• 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.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.22 no.4
• /
• pp.268-278
• /
• 2020

Flowering time has been put forward due to the recent abnormally warm winter, which often caused damages of flower buds by late frosts persistently. In the present study, cumulative chill unit and cumulative heat unit of Niitaka pear, which are required for releasing the endogenous dormancy and for flowering after breaking dormancy, respectively, were compared between flowering time prediction models used in South K orea. Observation weather data were collected at eight locations for the recent three years from 2018-2020. The dates of full bloom were also collected to determine the confidence level of models including DVR, mDVR and CD models. It was found that mDVR model tended to have smaller values (8.4%) of the coefficient of variation (cv) of chill units than any other models. The CD model tended to have a low value of cv (17.5%) for calculation of heat unit required to reach flowering after breaking dormancy. The mDVR model had the most accurate prediction of full bloom during the study period compared with the other models. The DVR model usually had poor skills in prediction of full bloom dates. In particular, the error of the DVR model was large especially in southern coastal areas (e.g., Ulju and Sacheon) where the temperature was warm. Our results indicated that the mDVR model had relatively consistent accuracy in prediction of full bloom dates over region and years of interest. When observation data for full bloom date are compiled for an extended period, the full bloom date can be predicted with greater accuracy improving the mDVR model further.

• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.43-57
• /
• 2012

To enhance the competitive advantage in a constantly changing business environment, an enterprise management must make the right decision in many business activities based on both internal and external information. Thus, providing accurate information plays a prominent role in management's decision making. Intuitively, historical data can provide a feasible estimate through the forecasting models. Therefore, if the service department can estimate the service quantity for the next period, the service department can then effectively control the inventory of service related resources such as human, parts, and other facilities. In addition, the production department can make load map for improving its product quality. Therefore, obtaining an accurate service forecast most likely appears to be critical to manufacturing companies. Numerous investigations addressing this problem have generally employed statistical methods, such as regression or autoregressive and moving average simulation. However, these methods are only efficient for data with are seasonal or cyclical. If the data are influenced by the special characteristics of product, they are not feasible. In our research, we propose a forecasting framework that predicts service demand of manufacturing organization by combining Case-based reasoning (CBR) and leveraging an unsupervised artificial neural network based clustering analysis (i.e., Self-Organizing Maps; SOM). We believe that this is one of the first attempts at applying unsupervised artificial neural network-based machine-learning techniques in the service forecasting domain. Our proposed approach has several appealing features : (1) We applied CBR and SOM in a new forecasting domain such as service demand forecasting. (2) We proposed our combined approach between CBR and SOM in order to overcome limitations of traditional statistical forecasting methods and We have developed a service forecasting tool based on the proposed approach using an unsupervised artificial neural network and Case-based reasoning. In this research, we conducted an empirical study on a real digital TV manufacturer (i.e., Company A). In addition, we have empirically evaluated the proposed approach and tool using real sales and service related data from digital TV manufacturer. In our empirical experiments, we intend to explore the performance of our proposed service forecasting framework when compared to the performances predicted by other two service forecasting methods; one is traditional CBR based forecasting model and the other is the existing service forecasting model used by Company A. We ran each service forecasting 144 times; each time, input data were randomly sampled for each service forecasting framework. To evaluate accuracy of forecasting results, we used Mean Absolute Percentage Error (MAPE) as primary performance measure in our experiments. We conducted one-way ANOVA test with the 144 measurements of MAPE for three different service forecasting approaches. For example, the F-ratio of MAPE for three different service forecasting approaches is 67.25 and the p-value is 0.000. This means that the difference between the MAPE of the three different service forecasting approaches is significant at the level of 0.000. Since there is a significant difference among the different service forecasting approaches, we conducted Tukey's HSD post hoc test to determine exactly which means of MAPE are significantly different from which other ones. In terms of MAPE, Tukey's HSD post hoc test grouped the three different service forecasting approaches into three different subsets in the following order: our proposed approach > traditional CBR-based service forecasting approach > the existing forecasting approach used by Company A. Consequently, our empirical experiments show that our proposed approach outperformed the traditional CBR based forecasting model and the existing service forecasting model used by Company A. The rest of this paper is organized as follows. Section 2 provides some research background information such as summary of CBR and SOM. Section 3 presents a hybrid service forecasting framework based on Case-based Reasoning and Self-Organizing Maps, while the empirical evaluation results are summarized in Section 4. Conclusion and future research directions are finally discussed in Section 5.

