• Journal of KIISE
• /
• v.43 no.10
• /
• pp.1085-1093
• /
• 2016

Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.2D
• /
• pp.233-239
• /
• 2006

Most research for until at now link travel time were research for mean link travel time calculate or estimate which uses the average of the individual vehicle. however, the link travel time distribution is divided caused by with the impact factor which is various traffic condition, signal operation condition and the road conditional etc. preceding study result for link travel time distribution characteristic showed that the patterns of going through traffic were divided up to 2 in the link travel times. therefore, it will be more accurate to divide up the link travel time into the one involving delay and the other without delay, rather than using the average link travel time in terms of assessing the traffic situation. this study is it analyzed transit hour distribution characteristic and a cause using examine to the variables which give an effect at link travel time distribute using simulation program and determinate link travel time distribute ratio estimation model. to assess the distribution of the link travel times, this research develops the regression model and the fuzzy model. the variables that have high level of correlations in both estimation models are the rest time of green ball and the delay vehicles. these variables were used to construct the methods in the estimation models. The comparison of the two estimation models-fuzzy and regression model- showed that fuzzy model out-competed the regression model in terms of reliability and applicability.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.113-127
• /
• 2016

Among the techniques for recommendation, collaborative filtering (CF) is commonly recognized to be the most effective for implementing recommender systems. Until now, CF has been popularly studied and adopted in both academic and real-world applications. The basic idea of CF is to create recommendation results by finding correlations between users of a recommendation system. CF system compares users based on how similar they are, and recommend products to users by using other like-minded people's results of evaluation for each product. Thus, it is very important to compute evaluation similarities among users in CF because the recommendation quality depends on it. Typical CF uses user's explicit numeric ratings of items (i.e. quantitative information) when computing the similarities among users in CF. In other words, user's numeric ratings have been a sole source of user preference information in traditional CF. However, user ratings are unable to fully reflect user's actual preferences from time to time. According to several studies, users may more actively accommodate recommendation of reliable others when purchasing goods. Thus, trust relationship can be regarded as the informative source for identifying user's preference with accuracy. Under this background, we propose a new hybrid recommender system that fuses CF and social network analysis (SNA). The proposed system adopts the recommendation algorithm that additionally reflect the result analyzed by SNA. In detail, our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and trust relationship information between users when calculating user similarities. For this, our system creates and uses not only user-item rating matrix, but also user-to-user trust network. As the methods for calculating user similarity between users, we proposed two alternatives - one is algorithm calculating the degree of similarity between users by utilizing in-degree and out-degree centrality, which are the indices representing the central location in the social network. We named these approaches as 'Trust CF - All' and 'Trust CF - Conditional'. The other alternative is the algorithm reflecting a neighbor's score higher when a target user trusts the neighbor directly or indirectly. The direct or indirect trust relationship can be identified by searching trust network of users. In this study, we call this approach 'Trust CF - Search'. To validate the applicability of the proposed system, we used experimental data provided by LibRec that crawled from the entire FilmTrust website. It consists of ratings of movies and trust relationship network indicating who to trust between users. The experimental system was implemented using Microsoft Visual Basic for Applications (VBA) and UCINET 6. To examine the effectiveness of the proposed system, we compared the performance of our proposed method with one of conventional CF system. The performances of recommender system were evaluated by using average MAE (mean absolute error). The analysis results confirmed that in case of applying without conditions the in-degree centrality index of trusted network of users(i.e. Trust CF - All), the accuracy (MAE = 0.565134) was lower than conventional CF (MAE = 0.564966). And, in case of applying the in-degree centrality index only to the users with the out-degree centrality above a certain threshold value(i.e. Trust CF - Conditional), the proposed system improved the accuracy a little (MAE = 0.564909) compared to traditional CF. However, the algorithm searching based on the trusted network of users (i.e. Trust CF - Search) was found to show the best performance (MAE = 0.564846). And the result from paired samples t-test presented that Trust CF - Search outperformed conventional CF with 10% statistical significance level. Our study sheds a light on the application of user's trust relationship network information for facilitating electronic commerce by recommending proper items to users.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.9
• /
• pp.4214-4223
• /
• 2012

The argument related to the use of real and anonymous names on the Internet bulletin board has recently become a main issue. When using real names, it is possible to violate free discussion and privacy. Also, when using anonymous names, it is possible to have the reverse function of the Internet in regard to the use of malicious replies or the distribution of false ideas. Therefore, this paper has made it possible to prevent the spread of the user's personal information and execute the single log-in process by using the XML-token method which is one of the SSO technologies. Also, by issuing virtual IDs and forming the path when establishing tokens, the anonymous bulletin board which provides anonymity with a conditional tracing process has been suggested. After analyzing the performance of visitor numbers at authentication time, the anonymous bulletin board based on the group signature method showed the average response rate of 0.72 seconds, 0.18 seconds, which was suggested scheme. In the authentication time 4-5 times faster response speed, respectively. Also, since the suggested system does not have to provide a single authentication process or make the user provide his or her signature, the level of user's convenience seems to be much higher. Such a result shows that the system suggested on the anonymous bulletin board has a more appropriate level of user's convenience.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.2
• /
• pp.819-823
• /
• 2014

