• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.25-38
• /
• 2019

Selecting high-quality information that meets the interests and needs of users among the overflowing contents is becoming more important as the generation continues. In the flood of information, efforts to reflect the intention of the user in the search result better are being tried, rather than recognizing the information request as a simple string. Also, large IT companies such as Google and Microsoft focus on developing knowledge-based technologies including search engines which provide users with satisfaction and convenience. Especially, the finance is one of the fields expected to have the usefulness and potential of text data analysis because it's constantly generating new information, and the earlier the information is, the more valuable it is. Automatic knowledge extraction can be effective in areas where information flow is vast, such as financial sector, and new information continues to emerge. However, there are several practical difficulties faced by automatic knowledge extraction. First, there are difficulties in making corpus from different fields with same algorithm, and it is difficult to extract good quality triple. Second, it becomes more difficult to produce labeled text data by people if the extent and scope of knowledge increases and patterns are constantly updated. Third, performance evaluation is difficult due to the characteristics of unsupervised learning. Finally, problem definition for automatic knowledge extraction is not easy because of ambiguous conceptual characteristics of knowledge. So, in order to overcome limits described above and improve the semantic performance of stock-related information searching, this study attempts to extract the knowledge entity by using neural tensor network and evaluate the performance of them. Different from other references, the purpose of this study is to extract knowledge entity which is related to individual stock items. Various but relatively simple data processing methods are applied in the presented model to solve the problems of previous researches and to enhance the effectiveness of the model. From these processes, this study has the following three significances. First, A practical and simple automatic knowledge extraction method that can be applied. Second, the possibility of performance evaluation is presented through simple problem definition. Finally, the expressiveness of the knowledge increased by generating input data on a sentence basis without complex morphological analysis. The results of the empirical analysis and objective performance evaluation method are also presented. The empirical study to confirm the usefulness of the presented model, experts' reports about individual 30 stocks which are top 30 items based on frequency of publication from May 30, 2017 to May 21, 2018 are used. the total number of reports are 5,600, and 3,074 reports, which accounts about 55% of the total, is designated as a training set, and other 45% of reports are designated as a testing set. Before constructing the model, all reports of a training set are classified by stocks, and their entities are extracted using named entity recognition tool which is the KKMA. for each stocks, top 100 entities based on appearance frequency are selected, and become vectorized using one-hot encoding. After that, by using neural tensor network, the same number of score functions as stocks are trained. Thus, if a new entity from a testing set appears, we can try to calculate the score by putting it into every single score function, and the stock of the function with the highest score is predicted as the related item with the entity. To evaluate presented models, we confirm prediction power and determining whether the score functions are well constructed by calculating hit ratio for all reports of testing set. As a result of the empirical study, the presented model shows 69.3% hit accuracy for testing set which consists of 2,526 reports. this hit ratio is meaningfully high despite of some constraints for conducting research. Looking at the prediction performance of the model for each stocks, only 3 stocks, which are LG ELECTRONICS, KiaMtr, and Mando, show extremely low performance than average. this result maybe due to the interference effect with other similar items and generation of new knowledge. In this paper, we propose a methodology to find out key entities or their combinations which are necessary to search related information in accordance with the user's investment intention. Graph data is generated by using only the named entity recognition tool and applied to the neural tensor network without learning corpus or word vectors for the field. From the empirical test, we confirm the effectiveness of the presented model as described above. However, there also exist some limits and things to complement. Representatively, the phenomenon that the model performance is especially bad for only some stocks shows the need for further researches. Finally, through the empirical study, we confirmed that the learning method presented in this study can be used for the purpose of matching the new text information semantically with the related stocks.

• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.10
• /
• pp.493-501
• /
• 2007

The imprecise real-time system provides flexibility in scheduling time-critical tasks. Most scheduling problems of satisfying both 0/1 constraint and timing constraints, while the total error is minimized, are NP-complete when the optional tasks have arbitrary processing times. Liu suggested a reasonable strategy of scheduling tasks with the 0/1 constraint on uniprocessors for minimizing the total error. Song et at suggested a reasonable strategy of scheduling tasks with the 0/1 constraint on multiprocessors for minimizing the total error. But, these algorithms are all off-line algorithms. In the online scheduling, the NORA algorithm can find a schedule with the minimum total error for the imprecise online task system. In NORA algorithm, EDF strategy is adopted in the optional scheduling. On the other hand, for the task system with 0/1 constraint, EDF_Scheduling may not be optimal in the sense that the total error is minimized. Furthermore, when the optional tasks are scheduled in the ascending order of their required processing times, NORA algorithm which EDF strategy is adopted may not produce minimum total error. Therefore, in this paper, an online algorithm is proposed to minimize total error for the imprecise task system with 0/1 constraint. Then, to compare the performance between the proposed algorithm and NORA algorithm, a series of experiments are performed. As a conseqence of the performance comparison between two algorithms, it has been concluded that the proposed algorithm can produce similar total error to NORA algorithm when the optional tasks are scheduled in the random order of their required processing times but, the proposed algorithm can produce less total error than NORA algorithm especially when the optional tasks are scheduled in the ascending order of their required processing times.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.17 no.4
• /
• pp.384-398
• /
• 2015

