• Journal of Bio-Environment Control
• /
• v.27 no.1
• /
• pp.34-39
• /
• 2018

This research was conducted to estimate moisture content in cucurbitaceae seedlings, such as cucumber and watermelon, using hyperspectral imagery. Using a hyperspectral image acquisition system, the reflectance of leaf area of cucumber and watermelon seedlings was calculated after providing water stress. Then, moisture content in each seedling was measured by using a dry oven. Finally, using reflectance and moisture content, the moisture content estimation models were developed by PLSR analysis. After developing the estimation models, performance of the cucumber showed 0.73 of $R^2$, 1.45% of RMSE, and 1.58% of RE. Performance of the watermelon showed 0.66 of $R^2$, 1.06% of RMSE, and 1.14% of RE. The model performed slightly better after removing one sample from cucumber seedlings as outlier and unnecessary. Hence, the performance of new model for cucumber seedlings showed 0.79 of $R^2$, 1.10% of RMSE, and 1.20% of RE. The model performance combined with all samples showed 0.67 of $R^2$, 1.26% of RMSE, and 1.36% of RE. The model of cucumber showed better performance than the model of watermelon. This is because variables of cucumber are consisted of widely distributed variation, and it affected the performance. Further, accuracy and precision of the cucumber model were increased when an insignificant sample was eliminated from the dataset. Finally, it is considered that both models can be significantly used to estimate moisture content, as gradients of trend line are almost same and intersected. It is considered that the accuracy and precision of the estimating models possibly can be improved, if the models are constructed by using variables with widely distributed variation. The improved models will be utilized as the basis for developing low-priced sensors.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.157-176
• /
• 2018

The purpose of this research is to develop a detection model for companies designated as administrative issue in KOSDAQ market using financial data. Administration issue designates the companies with high potential for delisting, which gives them time to overcome the reasons for the delisting under certain restrictions of the Korean stock market. It acts as an alarm to inform investors and market participants of which companies are likely to be delisted and warns them to make safe investments. Despite this importance, there are relatively few studies on administration issues prediction model in comparison with the lots of studies on bankruptcy prediction model. Therefore, this study develops and verifies the detection model of the companies designated as administrative issue using financial data of KOSDAQ companies. In this study, logistic regression and decision tree are proposed as the data mining models for detecting administrative issues. According to the results of the analysis, the logistic regression model predicted the companies designated as administrative issue using three variables - ROE(Earnings before tax), Cash flows/Shareholder's equity, and Asset turnover ratio, and its overall accuracy was 86% for the validation dataset. The decision tree (Classification and Regression Trees, CART) model applied the classification rules using Cash flows/Total assets and ROA(Net income), and the overall accuracy reached 87%. Implications of the financial indictors selected in our logistic regression and decision tree models are as follows. First, ROE(Earnings before tax) in the logistic detection model shows the profit and loss of the business segment that will continue without including the revenue and expenses of the discontinued business. Therefore, the weakening of the variable means that the competitiveness of the core business is weakened. If a large part of the profits is generated from one-off profit, it is very likely that the deterioration of business management is further intensified. As the ROE of a KOSDAQ company decreases significantly, it is highly likely that the company can be delisted. Second, cash flows to shareholder's equity represents that the firm's ability to generate cash flow under the condition that the financial condition of the subsidiary company is excluded. In other words, the weakening of the management capacity of the parent company, excluding the subsidiary's competence, can be a main reason for the increase of the possibility of administrative issue designation. Third, low asset turnover ratio means that current assets and non-current assets are ineffectively used by corporation, or that asset investment by corporation is excessive. If the asset turnover ratio of a KOSDAQ-listed company decreases, it is necessary to examine in detail corporate activities from various perspectives such as weakening sales or increasing or decreasing inventories of company. Cash flow / total assets, a variable selected by the decision tree detection model, is a key indicator of the company's cash condition and its ability to generate cash from operating activities. Cash flow indicates whether a firm can perform its main activities(maintaining its operating ability, repaying debts, paying dividends and making new investments) without relying on external financial resources. Therefore, if the index of the variable is negative(-), it indicates the possibility that a company has serious problems in business activities. If the cash flow from operating activities of a specific company is smaller than the net profit, it means that the net profit has not been cashed, indicating that there is a serious problem in managing the trade receivables and inventory assets of the company. Therefore, it can be understood that as the cash flows / total assets decrease, the probability of administrative issue designation and the probability of delisting are increased. In summary, the logistic regression-based detection model in this study was found to be affected by the company's financial activities including ROE(Earnings before tax). However, decision tree-based detection model predicts the designation based on the cash flows of the company.

