• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.7
• /
• pp.378-388
• /
• 2000

In this paper, we propose Fuzzy Polynomial Neural Networks(FPNN) based on Polynomial Neural Networks(PNN) and Fuzzy Neural Networks(FNN) for model identification of complex and nonlinear systems. The proposed FPNN is generated from the mutually combined structure of both FNN and PNN. The one and the other are considered as the premise part and consequence part of FPNN structure respectively. As the consequence part of FPNN, PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and self-organizing networks that can be generated. FPNN is available effectively for multi-input variables and high-order polynomial according to the combination of FNN with PNN. Accordingly it is possible to consider the nonlinearity characteristics of process and to get better output performance with superb predictive ability. As the premise part of FPNN, FNN uses both the simplified fuzzy inference as fuzzy inference method and error back-propagation algorithm as learning rule. The parameters such as parameters of membership functions, learning rates and momentum coefficients are adjusted using genetic algorithms. And we use two kinds of FNN structure according to the division method of fuzzy space of input variables. One is basic FNN structure and uses fuzzy input space divided by each separated input variable, the other is modified FNN structure and uses fuzzy input space divided by mutually combined input variables. In order to evaluate the performance of proposed models, we use the nonlinear function and traffic route choice process. The results show that the proposed FPNN can produce the model with higher accuracy and more robustness than any other method presented previously. And also performance index related to the approximation and prediction capabilities of model is evaluated and discussed.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.2
• /
• pp.327-344
• /
• 2007

Ridge partial least squares regression (RPLS) is a regression method which can be obtained by combining ridge regression and partial least squares regression and is intended to provide better predictive ability and less sensitive to overfitting. In this paper, explicit expressions for the shrinkage factor of RPLS are developed. The structure of the shrinkage factor is explored and compared with those of other biased regression methods, such as ridge regression, principal component regression, ridge principal component regression, and partial least squares regression using a near infrared data set.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.87-91
• /
• 2005

The cascade-correlation (CC) learning algorithm of Fahlman and Lebiere is one of the most influential constructive algorithm in a neural network. Cascading the hidden neurons results in a network that can represent very strong nonlinearities. Although this power is in principle useful, it can be a disadvantage if such strong nonlinearity is not required to solve the problem. 3 models are presented and compared empirically. All of them are based on valiants of the cascade architecture and output neurons weights training of the CC algorithm. Empirical results indicate the followings： (1) In the pattern classification, the model that train only new hidden neuron to output layer connection weights shows the best predictive ability; (2) In the function approximation, the model that removed input-output connection and used sigmoid-linear activation function is better predictability than CasCor algorithm.

• Journal of the Korean Institute of Gas
• /
• v.2 no.3
• /
• pp.88-95
• /
• 1998

Vibration analysis of rotating machinery can give an indication of possible faults thus allowing maintenance before further damage occurs. Current predictive maintenance system installed in Pyung-tak has the ability to diagnose the mechanical problems within the LNG Pump when the vibration exceeds preset overall alarm levels. In this study, LNG pump auto-diagnosis system based upon Windows NT and DSP Board is developed. This system analysis velocity signal acquired from dual accelerometer input monitor system to diagnose pump condition. Many plots which display machine condition are shown and features of vibration are stored in every time. If the fault is found, the system diagnoses automatically using expert system and trend monitoring. Operator checks pump condition intuitively using personal computer monitor.

