• The Korean Journal of Applied Statistics
• /
• v.23 no.5
• /
• pp.977-985
• /
• 2010

In this paper, we propose an approach to conduct partial sufficient dimension reduction with heavily unbalanced categorical predictors. For this, we consider integrated categorical predictors and investigate certain conditions that the integrated categorical predictor is fully informative to partial sufficient dimension reduction. For illustration, the proposed approach is implemented on optimal partial sliced inverse regression in simulation and data analysis.

• Journal of Industrial Technology
• /
• v.28 no.B
• /
• pp.101-109
• /
• 2008

In general, non-stationary or chaos time series forecasting is very difficult since there exists a drift and/or nonlinearities in them. To overcome this situation, we suggest a new prediction method based on multiple model TS fuzzy predictors combined with preprocessing of time series data, where, instead of time series data, the differences of them are applied to predictors as input. In preprocessing procedure, the candidates of optimal difference interval are determined by using con-elation analysis and corresponding difference data are generated. And then, for each of them, TS fuzzy predictor is constructed by using k-means clustering algorithm and least squares method. Finally, the best predictor which minimizes the performance index is selected and it works on hereafter for prediction. Computer simulation is performed to show the effectiveness and usefulness of our method.

• Journal of Industrial Technology
• /
• v.29 no.B
• /
• pp.9-15
• /
• 2009

In the case of traditional binary encoding technique, it takes long time to converge the optimal solutions and brings about complexity of the systems due to encoding and decoding procedures. However, the ROGAs (real-coded genetic algorithms) do not require these procedures, and the k-means clustering algorithm can avoid global searching space. Thus, this paper proposes a new approach by using their advantages. The proposed method constructs the multiple predictors using the optimal differences that can reveal the patterns better and properties concealed in non-stationary time series where the k-means clustering algorithm is used for data classification to each predictor, then selects the best predictor. After selecting the best predictor, the cluster centers of the predictor are tuned finely via RCGKA in secondary tuning procedure. Therefore, performance of the predictor can be more enhanced. Finally, we verifies the prediction performance of the proposed system via simulating typical time series examples.

• Journal of Sensor Science and Technology
• /
• v.28 no.2
• /
• pp.88-93
• /
• 2019

This paper is concerned with distributed fusion moving average prediction for continuous-time linear stochastic systems with multiple sensors. A distributed fusion with the weighted sum structure is applied to the optimal local moving average predictors. The distributed fusion prediction algorithm represents the optimal linear fusion by weighting matrices under the minimum mean square criterion. The derivation of equations for error cross-covariances between the local predictors is the key of this paper. Example demonstrates effectiveness of the distributed fusion moving average predictor.

• Journal of The Korean Society of Clinical Toxicology
• /
• v.6 no.1
• /
• pp.32-36
• /
• 2008

Purpose: The major complication of acute organophosphate (OP) poisoning is respiratory failure as a result of cholinergic toxicity. Many clinicians find it difficult to predict the optimal time to initiate mechanical ventilation (MV) weaning, and as a result have tended to provide a prolonged ventilator support period. The purpose of this study is to determine any clinical predictors based on patients characteristics and laboratory findings to assist in the optimal timing of mechanical ventilator weaning. Methods: We reviewed medical and intensive care records of 44 patients with acute OP poisoning who required mechanical ventilation admitted to medical intensive care unit between July 1998 and June 2007. Patient information regarding the poisoning, clinical data and demographic features, APACHE II score, laboratory data, and serial cholinesterase (chE) levels were collected. Base on the time period of MV, the patients were divided into two groups: early group (wean time < 7 days, n = 28) and delayed group (${\geq}$ 7 days, n = 16). Patients were assessed for any clinical characteristics and predictors associated with the MV weaning period. Results: During the study period, 44 patients were enrolled in this study. We obtained the sensitivity and specificity values of predictors in the late weaning group. APACHE II score and a reciprocal convert of hypoxic index but specificity (83.8%) is only APACHE II score. Also, the chE concentration (rho = -0.517, p = 0.026) and APACHE II score (rho = 0.827, p < 0.001) correlated with a longer mechanical ventilation duration. Conclusion: In patients with acute OP poisoning who required mechanical ventilation, the APACHE II scoring system on a point scale of less than 17 and decrements in cholinesterase levels on 1-3 days were good predictors of delayed MV weaning.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.1
• /
• pp.173-180
• /
• 2009

It is difficult to predict non-stationary or chaotic time series which includes the drift and/or the non-linearity as well as uncertainty. To solve it, we propose an effective prediction method which adopts data preprocessing and multiple model TS fuzzy predictors combined with model selection mechanism. In data preprocessing procedure, the candidates of the optimal difference interval are determined based on the correlation analysis, and corresponding difference data sets are generated in order to use them as predictor input instead of the original ones because the difference data can stabilize the statistical characteristics of those time series and better reveals their implicit properties. Then, TS fuzzy predictors are constructed for multiple model bank, where k-means clustering algorithm is used for fuzzy partition of input space, and the least squares method is applied to parameter identification of fuzzy rules. Among the predictors in the model bank, the one which best minimizes the performance index is selected, and it is used for prediction thereafter. Finally, the error compensation procedure based on correlation analysis is added to improve the prediction accuracy. Some computer simulations are performed to verify the effectiveness of the proposed method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.134-134
• /
• 2022

