• Journal of the Korean Society for Marine Environment & Energy
• /
• v.18 no.4
• /
• pp.263-273
• /
• 2015

We estimated the global inflow and stock of plastic marine debris. In South Korea, we estimated that the annual inflow of plastic marine debris (72,956 tons) was about 1.4% of annual plastics consumption (5.2 million tons) in 2012. By applying this 1.4% ratio to global plastics production from 1950 to 2013, we estimated that 4.2 million tons of plastic debris entered the ocean in 2013 and that there is a stock of 86 million tons of plastic marine debris as of the end of 2013, assuming zero outflow. In addition, with a logistic model, if 4% of petroleum is turned into plastics, the final stock of plastic marine debris shall be 199 million tons at the end. As the inflow and the stock are different units of measurement, better indicators to assess the effectiveness of inflow-reducing policies are needed. And, as the pollution from plastic marine debris is almost irreversible, countermeasures to prevent it should be valued more, and stronger preventive measures should be taken under the precautionary principle. As this is a preliminary study based on limited information, further research is needed to clarify the tendency of inflow and stock of plastic marine debris.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.04a
• /
• pp.347-356
• /
• 2000

This paper compares four models of artificial neural networks (ANN) supported by genetic algorithms the prediction of stock price index. Previous research proposed many hybrid models of ANN and genetic algorithms(GA) in order to train the network, to select the feature subsets, and to optimize the network topologies. Most these studies, however, only used GA to improve a part of architectural factors of ANN. In this paper, GA simultaneously optimized multiple factors of ANN. Experimental results show that GA approach to simultaneous optimization for ANN (SOGANN3) outperforms the other approaches.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.850-856
• /
• 2010

With skyrocketing number of people who use smartphone, the technology of wireless internet that is mobile-phone, Wi-Fi, Wibro, HSDPA has been developed remarkably. The environment that one can use wireless internet easily and inexpensively anywhere has been made. So, the customer of railway have needs and desire that could use the wireless internet network as travelling in rolling-stock. Although KTX, KTX-II and some subway agency has built-up wireless internet network and serviced it, it's closed infra and inconvenient environment has been criticized. So, we survey the wireless internet network that is serviced at present and the way to build wirelee internet infra to satisfy the needs of customers.

• Information Systems Review
• /
• v.22 no.4
• /
• pp.21-39
• /
• 2020

Recently, deep learning has shown high performance in various applications such as pattern analysis and image classification. Especially known as a difficult task in the field of machine learning research, stock market forecasting is an area where the effectiveness of deep learning techniques is being verified by many researchers. This study proposed a deep learning Convolutional Neural Network (CNN) model to predict the direction of stock prices. We then used the feature selection method to improve the performance of the model. We compared the performance of machine learning classifiers against CNN. The classifiers used in this study are as follows: Logistic Regression, Decision Tree, Neural Network, Support Vector Machine, Adaboost, Bagging, and Random Forest. The results of this study confirmed that the CNN showed higher performancecompared with other classifiers in the case of feature selection. The results show that the CNN model effectively predicted the stock price direction by analyzing the embedded values of the financial data

• Journal of the Korean Operations Research and Management Science Society
• /
• v.38 no.4
• /
• pp.11-33
• /
• 2013

We analyzed the structures and properties of the global financial market networks using social network analysis approach. The Minimum Spanning Tree (MST) lengths and networks of the global financial markets based on the correlation coefficients have been analyzed. Firstly, similar to the previous studies on the global stock indices using MST length, the diversification effects in the global multi-asset portfolio can disappear during the crisis as the correlations among the asset class and within the asset class increase due to the system risks. Second, through the network visualization, we found the clustering of the asset class in the global financial markets network, which confirms the possible diversification effect in the global multi-asset portfolio. Meanwhile, we found the changes in the structure of the network during the crisis. For the last one, in terms of the degree centrality, the stock indices were the most influential to other assets in the global financial markets network, while in terms of the betweenness centrality, Gold, Silver and AUD. In the practical perspective, we propose the methods such as MST length and network visualization to monitor the change of the correlation risk for the risk management of the multi-asset portfolio.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.187-195
• /
• 2010

IP camera which transmits image signal in network includes web server, network interface unit and CCD(Charge-Coupled Device) module. IP camera is able to transmit image signals by network in real time and to monitor the scene image always by IP or Web address. IP camera is substituted for analog camera now gradually according to the development and progress of camera technology and expect it to extend the boundary in rolling stock gradually cause of the excellent expansibility and noise solution of analog camera. We survey the IP camera system composition in rolling stock and so this can be a help to develop and design IP camera system, because it has unsolved problems for common use of IP camera.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.10
• /
• pp.441-450
• /
• 2014