In this paper, the high-resolution Weather Research and Forecasting/Noah-MultiParameterization (WRF/Noah-MP) modeling system is configured for the Cheongmicheon Farmland site in Korea (CFK), and its performance in land and atmospheric simulation is evaluated using the observed data at CFK during the 2014 special observation period (21 August-10 September). In order to explore the usefulness of turning on Noah-MP dynamic vegetation in midterm simulations of surface and atmospheric variables, two numerical experiments are conducted without dynamic vegetation and with dynamic vegetation (referred to as CTL and DVG experiments, respectively). The main results are as following. 1) CTL showed a tendency of overestimating daytime net shortwave radiation, thereby surface heat fluxes and Bowen ratio. The CTL experiment showed reasonable magnitudes and timing of air temperature at 2 m and 10 m; especially the small error in simulating minimum air temperature showed high potential for predicting frost and leaf wetness duration. The CTL experiment overestimated 10-m wind and precipitation, but the beginning and ending time of precipitation were well captured. 2) When the dynamic vegetation was turned on, the WRF/Noah-MP system showed more realistic values of leaf area index (LAI), net shortwave radiation, surface heat fluxes, Bowen ratio, air temperature, wind and precipitation. The DVG experiment, where LAI is a prognostic variable, produced larger LAI than CTL, and the larger LAI showed better agreement with the observed. The simulated Bowen ratio got closer to the observed ratio, indicating reasonable surface energy partition. The DVG experiment showed patterns similar to CTL, with differences for maximum air temperature. Both experiments showed faster rising of 10-m air temperature during the morning growth hours, presumably due to the rapid growth of daytime mixed layers in the Yonsei University (YSU) boundary layer scheme. The DVG experiment decreased errors in simulating 10-m wind and precipitation. 3) As horizontal resolution increases, the models did not show practical improvement in simulation performance for surface fluxes, air temperature, wind and precipitation, and required three-dimensional observation for more agricultural land spots as well as consistency in model topography and land cover data.

• Journal of Korea Water Resources Association
• /
• v.54 no.10
• /
• pp.795-805
• /
• 2021

In this study, after developing an LSTM-based deep learning model for estimating daily runoff in the Soyang River Dam basin, the accuracy of the model for various combinations of model structure and input data was investigated. A model was built based on the database consisting of average daily precipitation, average daily temperature, average daily wind speed (input up to here), and daily average flow rate (output) during the first 12 years (1997.1.1-2008.12.31). The Nash-Sutcliffe Model Efficiency Coefficient (NSE) and RMSE were examined for validation using the flow discharge data of the later 12 years (2009.1.1-2020.12.31). The combination that showed the highest accuracy was the case in which all possible input data (12 years of daily precipitation, weather temperature, wind speed) were used on the LSTM model structure with 64 hidden units. The NSE and RMSE of the verification period were 0.862 and 76.8 m³/s, respectively. When the number of hidden units of LSTM exceeds 500, the performance degradation of the model due to overfitting begins to appear, and when the number of hidden units exceeds 1000, the overfitting problem becomes prominent. A model with very high performance (NSE=0.8~0.84) could be obtained when only 12 years of daily precipitation was used for model training. A model with reasonably high performance (NSE=0.63-0.85) when only one year of input data was used for model training. In particular, an accurate model (NSE=0.85) could be obtained if the one year of training data contains a wide magnitude of flow events such as extreme flow and droughts as well as normal events. If the training data includes both the normal and extreme flow rates, input data that is longer than 5 years did not significantly improve the model performance.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.147-157
• /
• 2022

