• 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 the Korea Organic Resources Recycling Association
• /
• v.24 no.4
• /
• pp.59-68
• /
• 2016

The application of the Life Cycle Assessment (LCA) methodology to assess the environmental impact of rapeseed cultivation in winter fallow after harvesting rice was investigated and compared with barley cultivation in crop rotation system. Data for input materials were collected and analyzed by 1 ton rapeseed and barley as functional unit. For the Life Cycle Impact Assessment (LCIA) the Eco-indicator 95 method has been chosen because this is well documented and regularly applied impact method. From the comparison of impact categories such as greenhouse effect, ozone depletion, acidification, heavy metals, carcinogens, summer smog, and energy resources for 1 ton of final product, emission potential from rapeseed was higher than that from barley. The range from 65 to 96% of these potential came from chemical fertilizer. On the other hand, eutrophication potential from barley was higher than that from rapeseed, mainly came from utilizing the chemical fertilizer. During the cultivation of barley and rape, environmental burden by heavy metals was evaluated by 0.5 Pt, larger than points from other impact categories. The sum of points from all impact categories in barley and rapeseed was calculated to be 0.78 Pt and 0.82 Pt, respectively. From the sensitivity analysis for barley and rapeseed, scenario 1 (crop responses to fertilization level) showed the environmental burden was continuously increased with the amount of fertilization in barley cultivation, while it was not increased only at the optimum crop responses to fertilization in rapeseed (R3). With these results, rapeseed cultivation in winter fallow paddy contributed to the amounts of environmental burden much more than barley cultivation. It is, however, highly determined that environmental weighted point resulted from evaluating both cultivation was not significantly different.

• KSBB Journal
• /
• v.23 no.1
• /
• pp.90-95
• /
• 2008

In this study, a combined process of sequential anaerobic-aerobic digestion (SAAD), fluidized-bed bioreactor (FBBR), and ultrafiltration (UF) for the treatment of small scale food waste leachate was developed and evaluated. The SAAD process was tested for performance and stability by subjecting leachate from food waste to a two-phase anaerobic digestion. The main process used FBBR composed of aerators for oxygen supply and fluidization, three 5 ton reaction chambers containing an aerobic mesophilic microorganism immobilized in PE (polyethylene), and a sedimentation chamber. The HRTs (hydraulic retention time) of the combined SAAD-FBBR-UF process were 30, 7, and 1 day, and the operation temperature was set to the optimal one for microbial growth. The pilot process maintained its performance even when the CODcr of input leachate fluctuated largely. During the operation, average CODcr, TKN, TP, and salt of the effluent were 1,207mg/L, 100mg/L, 50 mg/L, and 0.01 %, which corresponded to the removal efficiencies of 99.4%, 98.6%, 89.6%, and 98.5%, respectively. These results show that the developed process is able to manage high concentration leachate from food waste and remove CODcr, TKN, TP, and salt effectively.

• Radiation Oncology Journal
• /
• v.16 no.2
• /
• pp.195-202
• /
• 1998

Purpose : In order to obtain basic data for treatment plan in radiosurgery, we measured small fields of 6 MV X-rays and compared the measured data with our Monte Carlo simulations for the small fields. Materials and Methods : The small fields of 1.0, 2.0 and 3.0 cm in diameter were used in this study. Percentage depth dose (PDD) and beam Profiles of those fields were measured and calculated. A small semiconductor detector, water phantoms, and a remote control system were used for the measurement Monte Carlo simulations were Performed using the EGS4 code with the input data prepared for the energy distribution of 6 MV X-rays, beam divergence, circular fields and the geometry of the water phantoms. Results : In the case of PDD values, the calculated values were lower than the measured values for all fields and depths, with the differences being 0.3 to 5.7% at the depths of 20 to 20.0 cm and 0.0 to 8.9% at the surface regions. As a result of the analysis of beam profiles for all field sizes at a depth of loom in water phantom, the measured 90% dose widths were in good agreement with the calculated values, however, the calculated Penumbra radii were 0.1 cm shorter than measured values. Conclusion : The measured PDDs and beam profiles agreement with the Monte Carlo calculations approximately. However, it is different when it comes to calculations in the area of phantom surface and penumbra because the Monte Carlo calculations were performed under the simplified geometries. Therefore, we have to study how to include the actual geometries and more precise data for the field area in Monte Carlo calculations. The Monte Carlo calculations will be used as a useful tool for the very complicated conditions in measurement and verification.