• Journal of Korea Water Resources Association
• /
• v.54 no.10
• /
• pp.819-833
• /
• 2021

This study is to evaluate applicability of linkage modeling using PHABSIM (Physical Habitat Simulation System) and SWAT (Soil and Water Assessment Tool) and to estimate ecological flow for target fishes of Andong downstream (4,565.7 km²). The SWAT was established considering 2 multi purpose dam (ADD, IHD) and 1 streamflow gauging station (GD). The SWAT was calibrated and validated with 9 years (2012 ~ 2020) data of 1 stream (GD) and 2 multi-purpose dam (ADD, IHD). For streamflow and dam inflows (GD, ADD and IHD), R², NSE and RMSE were 0.52 ~ 0.74, 0.48 ~ 0.71, and 0.92 ~ 2.51 mm/day respectively. As a result of flow duration analysis for 9 years (2012 ~ 2020) using calibrated streamflow, the average Q185 and Q275 were 36.5 m³/sec (-1.4%) and 23.8 m³/sec (0%) respectively compared with the observed flow duration and were applied to flow boundary condition of PHABSIM. The target stream was selected as the 410 m section where GD is located, and stream cross-section and hydraulic factors were constructed based on Nakdong River Basic Plan Report and HEC-RAS. The dominant species of the target stream was Zacco platypus and the sub-dominant species was Puntungia herzi Herzenstein, and the HSI (Habitat Suitability Index) of target species was collected through references research. As the result of PHABSIM water level and velocity simulation, error of Q185 and Q275 were analyzed -0.12 m, +0.00 m and +0.06 m/s, +0.09 m/s respectively. The average WUA (Weighted Usable Area) and ecological flow of Zacco platypus and Puntungia herzi Herzenstein were evaluated 76,817.0 m²/1000m, 20.0 m³/sec and 46,628.6 m²/1000m, 9.0 m³/sec. This results indicated Zacco platypus is more adaptable to target stream than Puntungia herzi Herzenstein.

• Journal of Korea Water Resources Association
• /
• v.53 no.12
• /
• pp.1081-1095
• /
• 2020

This study is to evaluate stream flow and water quality changes of Yeongsan river basin (3,371.4 km2) by inter-basin water transfer (IBWT) from Juam dam of Seomjin river basin using SWAT (Soil and Water Assessment Tool). The SWAT was established using inlet function for IBWT between donor and receiving basins. The SWAT was calibrated and validated with 14 years (2005 ~ 2018) data of 1 stream (MR) and 2 multi-functional weir (SCW, JSW) water level gauging stations, and 3 water quality stations (GJ2, NJ, and HP) including data of IBWT and effluent from wastewater treatment plants of Yeongsan river basin. For streamflow and weir inflows (MR, SCW, and JSW), the coefficient of determination (R2), Nash-Sutcliffe efficiency (NSE), root mean square error (RMSE), and percent bias (PBIAS) were 0.69 ~ 0.81, 0.61 ~ 0.70, 1.34 ~ 2.60 mm/day, and -8.3% ~ +7.6% respectively. In case of water quality, the R2 of SS, T-N, and T-P were 0.69 ~ 0.81, 0.61 ~ 0.70, and 0.54 ~ 0.63 respectively. The Yeongsan river basin average streamflow was 12.0 m3/sec and the average SS, T-N, and T-P were 110.5 mg/L, 4.4 mg/L, 0.18 mg/L respectively. Under the 130% scenario of IBWT amount, the streamflow, SS increased to 12.94 m3/sec (+7.8%), 111.26 mg/L (+0.7%) and the T-N, T-P decreased to 4.17 mg/L (-5.2%), 0.165 mg/L (-8.3%) respectively. Under the 70% scenario of IBWT amount, the streamflow, SS decreased to 11.07 m3/sec (-7.8%), 109.74 mg/L (-0.7%) and the T-N, T-P increased to 4.68 mg/L (+6.4%), 0.199 mg/L (+10.6%) respectively.