The stock market is constantly changing and sometimes the stock prices unaccountably plummet or surge. So, the stock market is recognized as a complex system and the change on the stock prices is unpredictable. Recently, many researchers try to understand the stock market as the network among individual stocks and to find a clue about the change of the stock prices from big data being created in real time from Internet. We focus on the correlation between the stock prices and the human interactions in Internet especially in the stock message boards. To uncover this correlation, we collected and investigated the articles concerning with 57 target companies, members of KOSPI200. From the analysis result, we found that there is no significant correlation between the stock prices and the article volume, but the strength of correlation between the article volume and the stock prices is relevant to the stock return. We propose a new method for recommending stock portfolio base on the result of our analysis. According to the simulated investment test using the article data from the stock message boards in 'Daum' portal site, the returns of our portfolio is about 1.55% per month, which is about 0.72% and 1.21% higher than that of the Markowitz's efficient portfolio and that of the KOSPI average respectively. Also, the case using the data from 'Naver' portal site, the stock returns of our proposed portfolio is about 0.90%, which is 0.35%, 0.40%, and 0.58% higher than those of our previous portfolio, Markowitz's efficient portfolio, and KOSPI average respectively. This study presents that collective human behavior on Internet stock message board can be much helpful to understand the stock market and the correlation between the stock price and the collective human behavior can be used to invest in stocks.

• The KIPS Transactions:PartB
• /
• v.14B no.2
• /
• pp.127-134
• /
• 2007

There are many researches about the intelligent stock trading systems with the help of the advance of the artificial intelligence such as machine learning techniques, Though the establishment of the reasonable trading policy plays an important role in the performance of the trading systems most researches focused on the improvement of the predictability. Also some previous works, which treated the trading policy, treated the simplified versions dependent on the predictors in less systematic ways. In this paper, we propose the integrated multiple simulation' as a method of optimizing trading performance of stock trading systems. The propose method is adopted in the NXShell a development environment for neural network based stock trading systems. Under the proposed integrated multiple simulation', we simulate the multiple tradings for all combinations of the neural network's outputs and the trading policy parameters, evaluate the learning performance according to the various metrics and establish the optimal policy for a given prediction module based on the resulting performance. In the experiment, we present the trading policy comparison results using the stock value data from the KOSPI and KOSDAQ.

• Journal of the Korea Convergence Society
• /
• v.10 no.1
• /
• pp.7-12
• /
• 2019

The application of neural networks to stock forecasting has received a great deal of attention because no assumption about a suitable mathematical model has to be made prior to forecasting and they are capable of extracting useful information from data, which is required to describe nonlinear input-output relations of stock forecasting. The paper builds neural network models to forecast daily KOrea composite Stock Price Index (KOSPI), and their performance is demonstrated. MAPEs of NN1 model show 0.427 and 0.627 in its learning and test, respectively. Based on the predicted KOSPI price, the paper proposes an alpha trading for trades in Exchange Traded Funds (ETFs) that fluctuate with the KOSPI200. The alpha trading is tested with data from 125 trade days, and its trade return of 7.16 ~ 15.29 % suggests that the proposed alpha trading is effective.

• Journal of the Korean Society of Costume
• /
• v.51 no.2
• /
• pp.53-64
• /
• 2001

The purpose of this study is to create the program for efficient inventory management and reduction, investigating the present conditions and factors of the inventory throughout current apparel industry. The research method applied in this study is to survey 92 domestic companies which were randomly selected with respect to the kinds of goods produced : men′s wear, women′s wear, and unisex wear. The research can be summarized as follows : 1. The seasonal stock rate of current apparel industry was 28.75%, and the rate of men′s wear companies was higher than that of women′s and unisex wear companies. 19.43% of stock cost reflection rate was applied, and the stack cost of men′s and women′s wear companies was higher than that of unisex wear companies. 2. Periodic bargain sale was the most frequently used way of stock clearance, and "uniform price sale"and outlet stores were the second and the third irrespectively. Unisex wear companies appeared to be more enthusiastic in stock clearance than the companies belonging to the other two categories. The main places for the stock clearance were department stores, outlet stores and enterprises specialized in the stock clearance. 3. QR production was proved to be the most commonly adjusted method of stock reduction, and the emphasis on development of new design and the utilization of stock management system through computer network were the next, While unisex wear companies had established the positive policies, men′s wear companies took lukewarm altitudes in every aspect. The companies selling on an order were 18.64%, and unisex wear companies showed the higher rate. The lead-time after QR production was 10.91 days, and it seemed to take more time for men′s wear companies than for women′s and unisex wear companies. The rate of the chance in stock was proved to decrease by 12.94%, and there was found no meaningful difference among the three categories of apparel companies.