• 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 Preventive Medicine and Public Health
• /
• v.23 no.3 s.31
• /
• pp.285-295
• /
• 1990

The utilization of medical care services has been partly regionalized with the implementation of referral requirement by the government since July 1, 1989 when the health insurance coverage was extended to all the people. For the purpose of regionalization, the whole country has been primarily divided into tertiary care regions, and each of them again into secondary care regions. This study investigates the self-sufficiency for in-patient care services of secondary care regions focusing on why it varies among the regions. In doing so, analysis is performed to examine a model which embodies three sets of hypotheses as follows : 1) The regional self-sufficiency for medical care services would be subject to direct influences of regional characteristics, amount of available services and structural properties of regional medical care system ; 2) The regional characteristics would have indirect effects on the self-sufficiency which are mediated by medical care services ; and 3) The amount of available services would indirectly affect the self-sufficiency by influencing the structure of regional medical care system. The results of analysis were generally consistent with the model. The findings have some practical implications. The regional self-sufficiency for medical care services partly depends upon basic properties of each region which cannot be changed in a short period of time. Thus the self-sufficiency for medical care services can be improved mainly by health policy measures. In some of the regions the self-sufficiency for in-patient care services was much higher or lower than can be predicted from the bed-population ratio. Indication is that the allocation of health resources should be made considering a variety of factors bearing upon the supply of and demand for health care ; not on the basis of just a single criterion like the availability. The self-sufficiency of a certain region is related to not only its own characterstics but also the characteristics of neighboring regions. Therefore, attention should be also directed to the inter-regional relationships in health care when the needs for investment of health resources in a region are assessed. However, it should be noted that this study used the data collected before the referral requirement was imposed. A replication of this analysis using recent data would provide an evaluation of the impact on the self-sufficiency of the referral requirement as well as a confirmation of the findings of this study.

• Journal of Korea Foresty Energy
• /
• v.18 no.2
• /
• pp.92-99
• /
• 1999

This study was carried out to understand the primary production of biomass, vertical biomass distribution in the stand and the difference of biomass production for part of the trees by stand density for natural Pinus densiflora forest at Mt. Baekdoo located in northeastern China. The primary production of biomass was estimated by the layers of trees, shrubs, herbs for five density classes. For the biomass estimation of the Pinus densiflora trees in stern, stembark and the above-ground tree, the regression model of logW = a + blog(D$^2$H) + c(D$^2$H) was adapted for all of the density classes where W is dry weight, D$_1$ diameter at breast height, and H, tree height. For the biomass estimation in branch and needle, and the needle area, the regression model of logW=a+blogD+cD was adapted for all of the density classes. With increasing stand density the biomass of trees increased but that of shrubs and herbs decreased. Net primary production of biomass in parts of the tree also increased with increasing stand density. However the percentage of the needle biomass among the total biomass in the above-ground tree decreased with increasing stand density. Consequently, primary production rate of biomass in the above-ground tree increased. The primary production of biomass for each part of the trees in natural Pinus densiflora natural forests showed in descending order : stern, needle, branch, and stembark regardless of stand density.

• Environmental and Resource Economics Review
• /
• v.25 no.3
• /
• pp.377-401
• /
• 2016

This study analyzes how much cost the power generation and energy sector in South Korea have to bear due to the introduction of emissions trading scheme during 2016 - 2017. To this end, the data on the seventh basic plan for long-term electricity supply and demand is applied to the electricity market simulation model called M-Core, and then the model forecasts carbon dioxide emissions to compare with the free emission allowances in the first national emissions permit allocation plan. The main results are as follows. Carbon dioxide emissions are estimated to be less in 2016 but more than the free emission allowances in 2017. When the price of the allowances is changed from \10,000/ton to \20,000/ton, the cost of purchasing the allowances is ranged from \70 billion to \140 billion. Under the assumption that CO2 cost is incorporated into the variable cost, a reversal of merit order between coal and LNG generation takes place when the price of the allowances exceeds \80,000/ton.

• Journal of Environmental Science International
• /
• v.20 no.12
• /
• pp.1647-1661
• /
• 2011

The Government had devised legislation of Special Act and drew up guidelines for improving air quality in Seoul Metropolitan area. In 2007 local government of Seoul, Incheon and Gyeonggi conducted the results of application policy by reduced air pollutants emission for the first time. Although there was reduction of air pollutant emission in each local government, it was ineffective as expected using air pollution monitoring database. Therefore we worked out a way to prepare modeling input data using the results of enforcement plan. And we simulated surface $NO_2$ and PM10 before and after decrease in air pollutants emission and examine reduction effects of air pollution according to enforcement regulation except other influence, by using MM5-SMOKE-CMAQ system. Each local government calculated the amount of emission reduction under application policy, and we developed to prepare input data so as to apply to SMOKE system using emission reduction of enforcement plan. Distribution factor of emission reduction were classified into detailed source and fuel codes using code mapping method in order to allocate the decreased emission. The code mapping method also included a way to allocate spatial distribution by CAPSS distribution. According to predicted result using the reduction of NOx emission, $NO_2$ concentration was decreased from 19.1 ppb to 18.0 ppb in Seoul. In Gyeonggi and Incheon $NO^2$ concentrations were down to 0.65 ppb and 0.68 ppb after application of enforcement plan. PM10 concentration was reduced from 18.2 ${\mu}g/m^3$ to 17.5 ${\mu}g/m^3$ in Seoul. In Gyeonggi PM10 concentration was down to 0.51 ${\mu}g/m^3$ and in Incheon PM10 concentration was decreased about 0.47 ${\mu}g/m^3$ which was the lower concentration than any other cities.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.4
• /
• pp.22-32
• /
• 2013

