• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.143-156
• /
• 2012

People easily believe that news and stock index are closely related. They think that securing news before anyone else can help them forecast the stock prices and enjoy great profit, or perhaps capture the investment opportunity. However, it is no easy feat to determine to what extent the two are related, come up with the investment decision based on news, or find out such investment information is valid. If the significance of news and its impact on the stock market are analyzed, it will be possible to extract the information that can assist the investment decisions. The reality however is that the world is inundated with a massive wave of news in real time. And news is not patterned text. This study suggests the stock-index invest model based on "News Big Data" opinion mining that systematically collects, categorizes and analyzes the news and creates investment information. To verify the validity of the model, the relationship between the result of news opinion mining and stock-index was empirically analyzed by using statistics. Steps in the mining that converts news into information for investment decision making, are as follows. First, it is indexing information of news after getting a supply of news from news provider that collects news on real-time basis. Not only contents of news but also various information such as media, time, and news type and so on are collected and classified, and then are reworked as variable from which investment decision making can be inferred. Next step is to derive word that can judge polarity by separating text of news contents into morpheme, and to tag positive/negative polarity of each word by comparing this with sentimental dictionary. Third, positive/negative polarity of news is judged by using indexed classification information and scoring rule, and then final investment decision making information is derived according to daily scoring criteria. For this study, KOSPI index and its fluctuation range has been collected for 63 days that stock market was open during 3 months from July 2011 to September in Korea Exchange, and news data was collected by parsing 766 articles of economic news media M company on web page among article carried on stock information>news>main news of portal site Naver.com. In change of the price index of stocks during 3 months, it rose on 33 days and fell on 30 days, and news contents included 197 news articles before opening of stock market, 385 news articles during the session, 184 news articles after closing of market. Results of mining of collected news contents and of comparison with stock price showed that positive/negative opinion of news contents had significant relation with stock price, and change of the price index of stocks could be better explained in case of applying news opinion by deriving in positive/negative ratio instead of judging between simplified positive and negative opinion. And in order to check whether news had an effect on fluctuation of stock price, or at least went ahead of fluctuation of stock price, in the results that change of stock price was compared only with news happening before opening of stock market, it was verified to be statistically significant as well. In addition, because news contained various type and information such as social, economic, and overseas news, and corporate earnings, the present condition of type of industry, market outlook, the present condition of market and so on, it was expected that influence on stock market or significance of the relation would be different according to the type of news, and therefore each type of news was compared with fluctuation of stock price, and the results showed that market condition, outlook, and overseas news was the most useful to explain fluctuation of news. On the contrary, news about individual company was not statistically significant, but opinion mining value showed tendency opposite to stock price, and the reason can be thought to be the appearance of promotional and planned news for preventing stock price from falling. Finally, multiple regression analysis and logistic regression analysis was carried out in order to derive function of investment decision making on the basis of relation between positive/negative opinion of news and stock price, and the results showed that regression equation using variable of market conditions, outlook, and overseas news before opening of stock market was statistically significant, and classification accuracy of logistic regression accuracy results was shown to be 70.0% in rise of stock price, 78.8% in fall of stock price, and 74.6% on average. This study first analyzed relation between news and stock price through analyzing and quantifying sensitivity of atypical news contents by using opinion mining among big data analysis techniques, and furthermore, proposed and verified smart investment decision making model that could systematically carry out opinion mining and derive and support investment information. This shows that news can be used as variable to predict the price index of stocks for investment, and it is expected the model can be used as real investment support system if it is implemented as system and verified in the future.

• The Journal of Korean Society for Radiation Therapy
• /
• v.22 no.2
• /
• pp.97-103
• /
• 2010

Purpose: Treating same region with different modalities there is a limit to evaluate the total absorbed dose of normal tissues. The reason is that it does not support to communication each modalities yet. In this article, it evaluates absorbed dose of the patients who had been treated same region by a tomotherapy and a linear accelerator. Materials and Methods: After reconstructing anatomic structure with a anthropomorphic phantom, administrate 45 Gy to a tumor in linac plan system as well as prescribe 15 Gy in tomotherapy plan system for make an ideal treatment plan. After the plan which made by tomoplan system transfers to the oncentra plan system for reproduce plan under the same condition and realize total treatment plan with summation 45 Gy linac treatment plan. To evaluate the absorbed dose of two different modalities, do a comparative study both a simple summation dose values and integration dose values. Then compare and analyze absorbed dose of normal tissues and a tumor with the patients who had been exposured radiation by above two differents modalities. Results: The result of compared data, in case of minimum dose, there are big different dose values in spleen (12.4%). On the other hand, in case of the maximum dose, it reports big different in a small bowel (10.2%) and a cord (5.8%) in head & neck cancer patients, there presents that oral (20.3%), right lens (7.7%) in minimum dose value. About maximum dose, it represents that spinal (22.5), brain stem (12%), optic chiasm (8.9%), Rt lens (11.5%), mandible (8.1%), pituitary gland (6.2%). In case of Rt abdominal cancer patients, there represents big different minimum dose as Lt kidney (20.3%), stomach (8.1%) about pelvic cancer patients, it reports there are big different in minimum dose as a bladder (15.2%) as well as big different value in maximum dose as a small bowel (5.6%), a bladder (5.5%) in addition, making treatment plan it is able us to get. Conclusion: In case of comparing both simple summation absorbed dose and integration absorbed dose, the minimum dose are represented higher as well as the maximum dose come out lower and the average dose are revealed similar with our expected values data. It is able to evaluate tumor & normal tissue absorbed dose which could had been not realized by treatment plan system. The DVH of interesting region are prescribed lower dose than expected. From now on, it needs to develop the new modality which are able to realize exact dose distribution as well as integration absorbed dose evaluation in same treatment region with different modalities.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1669-1683
• /
• 2021