Objective: The aim was to evaluate roles of vitamin D3 (VD3) and beta-carotene (BC) in the development of esophageal squamous cell carcinoma (ESCC) in a high-risk area, Huai'an District, Huai'an City, China. Methods: 100 new ESCC diagnosed cases from 2007 to 2008 and 200 residency- age-, and sex-matched healthy controls were recruited. Data were collected from questionnaires, including a food frequency questionnaire (FFQ) to calculate the BC intake, and reversed phase high-performance liquid chromatography (RP-HPLC) was used to measure the serum concentrations of BC and VD3. Odds ratios (OR) and 95% confidence intervals (CI) were calculated in conditional logistic regression models. Results: The average dietary intake of BC was $3322.9{\mu}g$ (2032.4-5734.3) in the case group and $3626.8{\mu}g$ (1961.9-5827.9) in control group per capita per day with no significant difference by Wilcoxon test (p>0.05). However, the levels of VD3 and BC in the case group were significantly lower than in the control group (p<0.05). The OR values of the highest quartile and the lowest quartile of VD3 and BC in serum samples were both 0.13. Conclusion: Our results add to the evidence that high circulating levels of VD3 and BC are associated with a reduced risk of ESCC in this Chinese population.

• Atmosphere
• /
• v.27 no.1
• /
• pp.41-54
• /
• 2017

Organic carbon (OC) and elemental carbon (EC) in $PM_{2.5}$ were measured using Sunset OC/EC Field Analyzer at Seoul Hwangsa Monitoring Center from March to April, 2016. The mean concentrations of OC and EC during the entire period were $4.4{\pm}2.0{\mu}gC\;m^{-3}$ and $1.4{\pm}0.6{\mu}gC\;m^{-3}$, respectively. OC/EC ratio was $3.4{\pm}1.0$. The average concentrations of $PM_{10}$ and $PM_{2.5}$ were $57.4{\pm}25.9$ and $39.7{\pm}19.8{\mu}g\;m^{-3}$, respectively, which were detected by an optical particle counter. The OC and EC peaks were observed in the morning, which were impacted by vehicle emission, however, their diurnal variations were not noticeable. This is determined to be contributed by the long-range transported OC or secondary formation via photochemical reaction by volatile organic compounds at afternoon. A conditional probability function (CPF) model was used to identify the local source of pollution. High concentrations of $PM_{10}$ and $PM_{2.5}$ were observed from the westerly wind, regardless of wind speed. When wind velocity was high, a mixing plume of dust and pollution during long-range transport from China in spring was observed. In contrast, pollution in low wind velocity was from local source, regardless of direction. To know the effect of long-range transport on pollution, a concentration weighted trajectory (CWT) model was analyzed based on a potential source contribution function (PSCF) model in which 75 percentiles high concentration was picked out for CWT analysis. $PM_{10}$, $PM_{2.5}$, OC, and EC were dominantly contributed from China in spring, and EC results were similar in both PSCF and CWT. In conclusion, Seoul air quality in spring was mainly affected by a mixture of local pollution and anthropogenic pollutants originated in China than the Asian dust.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.481-490
• /
• 2002

Off-line handwritten character recognition is in difficulty of incomplete preprocessing because it has not dynamic information has various handwriting, extreme overlap of the consonant and vowel and many error image of stroke. Consequently off-line handwritten character recognition needs to study about preprocessing of various methods such as binarization and thinning. This paper considers running time of watershed algorithm and the quality of resulting image as preprocessing for off-line handwritten Korean character recognition. So it proposes application of effective watershed algorithm for segmentation of character region and background region in gray level character image and segmentation function for binarization by extracted watershed image. Besides it proposes thinning methods that effectively extracts skeleton through conditional test mask considering routing time and quality of skeleton, estimates efficiency of existing methods and this paper's methods as running time and quality. Average execution time on the previous method was 2.16 second and on this paper method was 1.72 second. We prove that this paper's method removed noise effectively with overlap stroke as compared with the previous method.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.6
• /
• pp.55-64
• /
• 2017

