• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.23-38
• /
• 2012

There is a large difference between purchasing patterns in an online shopping mall and in an offline market. This difference may be caused mainly by the difference in accessibility of online and offline markets. It means that an interval between the initial purchasing decision and its realization appears to be relatively short in an online shopping mall, because a customer can make an order immediately. Because of the short interval between a purchasing decision and its realization, an online shopping mall transaction usually contains fewer items than that of an offline market. In an offline market, customers usually keep some items in mind and buy them all at once a few days after deciding to buy them, instead of buying each item individually and immediately. On the contrary, more than 70% of online shopping mall transactions contain only one item. This statistic implies that traditional data mining techniques cannot be directly applied to online market analysis, because hardly any association rules can survive with an acceptable level of Support because of too many Null Transactions. Most market basket analyses on online shopping mall transactions, therefore, have been performed by expanding the co-occurrence criteria of traditional association rule mining. While the traditional co-occurrence criteria defines items purchased in one transaction as concurrently purchased items, the expanded co-occurrence criteria regards items purchased by a customer during some predefined period (e.g., a day) as concurrently purchased items. In studies using expanded co-occurrence criteria, however, the criteria has been defined arbitrarily by researchers without any theoretical grounds or agreement. The lack of clear grounds of adopting a certain co-occurrence criteria degrades the reliability of the analytical results. Moreover, it is hard to derive new meaningful findings by combining the outcomes of previous individual studies. In this paper, we attempt to compare expanded co-occurrence criteria and propose a guideline for selecting an appropriate one. First of all, we compare the accuracy of association rules discovered according to various co-occurrence criteria. By doing this experiment we expect that we can provide a guideline for selecting appropriate co-occurrence criteria that corresponds to the purpose of the analysis. Additionally, we will perform similar experiments with several groups of customers that are segmented by each customer's average duration between orders. By this experiment, we attempt to discover the relationship between the optimal co-occurrence criteria and the customer's average duration between orders. Finally, by a series of experiments, we expect that we can provide basic guidelines for developing customized recommendation systems. Our experiments use a real dataset acquired from one of the largest internet shopping malls in Korea. We use 66,278 transactions of 3,847 customers conducted during the last two years. Overall results show that the accuracy of association rules of frequent shoppers (whose average duration between orders is relatively short) is higher than that of causal shoppers. In addition we discover that with frequent shoppers, the accuracy of association rules appears very high when the co-occurrence criteria of the training set corresponds to the validation set (i.e., target set). It implies that the co-occurrence criteria of frequent shoppers should be set according to the application purpose period. For example, an analyzer should use a day as a co-occurrence criterion if he/she wants to offer a coupon valid only for a day to potential customers who will use the coupon. On the contrary, an analyzer should use a month as a co-occurrence criterion if he/she wants to publish a coupon book that can be used for a month. In the case of causal shoppers, the accuracy of association rules appears to not be affected by the period of the application purposes. The accuracy of the causal shoppers' association rules becomes higher when the longer co-occurrence criterion has been adopted. It implies that an analyzer has to set the co-occurrence criterion for as long as possible, regardless of the application purpose period.

• 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.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.43-56
• /
• 2020

