• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.271-280
• /
• 1999

인공신경망을 시계열예측에 적용하는 경우에 고려되어야 할 문제중, 특히 모형에 적합한 입력변수의 생성이 중요시되고 있는데, 이러한 분야는 인공신경망의 모형생성과정에서 입력변수에 대한 전처리기법으로써 다양하게 제시되어 왔다. 가장 최근의 입력변수 전처리기법으로써 제시되고 있는 신호처리기법은 전통적 주기분할처리방법인 푸리에변환기법(Fourier transforms)을 비롯하여 이를 확장시킨 개념인 웨이블릿변환기법(wavelet transforms) 등으로 대별될 수 있다. 이는 기본적으로 시계열이 다수의 주기(cycle)들로 구성된 상이한 시계열들의 집합이라는 가정에서 출발하고 있다. 전통적으로 이러한 시계열은 전기 또는 전자공학에서 주파수영역분할, 즉 고주파 및 저주파수를 분할하기 위한 기법에 적용되어 왔다. 그러나, 최근에는 이러한 연구가 다양한 분야에 활발하게 응용되기 시작하였으며, 그 중의 대표적인 예가 바로 경영분야의 재무시계열에 대한 분석이다. 전통적으로 재무시계열은 장, 단기의사결정을 가진 시장참여자들간의 거래특성이 시계열에 각기 달리 가격으로 반영되기 때문에 이러한 상이한 집단들의 고요한 거래움직임으로 말미암아 예를 들어, 주식시장이 프랙탈구조를 가지고 있다고 보기도 한다. 이처럼 재무시계열은 다양한 사회현상의 집합체라고 볼 수 있으며, 그만큼 예측모형을 구축하는데 어려움이 따른다. 본 연구는 이러한 시계열의 주기적 특성에 기반을 둔 신호처리분석으로서 기존의 시계열로부터 노이즈를 줄여 주면서 보다 의미있는 정보로 변환시켜줄 수 있는 웨이블릿분석 방법론을 새로운 필터링기법으로 사용하여 현재 많은 연구가 진행되고 있는 인공신경망의 모형결합을 통해 기존연구과는 다른 새로운 통합예측방법론을 제시하고자 한다. 본 연구에서는 제시하는 통합방법론은 크게 2단계 과정을 거쳐 예측모형으로 완성이 된다. 즉, 1차 모형단계에서 원시 재무시계열은 먼저 웨이브릿분석을 통해서 노이즈가 필터링 되는 동시에, 과거 재무시계열의 프랙탈 구조, 즉 비선형적인 움직임을 보다 잘 반영시켜 주는 다차원 주기요소를 가지는 시계열로 분해, 생성되며, 이렇게 주기에 따라 장단기로 분할된 시계열들은 2차 모형단계에서 신경망의 새로운 입력변수로서 사용되어 최종적인 인공 신경망모델을 구축하는 데 반영된다. 기존의 주기분할방법론은 모형개발자입장에서 여러 가지 통계기준치중에서 최적의 기준치를 합리적으로 선택해야 하는 문제가 추가적으로 발생하며, 본 연구에서는 이상의 제반 문제들을 개선시키기 위해 통합방법론으로서 기존의 인공신경망모형을 구조적으로 확장시켰다. 이 모형에서 기존의 입력층 이전단계에 새로운 층이 정의된다. 이렇게 해서 생성된 새로운 통합모형은 기존모형에서 생성되는 기본적인 학습파라미터와 더불어, 본 연구에서 새롭게 제시된 주기분할층의 파라미터들이 모형의 학습성과를 높이기 위해 함께 고려된다. 한편, 이러한 학습과정에서 추가적으로 고려해야 할 파라미터 갯수가 증가함에 따라서, 본 모델의 학습성과가 local minimum에 빠지는 문제점이 발생될 수 있다. 즉, 웨이블릿분석과 인공신경망모형을 모두 전역적으로 최적화시켜야 하는 문제가 발생한다. 본 연구에서는 이 문제를 해결하기 위해서, 최근 local minimum의 가능성을 최소화하여 전역적인 학습성과를 높여 주는 인공지능기법으로서 유전자알고리즘기법을 본 연구이 통합모델에 반영하였다. 이에 대한 실증사례 분석결과는 일일 환율예측문제를 적용하였을 경우, 기존의 방법론보다 더 나운 예측성과를 타나내었다.

• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.259-266
• /
• 2020

Many developments have been steadily carried out by researchers with applying knowledge-based expert system or machine learning algorithms to the financial field. In particular, it is now common to perform knowledge based system trading in using stock prices. Recently, deep learning technologies have been applied to real fields of stock trading marketplace as GPU performance and large scaled data have been supported enough. Especially, LSTM has been tried to apply to stock price prediction because of its compatibility for time series data. In this paper, we implement stock price prediction using LSTM. In modeling of LSTM, we propose a fitness combination of model parameters and activation functions for best performance. Specifically, we propose suitable selection methods of initializers of weights and bias, regularizers to avoid over-fitting, activation functions and optimization methods. We also compare model performances according to the different selections of the above important modeling considering factors on the real-world stock price data of global major companies. Finally, our experimental work brings a fitness method of applying LSTM model to stock price prediction.

• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.127-146
• /
• 2017

Services using artificial intelligence have begun to emerge in daily life. Artificial intelligence is applied to products in consumer electronics and communications such as artificial intelligence refrigerators and speakers. In the financial sector, using Kensho's artificial intelligence technology, the process of the stock trading system in Goldman Sachs was improved. For example, two stock traders could handle the work of 600 stock traders and the analytical work for 15 people for 4weeks could be processed in 5 minutes. Especially, big data analysis through machine learning among artificial intelligence fields is actively applied throughout the financial industry. The stock market analysis and investment modeling through machine learning theory are also actively studied. The limits of linearity problem existing in financial time series studies are overcome by using machine learning theory such as artificial intelligence prediction model. The study of quantitative financial data based on the past stock market-related numerical data is widely performed using artificial intelligence to forecast future movements of stock price or indices. Various other studies have been conducted to predict the future direction of the market or the stock price of companies by learning based on a large amount of text data such as various news and comments related to the stock market. Investing on commodity asset, one of alternative assets, is usually used for enhancing the stability and safety of traditional stock and bond asset portfolio. There are relatively few researches on the investment model about commodity asset than mainstream assets like equity and bond. Recently machine learning techniques are widely applied on financial world, especially on stock and bond investment model and it makes better trading model on this field and makes the change on the whole financial area. In this study we made investment model using Support Vector Machine among the machine learning models. There are some researches on commodity asset focusing on the price prediction of the specific commodity but it is hard to find the researches about investment model of commodity as asset allocation using machine learning model. We propose a method of forecasting four major commodity indices, portfolio made of commodity futures, and individual commodity futures, using SVM model. The four major commodity indices are Goldman Sachs Commodity Index(GSCI), Dow Jones UBS Commodity Index(DJUI), Thomson Reuters/Core Commodity CRB Index(TRCI), and Rogers International Commodity Index(RI). We selected each two individual futures among three sectors as energy, agriculture, and metals that are actively traded on CME market and have enough liquidity. They are Crude Oil, Natural Gas, Corn, Wheat, Gold and Silver Futures. We made the equally weighted portfolio with six commodity futures for comparing with other commodity indices. We set the 19 macroeconomic indicators including stock market indices, exports & imports trade data, labor market data, and composite leading indicators as the input data of the model because commodity asset is very closely related with the macroeconomic activities. They are 14 US economic indicators, two Chinese economic indicators and two Korean economic indicators. Data period is from January 1990 to May 2017. We set the former 195 monthly data as training data and the latter 125 monthly data as test data. In this study, we verified that the performance of the equally weighted commodity futures portfolio rebalanced by the SVM model is better than that of other commodity indices. The prediction accuracy of the model for the commodity indices does not exceed 50% regardless of the SVM kernel function. On the other hand, the prediction accuracy of equally weighted commodity futures portfolio is 53%. The prediction accuracy of the individual commodity futures model is better than that of commodity indices model especially in agriculture and metal sectors. The individual commodity futures portfolio excluding the energy sector has outperformed the three sectors covered by individual commodity futures portfolio. In order to verify the validity of the model, it is judged that the analysis results should be similar despite variations in data period. So we also examined the odd numbered year data as training data and the even numbered year data as test data and we confirmed that the analysis results are similar. As a result, when we allocate commodity assets to traditional portfolio composed of stock, bond, and cash, we can get more effective investment performance not by investing commodity indices but by investing commodity futures. Especially we can get better performance by rebalanced commodity futures portfolio designed by SVM model.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.3 no.2
• /
• pp.125-133
• /
• 2005

Methodologies of NEWTRIT model, NRC model and AIRDOS-EPA model, which are off-site dose assessment models for regulatory compliance from routine releases of tritium into the environment, were investigated. Using the domestic data, if available, the predictive results of the models were compared. Among them, recently developed NEWTRIT model considers only doses from organically bounded tritium (OBT) due to environmental releases of tritiated water (HTO) . A total dose from all exposure pathways predicted from AIRDOS-EPA model was 1.03 and 2.46 times higher than that from NEWTRIT model and NRC model, respectively. From above result, readers should not have an understanding that a predictive dose from NRC model may be underestimated compared with a realistic dose. It is because of that both mathematical models and corresponding parameter values for regulatory compliance are based on the conservative assumptions. For a dose by food consumption predicted from NEWTRIT model, the contribution of OBT was nearly equivalent to that of HTO due to relatively high consumption of grains in Korean. Although a total dose predicted from NEWTRIT model is similar to that from AIRDOS-EPA model, NEIIfTRIT model may be have a meaning in the understanding of phenomena for the behavior of HTO released into the environment.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2005.06a
• /
• pp.464-473
• /
• 2005

