• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1037-1051
• /
• 2021

Biochemical oxygen demand (BOD) concentration, one of important water quality indicators, is treated as the measuring item for the ecological chapter in lakes and rivers. This investigation employed novel two-stage hybrid paradigm (i.e., wavelet-based gated recurrent unit, wavelet-based generalized regression neural networks, and wavelet-based random forests) to predict BOD concentration in the Dosan and Hwangji stations, South Korea. These models were assessed with the corresponding independent models (i.e., gated recurrent unit, generalized regression neural networks, and random forests). Diverse water quality and quantity indicators were implemented for developing independent and two-stage hybrid models based on several input combinations (i.e., Divisions 1-5). The addressed models were evaluated using three statistical indices including the root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), and correlation coefficient (CC). It can be found from results that the two-stage hybrid models cannot always enhance the predictive precision of independent models confidently. Results showed that the DWT-RF5 (RMSE = 0.108 mg/L) model provided more accurate prediction of BOD concentration compared to other optimal models in Dosan station, and the DWT-GRNN4 (RMSE = 0.132 mg/L) model was the best for predicting BOD concentration in Hwangji station, South Korea.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.4B
• /
• pp.399-412
• /
• 2010

The goal of this research is to apply the neural networks models for the temporal disaggregation of the yearly pan evaporation (PE) data, Republic of Korea. The neural networks models consist of multilayer perceptron neural networks model (MLP-NNM) and generalized regression neural networks model (GRNNM), respectively. And, for the performances evaluation of the neural networks models, they are composed of training and test performances, respectively. The three types of data such as the historic, the generated, and the mixed data are used for the training performance. The only historic data, however, is used for the testing performance. From this research, we evaluate the application of MLP-NNM and GRNNM for the temporal disaggregation of nonlinear time series data. We should, furthermore, construct the credible monthly PE data from the temporal disaggregation of the yearly PE data, and can suggest the available data for the evaluation of irrigation and drainage networks system.

• Journal of the Korean Data and Information Science Society
• /
• v.12 no.2
• /
• pp.1-10
• /
• 2001

Neural networks we increasingly being seen as an addition to the statistics toolkit which should be considered alongside both classical and modern statistical methods. Neural networks are usually useful for classification and function estimation. In this paper we concentrate on function estimation using neural networks with weight decay factor The use of weight decay seems both to help the optimization process and to avoid overfitting. In this type of neural networks, the problem to decide the number of hidden nodes, weight decay parameter and iteration number of learning is very important. It is called the optimization of weight decay neural networks. In this paper we propose a automatic optimization based on genetic algorithms. Moreover, we compare the weight decay neural network automatically learned according to automatic optimization with ordinary neural network, projection pursuit regression and support vector machines.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.7
• /
• pp.531-535
• /
• 2004

A new method is presented to construct a classifier. This was accomplished by combining a generalized regression neural network (GRNN) and a genetic algorithm (GA). The classifier constructed in this way is referred to as a GA-GRNN. The GA played a role of controlling training factors simultaneously. The GA-GRNN was applied to classify 4 different Promoter sequences. The training and test data were composed of 115 and 58 sequence patterns, respectively. The classifier performance was investigated in terms of the classification sensitivity and prediction accuracy. Compared to conventional GRNN, GA-GRNN significantly improved the total classification sensitivity as well as the total prediction accuracy. As a result, the proposed GA-GRNN demonstrated improved classification sensitivity and prediction accuracy over the convention GRNN.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.7
• /
• pp.525-530
• /
• 2004

A classifier was constructed by using a generalized regression neural network (GRU) and random generator (RG), which was applied to classify DNA sequences. Three data sets evaluated are eukaryotic and prokaryotic sequences (Data-I), eukaryotic sequences (Data-II), and prokaryotic sequences (Data-III). For each data set, the classifier performance was examined in terms of the total classification sensitivity (TCS), individual classification sensitivity (ICS), total prediction accuracy (TPA), and individual prediction accuracy (IPA). For a given spread, the RG played a role of generating a number of sets of spreads for gaussian functions in the pattern layer Compared to the GRNN, the RG-GRNN significantly improved the TCS by more than 50%, 60%, and 40% for Data-I, Data-II, and Data-III, respectively. The RG-GRNN also demonstrated improved TPA for all data types. In conclusion, the proposed RG-GRNN can effectively be used to classify a large, multivariable promoter sequences.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.24 no.12
• /
• pp.830-836
• /
• 2012

