• Journal of Intelligence and Information Systems
• /
• v.21 no.4
• /
• pp.93-110
• /
• 2015

The recommender system is a system which recommends products to the customers who are likely to be interested in. Based on automated information filtering technology, various recommender systems have been developed. Collaborative filtering (CF), one of the most successful recommendation algorithms, has been applied in a number of different domains such as recommending Web pages, books, movies, music and products. But, it has been known that CF has a critical shortcoming. CF finds neighbors whose preferences are like those of the target customer and recommends products those customers have most liked. Thus, CF works properly only when there's a sufficient number of ratings on common product from customers. When there's a shortage of customer ratings, CF makes the formation of a neighborhood inaccurate, thereby resulting in poor recommendations. To improve the performance of CF based recommender systems, most of the related studies have been focused on the development of novel algorithms under the assumption of using a single profile, which is created from user's rating information for items, purchase transactions, or Web access logs. With the advent of big data, companies got to collect more data and to use a variety of information with big size. So, many companies recognize it very importantly to utilize big data because it makes companies to improve their competitiveness and to create new value. In particular, on the rise is the issue of utilizing personal big data in the recommender system. It is why personal big data facilitate more accurate identification of the preferences or behaviors of users. The proposed recommendation methodology is as follows: First, multimodal user profiles are created from personal big data in order to grasp the preferences and behavior of users from various viewpoints. We derive five user profiles based on the personal information such as rating, site preference, demographic, Internet usage, and topic in text. Next, the similarity between users is calculated based on the profiles and then neighbors of users are found from the results. One of three ensemble approaches is applied to calculate the similarity. Each ensemble approach uses the similarity of combined profile, the average similarity of each profile, and the weighted average similarity of each profile, respectively. Finally, the products that people among the neighborhood prefer most to are recommended to the target users. For the experiments, we used the demographic data and a very large volume of Web log transaction for 5,000 panel users of a company that is specialized to analyzing ranks of Web sites. R and SAS E-miner was used to implement the proposed recommender system and to conduct the topic analysis using the keyword search, respectively. To evaluate the recommendation performance, we used 60% of data for training and 40% of data for test. The 5-fold cross validation was also conducted to enhance the reliability of our experiments. A widely used combination metric called F1 metric that gives equal weight to both recall and precision was employed for our evaluation. As the results of evaluation, the proposed methodology achieved the significant improvement over the single profile based CF algorithm. In particular, the ensemble approach using weighted average similarity shows the highest performance. That is, the rate of improvement in F1 is 16.9 percent for the ensemble approach using weighted average similarity and 8.1 percent for the ensemble approach using average similarity of each profile. From these results, we conclude that the multimodal profile ensemble approach is a viable solution to the problems encountered when there's a shortage of customer ratings. This study has significance in suggesting what kind of information could we use to create profile in the environment of big data and how could we combine and utilize them effectively. However, our methodology should be further studied to consider for its real-world application. We need to compare the differences in recommendation accuracy by applying the proposed method to different recommendation algorithms and then to identify which combination of them would show the best performance.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.35 no.2
• /
• pp.87-92
• /
• 2015

This experiment was conducted to evaluate the effect of seeding methods and application levels of nitrogen fertilizer on the yield and forage quality of whole crop rice (WCR). The WCR variety "Namil" was directly seeded on April 25 and transplanted on May 25. Five levels of nitrogen fertilizer were applied (90, 110, 140, 170 and 200 kg/ha). There were no significant differences (p<0.05) of the emergence date, heading date and disease resistance based on the nitrogen fertilizer rates; however, the WCR became dark at higher nitrogen fertilizer rates. The plant height increased at higher nitrogen fertilizer rates and the tiller number showed the same trend. In contrast to a direct seeding method, transplanting increased the tiller number. The dry matter (DM) content did not show a certain tendency based on nitrogen fertilizer rates, while the fresh and dry matter yields increased with incremental changes of the nitrogen fertilizer rates (p<0.01), and the transplant method increased the yield size. In yield analysis, the plot direct-seeded with 140 kg N/ha and the transplanting with 170kg N/ha showed the highest yields. The crude protein (CP) content increased with higher nitrogen fertilizer rate, but there was no significant differences between transplant and direct-seeding methods. The content of ADF (acid detergent fiber) and NDF (neutral detergent fiber) increased with higher nitrogen fertilizer rate, but total digestible nutrient (TDN) content decreased with increased nitrogen levels. Although high nitrogen applications increased the fresh and DM yields, the 140 kg/ha nitrogen fertilizer level is recommended as the proper nitrogen fertilizer level, considering both yield and the environments.