• Asia pacific journal of information systems
• /
• v.20 no.3
• /
• pp.115-137
• /
• 2010

Information technology (IT) outsourcing, the use of a third-party vendor to provide IT services, started in the late 1980s and early 1990s in Korea, and has increased rapidly since 2000. Recently, firms have increased their efforts to capture greater value from IT outsourcing. To date, there have been a large number of studies on IT outsourcing. Most prior studies on IT outsourcing have focused on outsourcing practices and decisions, and little attention has been paid to objectively measuring the value of IT outsourcing. In addition, studies that examined the performance of IT outsourcing have mainly relied on anecdotal evidence or practitioners' perceptions. Our study examines the contribution of IT outsourcing to economic growth in Korean industries over the 1990 to 2007 period, using a production function framework and a panel data set for 54 industries constructed from input-output tables, fixed-capital formation tables, and employment tables. Based on the framework and estimation procedures that Han, Kauffman and Nault (2010) used to examine the economic impact of IT outsourcing in U.S. industries, we evaluate the impact of IT outsourcing on output and productivity in Korean industries. Because IT outsourcing started to grow at a significantly more rapid pace in 2000, we compare the impact of IT outsourcing in pre- and post-2000 periods. Our industry-level panel data cover a large proportion of Korean economy-54 out of 58 Korean industries. This allows us greater opportunity to assess the impacts of IT outsourcing on objective performance measures, such as output and productivity. Using IT outsourcing and IT capital as our primary independent variables, we employ an extended Cobb-Douglas production function in which both variables are treated as factor inputs. We also derive and estimate a labor productivity equation to assess the impact of our IT variables on labor productivity. We use data from seven years (1990, 1993, 2000, 2003, 2005, 2006, and 2007) for which both input-output tables and fixed-capital formation tables are available. Combining the input-output tables and fixed-capital formation tables resulted in 54 industries. IT outsourcing is measured as the value of computer-related services purchased by each industry in a given year. All the variables have been converted to 2000 Korean Won using GDP deflators. To calculate labor hours, we use the average work hours for each sector provided by the OECD. To effectively control for heteroskedasticity and autocorrelation present in our dataset, we use the feasible generalized least squares (FGLS) procedures. Because the AR1 process may be industry-specific (i.e., panel-specific), we consider both common AR1 and panel-specific AR1 (PSAR1) processes in our estimations. We also include year dummies to control for year-specific effects common across industries, and sector dummies (as defined in the GDP deflator) to control for time-invariant sector-specific effects. Based on the full sample of 378 observations, we find that a 1% increase in IT outsourcing is associated with a 0.012~0.014% increase in gross output and a 1% increase in IT capital is associated with a 0.024~0.027% increase in gross output. To compare the contribution of IT outsourcing relative to that of IT capital, we examined gross marginal product (GMP). The average GMP of IT outsourcing was 6.423, which is substantially greater than that of IT capital at 2.093. This indicates that on average if an industry invests KRW 1 millon, it can increase its output by KRW 6.4 million. In terms of the contribution to labor productivity, we find that a 1% increase in IT outsourcing is associated with a 0.009~0.01% increase in labor productivity while a 1% increase in IT capital is associated with a 0.024~0.025% increase in labor productivity. Overall, our results indicate that IT outsourcing has made positive and economically meaningful contributions to output and productivity in Korean industries over the 1990 to 2007 period. The average GMP of IT outsourcing we report about Korean industries is 1.44 times greater than that in U.S. industries reported in Han et al. (2010). Further, we find that the contribution of IT outsourcing has been significantly greater in the 2000~2007 period during which the growth of IT outsourcing accelerated. Our study provides implication for policymakers and managers. First, our results suggest that Korean industries can capture further benefits by increasing investments in IT outsourcing. Second, our analyses and results provide a basis for managers to assess the impact of investments in IT outsourcing and IT capital in an objective and quantitative manner. Building on our study, future research should examine the impact of IT outsourcing at a more detailed industry level and the firm level.

