• 전기학회논문지
• /
• 제65권7호
• /
• pp.1236-1241
• /
• 2016

Cancer has been the most frequent in Korea, and pathogenesis and progression of cancer have been known to be occurred through various causes and stages. Recently, the research of chromosomal and genetic disorder and the research about prognostic factor to predict occurrence, recurrence and progress of chromosomal and genetic disorder have been performed actively. In this paper, we analyzed DNA methylation data downloaded from TCGA (The Cancer Genome Atlas), open database, to research bladder cancer which is the most frequent among urinary system cancers. Using three level of methylation data which had the most preprocessing, 59 candidate CpG island were extracted from 480,000 CpG island, and then we analyzed extracted CpG island applying data mining technique. As a result, cg12840719 CpG island were analyzed significant, and in Cox's regression we can find the CpG island with high relative risk in comparison with other CpG island. Shown in the result of classification analysis, the CpG island which have high correlation with bladder cancer are cg03146993, cg07323648, cg12840719, cg14676825 and classification accuracy is about 76%. Also we found out that positive predictive value, the probability which predicts cancer in case of cancer was 72.4%. Through the verification of candidate CpG island from the result, we can utilize this method for diagnosing and treating cancer.

• 전기학회논문지
• /
• 제60권4호
• /
• pp.862-870
• /
• 2011

In this paper, we introduce a new topology of Radial Basis Function-based Polynomial Neural Networks (RPNN) that is based on a genetically optimized multi-layer perceptron with Radial Polynomial Neurons (RPNs). This study offers a comprehensive design methodology involving mechanisms of optimization algorithms, especially Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization (PSO) algorithms. In contrast to the typical architectures encountered in Polynomial Neural Networks (PNNs), our main objective is to develop a design strategy of RPNNs as follows : (a) The architecture of the proposed network consists of Radial Polynomial Neurons (RPNs). In here, the RPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Fuzzy C-Means (FCM) clustering method. The RPN dwells on the concepts of a collection of radial basis function and the function-based nonlinear (polynomial) processing. (b) The PSO-based design procedure being applied at each layer of RPNN leads to the selection of preferred nodes of the network (RPNs) whose local characteristics (such as the number of input variables, a collection of the specific subset of input variables, the order of the polynomial, and the number of clusters as well as a fuzzification coefficient in the FCM clustering) can be easily adjusted. The performance of the RPNN is quantified through the experimentation where we use a number of modeling benchmarks - NOx emission process data of gas turbine power plant and learning machine data(Automobile Miles Per Gallon Data) already experimented with in fuzzy or neurofuzzy modeling. A comparative analysis reveals that the proposed RPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• Tribology and Lubricants
• /
• 제31권6호
• /
• pp.294-301
• /
• 2015

In this paper, we predict the rotordynamic force coefficients of tilting pad journal bearings (TPJBs) with rocker-back pivots, and we compare the predictions to recently published predictions and test data. The present TPJB model considers the rocker-back pivot stiffness calculated based on the Hertzian contact-stress theory, which is nonlinear with the application of a force . For the five-pad TPJB in load-between-pad and load-on-pad configurations, the predictions show the pressure- and film-thickness distributions, the deflection and stiffness of the individual pivots, and bearing stiffness and damping coefficients. The minimum film thickness and peak pressure occur at the bottom pad on which the applied load is directed. Because of the preload, the pres- sure is positive even at the upper pad in the opposite direction to the applied load. The pivot deflection and stiff- ness are maximum at the bottom pad that receives the heaviest pressure load. The predicted stiffness coefficients increase as the static load and rotor speed increase, while the damping coefficients decrease as the rotor speed increases, but increase as the static load increases. In general, the predicted stiffness coefficients agree well with the test data. The predicted damping coefficients overestimate the test data, particularly for large static loads. In general, the current predictive model considering the pivot stiffness improves the accuracy of the rotordynamic performance compared to previously reported models.