• Journal of Ecology and Environment
• /
• v.33 no.2
• /
• pp.165-173
• /
• 2010

Soil respiration ($R_S$) is a critical component of the annual carbon balance of forests, but few studies thus far have attempted to evaluate empirical regression models in $R_S$. The principal objectives of this study were to evaluate the relationship between $R_S$ rates and soil temperature (ST) and soil water content (SWC) in soil from a cool-temperate deciduous broad-leaved forest, and to evaluate empirical regression models for the prediction of $R_S$ using ST and SWC. We have been measuring $R_S$, using an open-flow gas-exchange system with an infrared gas analyzer during the snowfree season from 1999 to 2001 at the Takayama Forest, Japan. To evaluate the empirical regression models used for the prediction of $R_S$, we compared a simple exponential regression (flux = $ae^{bt}$Eq. [1]) and two polynomial multiple-regression models (flux = $ae^{bt}{\times}({\theta}{\nu}-c){\times}(d-{\theta}{\nu})^f:$ Eq. [2] and flux = $ae^{bt}{\times}(1-(1-({\theta}{\nu}/c))^2)$: Eq. [3]) that included two variables (ST: t and SWC: ${\theta}{\nu}$) and that utilized hourly data for $R_S$. In general, daily mean $R_S$ rates were positively well-correlated with ST, but no significant correlations were observed with any significant frequency between the ST and $R_S$ rates on periods of a day based on the hourly $R_S$ data. Eq. (2) has many more site-specific parameters than Eq. (3) and resulted in some significant underestimation. The empirical regression, Eq. (3) was best explained by temporal variations, as it provided a more unbiased fit to the data compared to Eq. (2). The Eq. (3) (ST $\times$ SWC function) also increased the predictive ability as compared to Eq. (1) (only ST exponential function), increasing the $R^2$ from 0.71 to 0.78.

• Safety and Health at Work
• /
• v.8 no.2
• /
• pp.162-168
• /
• 2017

Background: Pelvic ring fractures (PRFs) may influence the daily activities and quality of life of the injured. The aim of this retrospective study was to explore the functional outcomes and factors related to return to work (RTW) after PRF. Methods: During the years 2003-2012, 282 injured individuals aged 20-55 years on the date of the accident, were hospitalized and treated for PRFs in a large tertiary hospital in Athens, Greece. One hundred and three patients were traced and contacted; 77 who were on paid employment prior to the accident gave their informed consent to participate in the survey, which was conducted in early 2015 through telephone interviews. The questionnaire included variables related to injury, treatment and activities, and the Majeed pelvic score. Univariate and multiple regression analyses were used for statistical assessment. Results: Almost half of the injured (46.7%) fully RTW, and earning losses were reported to be 35% after PRF. The univariate analysis confirmed that RTW was significantly related to accident site (labor or not), the magnitude of the accident's force, concomitant injuries, duration of hospitalization, time to RTW, engagement to the same sport, Majeed score, and complications such as limp and pain as well as urologic and sexual complaints (p < 0.05 for all). On multiple logistic regression analysis, the accident sustained out of work (odds ratio: 6.472, 95% confidence interval: 1.626-25.769) and Majeed score (odds ratio: 3.749, 95% confidence interval: 2.092-6.720) were identified as independent predictive factors of full RTW. Conclusion: PRFs have severe socioeconomic consequences. Possible predictors of RTW should be taken into account for health management and policies.

• Journal of the Korean Institute of Gas
• /
• v.16 no.1
• /
• pp.26-32
• /
• 2012

The autoignition temperature is one of the most important physical properties used to determine the flammability characteristics of chemical substances. Despite the needs of the experimental autoignition temperature data for the design of chemical plants, it is not easy to get the data. This study have built and compared partial least squares (PLS) and support vector machine (SVM) models to predict the autoignition temperatures of 503 organic compounds out of DIPPR 801. As the independent variables of the models, 59 functional groups were chosen based on the group contribution method. The prediction errors calculated from cross-validation were employed to determine the optimal parameters of two models. And, particle swarm optimization was used to get three parameters of SVM model. The PLS and SVM results of the average absolute errors for the whole data range from 58.59K and 29.11K, respectively, indicating that the predictive ability of the SVM is much superior than PLS.