• Korean Journal of Ecology and Environment
• /
• v.38 no.3 s.113
• /
• pp.361-371
• /
• 2005

The objective of study was to diagnose integrative ecological health of Daejeon Stream, one of the tributaries of Guem River, during May 2004 ${\sim}$ April 2005. The research approach was primarily based on a Qualitative Habitat Evaluation Index (QHEI) and the Index of Biological Integrity (IBI) using fish assemblage. These outcomes were compared with conventional chemical dataset. For the experiment, four sampling sites were chosen from Daejeon Stream and long-term water quality data during 1995 ${\sim}$ 2004 (obtained from the Ministry of Environment) were analyzed in the spatial and temporal aspects. For the biological health assessment, we developed a stream health assessment model (SHA model) far regional applications. We found that current water quality conditions, based on the COD, BOD, TN and TP, were enhanced by 1.6 ${\sim}$ 5.3 fold over the period of 1995 ${\sim}$ 2004 and that the parameters showed a typical longitudinal decline from the upstream to downstream reach. The differences of water quality between the two reaches were more than 4.4 times, indicating a large spatial variations within the stream. The health conditions, based on the SHA model, averaged 23 and varied from 20 to 26 depending on the sampling stations. Values of the QHEI varied from 39 (Poor condition) to 124 (Cood condition)and values of QHEI in the reach of S2 ${\sim}$ S4 had significantly lower than in the headwater site (S1). Also, biological stream health, based on the criteria of US EPA (1993), was judged as 'Poor condition', in the S4 where TN, TP, BOD and COD were highest. In the meantime, maximum value of SHA (26) was found in the upstream reach (S1) where the water quality and QHEI were best. We also found that compositions of sensitive species showed a linear function with water quality conditions and this pattern was evident in the tolerant species. Thus, the biological stream health, based on the SHA model, matched well water chemistry. Overall outcomes suggest that the biological health impact was a function of chemical degradation and physical habitat quality in the stream.

• Journal of Korean Society of Forest Science
• /
• v.98 no.6
• /
• pp.791-798
• /
• 2009

The role of forest and soil carbon under global climate change is getting important as a carbon sink and it is necessary to research on applicable forest models as well as in the field for a study of these dynamics. On this study, historical annual litter dataset as a major input data for the forest soil carbon model, Yasso was established using a dendrochronological reconstruction method, and the soil carbon dynamics of a Pinus densiflora forest in Gwangneung, Korea was simulated using Yasso. The amount of litter (needle, branch, stem and fine root) production, which was estimated using the dendrochronological method, has increased continuously from 1971 to 2006. Furthermore, there was no significant error between estimated and measured values of litter production (needle and branch) in 2006. The average of simulated soil carbon stock up to 30 cm depth was $46.30{\pm}4.28tCha^{-1}$, which accounted for 53% of carbon stock in trees of the forest, and had no significant difference and error with measured soil carbon stock. Under the climate change trend in Korea according to IPCC A1B scenario, it was estimated that the simulated soil carbon stock in the region would increase continuously from 1971 to 2041 and then decreased until 2100. Compared to the result of the scenario that there is no climate change, the soil carbon stock could be decreased up to 7.58% at 2100. It was inferred the dendrochronological reconstruction method and simulation of Yasso model are useful to estimate soil carbon dynamics of the natural P. densiflora forest. Follow-up researches, such as improvement of the dendrochronological method and Yasso model and their application and validation in various environment, are needed to produce more reliable results.

• Journal of Cadastre & Land InformatiX
• /
• v.47 no.2
• /
• pp.107-120
• /
• 2017