This study tried to propose a smart farm technology strategy suitable for the domestic situation, focusing on the differentiation suitable for the domestic situation of ICT technology. In the case of advanced countries in the overseas agricultural industry, it was confirmed that they focused on the development of a specific stage that reflected the geographical characteristics of each country, the characteristics of the agricultural industry, and the characteristics of the people's demand. Confirmed that no enemy development is being performed. Therefore, in response to problems such as a rapid decrease in the domestic rural population, aging population, loss of agricultural price competitiveness, increase in fallow land, and decrease in use rate of arable land, this study aims to develop smart farm ICT technology in the future to create quality agricultural products and have price competitiveness. It was suggested that the smart farm should be promoted by paying attention to the excellent performance, ease of use due to the aging of the labor force, and economic feasibility suitable for a small business scale. First, in terms of economic feasibility, the ICT technology is configured by selecting only the functions necessary for the small farm household (primary) business environment, and the smooth communication system with these is applied to the ICT technology to gradually update the functions required by the actual farmhouse. suggested that it may contribute to the reduction. Second, in terms of performance, it is suggested that the operation accuracy can be increased if attention is paid to improving the communication function of ICT, such as adjusting the difficulty of big data suitable for the aging population in Korea, using a language suitable for them, and setting an algorithm that reflects their prediction tendencies. Third, the level of ease of use. Smart farms based on ICT technology for the development of the Industry6.0 (1.0(Agriculture, Forestry) + 2.0(Agricultural and Water & Water Processing) + 3.0 (Service, Rural Experience, SCM)) perform operations according to specific commands, finally suggested that ease of use can be promoted by presetting and standardizing devices based on big data configuration customized for each regional environment.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.141-154
• /
• 2019

Rapid growth of internet technology and social media is progressing. Data mining technology has evolved to enable unstructured document representations in a variety of applications. Sentiment analysis is an important technology that can distinguish poor or high-quality content through text data of products, and it has proliferated during text mining. Sentiment analysis mainly analyzes people's opinions in text data by assigning predefined data categories as positive and negative. This has been studied in various directions in terms of accuracy from simple rule-based to dictionary-based approaches using predefined labels. In fact, sentiment analysis is one of the most active researches in natural language processing and is widely studied in text mining. When real online reviews aren't available for others, it's not only easy to openly collect information, but it also affects your business. In marketing, real-world information from customers is gathered on websites, not surveys. Depending on whether the website's posts are positive or negative, the customer response is reflected in the sales and tries to identify the information. However, many reviews on a website are not always good, and difficult to identify. The earlier studies in this research area used the reviews data of the Amazon.com shopping mal, but the research data used in the recent studies uses the data for stock market trends, blogs, news articles, weather forecasts, IMDB, and facebook etc. However, the lack of accuracy is recognized because sentiment calculations are changed according to the subject, paragraph, sentiment lexicon direction, and sentence strength. This study aims to classify the polarity analysis of sentiment analysis into positive and negative categories and increase the prediction accuracy of the polarity analysis using the pretrained IMDB review data set. First, the text classification algorithm related to sentiment analysis adopts the popular machine learning algorithms such as NB (naive bayes), SVM (support vector machines), XGboost, RF (random forests), and Gradient Boost as comparative models. Second, deep learning has demonstrated discriminative features that can extract complex features of data. Representative algorithms are CNN (convolution neural networks), RNN (recurrent neural networks), LSTM (long-short term memory). CNN can be used similarly to BoW when processing a sentence in vector format, but does not consider sequential data attributes. RNN can handle well in order because it takes into account the time information of the data, but there is a long-term dependency on memory. To solve the problem of long-term dependence, LSTM is used. For the comparison, CNN and LSTM were chosen as simple deep learning models. In addition to classical machine learning algorithms, CNN, LSTM, and the integrated models were analyzed. Although there are many parameters for the algorithms, we examined the relationship between numerical value and precision to find the optimal combination. And, we tried to figure out how the models work well for sentiment analysis and how these models work. This study proposes integrated CNN and LSTM algorithms to extract the positive and negative features of text analysis. The reasons for mixing these two algorithms are as follows. CNN can extract features for the classification automatically by applying convolution layer and massively parallel processing. LSTM is not capable of highly parallel processing. Like faucets, the LSTM has input, output, and forget gates that can be moved and controlled at a desired time. These gates have the advantage of placing memory blocks on hidden nodes. The memory block of the LSTM may not store all the data, but it can solve the CNN's long-term dependency problem. Furthermore, when LSTM is used in CNN's pooling layer, it has an end-to-end structure, so that spatial and temporal features can be designed simultaneously. In combination with CNN-LSTM, 90.33% accuracy was measured. This is slower than CNN, but faster than LSTM. The presented model was more accurate than other models. In addition, each word embedding layer can be improved when training the kernel step by step. CNN-LSTM can improve the weakness of each model, and there is an advantage of improving the learning by layer using the end-to-end structure of LSTM. Based on these reasons, this study tries to enhance the classification accuracy of movie reviews using the integrated CNN-LSTM model.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.19-38
• /
• 2017