• Biomolecules & Therapeutics
• /
• 제23권4호
• /
• pp.379-385
• /
• 2015

The eye irritation potential of drug candidates or pharmaceutical ingredients should be evaluated if there is a possibility of ocular exposure. Traditionally, the ocular irritation has been evaluated by the rabbit Draize test. However, rabbit eyes are more sensitive to irritants than human eyes, therefore substantial level of false positives are unavoidable. To resolve this species difference, several three-dimensional human corneal epithelial (HCE) models have been developed as alternative eye irritation test methods. Recently, we introduced a new HCE model, MCTT HCE$^{TM}$ which is reconstructed with non-transformed human corneal cells from limbal tissues. Here, we examined if MCTT HCE$^{TM}$ can be employed to evaluate eye irritation potential of solid substances. Through optimization of washing method and exposure time, treatment time was established as 10 min and washing procedure was set up as 4 times of washing with 10 mL of PBS and shaking in 30 mL of PBS in a beaker. With the established eye irritation test protocol, 11 solid substances (5 non-irritants, 6 irritants) were evaluated which demonstrated an excellent predictive capacity (100% accuracy, 100% specificity and 100% sensitivity). We also compared the performance of our test method with rabbit Draize test results and in vitro cytotoxicity test with 2D human corneal epithelial cell lines.

• Nutrition Research and Practice
• /
• 제11권4호
• /
• pp.300-306
• /
• 2017

BACKGROUND/OBJECTIVES: The doubly labeled water (DLW) method is considered the gold standard for the measurement of total energy expenditure (TEE), which serves to estimate energy requirements. This study evaluated the accuracy of predictive dietary reference intake (DRI) equations for determining the estimated energy requirements (EER) of Korean adults by using the DLW as a reference method. SUBJECTS/METHODS: Seventy-one participants (35 men and 36 women) aged between 20 and 49 years were included in the study. The subjects' EER, calculated by using the DRI equation ($EER_{DRI}$), was compared with their TEE measured by the DLW method ($TEE_{DLW}$). RESULTS: The DRI equations for EER underestimated TEE by -36.3 kcal/day (-1.3%) in men and -104.5 kcal/day (-4.9%) in women. The percentages of accurate predictions among subjects were 77.1% in men and 62.9% in women. There was a strong linear correlation between $EER_{DRI}$ and $TEE_{DLW}$ (r = 0.783, P < 0.001 in men and r = 0.810, P < 0.001 in women). CONCLUSIONS: The present study supports the use of DRI prediction equations to determine EER in Korean adults. More studies are needed to confirm our results and to assess the validity of these equations in other population groups, including children, adolescents, and older adults.

• 한국지능시스템학회논문지
• /
• 제16권3호
• /
• pp.332-337
• /
• 2006

It has been suggested that the endoscopic color of intramucosal gastric carcinoma is correlated with mucosal vascularity within the carcinomatous tissue. The development of electronic endoscopy has made it possible to quantitatively measure the mucosal hemoglobin volume, using a hemoglobin index. The aim of this study was to make a software program to calculate the hemoglobin index (IHb) and then investigate whether the mucosal IHb determined from the electronic endoscopic data is a useful marker for evaluating the color of intramucosal gastric carcinoma, in particular with regard to its value for discriminating between the histologic types. The mean values of IHb for the carcinoma (IHb-C) and the mean values of IHb for the surrounding non-cancerous mucosa (IHb-N) were calculated in 75 intestinal-type and 34 diffuse-type gastric carcinomas. Then, we analyzed the ratio of the IHb-C to IHb-N. The mean IHb-C/IHb-N ratio in the intestinal-type carcinoma group was higher than that in the diffuse-type carcinoma group (1.28$\pm$0.19 vs. 0.81$\pm$0.18, respectively, p<0.001). When the cut-off point of the C/N ratio was set at 1.00, the accuracy rate, the sensitivity, the specificity, and the positive and negative predictive values of a C/R ratio below 1.00 for the differential diagnosis of diffuse-type carcinoma from intestinal-type carcinoma were 94.5%, 94.1%, 94.7%, 88.9% and 97.3%, respectively. IHb is useful for quantitative measurement of the endoscopic color in intramucosal gastric carcinoma and the IHb-C/IHb-N ratio would be helpful in distinguishing diffuse-type carcinoma from intestinal-type carcinoma.