• Journal of Bio-Environment Control
• /
• v.4 no.1
• /
• pp.50-58
• /
• 1995

These studies were carried out to develop a system for non -destructive and continuous measurement of fresh weight and to analyse the growth response of leaf lettuce under the different nutrient solution and light condition with this system. The developed measurement system was consisted of four load cells and a microcomputer. The output from the system was highly positive correlation with the plant fresh weight above the surface of the hydroponic solution. The top fresh weight of plant could be measured within the error $\pm$ 1.0g in the range of 0 - 2000g. The top fresh weight of leaf lettuce increased 44 times at 18th day after transferring to the nutrient solution, and the maximum growth rate was observed at 13th day after transferring. The growth rate was 10.7- 29.6% per day during 18 days. Optimum concentration of the nutrient solution for the growth of lettuce was 1.4 - 2.2 mS/cm of EC level. When the light condition was changed from dark to light, the fresh weight was temporarily decreased, but the fresh weight increased under the opposite condition. Top fresh weight of leaf lettuce in the darkness normally increased within 12 hours after darkness treatment, and then slowly increased until 78 hours under continuous dark condition. After that times, the fresh weight began to decrease.

• Science of Emotion and Sensibility
• /
• v.21 no.1
• /
• pp.59-70
• /
• 2018

With the breakthrough of speech recognition technology, conversational agents have become pervasive through smartphones and smart speakers. The recognition accuracy of speech recognition technology has developed to the level of human beings, but it still shows limitations on understanding the underlying meaning or intention of words, or understanding long conversation. Accordingly, the users experience various errors when interacting with the conversational agents, which may negatively affect the user experience. In addition, in the case of smart speakers with a voice as the main interface, the lack of feedback on system and transparency was reported as the main issue when the users using. Therefore, there is a strong need for research on how users can better understand the capability of the conversational agents and mitigate negative emotions in error situations. In this study, we applied social strategies, "forewarning" and "apology", to conversational agent and investigated how these strategies affect users' perceptions of the agent in breakdown situations. For the study, we created a series of demo videos of a user interacting with a conversational agent. After watching the demo videos, the participants were asked to evaluate how they liked and trusted the agent through an online survey. A total of 104 respondents were analyzed and found to be contrary to our expectation based on the literature study. The result showed that forewarning gave a negative impression to the user, especially the reliability of the agent. Also, apology in a breakdown situation did not affect the users' perceptions. In the following in-depth interviews, participants explained that they perceived the smart speaker as a machine rather than a human-like object, and for this reason, the social strategies did not work. These results show that the social strategies should be applied according to the perceptions that user has toward agents.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_3
• /
• pp.2035-2046
• /
• 2021