High-capacity, high-definition image applications need to process considerable amounts of data at high speed. Accordingly, users of these applications demand a high-speed parallel execution system. To increase the speed of a parallel execution system, Park (2004) proposed a technique, called MAMS (Multi-Access Memory System), to access data in several execution units without the conflict of parallel processing memories. Since then, many studies on MAMS have been conducted, furthering the technique to MAMS-PP16 and MAMS-PP64, among others. As a memory architecture for parallel processing, MAMS must be constructed in one chip; therefore, a method to achieve the identical functionality as the existing MAMS while minimizing the architecture needs to be studied. This study proposes a method of miniaturizing the MAMS architecture in which the architectures of the ACR (Address Calculation and Routing) circuit and MMS (Memory Module Selection) circuit, which deliver data in memories to parallel execution units (PEs), do not use the MMS circuit, but are constructed as one shift and conditional statements whose number is the same as that of memory modules inside the ACR circuit. To verify the performance of the realized architecture, the study conducted the processing time of the proposed MAMS-PP64 through an image correlation test, the results of which demonstrated that the ratio of the image correlation from the proposed architecture was improved by 1.05 on average.

• Journal of Korea Trade
• /
• v.26 no.4
• /
• pp.1-22
• /
• 2022

Purpose - This paper empirically investigates the effect of a rise in the global value chain (GVC) on the industry-level efficiency of resource allocation (based on plant-level inefficiency measures) in Korea, with a focus on various channels through which a rise in the GVC can increase competition among firms and thus induce resources to be allocated more efficiently across firms. Design/methodology - We empirically investigate the relationship between the industry-specific importance of GVC and the industry-level allocative inefficiency that is measured as the dispersion of the plant-level marginal revenue of capital (MRK) as in Hsieh and Klenow's (2009) influential model. We compute MRK dispersion for industries sorted by various characteristics that are closely related to firm/industry sensitivity to the GVC. In other words, we compute the average industry-level MRK dispersion for industries sorted by industry-specific importance of GVC and compute the difference between the two groups of industries (higher vs. lower than the median GVC); we also calculate the difference between industries sorted by industry-specific export (import) intensity. This is our difference-in-difference estimate of the MRK dispersion associated with the GVC for the export (import)-intensive industry versus the non-export (non-import)-intensive industry. This difference-in-difference estimate of the MRK dispersion conditional vs. unconditional on firm-level productivity is then calculated further (triple-difference estimate). Findings - A rise in GVC is associated with a decrease in the MRK dispersion in the export-intensive industry compared to the non-export-intensive industry. The same is true for industries that rely heavily on imports versus those that do not (i.e., import intensive vs. non-intensive). Furthermore, the reduction in the MRK dispersion in the export-intensive industry associated with an increase in the GVC is disproportionately greater for high-productivity firms. In contrast, the negative relationship between GVC and MRK dispersion in the import-intensive industry is disproportionately smaller for high-productivity firms. Originality/value - Existing studies focus on the relationship between GVC and aggregate output, exports, and imports at the country level. We investigate detailed firm/industry-level mechanisms that determine the relationship between GVC, trade, and productivity. Using the plant-level data in South Korea, we investigate how GVC is related to the cross-firm MRK dispersion, an important measure of allocative inefficiency, based on Hsieh and Klenow's (2009) influential economic theory. This is the first study to provide plant-level evidence of how GVC affects MRK dispersion. Furthermore, we examine how the relationship between GVC and MRK-dispersion varies across export intensity, import intensity, and firm-level productivity, providing insight into how GVC can affect firms' exposure to competition in the global market differently depending on market conditions and thus generate trade-related productivity gains.

• Korean Journal of Social Welfare Studies
• /
• v.44 no.2
• /
• pp.169-199
• /
• 2013

This study has a purpose to analyze trajectories of life satisfaction of the elderly after their retirement and how the characteristics of individual, retirement and family relationship have an effect on the life satisfaction. This study has investigated the Korean elderly, who had been retired, using the data from three waves(1st wave(2005)~3rd wave(2009) of the Korean Retirement and Income Panel(KReIS). Data analysis has been used to identify the predictors of the intercept and slope related to the life satisfaction after retirement, focusing the trajectories of the life satisfaction after retirement and individual characteristics, retirement characteristics and family relationship with application of the growth curve model by Amos 20.0. First, the intercept of the life satisfaction after retirement was somewhat below average. Life satisfaction averagely increased little by little from 1st wave to 3rd wave. Second, by conducting the conditional growth curve model, the study revealed that the intercept of the life satisfaction after retirement is high on individual characteristics(sex, educational level, income, health status) and in retirement characteristics(voluntary retirement) and satisfaction with family relationship and married life). Furthermore, health status, voluntary retirement, and satisfaction with family relationship asserted the meaningful variables in the slope of life satisfaction after retirement.