• Ocean and Polar Research
• /
• v.37 no.1
• /
• pp.49-59
• /
• 2015

Spatial variation in the reproductive effort of Manila clam Ruditapes philippinarum is often closely associated with variation in the seawater temperature and food availability, which determines gonad maturity and the quantity of gamates produced during spawning. Previous studies also have reported that severe infection by the protozoan parasite Perkinsus olseni exerts a negative impact on clam reproduction, retarding gonad maturation or decreasing the reproductive effort. In the present study, we investigated impacts of P. olseni infection on the reproductive condition of Manila clam during a spawning season. Histology revealed that 54% of female clams in Wando off the south coast were in spawning, while only 10% of the female from Gomso and 0% of the female from Seonjaedo in Gyeonggi bay off the west coast were engaged in spawning at the end of May in 2004. Ray's fluid thioglycollate media (RFTM) assay was applied to assess P. olseni infection and indicated that the infection intensity in Wando ($3,608,000{\pm}258,000cells/g$ wet tissue) was significantly higher than the levels in Gomso ($1,305,000{\pm}106,000cells/g$ wet tissue) and Seonjaedo ($1,083,000{\pm}137,000cells/g$ wet tissue, p < 0.001). The size of the ripe female follicle determined from histology was significantly smaller in Wando ($0.032mm^2$) compared to the sizes in Gomso ($0.059mm^2$) and Seonjaedo ($0.052mm^2$, p < 0.05). Accordingly, the number of ripe eggs in the follicle was significantly fewer among clams in Wando (14) compared to the numbers determined in Gomso (23) and Seonjaedo (22). The absolute quantity of egg in ripe clams from Wando (31.01 mg) was also significantly smaller than Seonjaedo (61.79 mg) and Gomso (133.3 mg). Quantity of total protein, carbohydrate, and lipid in the tissue in the Wando samples was significantly smaller than the quantities determined in Gomso and Seonjaedo (p < 0.001). The observed poor reproductive condition and proximate tissue composition of the females in Wando were, in part, explained by the extremely high level of the parasites, sapping the ability to store energy in the host tissues, which is used in tissue growth and the egg production.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.43 no.6
• /
• pp.16-24
• /
• 2015

This study quantified storage and annual uptake of carbon for riparian greenspaces established in watersheds of four major rivers in South Korea and explored desirable strategies to improve carbon reduction effects of riparian greenspaces. Greenspace structure and planting technique in the 40 study sites sampled were represented by single-layered planting of small trees in low density, with stem diameter at breast height of $6.9{\pm}0.2cm$ and planting density of $10.4{\pm}0.8trees/100m^2$ on average. Storage and annual uptake of carbon per unit area by planted trees averaged $8.2{\pm}0.5t/ha$ and $1.7{\pm}0.1t/ha/yr$, respectively, increasing as planting density got higher. Mean organic matter and carbon storage in soils were $1.4{\pm}0.1%$ and $26.4{\pm}1.5t/ha$, respectively. Planted trees and soils per ha stored the amount of carbon emitted from gasoline consumption of about 61 kL, and the trees per ha annually offset carbon emissions from gasoline use of about 3 kL. These carbon reduction effects are associated with tree growth over five years to fewer than 10 years after planting, and predicted to become much greater as the planted trees grow. This study simulated changes in annual carbon uptake by tree growth over future 30 years for typical planting models selected as different from the planting technique in the study sites. The simulation revealed that cumulative annual carbon uptake for a multilayered and grouped ecological planting model with both larger tree size and higher planting density was approximately 1.9 times greater 10 years after planting and 1.5 times greater 30 years after than that in the study sites. Strategies to improve carbon reduction effects of riparian greenspaces suggest multilayered and grouped planting mixed with relatively large trees, middle/high density planting of native species mixed with fast-growing trees, and securing the soil environment favorable for normal growth of planting tree species. The research findings are expected to be useful as practical guidelines to improve the role of a carbon uptake source, in addition to water quality conservation and wildlife inhabitation, in implementing riparian greenspace projects under the beginning stage.