There are many wildfire risk indices worldwide, but objective comparisons between such various wildfire risk indices and surface dryness indices have not been conducted for the wildfire cases in Korea. This paper describes a sensitivity analysis on the wildfire risk indices and surface dryness indices for Korea using LDAPS(Local Analysis and Prediction System) meteorological dataset on a 1.5-km grid and MODIS(Moderate-resolution Imaging Spectroradiometer) satellite images on a 1-km grid. We analyzed the meteorology-based wildfire risk indices such as the Australian FFDI(forest fire danger index), the Canadian FFMC(fine fuel moisture code), the American HI(Haines index), and the academically presented MNI(modified Nesterov index). Also we examined the satellite-based surface dryness indices such as NDDI(normalized difference drought index) and TVDI(temperature vegetation dryness index). As a result of the comparisons between the six indices regarding 120 wildfire cases with the area damaged over 1ha during the period between January 2013 and May 2017, we found that the FFDI and FFMC showed a good predictability for most wildfire cases but the MNI and TVDI were not suitable for Korea. The NDDI can be used as a proxy parameter for wildfire risk because its average CDF(cumulative distribution function) scores were stably high irrespective of fire size. The indices tested in this paper should be carefully chosen and used in an integrated way so that they can contribute to wildfire forecasting in Korea.

• Korean Journal of Ecology and Environment
• /
• v.42 no.3
• /
• pp.382-393
• /
• 2009

The objectives of this study were to characterize long-term annual and seasonal trophic state of Topjeong Reservoir using conventional variables of Trophic State Index (TSI) and to determine the empirical relations between the trophic parameters. For the analysis, we used water quality dataset of 1995$\sim$2007, which is obtained from the Ministry of Environment, Korea and the number of parameters was 9. Annual ambient mean values of TN and TP were 1.78 mg $L^{-1}$ and 0.03 mg $L^{-1}$, respectively and TN : TP ratios averaged 76, indicating that this system was nitrogen-rich hypertrophic, and was probably phosphorus-limitation for algal growth. Therefore, nitrogen varied little with seasons and years, and total phosphorus (TP) varied depending on season and year. Monsoon dilutions of TP occurred in August and monthly fluctuations of suspended solid (SS) was similar to those of chlorophyll-$\alpha$ (CHL). Annual mean values of BOD and $COD_{Mn}$ were 1.61 mg $L^{-1}$ and 4.23 mg $L^{-1}$, respectively and the interannual values were directly influenced by the intensity of annual rainfall. There were no significant differences in the trophic variables between the two sampling sites. Mean values of Trophic State Index (TSI, Carlson, 1977), based on TN, TP, CHL, and SD (Secchi depth), turned out as eutrophic state, except for the TN (hypertrophic). Regression analyses of log-transformed seasonal CHL against TP and TN showed that variation of the CHL was explained 37% by the variation of TP ($R^2$=0.37, p<0.001, r=0.616), but not by TN ($R^2$=0.03, p>0.05). Regression coefficient of $Log_{10}$CHL vs $Log_{10}SD$ was 0.330 (p<0.003, r=0.580), indicating that transparency is regulated by the organic matter in the system. Results, data suggest that one of the ways controlling the eutrophication would be a reduction of phosphorus from the watershed.

• Food Science of Animal Resources
• /
• v.31 no.2
• /
• pp.280-289
• /
• 2011

Analyses were conducted to estimate the effect of backfat thickness (BFT) on carcass grade factors and carcass price in Hanwoo cows and steers. Data on grade factors and prices were collected from 69,159 Hanwoo carcasses (n = 13,376 cows, n = 55,783 steers) abtained at the Nonghyup Seoul slaughter house in 2009. Carcass BFTs were divided into nine categories from ${\leq}$ 3 mm to ${\qeq}$ 25 mm. The average BFTs were 11.93 mm in cows and 12.57 mm in steers. An increase in the BFT resulted in an increase in carcass weight, loin-eye area, skeletal maturity, fat color, but decreases in the yield index and yield grade (from grade A to C) in cows and steers. Carcass unit price (Won/kg) improved if the carcass was sold with a BFT of 13-15 mm in cows and 10-12 mm in steers. Marbling score and quality grade increased significantly to 21 mm BFT but decreased from a BFT of 22 mm in cows and steers. BFT was significantly correlated with yield index (cow, r = $-0.97^{**}$; steer, r = $-0.96^{**}$), marbling score (cow, r = $0.20^{**}$; steer, r = $0.14^{**}$), and carcass price (cow, r = $0.03^{**}$; steer, r = $-0.11^{**}$). These results could be used as a fundamental dataset for further research to increase the productivity of Hanwoo carcasses.