Recommender systems help users make the best choice among various options. Especially, recommender systems play important roles in internet sites as digital information is generated innumerable every second. Many studies on recommender systems have focused on an accurate recommendation. However, there are some problems to overcome in order for the recommendation system to be commercially successful. First, there is a lack of transparency in the recommender system. That is, users cannot know why products are recommended. Second, the recommender system cannot immediately reflect changes in user preferences. That is, although the preference of the user's product changes over time, the recommender system must rebuild the model to reflect the user's preference. Therefore, in this study, we proposed a recommendation methodology using topic modeling and sequential association rule mining to solve these problems from review data. Product reviews provide useful information for recommendations because product reviews include not only rating of the product but also various contents such as user experiences and emotional state. So, reviews imply user preference for the product. So, topic modeling is useful for explaining why items are recommended to users. In addition, sequential association rule mining is useful for identifying changes in user preferences. The proposed methodology is largely divided into two phases. The first phase is to create user profile based on topic modeling. After extracting topics from user reviews on products, user profile on topics is created. The second phase is to recommend products using sequential rules that appear in buying behaviors of users as time passes. The buying behaviors are derived from a change in the topic of each user. A collaborative filtering-based recommendation system was developed as a benchmark system, and we compared the performance of the proposed methodology with that of the collaborative filtering-based recommendation system using Amazon's review dataset. As evaluation metrics, accuracy, recall, precision, and F1 were used. For topic modeling, collapsed Gibbs sampling was conducted. And we extracted 15 topics. Looking at the main topics, topic 1, top 3, topic 4, topic 7, topic 9, topic 13, topic 14 are related to "comedy shows", "high-teen drama series", "crime investigation drama", "horror theme", "British drama", "medical drama", "science fiction drama", respectively. As a result of comparative analysis, the proposed methodology outperformed the collaborative filtering-based recommendation system. From the results, we found that the time just prior to the recommendation was very important for inferring changes in user preference. Therefore, the proposed methodology not only can secure the transparency of the recommender system but also can reflect the user's preferences that change over time. However, the proposed methodology has some limitations. The proposed methodology cannot recommend product elaborately if the number of products included in the topic is large. In addition, the number of sequential patterns is small because the number of topics is too small. Therefore, future research needs to consider these limitations.

• Journal of Korea Water Resources Association
• /
• v.54 no.10
• /
• pp.835-848
• /
• 2021

In Jeju Island which has peculiarity for its geological features and hydrology system, hydrological factor analysis for the effective water management is necessary. Because in-situ hydro-meteorological data is affected by surrounding environment, the in-situ dataset could not be the spatially representative for the study area. For this reason, remote sensing data may be used to overcome the limit of the in-situ data. In this study, applicability assessment of MOD16 evapotranspiration data, Globas Land Data Assimilation System (GLDAS) based evapotranspiration/soil moisture data, and Advanced SCATterometer (ASCAT) soil moisture product which were evaluated their applicability on other study areas was conducted. In the case of evapotranspiration, comparison with total precipitation and flux-tower based evapotranspiration were conducted. And for soil moisture, 6 in-situ data and ASCAT soil moisture product were compared on each site. As a result, 57% of annual precipitation was calculated as evapotranspiration, and the correlation coefficient between MOD16 evapotranspiration and GLDAS evapotranspiration was 0.759, which was a robust value. The correlation coefficient was 0.434, indicating a relatively low fit. In the case of soil moisture, in the case of the GLDAS data, the RMSE value was less than 0.05 at all sites compared to the in-situ data, and a statistically significant result was obtained as a result of the significance test of the correlation coefficient. However, for satellite data, RMSE over than 0.05 were found at Wolgak and there was no correlation at Sehwa and Handong points. It is judged that the above results are due to insufficient quality control and spatial representation of the evapotranspiration and soil moisture sensors installed in Jeju Island. It is estimated as the error that appears when adjacent to the coast. Through this study, the necessity of improving the existing ground observation data of hydrometeorological factors is emphasized.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.198-221
• /
• 2021

After large-scale reforestation in the 1960s and 1970s, forests in Korea have gradually been aging. Net ecosystem CO₂ exchange of old-growth forests is theoretically near zero; however, it can be a CO₂ sink or source depending on the intervention of disturbance or management. In this study, we report the CO₂ budget dynamics of the Gwangneung deciduous old-growth forest (GDK) in Korea and examined the following two questions: (1) is the preserved GDK indeed CO₂ neutral as theoretically known? and (2) can we explain the dynamics of CO₂ budget by the common mechanisms reported in the literature? To answer, we analyzed the 15-year long CO₂ flux data measured by eddy covariance technique along with other biometeorological data at the KoFlux GDK site from 2006 to 2020. The results showed that (1) GDK switched back-and-forth between sink and source of CO₂ but averaged to be a week CO₂ source (and turning to a moderate CO₂ source for the recent five years) and (2) the interannual variability of solar radiation, growing season length, and leaf area index showed a positive correlation with that of gross primary production (GPP) (R²=0.32~0.45); whereas the interannual variability of both air and surface temperature was not significantly correlated with that of ecosystem respiration (RE). Furthermore, the machine learning-based model trained using the dataset of early monitoring period (first 10 years) failed to reproduce the observed interannual variations of GPP and RE for the recent five years. Biomass data analysis suggests that carbon emissions from coarse woody debris may have contributed partly to the conversion to a moderate CO₂ source. To properly understand and interpret the long-term CO₂ budget dynamics of GDK, new framework of analysis and modeling based on complex systems science is needed. Also, it is important to maintain the flux monitoring and data quality along with the monitoring of coarse woody debris and disturbances.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1285-1300
• /
• 2022