AI intelligent agriculture and digital agriculture are important for the science of agriculture. Leaf chlorophyll contents(LCC) are one of the most important indicators to determine the growth status of vegetable crops. In this study, a support vector machine (SVM) regression model was produced using an unmanned aerial vehicle-based RGB camera and a multispectral (MSP) sensor for onions and garlic, and the LCC estimation applicability of the RGB camera was reviewed by comparing it with the MSP sensor. As a result of this study, the RGB-based LCC model showed lower results than the MSP-based LCC model with an average R² of 0.09, RMSE 18.66, and nRMSE 3.46%. However, the difference in accuracy between the two sensors was not large, and the accuracy did not drop significantly when compared with previous studies using various sensors and algorithms. In addition, the RGB-based LCC model reflects the field LCC trend well when compared with the actual measured value, but it tends to be underestimated at high chlorophyll concentrations. It was possible to confirm the applicability of the LCC estimation with RGB considering the economic feasibility and versatility of the RGB camera. The results obtained from this study are expected to be usefully utilized in digital agriculture as AI intelligent agriculture technology that applies artificial intelligence and big data convergence technology.

• Journal of Wetlands Research
• /
• v.16 no.1
• /
• pp.19-32
• /
• 2014

The purpose of this paper is to obtain reliable rainfall data for runoff simulation and other hydrological analysis by the calibration of gauge rainfall. The calibrated gauge rainfall could be close to the actual value with rainfall on the ground. In order to analyze the wind effect of ground rain gauge, we selected the rain gauge sites with and without a windshield and standard rain gauge data from Chupungryeong weather station installed by standard of WMO. Simple linear regression model and artificial neural networks were used for the calibration of rainfalls, and we verified the reliability of the calibrated rainfalls through the runoff analysis using $Vflo^{TM}$. Rainfall calibrated by linear regression is higher amount of rainfall in 5%~18% than actual rainfall, and the wind remarkably affects the rainfall amount in the range of wind speed of 1.6~3.3m/s. It is hard to apply the linear regression model over 5.5m/s wind speed, because there is an insufficient wind speed data over 5.5m/s and there are also some outliers. On the other hand, rainfall calibrated by neural networks is estimated lower rainfall amount in 10~20% than actual rainfall. The results of the statistical evaluations are that neural networks model is more suitable for relatively big standard deviation and average rainfall. However, the linear regression model shows more suitable for extreme values. For getting more reliable rainfall data, we may need to select the suitable model for rainfall calibration. We expect the reliable hydrologic analysis could be performed by applying the calibration method suggested in this research.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.6
• /
• pp.581-590
• /
• 2017

This study analyzes the effect of floating population, locational characteristics and spatial autocorrelation on foodservice sales using big data provided by the Seoul Institute. Although big data provided by public sector is growing recently, research difficulties are occurred due to the difference of aggregation units of data. In this study, the aggregation unit of a dependent variable, sales of foodservice is SKT unit but those of independent variables are various, which are provided as the aggregation unit of Korea National Statistical Office, administration dong unit and point. To overcome this problem, we convert all data to the SKT aggregation unit. The spatial error model, SEM is used for analysing spatial autocorrelation. Floating population, the number of nearby workers, and the area of aggregation unit effect positively on foodservice sales. In addition, the sales of Jung-gu, Yeongdeungpo-gu and Songpa-gu are less than that of Gangnam-gu. This study provides implications for further study by showing the usefulness and limitations of converting aggregation units of heterogeneous spatial data.