Since the percentage of vehicles equipped with Hi-pass, an electronic toll collecting device, has increased rapidly, it is very crucial to determine the optimal location of Hi-pass lanes at a toll plaza in terms of traffic control and operation. In this study, the appropriateness of existing Hi-pass lanes of a toll plaza is evaluated considering its physical geometry and traffic characteristics. A new evaluating criterion called "traffic dispersion rate" is developed in order to measure the level of traffic spreading across the toll booth lanes at a toll plaza. Logistic regression models are constructed to estimate the relationship between the traffic dispersion rate and its affecting variables. The model estimation results show that several variables including Hi-pass lane traffic volume, length of toll plaza, entering/exiting taper lengths, and locations of Hi-pass lanes. The results also suggest that traffic dispersion rate can be increased by adjusting the location of Hi-pass lanes. The study enables us to quantify traffic dispersion rate which can be used to optimize the location and operation of Hi-pass lanes at toll plazas.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.115-122
• /
• 2016

This paper proposes a system to detect driver's cognitive state by internal and external information of vehicle. The proposed system can measure driver's eye gaze. This is done by concept of information delivery and mutual information measure. For this study, we set up two web-cameras at vehicles to obtain visual information of the driver and front of the vehicle. We propose Gestalt principle based selective attention model to define information quantity of road scene. The saliency map based on gestalt principle is prominently represented by stimulus such as traffic signals. The proposed system assumes driver's cognitive resource allocation on the front scene by gaze analysis and head pose direction information. Then we use several feature algorithms for detecting driver's characteristics in real time. Modified census transform (MCT) based Adaboost is used to detect driver's face and its component whereas POSIT algorithms are used for eye detection and 3D head pose estimation. Experimental results show that the proposed system works well in real environment and confirm its usability.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.2
• /
• pp.501-514
• /
• 2015

Earthwork is a basic operation for all forms of civil works and affects construction time, cost and productivity. It is a mechanized operation that needs various construction equipment as a group and uses a lot of fuel for construction equipment. But, the problem is that earthwork operation is usually performed by equipment operator's heuristic and intuition, which can cause low productivity, high fuel consumption, and high carbon dioxide emission. As one of solutions for this problem, the fleet management system for construction equipment is suggested for effective earthwork planning, optimal equipment allocation, efficient machine operation, fast information exchange, and so forth. The purpose of this research is to suggest core methods for developing the equipment fleet management system. The methods include 3D solid parametric model generation, soil distribution using Cctree data structure, equipment fleet construction and equipment fleet operation. A simulation test is performed to verify the effectiveness of the equipment fleet management system in terms of equipment operating ratio, fuel usage, and $CO_2$ emission.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.1
• /
• pp.97-102
• /
• 2000

Subband coding is to divide the signal frequency band into a set of uncorrelated frequency bands by filtering and then to encode each of these subbands using a bit allocation rationale matched to the signal energy in that subband. The actual coding of the subband signal can be done using waveform encoding techniques such as PCM, DPCM and vector quantizer(VQ) in order to obtain higher data compression. Most researchers have focused on the error in the quantizer, but not on the overall reconstruction error and its dependence on the filter bank. This paper provides a thorough analysis of subband codecs and further development of optimum filter bank design using vector quantizer. We compute the mean squared reconstruction error(MSE) which depends on N the number of entries in each code book, k the length of each code word, and on the filter bank coefficients. We form this MSE measure in terms of the equivalent quantization model and find the optimum FIR filter coefficients for each channel in the M-band structure for a given bit rate, given filter length, and given input signal correlation model. Specific design examples are worked out for 4-tap filter in 2-band paraunitary filter bank structure. These optimum paraunitary filter coefficients are obtained by using Monte Carlo simulation. We expect that the results of this work could be contributed to study on the optimum design of subband codecs using vector quantizer.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.6
• /
• pp.1107-1114
• /
• 2004

System Packet Interface Level 4 Phase 2(SPI-4.2) is an interface for packet and cell transfer between a physical layer(PHY) device and a link layer device, for aggregate bandwidths of OC-192 ATM and Packet Over Sonet/SDH(POS), as well as 10Gbps Ethernet applications. SPI-4.2 core consists of Tx and Rx modules and supports full duplex communication. Tx module of SPI-4.2 core writes 64-bit data word and 14-bit header information from the user interface into asynchronous FIFO and transmits DDR(Double Data Rate) data over PL4 interface. Rx module of SPI-4.2 core operates in vice versa. Tx and Rx modules of SPI-4.2 core are designed to support maximum 256-channel and control the bandwidth allocation by configuring the calendar memory. Automatic DIP4 and DIP-2 parity generation and checking are implemented within the designed core. The designed core uses Xilinx ISE 5.li tool and is described in VHDL Language and is simulated by Model_SIM 5.6a. The designed core operates at 720Mbps data rate per line, which provides an aggregate bandwidth of 11.52Gbps. SPI-4.2 interface core is suited for line cards in gigabit/terabit routers, and optical cross-connect switches, and SONET/SDH-based transmission systems.