Turbidity, the measure of the cloudiness of water, is used as an important index for water quality management. The turbidity can vary greatly in small river systems, which affects water quality in national rivers. Therefore, the generation of high-resolution spatial information on turbidity is very important. In this study, a turbidity retrieval model using the Korea Multi-Purpose Satellite-3 and -3A (KOMPSAT-3/3A) images was developed for high-resolution turbidity mapping of Han River system based on eXtreme Gradient Boosting (XGBoost) algorithm. To this end, the top of atmosphere (TOA) spectral reflectance was calculated from a total of 24 KOMPSAT-3/3A images and 150 Landsat-8 images. The Landsat-8 TOA spectral reflectance was cross-calibrated to the KOMPSAT-3/3A bands. The turbidity measured by the National Water Quality Monitoring Network was used as a reference dataset, and as input variables, the TOA spectral reflectance at the locations of in situ turbidity measurement, the spectral indices (the normalized difference vegetation index, normalized difference water index, and normalized difference turbidity index), and the Moderate Resolution Imaging Spectroradiometer (MODIS)-derived atmospheric products(the atmospheric optical thickness, water vapor, and ozone) were used. Furthermore, by analyzing the KOMPSAT-3/3A TOA spectral reflectance of different turbidities, a new spectral index, new normalized difference turbidity index (nNDTI), was proposed, and it was added as an input variable to the turbidity retrieval model. The XGBoost model showed excellent performance for the retrieval of turbidity with a root mean square error (RMSE) of 2.70 NTU and a normalized RMSE (NRMSE) of 14.70% compared to in situ turbidity, in which the nNDTI proposed in this study was used as the most important variable. The developed turbidity retrieval model was applied to the KOMPSAT-3/3A images to map high-resolution river turbidity, and it was possible to analyze the spatiotemporal variations of turbidity. Through this study, we could confirm that the KOMPSAT-3/3A images are very useful for retrieving high-resolution and accurate spatial information on the river turbidity.

• 한국노년학
• /
• v.29 no.4
• /
• pp.1559-1575
• /
• 2009

As the basic old-age pension system was enforced in 2008, the base for old-age income security was founded. However, due to the basic old-age pension played a minor role as assistant allowance, it did not reach to sufficient level to cover full income security system. It is estimated that the dependency on private transfer income among the elderly who are difficult to be economically independent is still high. Therefore the poverty rate of the elderly households, who are not economically active or who are not protected by old-age income security system, is more likely to be higher than that of non-elderly households. Based on the assumption that public transfer income system should become a central means of old-age life guarantee, this study examined the poverty mitigation effects among the elderly households by comparing the private transfer income and the public transfer income. For this purpose, we selected single-elderly-households who have been considered the most vulnerable to poverty. We used 2006- 2008 Household Income and Expenditure Survey dataset that contained single-elderly who were older than 65 years old. To understand the conditions of poverty among single-elderly-households and the degree of poverty-reducing effect originated from income transfer system, we compared the poverty rates of total households and the whole elderly households. Next, we analysed the poverty of the single-elderly-households by social demographic factors such as gender, age, and economic activity. Our major findings are as follows: First, the poverty rate of the whole elderly households were not reduced, even though the basic old-age pension and long-term care management system were enforced in 2008. Second, half of the elderly households including single-elderly-households belonged to the absolute poverty line. Relatively higher level of poverty among the single-elderly-households was found especially those who were female, unemployed, low-educated, older, and rural single-elderly-households. Third, the effect of the public transfer income on mitigating the single-elderly-households poverty showed a little progress. However, even greater poverty reducing effect was found by the private transfer income system. Fourth, in a group of the public transfer systems, the public assistance such as supporting living costs contributed more to reduce poverty of the elderly population than the public pension system did.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.655-667
• /
• 2023