• 부동산연구
• /
• 제27권3호
• /
• pp.71-86
• /
• 2017

본 연구의 목적은 딥 러닝 방법을 부동산가격지수 예측에 적용해보고, 기존의 시계열분석 방법과의 비교를 통해 부동산 시장 예측의 새로운 방법으로서 활용가능성을 확인하는 것이다. 딥 러닝(deep learning)방법인 DNN(Deep Neural Networks)모형 및 LSTM(Long Shot Term Memory networks)모형과 시계열분석 방법인 ARIMA(autoregressive integrated moving average)모형을 이용하여 여러 가지 부동산가격지수에 대한 예측을 시도하였다. 연구결과 첫째, 딥 러닝 방법의 예측력이 시계열분석 방법보다 우수한 것으로 나타났다. 둘째, 딥 러닝 방법 중에서는 DNN모형의 예측력이 LSTM모형의 예측력보다 우수하나 그 정도는 미미한 수준인 것으로 나타났다. 셋째, 딥 러닝 방법과 ARIMA모형은 부동산 가격지수(real estate price index) 중 아파트 실거래가격지수(housing sales price index)에 대한 예측력이 가장 부족한 것으로 나타났다. 향후 딥 러닝 방법을 활용함으로써 부동산 시장에 대한 예측의 정확성을 제고할 수 있을 것으로 기대된다.

• 품질경영학회지
• /
• 제47권3호
• /
• pp.497-508
• /
• 2019

Purpose: The purpose of this study is to overcome limitations of conventional studies that to predict Baltic Dry Index (BDI). The study proposed applications of Artificial Neural Network (ANN) named Long Short-Term Memory (LSTM) to predict BDI. Methods: The BDI time-series prediction was carried out through eight variables related to the dry bulk market. The prediction was conducted in two steps. First, identifying the goodness of fitness for the BDI time-series of specific ANN models and determining the network structures to be used in the next step. While using ANN's generalization capability, the structures determined in the previous steps were used in the empirical prediction step, and the sliding-window method was applied to make a daily (one-day ahead) prediction. Results: At the empirical prediction step, it was possible to predict variable y(BDI time series) at point of time t by 8 variables (related to the dry bulk market) of x at point of time (t-1). LSTM, known to be good at learning over a long period of time, showed the best performance with higher predictive accuracy compared to Multi-Layer Perceptron (MLP) and Recurrent Neural Network (RNN). Conclusion: Applying this study to real business would require long-term predictions by applying more detailed forecasting techniques. I hope that the research can provide a point of reference in the dry bulk market, and furthermore in the decision-making and investment in the future of the shipping business as a whole.

• 한국환경보건학회지
• /
• 제45권5호
• /
• pp.457-464
• /
• 2019

Objectives: Quantitative structure-activity relationship (QSAR) is one of the effective alternatives to animal testing, but its credibility in terms of toxicity prediction has been questionable. Thus, this work aims to evaluate its predictive capacity and find ways of improving its credibility. Methods: Using $TOPKAT^{(R)}$, OECD toolbox, and $Derek^{(R)}$, all of which have been applied world-wide in the research, industrial, and regulatory fields, an analysis of prediction credibility markers including accuracy (A), sensitivity (S), specificity (SP), false negative (FN), and false positive (FP) was conducted. Results: The multi-application of QSARs elevated the precision credibility relative to individual applications of QSARs. Moreover, we found that the type of chemical structure affects the credibility of markers significantly. Conclusions: The credibility of individual QSAR is insufficient for both the prediction of chemical toxicity and regulation of hazardous chemicals. Thus, to increase the credibility, multi-QSAR application, and compensation of the prediction deviation by chemical structure are required.

• 한국환경보건학회지
• /
• 제45권5호
• /
• pp.511-519
• /
• 2019

Objectives: The standard method for the enumeration of environmental Legionella is culturing, which has several disadvantages, including long incubation and poor sensitivity. The purpose of this study is to demonstrate the usefulness of real-time PCR and to improve the standard method. Methods: In 200 environmental water samples, a real-time PCR and culture were conducted to detect and quantify Legionella. Using with the results of the survey, we compared the real-time PCR with the culture. Results: Each real-time PCR assay had 100% specificity and excellent sensitivity (5 GU/reaction). In the culture, 36 samples were positive and 164 samples were negative. Based on the results of the culture, real-time PCR showed a high negative predictive value of 99%, 35 samples were true positive, 105 samples were true negative, 59 samples were false positive and one sample was a false negative. Quantitative analysis of the two methods indicated a weak linear correlation ($r^2=0.29$, $r^2=0.61$, respectively). Conclusions: Although it is difficult to directly apply quantitative analysis results of real-time PCR in the enumeration of environmental Legionella, it can be used as a complementary means of culturing to rapidly screen negative samples and to improve the accuracy of diagnosis.