• Journal of the Korean Society of Safety
• /
• v.32 no.2
• /
• pp.132-146
• /
• 2017

Appropriate speed limits at a reasonable level in urban roads are highly important factors for efficient and safe movement. Thus, it is greatly necessary to develop the objective models or methodology based on engineering study considering factors such as traffic accident rates, roadside development levels, and roadway geometry characteristics etc. The purpose of this study is to develop the estimate model of appropriate speed limits at each road sections in urban roads using traffic information big data and field specific data and to review the effects of accident decrease. In this study, the estimate method of appropriate speed limits in directional two or more lanes of urban roads is reflecting features of actual variables in a form of adjustment factor on the basis of the maximum statutory speed limits. As a result of investigating and testing influential variables, the main variables to affect the operating speed are the function of road, the existence of median, the width of lane, the number of traffic entrance/exit path and the number of traffic signal or nonsignal at intersection and crosswalk. As a result of testing this model, when the differences are bigger between the real operating speed and the recommended speed limits using model developed in this study, the accident rate generally turns out to be higher. In case of using the model proposed in this study, it means accident rate can be lower. When the result of this study is applied, the speed limits of directional two or more lane roads in Seoul appears about 11km/h lower than the current speed limits. The decrease of average operating speed caused by the decrease of speed limits is 2.8km/h, and the decrease effect of whole accidents according to the decrease of speed is 18% at research road. In case that accident severity is considered, the accident decrease effects are expected to 17~24% in fatalities, 11~17% in seriously injured road user, 6~9% in slightly injured road user, 5~6% in property damage only accidents.

• Fire Science and Engineering
• /
• v.33 no.6
• /
• pp.173-180
• /
• 2019

Oil tank fires need to be suppressed differently from other oil-related fires, due to the high-temperature flames and hot updraft above the tank, in the former case, that cause the destruction of large amounts of foam. We studied high-capacity foam discharge systems based on the standards of the American Petroleum Institute (API), National Fire Protection Association (NFPA), British Standard European Norm (BS EN), and the laws of Japan. The performance of a high-capacity foam discharge system was measured by conducting real fire experiments with model oil tanks. We concluded that lightweight and easily movable high-capacity foam discharge systems should be urgently introduced in domestic operations. Additionally, the obstacles faced by major tanks, such as long-distance installation of large-diameter fire hoses and narrowing of firefighting spaces, should be resolved depending on the conditions of the site.

• Journal of Soil and Groundwater Environment
• /
• v.22 no.6
• /
• pp.66-73
• /
• 2017

Empirical erosion models like Universal Soil Loss Equation (USLE) models have been widely used to make spatially distributed soil erosion vulnerability maps. Even if the models detect vulnerable sites relatively well utilizing big data related to climate, geography, geology, land use, etc within study domains, they do not adequately describe the physical process of soil erosion on the ground surface caused by rainfall or overland flow. In other words, such models are still powerful tools to distinguish the erosion-prone areas at large scale, but physics-based models are necessary to better analyze soil erosion and deposition as well as the eroded particle transport. In this study a physics-based soil erosion modeling system was developed to produce both runoff and sediment yield time series at watershed scale and reflect them in the erosion and deposition maps. The developed modeling system consists of 3 sub-systems: rainfall pre-processor, geography pre-processor, and main modeling processor. For modeling system validation, we applied the system for various erosion cases, in particular, rainfall-runoff-sediment yield simulation and estimation of probable maximum sediment (PMS) correlated with probable maximum rainfall (PMP). The system provided acceptable performances of both applications.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1243-1248
• /
• 2018

Metal Powder Metallurgy is a manufacturing technology that makes unique model parts or a certain type of product by using a hardening phenomenon when a powder of metal or metal oxide is put it into a mold and compression-molded by a press and then heated and sintered at a high temperature. Powder metallurgical press equipment is mainly used to make the parts of automobile, electronic parts and so on, and most of them are manufactured using precise servo motor. The intelligent precision servo control powder molding press system which is designed and implemented in this paper has advantages of lowering the price and maintaining the precision by using the mechanical camshaft for the upper ram part and precisely controlling the lower ram part using the high precision servo system. In addition, OPC-based monitoring and process data collection systems are designed and implemented to provide scalability that can be applied to smart manufacturing management systems that utilize Big Data in the future.

• Journal of Information Technology Services
• /
• v.19 no.6
• /
• pp.1-13
• /
• 2020

Recently, 80% of big data consists of unstructured text data. In particular, various types of documents are stored in the form of large-scale unstructured documents through social network services (SNS), blogs, news, etc., and the importance of unstructured data is highlighted. As the possibility of using unstructured data increases, various analysis techniques such as text mining have recently appeared. Therefore, in this study, topic modeling technique was applied to the Korea Highway Corporation's voice of customer (VOC) data that includes customer opinions and complaints. Currently, VOC data is divided into the business areas of Korea Expressway Corporation. However, the classified categories are often not accurate, and the ambiguous ones are classified as "other". Therefore, in order to use VOC data for efficient service improvement and the like, a more systematic and efficient classification method of VOC data is required. To this end, this study proposed two approaches, including method using only the latent dirichlet allocation (LDA), the most representative topic modeling technique, and a new method combining the LDA and the word embedding technique, Word2vec. As a result, it was confirmed that the categories of VOC data are relatively well classified when using the new method. Through these results, it is judged that it will be possible to derive the implications of the Korea Expressway Corporation and utilize it for service improvement.