• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.125-140
• /
• 2013

We call a data set in which the number of records belonging to a certain class far outnumbers the number of records belonging to the other class, 'imbalanced data set'. Most of the classification techniques perform poorly on imbalanced data sets. When we evaluate the performance of a certain classification technique, we need to measure not only 'accuracy' but also 'sensitivity' and 'specificity'. In a customer churn prediction problem, 'retention' records account for the majority class, and 'churn' records account for the minority class. Sensitivity measures the proportion of actual retentions which are correctly identified as such. Specificity measures the proportion of churns which are correctly identified as such. The poor performance of the classification techniques on imbalanced data sets is due to the low value of specificity. Many previous researches on imbalanced data sets employed 'oversampling' technique where members of the minority class are sampled more than those of the majority class in order to make a relatively balanced data set. When a classification model is constructed using this oversampled balanced data set, specificity can be improved but sensitivity will be decreased. In this research, we developed a hybrid model of support vector machine (SVM), artificial neural network (ANN) and decision tree, that improves specificity while maintaining sensitivity. We named this hybrid model 'hybrid SVM model.' The process of construction and prediction of our hybrid SVM model is as follows. By oversampling from the original imbalanced data set, a balanced data set is prepared. SVM_I model and ANN_I model are constructed using the imbalanced data set, and SVM_B model is constructed using the balanced data set. SVM_I model is superior in sensitivity and SVM_B model is superior in specificity. For a record on which both SVM_I model and SVM_B model make the same prediction, that prediction becomes the final solution. If they make different prediction, the final solution is determined by the discrimination rules obtained by ANN and decision tree. For a record on which SVM_I model and SVM_B model make different predictions, a decision tree model is constructed using ANN_I output value as input and actual retention or churn as target. We obtained the following two discrimination rules: 'IF ANN_I output value <0.285, THEN Final Solution = Retention' and 'IF ANN_I output value ${\geq}0.285$, THEN Final Solution = Churn.' The threshold 0.285 is the value optimized for the data used in this research. The result we present in this research is the structure or framework of our hybrid SVM model, not a specific threshold value such as 0.285. Therefore, the threshold value in the above discrimination rules can be changed to any value depending on the data. In order to evaluate the performance of our hybrid SVM model, we used the 'churn data set' in UCI Machine Learning Repository, that consists of 85% retention customers and 15% churn customers. Accuracy of the hybrid SVM model is 91.08% that is better than that of SVM_I model or SVM_B model. The points worth noticing here are its sensitivity, 95.02%, and specificity, 69.24%. The sensitivity of SVM_I model is 94.65%, and the specificity of SVM_B model is 67.00%. Therefore the hybrid SVM model developed in this research improves the specificity of SVM_B model while maintaining the sensitivity of SVM_I model.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.109-125
• /
• 2019