Algal bloom outbreaks are frequently reported around the world, and serious water pollution problems arise every year in Korea. It is necessary to protect the aquatic ecosystem through continuous management and rapid response. Many studies using satellite images are being conducted to estimate the concentration of chlorophyll-a (Chl-a), an indicator of algal bloom occurrence. However, machine learning models have recently been used because it is difficult to accurately calculate Chl-a due to the spectral characteristics and atmospheric correction errors that change depending on the water system. It is necessary to consider the factors affecting algal bloom as well as the satellite spectral index. Therefore, this study constructed a dataset by considering water quality, hydrological and meteorological factors, and sentinel-2 images in combination. Representative ensemble models random forest and extreme gradient boosting (XGBoost) were used to predict the concentration of Chl-a in eight weirs located on the Nakdong river over the past five years. R-squared score (R²), root mean square errors (RMSE), and mean absolute errors (MAE) were used as model evaluation indicators, and it was confirmed that R² of XGBoost was 0.80, RMSE was 6.612, and MAE was 4.457. Shapley additive expansion analysis showed that water quality factors, suspended solids, biochemical oxygen demand, dissolved oxygen, and the band ratio using red edge bands were of high importance in both models. Various input data were confirmed to help improve model performance, and it seems that it can be applied to domestic and international algal bloom detection.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.79-104
• /
• 2020

Recently, as deep learning has attracted attention, the use of deep learning is being considered as a method for solving problems in various fields. In particular, deep learning is known to have excellent performance when applied to applying unstructured data such as text, sound and images, and many studies have proven its effectiveness. Owing to the remarkable development of text and image deep learning technology, interests in image captioning technology and its application is rapidly increasing. Image captioning is a technique that automatically generates relevant captions for a given image by handling both image comprehension and text generation simultaneously. In spite of the high entry barrier of image captioning that analysts should be able to process both image and text data, image captioning has established itself as one of the key fields in the A.I. research owing to its various applicability. In addition, many researches have been conducted to improve the performance of image captioning in various aspects. Recent researches attempt to create advanced captions that can not only describe an image accurately, but also convey the information contained in the image more sophisticatedly. Despite many recent efforts to improve the performance of image captioning, it is difficult to find any researches to interpret images from the perspective of domain experts in each field not from the perspective of the general public. Even for the same image, the part of interests may differ according to the professional field of the person who has encountered the image. Moreover, the way of interpreting and expressing the image also differs according to the level of expertise. The public tends to recognize the image from a holistic and general perspective, that is, from the perspective of identifying the image's constituent objects and their relationships. On the contrary, the domain experts tend to recognize the image by focusing on some specific elements necessary to interpret the given image based on their expertise. It implies that meaningful parts of an image are mutually different depending on viewers' perspective even for the same image. So, image captioning needs to implement this phenomenon. Therefore, in this study, we propose a method to generate captions specialized in each domain for the image by utilizing the expertise of experts in the corresponding domain. Specifically, after performing pre-training on a large amount of general data, the expertise in the field is transplanted through transfer-learning with a small amount of expertise data. However, simple adaption of transfer learning using expertise data may invoke another type of problems. Simultaneous learning with captions of various characteristics may invoke so-called 'inter-observation interference' problem, which make it difficult to perform pure learning of each characteristic point of view. For learning with vast amount of data, most of this interference is self-purified and has little impact on learning results. On the contrary, in the case of fine-tuning where learning is performed on a small amount of data, the impact of such interference on learning can be relatively large. To solve this problem, therefore, we propose a novel 'Character-Independent Transfer-learning' that performs transfer learning independently for each character. In order to confirm the feasibility of the proposed methodology, we performed experiments utilizing the results of pre-training on MSCOCO dataset which is comprised of 120,000 images and about 600,000 general captions. Additionally, according to the advice of an art therapist, about 300 pairs of 'image / expertise captions' were created, and the data was used for the experiments of expertise transplantation. As a result of the experiment, it was confirmed that the caption generated according to the proposed methodology generates captions from the perspective of implanted expertise whereas the caption generated through learning on general data contains a number of contents irrelevant to expertise interpretation. In this paper, we propose a novel approach of specialized image interpretation. To achieve this goal, we present a method to use transfer learning and generate captions specialized in the specific domain. In the future, by applying the proposed methodology to expertise transplant in various fields, we expected that many researches will be actively conducted to solve the problem of lack of expertise data and to improve performance of image captioning.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.139-156
• /
• 2021

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.