Collaborative filtering (CF) algorithm has been popularly used for implementing recommender systems. Until now, there have been many prior studies to improve the accuracy of CF. Among them, some recent studies adopt 'hybrid recommendation approach', which enhances the performance of conventional CF by using additional information. In this research, we propose a new hybrid recommender system which fuses CF and the results from the social network analysis on trust and distrust relationship networks among users to enhance prediction accuracy. The proposed algorithm of our study is based on memory-based CF. But, when calculating the similarity between users in CF, our proposed algorithm considers not only the correlation of the users' numeric rating patterns, but also the users' in-degree centrality values derived from trust and distrust relationship networks. In specific, it is designed to amplify the similarity between a target user and his or her neighbor when the neighbor has higher in-degree centrality in the trust relationship network. Also, it attenuates the similarity between a target user and his or her neighbor when the neighbor has higher in-degree centrality in the distrust relationship network. Our proposed algorithm considers four (4) types of user relationships - direct trust, indirect trust, direct distrust, and indirect distrust - in total. And, it uses four adjusting coefficients, which adjusts the level of amplification / attenuation for in-degree centrality values derived from direct / indirect trust and distrust relationship networks. To determine optimal adjusting coefficients, genetic algorithms (GA) has been adopted. Under this background, we named our proposed algorithm as SNACF-GA (Social Network Analysis - based CF using GA). To validate the performance of the SNACF-GA, we used a real-world data set which is called 'Extended Epinions dataset' provided by 'trustlet.org'. It is the data set contains user responses (rating scores and reviews) after purchasing specific items (e.g. car, movie, music, book) as well as trust / distrust relationship information indicating whom to trust or distrust between users. The experimental system was basically developed using Microsoft Visual Basic for Applications (VBA), but we also used UCINET 6 for calculating the in-degree centrality of trust / distrust relationship networks. In addition, we used Palisade Software's Evolver, which is a commercial software implements genetic algorithm. To examine the effectiveness of our proposed system more precisely, we adopted two comparison models. The first comparison model is conventional CF. It only uses users' explicit numeric ratings when calculating the similarities between users. That is, it does not consider trust / distrust relationship between users at all. The second comparison model is SNACF (Social Network Analysis - based CF). SNACF differs from the proposed algorithm SNACF-GA in that it considers only direct trust / distrust relationships. It also does not use GA optimization. The performances of the proposed algorithm and comparison models were evaluated by using average MAE (mean absolute error). Experimental result showed that the optimal adjusting coefficients for direct trust, indirect trust, direct distrust, indirect distrust were 0, 1.4287, 1.5, 0.4615 each. This implies that distrust relationships between users are more important than trust ones in recommender systems. From the perspective of recommendation accuracy, SNACF-GA (Avg. MAE = 0.111943), the proposed algorithm which reflects both direct and indirect trust / distrust relationships information, was found to greatly outperform a conventional CF (Avg. MAE = 0.112638). Also, the algorithm showed better recommendation accuracy than the SNACF (Avg. MAE = 0.112209). To confirm whether these differences are statistically significant or not, we applied paired samples t-test. The results from the paired samples t-test presented that the difference between SNACF-GA and conventional CF was statistical significant at the 1% significance level, and the difference between SNACF-GA and SNACF was statistical significant at the 5%. Our study found that the trust/distrust relationship can be important information for improving performance of recommendation algorithms. Especially, distrust relationship information was found to have a greater impact on the performance improvement of CF. This implies that we need to have more attention on distrust (negative) relationships rather than trust (positive) ones when tracking and managing social relationships between users.

