze chemical components in flue-cured tobacco using near infrared spectroscopy(NIRS). Samples were collected in '96 and '97 crop year and were scanned in the wavelengths of 400 ～ 2500 nm by near infrared analyzer(NIRSystem Co., Model 6500). Calibration equations were developed and then analyzed flue-cured samples by NIRS. The standard error of calibration(SEC) and performance (SEP) of '96 crop year samples between NIRS and standard laboratory analysis(SLA) were 0.18% and 0.24% for nicotine, 1.60% and 1.77% for total sugar, 0.13% and 0.15% for total nitrogen, 0.58% and 0.68% for crude ash, 0.23% and 0.28% for ether extracts, and 0.09% and 0.08% for chlorine, respectively. The coefficient of determination($R^2$) of calibration and prediction samples between NIRS and SLA of '96 crop year samples was 0.94～0.99 and 0.83～0.97 depending on chemical components, respectively. The SEC and SEP of '97 crop year samples were similar to those of '96 crop year samples. The SEP of '97 crop year samples which were analyzed using '96 calibration equation was 0.32 % for nicotine, 2.72% for total sugar, 0.14 % for total nitrogen, 1.00 % for crude ash, 0.48 for ether extracts and 0.17% for chlorine, respectively. The prediction result was more accurate when calibration and prediction samples were produced in the same crop year than those of the different crop year. The SEP of '96 and '97 crop year samples using calibration equation which was developed '96 plus '97 crop year samples was similar to that of '96 crop year samples using 96 calibration equation and that of '97 crop year samples using '97 calibration equation, respectively. The SEP of '97 crop year samples using calibration equation which was developed '96 plus '97 crop year samples was lower than that of '97 crop year samples analyzed by '96 calibration equation. To improve the analytical inaccuracy caused by the difference of crop year between calibration and prediction samples, we need to include the prediction sample spectra which are different from calibration sample spectra in recalibration sample spectra, and then develop recalibration equation. Although the analytical result using NIR is not as good as SLA, the chemical component analysis using NIR can apply to tobacco leaves, leaf process or tobacco manufacturing process which demand the rapid analytical result.

• 한국정보과학회논문지:정보통신
• /
• 제34권3호
• /
• pp.156-167
• /
• 2007

본 논문에서는 VBR(Variable-Bit-Rate) 트래픽의 비선형적이고 버스티한 특성을 모델화 한 GOP ARIMA(ARIMA for Group Of Pictures) 모델을 칼만 필터 알고리즘을 이용하여 실시간으로 예측하는 기법을 제안한다. 칼만 필터를 이용한 예측 기법은 GOP ARIMA의 상태공간 모델링 과정과 향후 N초 간의 트래픽을 예측하는 과정으로 구성된다. 실험을 위해 GOP의 크기가 각각 15인 세 가지 종류의 MPEG VBR 트래픽(뉴스, 드라마, 스포츠)을 제작하였고, 칼만 필터를 이용한 세 가지 종류의 트래픽의 예측 결과를 선형 예측법과 이중 지수 평활법을 이용해 예측한 결과와 비교해 예측 성능이 상대적으로 우수함을 확인할 수 있었다. 또한 예측값에 신뢰 구간을 설정하는 신뢰 구간 분석법을 통해 트래픽 관점에서 장면 변화를 예측하는 방법을 제시하였다. 본 논문의 칼만 필터 기반의 예측 알고리즘은 MPEG 기반 VBR 트래픽을 비롯한 기타 인터넷 트래픽을 실시간으로 예측하는 방법과 이를 이용해 인터넷 서버의 설계 및 자원 할당 정책 등을 위한 트래픽 엔지니어링 연구에 기여할 수 있을 것이다.