• Geophysics and Geophysical Exploration
• /
• v.10 no.3
• /
• pp.183-190
• /
• 2007

The site effects of seismic stations were evaluated by conducting a simultaneous inversion of the stochastic point-source ground-motion model (STGM model; Boore, 2003) parameters based on the accumulated dataset of horizontal shear-wave Fourier spectra. A model parameter $K_0$ and frequency-dependent site amplification function A(f) were used to express the site effects. Once after a H/V ratio of the Fourier spectra was used as an initial estimate of A(f) for the inversion, the final A(f) which is considered to be the result of combined effect of the crustal amplification and loca lsite effects was calculated by averaging the log residuals at the site from the inversion and adding the mean log residual to the H/V ratio. The seismic stations were classified into five classes according to $logA_{1-10}^{max}$(f), the maximum level of the site amplification function in the range of 1 Hz < f < 10 Hz, i.e., A: $logA_{1-10}^{max}$(f) < 0.2, B: 0.2 $\leq$ $logA_{1-10}^{max}$(f) < 0.4, C: 0.4 $\leq$ $logA_{1-10}^{max}$(f) < 0.6, D: 0.6 $\leq$ $logA_{1-10}^{max}$(f) < 0.8, E: 0.8 $\leq$ $logA_{1-10}^{max}$(f). Implication of the classified result was supported by observing a shift of the dominant frequency of average A(f) for each classified stations as the class changes. Change of site classes after moving seismic stations to a better site condition was successfully described by the result of the station classification. In addition, the observed PGA (Peak Ground Acceleration)-values for two recent moderate earthquakes were well classified according to the proposed station classes.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.39-54
• /
• 2013

Recent explosive increase of electronic commerce provides many advantageous purchase opportunities to customers. In this situation, customers who do not have enough knowledge about their purchases, may accept product recommendations. Product recommender systems automatically reflect user's preference and provide recommendation list to the users. Thus, product recommender system in online shopping store has been known as one of the most popular tools for one-to-one marketing. However, recommender systems which do not properly reflect user's preference cause user's disappointment and waste of time. In this study, we propose a novel recommender system which uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user's preference. The research data is collected from the real-world online shopping store, which deals products from famous art galleries and museums in Korea. The data initially contain 5759 transaction data, but finally remain 3167 transaction data after deletion of null data. In this study, we transform the categorical variables into dummy variables and exclude outlier data. The proposed model consists of two steps. The first step predicts customers who have high likelihood to purchase products in the online shopping store. In this step, we first use logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. We perform above data mining techniques using SAS E-Miner software. In this study, we partition datasets into two sets as modeling and validation sets for the logistic regression and decision trees. We also partition datasets into three sets as training, test, and validation sets for the artificial neural network model. The validation dataset is equal for the all experiments. Then we composite the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. Bagging is the abbreviation of "Bootstrap Aggregation" and it composite outputs from several machine learning techniques for raising the performance and stability of prediction or classification. This technique is special form of the averaging method. Bumping is the abbreviation of "Bootstrap Umbrella of Model Parameter," and it only considers the model which has the lowest error value. The results show that bumping outperforms bagging and the other predictors except for "Poster" product group. For the "Poster" product group, artificial neural network model performs better than the other models. In the second step, we use the market basket analysis to extract association rules for co-purchased products. We can extract thirty one association rules according to values of Lift, Support, and Confidence measure. We set the minimum transaction frequency to support associations as 5%, maximum number of items in an association as 4, and minimum confidence for rule generation as 10%. This study also excludes the extracted association rules below 1 of lift value. We finally get fifteen association rules by excluding duplicate rules. Among the fifteen association rules, eleven rules contain association between products in "Office Supplies" product group, one rules include the association between "Office Supplies" and "Fashion" product groups, and other three rules contain association between "Office Supplies" and "Home Decoration" product groups. Finally, the proposed product recommender systems provides list of recommendations to the proper customers. We test the usability of the proposed system by using prototype and real-world transaction and profile data. For this end, we construct the prototype system by using the ASP, Java Script and Microsoft Access. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The participants for the survey are 173 persons who use MSN Messenger, Daum Caf$\acute{e}$, and P2P services. We evaluate the user satisfaction using five-scale Likert measure. This study also performs "Paired Sample T-test" for the results of the survey. The results show that the proposed model outperforms the random selection model with 1% statistical significance level. It means that the users satisfied the recommended product list significantly. The results also show that the proposed system may be useful in real-world online shopping store.