• Information Systems Review
• /
• v.18 no.1
• /
• pp.57-78
• /
• 2016

Hacking has raised many critical issues in the modern world, particularly because the size and cost of the damages caused by this disruptive activity have steadily increased. Accordingly, many significant studies have been conducted by behavioral scientists to understand hackers and their practices. Nonetheless, only qualitative methods, such as interviews, meta-studies, and media studies, have been employed in such studies because of hacker sampling limitations. Existing studies have determined that intrinsic motivation was the dominant factor influencing hackers, and that their techniques were mainly acquired from online hacking communities. However, such results have yet to be causally proven. This study attempted to identify the causal factors influencing the motivational and environmental factors encouraging hackers to learn hacking skills. To this end, hacker community members using the theory of planned behavior were observed to identify the causal factors of their learning of hacking skills. We selected a group of students who were developing their hacking skills. The survey was conducted over a two-week period in May 2015 with a total of 227 students as respondents. After list-wise deletion, 215 of the responses were deemed usable (94.7 percent). In summary, the hackers were aware that hacking skills are considered socially unethical, and their attitudes toward the learning of hacking skills were affected by both intrinsic and extrinsic motivations. In addition, the characteristics of the online hacking community affected their perceived behavioral control. This study introduced new concepts in the process of conducting a causal relationship analysis on a hacker sample. Moreover, this research expanded the discussion on the causal direction of subjective norms in unethical research, and empirically confirmed that both intrinsic and extrinsic motivations affect the learning of hacking skills. This study also made a practical contribution by raising the educational and policy response issues for ethical hackers and demonstrating the necessity to intensify the punishment for hacking.

• Horticultural Science & Technology
• /
• v.33 no.4
• /
• pp.501-510
• /
• 2015

In this study, we investigated the onset and release of endo-dormancy under natural conditions by observing bud break characteristics in 'Fuji' apple trees using water cuttings. Through examinations of bud break rate and days to bud break, we found that the endo-dormancy of 'Fuji' apple tree continues for 70 d from 165 to 255 d after full bloom (DAFB), from late October to early January of the following year. In addition, within 20 d of first bud break, based on a final bud break rate of 60% or more, we able to identify the timing of the changeover from para-dormancy to endo-dormancy, and endo-dormancy to eco-dormancy. Analysis of the chilling requirement during the endo-dormancy period revealed that chilling accumulation up to 255 DAFB to release endo-dormancy amounted to 666 and 517 h based on the CH and Utah models, respectively. Observation of internal changes in the bud during endo-dormancy showed that flower bud differentiation begins from mid-July, and t ime of inflorescence o f the disk f lower is a vailable to f ind. The f lower buds subsequently developed slowly but steadily during endo-dormancy and in the following year in February, the developmental stage of each organ had progressed. Moreover, the flower buds of 'Fuji' apples were mostly healthy during the dormancy period, but some exhibited necrosis of flower primordium, due partial cell damage from the formation of ice crystals rather than a direct effect of the low temperature. Flower buds were formed in both the axillary buds of bourse shoots and terminal buds of spurs, but lower bud differentiation was observed for the terminal buds of spurs at rate of about 65% of total buds, which was directly related to the bud size and shoot diameter.

• Korean Journal of Microbiology
• /
• v.51 no.2
• /
• pp.97-107
• /
• 2015

Wetlands constitute a transitional zone between terrestrial and aquatic ecosystems and have unique characteristics such as frequent inundation, inflow of nutrients from terrestrial ecosystems, presence of plants adapted to grow in water, and soil that is occasionally oxygen deficient due to saturation. These characteristics and the presence of vegetation determine physical and chemical properties that affect decomposition rates of organic matter (OM). Decomposition of OM is associated with activities of various extracellular enzymes (EE) produced by bacteria and fungi. Extracellular enzymes convert macromolecules to simple compounds such as labile organic carbon (C), nitrogen (N), phosphorus (P), and sulfur (S) that can be easily taken up by microbes and plants. Therefore, the enzymatic approach is helpful to understand the decomposition rates of OM and nutrient cycling in wetland soils. This paper reviews the physical and biogeochemical factors that regulate extracellular enzyme activities (EEa) in wetland soils, including those of ${\beta}$-glucosidase, ${\beta}$-N-acetylglucosaminidase, phosphatase, arylsulfatase, and phenol oxidase that decompose organic matter and release C, N, P, and S nutrients for microbial and plant growths. Effects of pH, water table, and particle size of OM on EEa were not significantly different among sites, whereas the influence of temperature on EEa varied depending on microbial acclimation to extreme temperatures. Addition of C, N, or P affected EEa differently depending on the nutrient state, C:N ratio, limiting factors, and types of enzymes of wetland soils. Substrate quality influenced EEa more significantly than did other factors. Also, drainage of wetland and increased temperature due to global climate change can stimulate phenol oxidase activity, and anthropogenic N deposition can enhance the hydrolytic EEa; these effects increase OM decomposition rates and emissions of $CO_2$ and $CH_4$ from wetland systems. The researches on the relationship between microbial structures and EE functions, and environmental factors controlling EEa can be helpful to manipulate wetland ecosystems for treating pollutants and to monitor wetland ecosystem services.