• Computers and Concrete
• /
• v.19 no.4
• /
• pp.419-427
• /
• 2017

With the rising global environmental awareness on energy saving and carbon reduction, as well as the environmental transition and natural disasters resulted from the greenhouse effect, waste resources should be efficiently used to save environmental space and achieve environmental protection principle of "sustainable development and recycling". This study used recycled cement mortar and adopted the volumetric method for experimental design, which replaced cement (0%, 10%, 20%, 30%) with recycled materials (fly ash, slag, glass powder) to test compressive strength and ultrasonic pulse velocity (UPV). The hyperbolic function for nonlinear multivariate regression analysis was used to build prediction models, in order to study the effect of different recycled material addition levels (the function of $R_m$(F, S, G) was used and be a representative of the content of recycled materials, such as fly ash, slag and glass) on the compressive strength and UPV of cement mortar. The calculated results are in accordance with laboratory-measured data, which are the mortar compressive strength and UPV of various mix proportions. From the comparison between the prediction analysis values and test results, the coefficient of determination $R^2$ and MAPE (mean absolute percentage error) value of compressive strength are 0.970-0.988 and 5.57-8.84%, respectively. Furthermore, the $R^2$ and MAPE values for UPV are 0.960-0.987 and 1.52-1.74%, respectively. All of the $R^2$ and MAPE values are closely to 1.0 and less than 10%, respectively. Thus, the prediction models established in this study have excellent predictive ability of compressive strength and UPV for recycled materials applied in cement mortar.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.1
• /
• pp.95-100
• /
• 2016

Background: Survival time of lymphoma patients can be estimated with the help of microarray technology. In this study, with the use of iterative Bayesian Model Averaging (BMA) method, survival time of Mantle Cell Lymphoma patients (MCL) was estimated and in reference to the findings, patients were divided into two high-risk and low-risk groups. Materials and Methods: In this study, gene expression data of MCL patients were used in order to select a subset of genes for survival analysis with microarray data, using the iterative BMA method. To evaluate the performance of the method, patients were divided into high-risk and low-risk based on their scores. Performance prediction was investigated using the log-rank test. The bioconductor package "iterativeBMAsurv" was applied with R statistical software for classification and survival analysis. Results: In this study, 25 genes associated with survival for MCL patients were identified across 132 selected models. The maximum likelihood estimate coefficients of the selected genes and the posterior probabilities of the selected models were obtained from training data. Using this method, patients could be separated into high-risk and low-risk groups with high significance (p<0.001). Conclusions: The iterative BMA algorithm has high precision and ability for survival analysis. This method is capable of identifying a few predictive variables associated with survival, among many variables in a set of microarray data. Therefore, it can be used as a low-cost diagnostic tool in clinical research.

• Korean Journal of Adult Nursing
• /
• v.17 no.3
• /
• pp.464-473
• /
• 2005

Purpose: The purpose of this study was to evaluate and compare the predictive ability of three mortality scoring systems; Acute Physiology and Chronic Health Evaluation(APACHE) III, Simplified Acute Physiology Score(SAPS) II, and Mortality Probability Model(MPM) II in discriminating in-hospital mortality for intensive care unit(ICU) patients with spontaneous intracerebral hemorrhage. Methods: Eighty-nine patients admitted to the ICU at a university hospital in Daejeon Korea were recruited for this study. Medical records of the subject were reviewed by a researcher from January 1, 2003 to March 31, 2004, retrospectively. Data were analyzed using SAS 8.1. General characteristic of the subjects were analyzed for frequency and percentage. Results: The results of this study were summarized as follows. The values of the Hosmer-Lemeshow's goodness-of-fit test for the APACHE III, the SAPS II and the MPM II were chi-square H=4.3849 p=0.7345, chi-square H=15.4491 p=0.0307, and chi-square H=0.3356 p=0.8455, respectively. Thus, The calibration of the MPM II found to be the best scoring system, followed by APACHE III. For ROC curve analysis, the areas under the curves of APACHE III, SAPS II, and MPM II were 0.934, 0.918 and 0.813, respectively. Thus, the discrimination of three scoring systems were satisfactory. For two-by-two decision matrices with a decision criterion of 0.5, the correct classification of three scoring systems were good. Conclusion: Both the APACHE III and the MPM II had an excellent power of mortality prediction and discrimination for spontaneous intracerebral hemorrhage patients in ICU.