Streamflow forecasting plays a crucial role in water resource control, especially in highly urbanized areas that are very vulnerable to flooding during heavy rainfall event. In addition to providing the accurate prediction, the evaluation of effects and importance of the input predictors can contribute to water manager. Recently, machine learning techniques have applied their advantages for modeling complex and nonlinear hydrological processes. However, the techniques have not considered properly the importance and uncertainty of the predictor variables. To address these concerns, we applied the GA-BART, that integrates a genetic algorithm (GA) with the Bayesian additive regression tree (BART) model for hourly streamflow forecasting and analyzing input predictors. The Jungrang urban basin was selected as a case study and a database was established based on 39 heavy rainfall events during 2003 and 2020 from the rain gauges and monitoring stations. For the goal of this study, we used a combination of inputs that included the areal rainfall of the subbasins at current time step and previous time steps and water level and streamflow of the stations at time step for multistep-ahead streamflow predictions. An analysis of multiple datasets including different input predictors was performed to define the optimal set for streamflow forecasting. In addition, the GA-BART model could reasonably determine the relative importance of the input variables. The assessment might help water resource managers improve the accuracy of forecasts and early flood warnings in the basin.

• ETRI Journal
• /
• v.31 no.2
• /
• pp.162-172
• /
• 2009

A linear-prediction-based blind equalization algorithm for single-input single-output (SISO) finite impulse response/infinite impulse response (FIR/IIR) channels is proposed. The new algorithm is based on second-order statistics, and it does not require channel order estimation. By oversampling the channel output, the SISO channel model is converted to a special single-input multiple-output (SIMO) model. Two forward linear predictors with consecutive prediction delays are applied to the subchannel outputs of the SIMO model. It is demonstrated that the partial parameters of the SIMO model can be estimated from the difference between the prediction errors when the length of the predictors is sufficiently large. The sufficient filter length for achieving the optimal prediction is also derived. Based on the estimated parameters, both batch and adaptive minimum-mean-square-error equalizers are developed. The performance of the proposed equalizers is evaluated by computer simulations and compared with existing algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3242-3265
• /
• 2023

Ensuring reliability of a machinery system involve the prediction of remaining useful life (RUL). In most RUL prediction approaches, noise is always considered for removal. Nevertheless, noise could be properly utilized to enhance the prediction capabilities. In this paper, we proposed a novel RUL prediction approach based on noise injection and a Kalman filter ensemble of modified bagging predictors. Firstly, we proposed a new method to insert Gaussian noises into both observation and feature spaces of an original training dataset, named GN-DAFC. Secondly, we developed a modified bagging method based on Kalman filter averaging, named KBAG. Then, we developed a new ensemble method which is a Kalman filter ensemble of KBAGs, named DKBAG. Finally, we proposed a novel RUL prediction approach GN-DAFC-DKBAG in which the optimal noise-injected training dataset was determined by a GN-DAFC-based searching strategy and then inputted to a DKBAG model. Our approach is validated on the NASA C-MAPSS dataset of aero-engines. Experimental results show that our approach achieves significantly better performance than a traditional Kalman filter ensemble of single learning models (KESLM) and the original DKBAG approaches. We also found that the optimal noise-injected data could improve the prediction performance of both KESLM and DKBAG. We further compare our approach with two advanced ensemble approaches, and the results indicate that the former also has better performance than the latters. Thus, our approach of combining optimal noise injection and DKBAG provides an effective solution for RUL estimation of machinery systems.

• Journal of Korean Neurosurgical Society
• /
• v.59 no.5
• /
• pp.478-484
• /
• 2016

Objective : To assess the clinical and radiological factors as predictors for successful outcomes in lumbar disc herniation (LDH) treatment. Methods : Two groups of patients with single level LDH (L4-5) requiring treatment were retrospectively studied. The surgery group (SG) included 34 patients, and 30 patients who initially refused the surgery were included in the nerve blocks group (NG). A visual analogue scale (VAS) for leg and back pain and motor deficit were initially evaluated before procedures, and repeated at 1, 6, and 12 months. Radiological factors including the disc herniation length, disc herniation area, canal length-occupying ratio, and canal area-occupying ratio were measured and compared. Predicting factors of successful outcomes were determined with multivariate logistic regression analysis after the optimal cut off values were established with a receiver operating characteristic curve. Results : There was no significant demographic difference between two groups. A multivariate logistic regression analysis with radiological and clinical (12 months follow-up) data revealed that the high disc herniation length with cutoff value 6.31 mm [odds ratio (OR) 2.35; confidence interval (CI) 1.21-3.98] was a predictor of successful outcomes of leg pain relief in the SG. The low disc herniation length with cutoff value 6.23 mm (OR 0.05; CI 0.003-0.89) and high baseline VAS leg (OR 12.63; CI 1.64-97.45) were identified as predictors of successful outcomes of leg pain relief in the NG. Conclusion : The patients with the disc herniation length larger than 6.31 mm showed successful outcomes with surgery whereas the patients with the disc herniation length less than 6.23 mm showed successful outcomes with nerve block. These results could be considered as a radiological criteria in choosing optimal treatment options for LDH.