Methodologies of NEWTRIT model, NRC model and AIRDOS-EPA model, which are off-site dose assessment models for regulatory compliance from routine releases of tritium into the environment, were investigated. Using the domestic data, if available, the predictive results of the models were compared. Among them, recently developed NEWTRIT model considers only doses from organically bounded tritium (OBT) due to environmental releases of tritiated water (HTO). A total dose from all exposure pathways predicted from AIRDOS-EPA model was 1.03 and 2.46 times higher than that from NEWTRIT model and NRC model, respectively. From above result, readers should not have an understanding that a predictive dose from NRC model may be underestimated compared with a realistic dose. It is because of that both mathematical models and corresponding parameter values for regulatory compliance are based on the conservative assumptions. For a dose by food consumption predicted from NEWTRIT model, the contribution of OBT was nearly equivalent to that of HTO due to relatively high consumption of grains in Korean. Although a total dose predicted from NEWTRIT model is similar to that from AIRDOS-EPA model, NEWTRIT model may be have a meaning in the understanding of phenomena for the behavior of HTO released into the environment.

• Journal of the Korean Geotechnical Society
• /
• v.24 no.6
• /
• pp.77-84
• /
• 2008

The existing equations for radial consolidation cannot account for the changes of well resistance with time and cannot predict the appropriate in-situ consolidation curve. In this study, small cylinder cell tests are performed to evaluate the discharge capacity of PVD. Also, a block sample of 1.2 m in diameter and 2.0 m in height was consolidated to observe the change in the drainage capacity with time for three types of PVD. From the test results on a block sample, the drainage curves normalized with initial drainage of each PVD are similar, regardless of the PVD type and the consolidation curve, which is predicted using solutions of radial consolidation based on the discharge capacity measured in a small cylinder cell tests, significantly overestimates the degree of consolidation. The term of well resistance in the radial consolidation solution was back-calculated to fit the consolidation curve of a large block sample and it is defined as the time dependent well resistance factor, L(t). The L(t) was found to be linearly proportional to the dimensionless time factor, Th. It was also shown that the consolidation curve evaluated by using L(t) provides more accurate prediction than the existing solution.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.1
• /
• pp.213-218
• /
• 2017

High-voltage power systems operate in order to generate and transmit electric power at power stations. Compared to low-power systems, high-power systems are complex in structure, large-scale, and expensive. When high-power cable accidents occur, most facilities are incapacitated-including low-power systems-causing huge economic losses. Great care must therefore be taken in designing, installing and managing power systems. Although dependent on installation circumstances and usage conditions, in some cases the cross-sectional areas of cables fall short of the critical area due to the expansion of and improper design and installation of power facilities. In this situation, the exceeded ampacity (allowable current) above the critical value caused by the operating current initiates the deterioration processes of power cables. In order to systematically monitor power cables operating at power stations, we have developed the first device of its kind in Korea. In this paper, we present the analyzed characteristics of expected temperatures of cables based on the load current of high-voltage cables operating at Korean Western Power Co. Ltd. We can predict the lifetime of cables by analyzing the temperature obtained from our device.

• The Korean Journal of Applied Statistics
• /
• v.26 no.3
• /
• pp.471-481
• /
• 2013

The current VaR Model based on J. P. Morgan's RiskMetrics has problem that actual loss exceeds VaR under unstable economic conditions because the current VaR Model can't re ect future economic conditions. In general, any corporation's stock price is determined by the rm's idiosyncratic factor as well as the common systematic factor that in uences all stocks in the portfolio. In this study, we propose an One-factor VaR Model for stock portfolio which is decomposed into the common systematic factor and the rm's idiosyncratic factor. We expect that the actual loss will not exceed VaR when the One-factor Model is implemented because the common systematic factor considering the future economic conditions is estimated. Also, we can allocate the stock portfolio to minimize the loss.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.52-56
• /
• 2004

The Information of classification and estimate about KOSPI200 index`s up and down in the stock market becomes an important standard of decision-making in designing portofolio in futures and option market. Because the coming trend of time series patterns, an economic indicator, is very subordinate to the most recent economic pattern, it is necessary to study the recent patterns most preferentially. This paper compares classification and estimated performance of SVM(Support Vector Machine) and Fuzzy SVM model that are getting into the spotlight in time series analyses, neural net models and various fields. Specially, it proves that Fuzzy SVM is superior by presenting the most suitable dimension to fuzzy membership function that has time series attribute in accordance with learning Data Base.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.10
• /
• pp.118-125
• /
• 2008

The outages of transmission lines give big damages to the industrial world Lightning outages occupy above 50[%] among the outages of transmission lines. To decrease the lightning outage rates, it is necessary to try countermeasures considering economical points. For the lightning protection of power transmission lines, it is very important to accurately predict the lightning outage rate because the reliability criterion for transmission line is normally specified as the number of flashovers per 100[km] per year. The phenomenon of an insulator flashover by a lightning stroke is a very complex electromagnetic event. And to calculate the lightning outage rates of transmission lines, so many calculation should be repeated because there are many overhead lines and power lines. Therefore it is necessary to develope a program for it. In this paper, we briefly introduce the basic concept for lightning outage calculation algorithm and the program.