• Nuclear Engineering and Technology
• /
• v.39 no.1
• /
• pp.63-74
• /
• 2007

In this paper, a reconfigurable controller consisting of a normal controller and a standby controller is designed to control the thermoelectric (TE) power in the SP-100 space reactor. The normal controller uses a model predictive control (MPC) method where the future TE power is predicted by using support vector regression. A genetic algorithm that can effectively accomplish multiple objectives is used to optimize the normal controller. The performance of the normal controller depends on the capability of predicting the future TE power. Therefore, if the prediction performance is degraded, the proportional-integral (PI) controller of the standby controller begins to work instead of the normal controller. Performance deterioration is detected by a sequential probability ratio test (SPRT). A lumped parameter simulation model of the SP-100 nuclear space reactor is used to verify the proposed reconfigurable controller. The results of numerical simulations to assess the performance of the proposed controller show that the TE generator power level controlled by the proposed reconfigurable controller could track the target power level effectively, satisfying all control constraints. Furthermore, the normal controller is automatically switched to the standby controller when the performance of the normal controller degrades.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.136-136
• /
• 2022

This study investigates the possibility of coupling empirical mode decomposition (EMD) for runoff prediction from machine learning (ML) models. Here, support vector regression (SVR) and convolutional neural network (CNN) were considered for ML algorithms. Precipitation (P), minimum temperature (Tmin), maximum temperature (Tmax) and their intrinsic mode functions (IMF) values were used for input variables at a monthly scale from Jan. 1973 to Dec. 2020 in the Grand river basin, Canada. The support vector machine-recursive feature elimination (SVM-RFE) technique was applied for finding the best combination of predictors among input variables. The results show that the proposed method outperformed the individual performance of SVR and CNN during the training and testing periods in the study area. According to the correlation coefficient (R), the EMD-SVR model outperformed the EMD-CNN model in both training and testing even though the CNN indicated a better performance than the SVR before using IMF values. The EMD-SVR model showed higher improvement in R value (38.7%) than that from the EMD-CNN model (7.1%). It should be noted that the coupled models of EMD-SVR and EMD-CNN represented much higher accuracy in runoff prediction with respect to the considered evaluation indicators, including root mean square error (RMSE) and R values.

• Annual Conference of KIPS
• /
• 2007.11a
• /
• pp.113-116
• /
• 2007

In this paper, our proposed Nonlinear Autoregressive Exogenous (NARX) based on Least Square-Support Vector Regression (LS-SVR) is introduced and tested for producing natural sounds. This nonlinear synthesizer perfectly reproduce voiced sounds, and also conserve the naturalness such as jitter and shimmer, compared to LPC does not keep these naturalness. However, the results of some phonation are quite different from the original sounds. These results are assumed that single-band model can not afford to control and decompose the high frequency components. Therefore multi-band model with wavelet filterbank is adopted for substituting single band model. As a results, multi-band model results in improved stability. Finally, nonlinear speech modeling using NARX based on LS-SVR can successfully reconstruct synthesized sounds nearly similar to original voiced sounds.

• International Journal of Computer Science & Network Security
• /
• v.24 no.9
• /
• pp.30-40
• /
• 2024

Building an accurate 3-D spatial road network model has become an active area of research now-a-days that profess to be a new paradigm in developing Smart roads and intelligent transportation system (ITS) which will help the public and private road impresario for better road mobility and eco-routing so that better road traffic, less carbon emission and road safety may be ensured. Dealing with such a large scale 3-D road network data poses challenges in getting accurate elevation information of a road network to better estimate the CO₂ emission and accurate routing for the vehicles in Internet of Vehicle (IoV) scenario. Clustering and regression techniques are found suitable in discovering the missing elevation information in 3-D spatial road network dataset for some points in the road network which is envisaged of helping the public a better eco-routing experience. Further, recently Explainable Artificial Intelligence (xAI) draws attention of the researchers to better interprete, transparent and comprehensible, thus enabling to design efficient choice based models choices depending upon users requirements. The 3-D road network dataset, comprising of spatial attributes (longitude, latitude, altitude) of North Jutland, Denmark, collected from publicly available UCI repositories is preprocessed through feature engineering and scaling to ensure optimal accuracy for clustering and regression tasks. K-Means clustering and regression using Support Vector Machine (SVM) with radial basis function (RBF) kernel are employed for 3-D road network analysis. Silhouette scores and number of clusters are chosen for measuring cluster quality whereas error metric such as MAE ( Mean Absolute Error) and RMSE (Root Mean Square Error) are considered for evaluating the regression method. To have better interpretability of the Clustering and regression models, SHAP (Shapley Additive Explanations), a powerful xAI technique is employed in this research. From extensive experiments , it is observed that SHAP analysis validated the importance of latitude and altitude in predicting longitude, particularly in the four-cluster setup, providing critical insights into model behavior and feature contributions SHAP analysis validated the importance of latitude and altitude in predicting longitude, particularly in the four-cluster setup, providing critical insights into model behavior and feature contributions with an accuracy of 97.22% and strong performance metrics across all classes having MAE of 0.0346, and MSE of 0.0018. On the other hand, the ten-cluster setup, while faster in SHAP analysis, presented challenges in interpretability due to increased clustering complexity. Hence, K-Means clustering with K=4 and SVM hybrid models demonstrated superior performance and interpretability, highlighting the importance of careful cluster selection to balance model complexity and predictive accuracy.