Glacier movement speed is the most basic measurement for glacial dynamics research and is a very important indicator in predicting sea level rise due to climate change. In this study, the two-dimensional velocity measurements of Campbell Glacier located in Terra Nova Bay in East Antarctica were observed through the SAR offset tracking technique. For this purpose, domestic KOMPSAT-5 SAR satellite images taken on July 9, 2021 and August 6, 2021 were acquired. The Multi-kernel SAR offset tracking proposed through previous studies is a technique to obtain the optimal result that satisfies both resolution and precision. However, since offset tracking is repeatedly performed according to the size of the kernel, intensive computational power and time are required. Therefore, in this study, we strategically proposed a coarse-to-fine offset tracking approach. Through coarse-to-fine SAR offset tracking, it is possible to obtain a result with improved observation precision (especially, about 4 times in azimuth direction) while maintaining resolution compared to general offset tracking results. Using this proposed technique, a two-dimensional velocity measurements of Campbell Glacier were generated. As a result of analyzing the two-dimensional movement velocity image, it was observed that the grounding line of Campbell Glacier exists at approximately latitude -74.56N. The flow velocity of Campbell Glacier Tongue analyzed in this study (185-237 m/yr) increased compared to that of 1988-1989 (140-240 m/yr). And compared to the flow velocity (181-268 m/yr) in 2010-2012, the movement speed near the ground line was similar, but it was confirmed that the movement speed at the end of the Campbell Glacier Tongue decreased. However, there is a possibility that this is an error that occurs because the study result of this study is an annual rate of glacier movement that occurred for 28 days. For accurate comparison, it will be necessary to expand the data in time series and accurately calculate the annual rate. Through this study, the two-dimensional velocity measurements of the glacier were observed for the first time using the KOMPSAT-5 satellite image, a domestic X-band SAR satellite. It was confirmed that the coarse-to-fine SAR offset tracking approach of the KOMPSAT-5 SAR image is very useful for observing the two-dimensional velocity of glacier movements.

• Korean Journal of Mineralogy and Petrology
• /
• v.35 no.1
• /
• pp.41-50
• /
• 2022

To study the properties of Sr²⁺ exchange into zeolite A with increasing the molar concentration of Na⁺ in given exchange solution, four single crystals of fully dehydrated Sr²⁺- and Na⁺- exchanged zeolite A were prepared by the bath method using mixed ion-exchange solutions. The Sr(NO₃)₂:NaNO₃ molar rations of the ion exchange solution were 1:1(crystal 1), 1:100(crystal 2), 1:250(crystal 3), and 1:500 (crystal 4), respectively, with a total concentration of 0.05 M. The single-crystals were then vacuum dehydration at 623 K and 1×10^-4 Pa for 2 days. Their single-crystal structures were determined by single-crystal synchrotron X-ray diffraction techniques in the cubic space group Pm3-m, at 100(1) K, and were then refined to the final error indices of R₁/wR₂=0.047/0.146, 0.048/0.142, 0.036/0.128, and 0.040/0.156 for crystals 1, 2, 3, and 4, respectively. In crystals 1 and 2, the 6 Sr²⁺ ions are found at three different crystallographic sites. In crystal 3, 1 Sr²⁺ and 10 Na⁺ ions are found in large cavity and sodalite unit. In crystal 4, only 12 Na⁺ ions occupy three equipoints. The degree of Sr²⁺ ion-exchange decreased sharply from 100 to 16.7 to 0% as the initial Na⁺ concentration increase and the Sr²⁺ concentration decrease. In addition, the unit cell constant of the zeolite framework decreased with this lower level of Sr²⁺ exchange.

• Journal of Korean Society of Transportation
• /
• v.32 no.3
• /
• pp.266-279
• /
• 2014

For the evaluation of roadway safety, diverse methods, including before-after studies, simple comparison using historic traffic accident data, methods based on experts' opinion or literature, have been applied. Especially, many research efforts have developed traffic accident prediction models in order to identify critical elements causing accidents and evaluate the level of safety. A traffic accident prediction model must secure predictability and transferability. By acquiring the predictability, the model can increase the accuracy in predicting the frequency of accidents qualitatively and quantitatively. By guaranteeing the transferability, the model can be used for other locations with acceptable accuracy. To this end, traffic accident prediction models using non-linear regression, artificial neural network, and structural equation were developed in this study. The predictability and transferability of three models were compared using a model development data set collected from 90 signalized intersections and a model validation data set from other 33 signalized intersections based on mean absolute deviation and mean squared prediction error. As a result of the comparison using the model development data set, the artificial neural network showed the highest predictability. However, the non-linear regression model was found out to be most appropriate in the comparison using the model validation data set. Conclusively, the artificial neural network has a strong ability in representing the relationship between the frequency of traffic accidents and traffic and road design elements. However, the predictability of the artificial neural network significantly decreased when the artificial neural network was applied to a new data which was not used in the model developing.