• 한국생물정보학회:학술대회논문집
• /
• 한국생물정보시스템생물학회 2004년도 The 3rd Annual Conference for The Korean Society for Bioinformatics Association of Asian Societies for Bioinformatics 2004 Symposium
• /
• pp.250-261
• /
• 2004

A novel method for ab initio prediction of protein tertiary structures, PROFESY (PROFile Enumerating SYstem), is introduced. This method utilizes secondary structure prediction information and fragment assembly. The secondary structure prediction of proteins is performed with the PREDICT method which uses PSI-BLAST to generate profiles and a distance measure in the pattern space. In order to predict the tertiary structure of a protein sequence, we assemble fragments in the fragment library constructed as a byproduct of PREDICT. The tertiary structure is obtained by minimizing the potential energy using the conformational space annealing method which enables one to sample diverse low lying minima of the energy function. We apply PROFESY for prediction of some proteins with known structures, which shows good performances. We also participated in CASP5 and applied PROFESY to new fold targets for blind predictions. The results were quite promising, despite the fact that PROFESY was in its early stage of development. In particular, the PROFESY result is the best for the hardest target T0161.

• 전자공학회논문지
• /
• 제53권12호
• /
• pp.50-56
• /
• 2016

이 논문은 UHD 영상을 지원하는 멀티 디코더 용 인트라 예측 회로의 구조와 설계를 제안하고 있다. 제안된 회로는 가장 최신의 비디오 압축 표준인 HEVC뿐만 아니라 H.264도 지원한다. 이 회로는 기본적인 인트라 예측 기능이외에 추가적으로 H.264 표준에 정의되어 있는 참조 샘플 필터 연산과 HEVC 표준에 정의되어 있는 약한 참조 샘플 필터 및 강한 참조 샘플 필터 연산을 처리하는 기능도 갖고 있다. 공통적인 연산부와 내부 저장소를 공유함으로써 회로의 크기를 감소시켰으며, 병렬 연산을 통하여 성능을 향상시켰다. 제안된 회로는 Verilog HDL(Hardware Description Language)을 이용하여 RTL(Register Transfer Level)로 기술하였으며, Cadence의 NC-Verilog를 이용하여 기능을 검증하였다. RTL 회로를 Synopsys의 Design Compiler 및 130nm 표준 셀 라이브러리를 이용하여 합성하였다. 합성된 게이트 수준 회로는 69,694개의 게이트로 구성되며, 최대 동작주파수 157MHz에서 4K-UHD HEVC 영상을 초당 100 ~ 280 프레임의 속도로 처리한다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제15권3호
• /
• pp.145-152
• /
• 2015

We consider an online selective-sample learning problem for sequence classification, where the goal is to learn a predictive model using a stream of data samples whose class labels can be selectively queried by the algorithm. Given that there is a limit to the total number of queries permitted, the key issue is choosing the most informative and salient samples for their class labels to be queried. Recently, several aggressive selective-sample algorithms have been proposed under a linear model for static (non-sequential) binary classification. We extend the idea to hidden Markov models for multi-class sequence classification by introducing reasonable measures for the novelty and prediction confidence of the incoming sample with respect to the current model, on which the query decision is based. For several sequence classification datasets/tasks in online learning setups, we demonstrate the effectiveness of the proposed approach.

• International journal of advanced smart convergence
• /
• 제11권2호
• /
• pp.30-37
• /
• 2022

Because fine dust (PM10) has a close effect on the environment, fine dust generated in the climate and living environment has a bad effect on the human body. In this study, the LSTM model was applied to predict and analyze the effect of fine dust on Gwangju Metropolitan City in Korea. This paper uses prediction values of input variables selected through correlation analysis to confirm fine dust prediction performance. In this paper, data from the Gwangju Metropolitan City area were collected to measure fine dust. The collection period is one year's worth of data was used from january to December of 2021, and the test data was conducted using three-month data from January to March of 2022. As a result of this study, in the as a result of predicting fine dust (PH10) and ultrafine dust (PH2.5) using the LSTM model, the RMSE was 4.61 and the test result value was as low as 4.37. This reason is judged to be the result of the contents of the one-year sample.