• Archives of Metallurgy and Materials
• /
• v.67 no.4
• /
• pp.1459-1463
• /
• 2022

The soft magnetic properties of Fe-based amorphous alloys can be controlled by their compositions through alloy design. Experimental data on these alloys show some discrepancy, however, with predicted values. For further improvement of the soft magnetic properties, machine learning processes such as random forest regression, k-nearest neighbors regression and support vector regression can be helpful to optimize the composition. In this study, the random forest regression method was used to find the optimum compositions of Fe-Si-B-C alloys. As a result, the lowest coercivity was observed in Fe_80.5Si_3.63B_13.54C_2.33 at.% and the highest saturation magnetization was obtained Fe_81.83Si_3.63B_12.63C_1.91 at.% with R² values of 0.74 and 0.878, respectively.

• Journal of Korean Society of Transportation
• /
• v.31 no.6
• /
• pp.53-66
• /
• 2013

The major purpose of this study is to evaluate methodologies to predict the injury severity of pedestrian-vehicle collisions. Methodologies to be evaluated and compared in this study include Binary Logistic Regression(BLR), Ordered Probit Model(OPM), Support Vector Machine(SVM) and Decision Tree(DT) method. Valuable insights into applying methodologies to analyze the characteristics of pedestrian injury severity are derived. For the purpose of identifying causal factors affecting the injury severity, statistical approaches such as BLR and OPM are recommended. On the other hand, to achieve better prediction performance, heuristic approaches such as SVM and DT are recommended. It is expected that the outcome of this study would be useful in developing various countermeasures for enhancing pedestrian safety.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.4
• /
• pp.526-533
• /
• 2014

In this study, we introduce design methodology to develop a guidance for issuing heavy rainfall warning by using both RBFNNs(Radial basis function neural networks) and SVR(Support vector regression) model, and then carry out the comparative studies between two pattern classifiers. Individual classifiers are designed as architecture realized with the aid of optimization and pre-processing algorithm. Because the predictive performance of the existing heavy rainfall forecast system is commonly affected from diverse processing techniques of meteorological data, under-sampling method as the pre-processing method of input data is used, and also data discretization and feature extraction method for SVR and FCM clustering and PSO method for RBFNNs are exploited respectively. The observed data, AWS(Automatic weather wtation), supplied from KMA(korea meteorological administration), is used for training and testing of the proposed classifiers. The proposed classifiers offer the related information to issue a heavy rain warning in advance before 1 to 3 hours by using the selected meteorological data and the cumulated precipitation amount accumulated for 1 to 12 hours from AWS data. For performance evaluation of each classifier, ETS(Equitable Threat Score) method is used as standard verification method for predictive ability. Through the comparative studies of two classifiers, neuro-fuzzy method is effectively used for improved performance and to show stable predictive result of guidance to issue heavy rainfall warning.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.6
• /
• pp.1341-1348
• /
• 2013

To solve the classification problems, various data mining techniques have been applied to database marketing, credit scoring and market forecasting. In this paper, we compare various techniques such as bagging, boosting, LASSO, random forest and support vector machine with the daily lens transaction data. The classical techniques-decision tree, logistic regression-are used too. The experiment shows that the random forest has a little smaller misclassification rate and standard error than those of other methods. The performance of the SVM is good in the sense of misclassfication rate and bad in the sense of standard error. Taking the model interpretation and computing time into consideration, we conclude that the LASSO gives the best result.

• Communications for Statistical Applications and Methods
• /
• v.10 no.1
• /
• pp.61-77
• /
• 2003

Due to the wide expansion of the internet, people can freely get information what they want with lesser efforts. However without adequate forms or rules to follow, it is getting more and more difficult to get necessary information. Because of seemingly chaotic status of the current web environment, it is sometimes called "Dizzy web" The user should wander from page to page to get necessary information. Therefore we need to construct system which properly recommends appropriate information for general user. The representative research field for this system is called Recommendation System(RS), The collaborative recommendation system is one of the RS. It was known to perform better than the other systems. When we perform the web user modeling or other web-mining tasks, the continuous feedback data is very important and frequently used. In this paper, we propose a collaborative recommendation system which can deal with the continuous feedback data and tried to construct the web page prediction system. We use a sojourn time of a user as continuous feedback data and combine the traditional model-based algorithm framework with the Support Vector Regression technique. In our experiments, we show the accuracy of our system and the computing time of page prediction compared with Pearson's correlation algorithm.algorithm.

• Journal of Digital Contents Society
• /
• v.15 no.6
• /
• pp.737-743
• /
• 2014

For single image super resolution (SR), interpolation based and example based algorithms are extensively used. The interpolation algorithms have the strength of theoretical simplicity. However, those algorithms are tending to produce high resolution images with jagged edges, because they are not able to use more priori information. Example based algorithms have been studied in the past few years. For example based SR, the nearest neighbor based algorithms are extensively considered. Among them, neighbor embedding (NE) has been inspired by manifold learning method, particularly locally linear embedding. However, the sizes of local training sets are always too small. So, NE algorithm is weak in the performance of the visuality and quantitative measure by the poor generalization of nearest neighbor estimation. An improved NE algorithm with Support Vector Regression (SVR) was proposed to solve this problem. Given a low resolution image, the pixel values in its high resolution version are estimated by the improved NE. Comparing with bicubic and NE, the improvements of 1.25 dB and 2.33 dB are achieved in PSNR. Experimental results show that proposed method is quantitatively and visually more effective than prior works using bicubic interpolation and NE.