In this study, the effects of heating control methods on heating control performance and energy consumption in the floor radiant heating control system of residential apartments were research by computer simulation. A general regression neural network(GRNN) control method for reducing indoor temperature overshoot and saving energy in floor radiant heating system is suggested. The GRNN control method shows good responses in comparison with the conventional and outdoor reset control methods for improving indoor thermal environment and reducing energy consumption.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.19-43
• /
• 2016

This study examines the causes of the Asian exchange rate crisis and compares it to the European Monetary System crisis. In 1997, emerging countries in Asia experienced financial crises. Previously in 1992, currencies in the European Monetary System had undergone the same experience. This was followed by Mexico in 1994. The objective of this paper lies in the generation of useful insights from these crises. This research presents a comparison of South Korea, United Kingdom and Mexico, and then compares three different models for prediction. Previous studies of economic crisis focused largely on the manual construction of causal models using linear techniques. However, the weakness of such models stems from the prevalence of nonlinear factors in reality. This paper uses a structural equation model to analyze the causes, followed by a neural network model to circumvent the linear model's weaknesses. The models are examined in the context of predicting exchange rates In this paper, data were quarterly ones, and Consumer Price Index, Gross Domestic Product, Interest Rate, Stock Index, Current Account, Foreign Reserves were independent variables for the prediction. However, time periods of each country's data are different. Lisrel is an emerging method and as such requires a fresh approach to financial crisis prediction model design, along with the flexibility to accommodate unexpected change. This paper indicates the neural network model has the greater prediction performance in Korea, Mexico, and United Kingdom. However, in Korea, the multiple regression shows the better performance. In Mexico, the multiple regression is almost indifferent to the Lisrel. Although Lisrel doesn't show the significant performance, the refined model is expected to show the better result. The structural model in this paper should contain the psychological factor and other invisible areas in the future work. The reason of the low hit ratio is that the alternative model in this paper uses only the financial market data. Thus, we cannot consider the other important part. Korea's hit ratio is lower than that of United Kingdom. So, there must be the other construct that affects the financial market. So does Mexico. However, the United Kingdom's financial market is more influenced and explained by the financial factors than Korea and Mexico.

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.27-29
• /
• 2005

Using a generalized regression neural network, etch microtrenching was modeled. All neurons in the pattern layer were equipped with multi-factored spreads and their complex effects on the prediction performance were optimized by means of a genetic algorithm. For comparison, GRNN model was constructed in a conventional way. Comparison result revealed that GA-GRNN model was more accurate than GRNN model by about 30%. The microtrenching data were collected during the etching of silicon oxynitride film and the etch process was characterized by a statistical experimental design.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2552-2554
• /
• 2003

난수발생기 (Random generator-RG)와 GRNN을 이용한 분류기 설계방식을 제안하며, 이를 프로모터 염기서열의 분류에 적용한다. 주어진 난수범위에서 다중 분류기를 발생하였으며, 그 성능을 예측정확도와 분류민감도 측면에서 평가하였고, 분류민감도는 다시 전체와 개별적 프로모터에 대해서 세분화하여 평가하였다. 최적화된 분류기 상호간의 비교에서 제안된 기법은 모든 임계점에 대해서, 전체 분류민감도와 전체 예측정확도를 향상시키었으며, 이는 전체 분류 민감도에서 더 두드러졌다. 한편, 개별적 프로모터에 대한 분류민감도와 예측정확도도 평균적으로 향상되었다. 이 같은 결과로 제안된 기법이 분류와 예측성능을 동시에 증진하는데 매우 효과적임을 알 수 있었다.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.10
• /
• pp.427-436
• /
• 2022

Korea Trade-Investment Promotion Agency (KOTRA) annually publishes the trade data in South Korea under the guidance of the Ministry of Trade, Industry and Energy in South Korea. The trade data usually contains Gross domestic product (GDP), a custom tariff, business score, and the price of export items in previous and this year, with regards to the trading items and the countries. However, it is challenging to figure out the meaningful insight so as to predict the future price on trading items every year due to the significantly large amount of data accumulated over the several years under the limited human/computing resources. Within this context, this paper proposes a multi layer perception that can predict the future price of potential trading items in the next year by training large amounts of past year's data with a low computational and human cost.