• Membrane Journal
• /
• v.25 no.2
• /
• pp.115-122
• /
• 2015

$SiO_2{\cdot}B_2O_3$ was prepared by trimethylborate (TMB)/tetraethylorthosilicate (TEOS) mole ratio 0.01 at $800^{\circ}C$. PDMS[poly(dimethysiloxane)]-$SiO_2{\cdot}B_2O_3$ composite membranes were prepared by adding porous $SiO_2{\cdot}B_2O_3$ to PDMS. To investigate the characteristics of PDMS-$SiO_2{\cdot}B_2O_3$ composite membrane, we observed PDMS-$SiO_2{\cdot}B_2O_3$ composite membrane using TG-DTA, FT-IR, BET, X-ray, and SEM. PDMS-$SiO_2{\cdot}B_2O_3$ composite membrane was studied on the permeabilities of $H_2$ and $N_2$ and the selectivity ($H_2/N_2$). Following the results of TG-DTA, BET, X-ray, FT-IR, $SiO_2{\cdot}B_2O_3$ was the amorphous porous $SiO_2{\cdot}B_2O_3$ with $247.6868m^2/g$ surface area and $37.7821{\AA}$ the mean of pore diameter. According to the TGA measurements, the thermal stability of PDMS-$SiO_2{\cdot}B_2O_3$ composite membrane was enhanced by inserting $SiO_2{\cdot}B_2O_3$. SEM observation showed that the size of dispersed $SiO_2{\cdot}B_2O_3$ in the PDMS-$SiO_2{\cdot}B_2O_3$ composite membrane was about $1{\mu}m$. The increasing of $SiO_2{\cdot}B_2O_3$ content in PDMS leaded the following results in the gas permeation experiment: the permeability of both $H_2$ and $N_2$ was increased, and the permeability of $H_2$ was higher than $N_2$, but the selectivity($H_2/N_2$) was decreased.

• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.117-129
• /
• 2015

As the Internet becomes ubiquitous, a large volume of information is posted on the Internet with exponential growth every day. Accordingly, it is not unusual that investors in stock markets gather and compile firm-specific or market-wide information through online searches. Importantly, it becomes easier for investors to acquire value-relevant information for their investment decision with the help of powerful search tools on the Internet. Our study examines whether or not the Internet helps investors assess a firm's value better by using firm-level data over long periods spanning from January 2004 to December 2013. To this end, we construct weekly-based search volume for information technology (IT) services firms on the Internet. We limit our focus to IT firms since they are often equipped with intangible assets and relatively less recognized to the public which makes them hard-to measure. To obtain the information on those firms, investors are more likely to consult the Internet and use the information to appreciate the firms more accurately and eventually improve their investment decisions. Prior studies have shown that changes in search volumes can reflect the various aspects of the complex human behaviors and forecast near-term values of economic indicators, including automobile sales, unemployment claims, and etc. Moreover, search volume of firm names or stock ticker symbols has been used as a direct proxy of individual investors' attention in financial markets since, different from indirect measures such as turnover and extreme returns, they can reveal and quantify the interest of investors in an objective way. Following this line of research, this study aims to gauge whether the information retrieved from the Internet is value relevant in assessing a firm. We also use search volume for analysis but, distinguished from prior studies, explore its impact on return comovements with market returns. Given that a firm's returns tend to comove with market returns excessively when investors are less informed about the firm, we empirically test the value of information by examining the association between Internet searches and the extent to which a firm's returns comove. Our results show that Internet searches are negatively associated with return comovements as expected. When sample is split by the size of firms, the impact of Internet searches on return comovements is shown to be greater for large firms than small ones. Interestingly, we find a greater impact of Internet searches on return comovements for years from 2009 to 2013 than earlier years possibly due to more aggressive and informative exploit of Internet searches in obtaining financial information. We also complement our analyses by examining the association between return volatility and Internet search volumes. If Internet searches capture investors' attention associated with a change in firm-specific fundamentals such as new product releases, stock splits and so on, a firm's return volatility is likely to increase while search results can provide value-relevant information to investors. Our results suggest that in general, an increase in the volume of Internet searches is not positively associated with return volatility. However, we find a positive association between Internet searches and return volatility when the sample is limited to larger firms. A stronger result from larger firms implies that investors still pay less attention to the information obtained from Internet searches for small firms while the information is value relevant in assessing stock values. However, we do find any systematic differences in the magnitude of Internet searches impact on return volatility by time periods. Taken together, our results shed new light on the value of information searched from the Internet in assessing stock values. Given the informational role of the Internet in stock markets, we believe the results would guide investors to exploit Internet search tools to be better informed, as a result improving their investment decisions.

• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.79-99
• /
• 2015

The prediction of bankruptcy has been extensively studied in the accounting and finance field. It can have an important impact on lending decisions and the profitability of financial institutions in terms of risk management. Many researchers have focused on constructing a more robust bankruptcy prediction model. Early studies primarily used statistical techniques such as multiple discriminant analysis (MDA) and logit analysis for bankruptcy prediction. However, many studies have demonstrated that artificial intelligence (AI) approaches, such as artificial neural networks (ANN), decision trees, case-based reasoning (CBR), and support vector machine (SVM), have been outperforming statistical techniques since 1990s for business classification problems because statistical methods have some rigid assumptions in their application. In previous studies on corporate bankruptcy, many researchers have focused on developing a bankruptcy prediction model using financial ratios. However, there are few studies that suggest the specific types of bankruptcy. Previous bankruptcy prediction models have generally been interested in predicting whether or not firms will become bankrupt. Most of the studies on bankruptcy types have focused on reviewing the previous literature or performing a case study. Thus, this study develops a model using data mining techniques for predicting the specific types of bankruptcy as well as the occurrence of bankruptcy in Korean small- and medium-sized construction firms in terms of profitability, stability, and activity index. Thus, firms will be able to prevent it from occurring in advance. We propose a hybrid approach using two artificial neural networks (ANNs) for the prediction of bankruptcy types. The first is a back-propagation neural network (BPN) model using supervised learning for bankruptcy prediction and the second is a self-organizing map (SOM) model using unsupervised learning to classify bankruptcy data into several types. Based on the constructed model, we predict the bankruptcy of companies by applying the BPN model to a validation set that was not utilized in the development of the model. This allows for identifying the specific types of bankruptcy by using bankruptcy data predicted by the BPN model. We calculated the average of selected input variables through statistical test for each cluster to interpret characteristics of the derived clusters in the SOM model. Each cluster represents bankruptcy type classified through data of bankruptcy firms, and input variables indicate financial ratios in interpreting the meaning of each cluster. The experimental result shows that each of five bankruptcy types has different characteristics according to financial ratios. Type 1 (severe bankruptcy) has inferior financial statements except for EBITDA (earnings before interest, taxes, depreciation, and amortization) to sales based on the clustering results. Type 2 (lack of stability) has a low quick ratio, low stockholder's equity to total assets, and high total borrowings to total assets. Type 3 (lack of activity) has a slightly low total asset turnover and fixed asset turnover. Type 4 (lack of profitability) has low retained earnings to total assets and EBITDA to sales which represent the indices of profitability. Type 5 (recoverable bankruptcy) includes firms that have a relatively good financial condition as compared to other bankruptcy types even though they are bankrupt. Based on the findings, researchers and practitioners engaged in the credit evaluation field can obtain more useful information about the types of corporate bankruptcy. In this paper, we utilized the financial ratios of firms to classify bankruptcy types. It is important to select the input variables that correctly predict bankruptcy and meaningfully classify the type of bankruptcy. In a further study, we will include non-financial factors such as size, industry, and age of the firms. Thus, we can obtain realistic clustering results for bankruptcy types by combining qualitative factors and reflecting the domain knowledge of experts.