• 한국산림과학회지
• /
• 제95권6호
• /
• pp.778-783
• /
• 2006

표고버섯의 재배와 출하 결정에서 단기 가격의 예측은 매우 중요하다. 표고버섯 가격의 형성에는 많은 요인들이 작용하고 있기 때문에 이를 구조모형으로 예측하는 것은 어려운 일이다. Box-Jenkins 방법을 이용한 표고버섯과 모형선정 과정에서 발생할 수 있는 오류를 줄이고 경우에 따라서는 더 높은 예측력을 가지기도 한다. 이 연구는 1992~2005년의 가락시장 표고버섯 중품 가격자료를 이용하여 시계열 분석 모형을 구축하고 단기 가격을 예측한 것이다. 그리고 분석에 포함되지 않은 2006년의 실제가격과 예측결과를 비교하였다. 분석 결과는 날씨 변화의 영향으로 시장에 교란이 발생하였던 시기를 제외하면 비교적 높은 정확도를 보여 주어 모형의 유용성을 시사한다.

• 한국항해항만학회지
• /
• 제48권2호
• /
• pp.109-115
• /
• 2024

To develop a shipping company insolvency prediction model, we sampled shipping companies that closed between 2005 and 2023. In addition, a closed company and a normal company with similar asset size were selected as a paired sample. For this study, data of a total of 82 companies, including 42 closed companies and 42 general companies, were obtained. These data were randomly divided into a training set (2/3 of data) and a testing set (1/3 of data). Training data were used to develop the model while test data were used to measure the accuracy of the model. In this study, a prediction model for Korean shipping insolvency was developed using financial ratio variables frequently used in previous studies. First, using the LASSO technique, main variables out of 24 independent variables were reduced to 9. Next, we set insolvent companies to 1 and normal companies to 0 and fitted logistic regression, LDA and QDA model. As a result, the accuracy of the prediction model was 82.14% for the QDA model, 78.57% for the logistic regression model, and 75.00% for the LDA model. In addition, variables 'Current ratio', 'Interest expenses to sales', 'Total assets turnover', and 'Operating income to sales' were analyzed as major variables affecting corporate insolvency.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권3호
• /
• pp.157-162
• /
• 2016

In this paper, a yield prediction model based on relevance vector machine (RVM) and a granular computing model (quotient space theory) is presented. With a granular computing model, massive and complex meteorological data can be analyzed at different layers of different grain sizes, and new meteorological feature data sets can be formed in this way. In order to forecast the crop yield, a grey model is introduced to label the training sample data sets, which also can be used for computing the tendency yield. An RVM algorithm is introduced as the classification model for meteorological data mining. Experiments on data sets from the real world using this model show an advantage in terms of yield prediction compared with other models.

• Journal of the Optical Society of Korea
• /
• 제13권2호
• /
• pp.279-285
• /
• 2009

Prediction of glucose concentration in the interstitial fluid (ISF) based on mid-infrared absorption spectroscopy was examined at the glucose fundamental absorption band of 1000 - 1500/cm (10 - 6.67 um) using multi-component analysis. Simulated ISF samples were prepared by including four major ISF components. Sodium lactate had absorption spectra that interfere with those of glucose. The rest NaCl, KCl and $CaCl_2$ did not have any signatures. A preliminary experiment based on Design of Experiment, an optimization method, proved that sodium lactate influenced the prediction accuracy of glucose. For the main experiment, 54 samples were prepared whose glucose and sodium lactate concentration varied independently. A partial least squares regression (PLSR) analysis was used to build calibration models. The prediction accuracy was dependent on spectrum preprocessing methods, and Mean Centering produced the best results. Depending on calibration sample sets whose sodium lactate had different concentration levels, the standard error prediction (SEP) of glucose ranged $17.19{\sim}21.02\;mg/dl$.