• Journal of Korea Spatial Information System Society
• /
• v.10 no.4
• /
• pp.77-88
• /
• 2008

There has been growing demands to manage the water quality of west coastal region due to the large scale urbanization along the coastal zone, the possibility of application of TMDL(Total Maximum Daily Loadings) to Han river, and the natural disaster such as oil spill incident in Taean, Chungnam. However, no system has been developed for such purposes. In this background, the demand of GIS based effective water quality management has been increased to monitor water quality environment and propose best management alternatives for Han river and Kyeonggi bay. This study mainly focused on the development of integrated water quality management system for Han river bas in and its estuary are a connected to Kyeonggi bay to support integrated water quality management and its plan. Integration was made based on GIS by spatial linking between water quality attributes and location information. A GIS DB was built to estimate the amount of generated and discharged water pollutants according to TMDL technical guide and it included input data to use two different water quality models--W ASP7 for Han river and EFDC for coastal area--to forecast water quality and to suggest BMP(Best management Practices). The results of BOD, TN, and TP from WASP7 were used as the input to run EFDC. Based on the study results, some critical areas which have relatively higher pollutant loadings were identified, and it was also identified that the locations discharging water pollutant loadings to river and seasonal factor affected water quality. And the relationship of water quality between river and its estuary area was quantitatively verified. The results showed that GIS based integrated system could be used as a tool for estimating status-quo of water quality and proposing economically effective BMPs to mitigate water pollution. Further studies need to be made for improving system's capabilities such as adding decision making function as well as cost-benefit analysis, etc. Also, the concrete methodology for water quality management using the system need to be developed.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.18 no.4
• /
• pp.307-319
• /
• 2016

A Land-Atmosphere Modeling Package (LAMP) for supporting agricultural and forest management was developed at the National Center for AgroMeteorology (NCAM). The package is comprised of two components; one is the Weather Research and Forecasting modeling system (WRF) coupled with Noah-Multiparameterization options (Noah-MP) Land Surface Model (LSM) and the other is an offline one-dimensional LSM. The objective of this paper is to briefly describe the two components of the NCAM-LAMP and to evaluate their initial performance. The coupled WRF/Noah-MP system is configured with a parent domain over East Asia and three nested domains with a finest horizontal grid size of 810 m. The innermost domain covers two Gwangneung deciduous and coniferous KoFlux sites (GDK and GCK). The model is integrated for about 8 days with the initial and boundary conditions taken from the National Centers for Environmental Prediction (NCEP) Final Analysis (FNL) data. The verification variables are 2-m air temperature, 10-m wind, 2-m humidity, and surface precipitation for the WRF/Noah-MP coupled system. Skill scores are calculated for each domain and two dynamic vegetation options using the difference between the observed data from the Korea Meteorological Administration (KMA) and the simulated data from the WRF/Noah-MP coupled system. The accuracy of precipitation simulation is examined using a contingency table that is made up of the Probability of Detection (POD) and the Equitable Threat Score (ETS). The standalone LSM simulation is conducted for one year with the original settings and is compared with the KoFlux site observation for net radiation, sensible heat flux, latent heat flux, and soil moisture variables. According to results, the innermost domain (810 m resolution) among all domains showed the minimum root mean square error for 2-m air temperature, 10-m wind, and 2-m humidity. Turning on the dynamic vegetation had a tendency of reducing 10-m wind simulation errors in all domains. The first nested domain (7,290 m resolution) showed the highest precipitation score, but showed little advantage compared with using the dynamic vegetation. On the other hand, the offline one-dimensional Noah-MP LSM simulation captured the site observed pattern and magnitude of radiative fluxes and soil moisture, and it left room for further improvement through supplementing the model input of leaf area index and finding a proper combination of model physics.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.19 no.3
• /
• pp.153-163
• /
• 2017

The objective of this study is to enhance the model's speed of estimating weather variables (e.g., minimum/maximum temperature, sunshine hour, PRISM (Parameter-elevation Regression on Independent Slopes Model) based precipitation), which are applied to the Agrometeorological Early Warning System (http://www.agmet.kr). The current process of weather estimation is operated on high-performance multi-core CPUs that have 8 physical cores and 16 logical threads. Nonetheless, the server is not even dedicated to the handling of a single county, indicating that very high overhead is involved in calculating the 10 counties of the Seomjin River Basin. In order to reduce such overhead, several cache and parallelization techniques were used to measure the performance and to check the applicability. Results are as follows: (1) for simple calculations such as Growing Degree Days accumulation, the time required for Input and Output (I/O) is significantly greater than that for calculation, suggesting the need of a technique which reduces disk I/O bottlenecks; (2) when there are many I/O, it is advantageous to distribute them on several servers. However, each server must have a cache for input data so that it does not compete for the same resource; and (3) GPU-based parallel processing method is most suitable for models such as PRISM with large computation loads.