As interest on intelligent search engines increases, various studies have been conducted to extract and utilize the features related to products intelligencely. In particular, when users search for goods in e-commerce search engines, the 'color' of a product is an important feature that describes the product. Therefore, it is necessary to deal with the synonyms of color terms in order to produce accurate results to user's color-related queries. Previous studies have suggested dictionary-based approach to process synonyms for color features. However, the dictionary-based approach has a limitation that it cannot handle unregistered color-related terms in user queries. In order to overcome the limitation of the conventional methods, this research proposes a model which extracts RGB values from an internet search engine in real time, and outputs similar color names based on designated color information. At first, a color term dictionary was constructed which includes color names and R, G, B values of each color from Korean color standard digital palette program and the Wikipedia color list for the basic color search. The dictionary has been made more robust by adding 138 color names converted from English color names to foreign words in Korean, and with corresponding RGB values. Therefore, the fininal color dictionary includes a total of 671 color names and corresponding RGB values. The method proposed in this research starts by searching for a specific color which a user searched for. Then, the presence of the searched color in the built-in color dictionary is checked. If there exists the color in the dictionary, the RGB values of the color in the dictioanry are used as reference values of the retrieved color. If the searched color does not exist in the dictionary, the top-5 Google image search results of the searched color are crawled and average RGB values are extracted in certain middle area of each image. To extract the RGB values in images, a variety of different ways was attempted since there are limits to simply obtain the average of the RGB values of the center area of images. As a result, clustering RGB values in image's certain area and making average value of the cluster with the highest density as the reference values showed the best performance. Based on the reference RGB values of the searched color, the RGB values of all the colors in the color dictionary constructed aforetime are compared. Then a color list is created with colors within the range of ${\pm}50$ for each R value, G value, and B value. Finally, using the Euclidean distance between the above results and the reference RGB values of the searched color, the color with the highest similarity from up to five colors becomes the final outcome. In order to evaluate the usefulness of the proposed method, we performed an experiment. In the experiment, 300 color names and corresponding color RGB values by the questionnaires were obtained. They are used to compare the RGB values obtained from four different methods including the proposed method. The average euclidean distance of CIE-Lab using our method was about 13.85, which showed a relatively low distance compared to 3088 for the case using synonym dictionary only and 30.38 for the case using the dictionary with Korean synonym website WordNet. The case which didn't use clustering method of the proposed method showed 13.88 of average euclidean distance, which implies the DBSCAN clustering of the proposed method can reduce the Euclidean distance. This research suggests a new color synonym processing method based on RGB values that combines the dictionary method with the real time synonym processing method for new color names. This method enables to get rid of the limit of the dictionary-based approach which is a conventional synonym processing method. This research can contribute to improve the intelligence of e-commerce search systems especially on the color searching feature.

• Information Systems Review
• /
• v.17 no.2
• /
• pp.77-100
• /
• 2015

This study examined the factors that influence the smartphone user's decision to accept the personalized mobile advertisement. As a theoretical basis, we applied the privacy calculus model (PCM) that illustrates how consumers are engaged in a dynamic adjustment process in which privacy risks are weighted against benefits of information disclosure. In particular, we investigated how smartphone users make a risk-benefit assessment under which personalized service as benefit-side factor and information privacy risks as a risk-side factor accompanying their acceptance of advertisements. Further, we extend the current PCM by considering advertisement fatigue as a new factor that may influence the user's acceptance. The research model with five (5) hypotheses was tested using data gathered from 215 respondents through a quasi-experimental survey method. During the survey, each participant was asked to navigate the website where the experimental simulation of a mobile advertisement service was provided. The results showed that three (3) out of five (5) hypotheses were supported. First, we found that the intention to accept advertisements is positively and significantly influenced by the perceived value of personalization. Second, perceived advertisement fatigue was also found to be a strong predictor of the intention to accept advertisements. However, we did not find any evidence of direct influence of privacy risks. Finally, we found that the significant moderating effect between the perceived value of personalization and advertisement fatigue. This suggests that the firms should provide effective tailored advertisement that can increase the perceived value of personalization to mitigate the negative impacts of advertisement fatigue.

• Spatial Information Research
• /
• v.11 no.3
• /
• pp.261-274
• /
• 2003

The effective probability-based tile pre-fetching algorithm and the collaborative cache replacement algorithm are able to reduce the response time for user's requests by transferring tiles which will be used in advance and determining tiles which should be removed from the restrictive cache space of a client based on the future access probabilities in Web GISs(Geographical Information Systems). The Web GISs have multi-level abstracted data for the quick response time when zoom-in and zoom-out queries are requested. But, the previous pre-fetching algorithm is applied on only two-dimensional pre-fetching space, and doesn't consider expanded pre-fetching space for multi-level abstracted data in Web GISs. In this thesis, a probability-based pre-fetching algorithm for multi-level abstracted in Web GISs was proposed. This algorithm expanded the previous two-dimensional pre-fetching space into three-dimensional one for pre-fetching tiles of the upper levels or lower levels. Moreover, we evaluated the effect of the proposed pre-fetching algorithm by using a simulation method. Through the experimental results, the response time for user requests was improved 1.8%∼21.6% on the average. Consequently, in Web GISs with multi-level abstracted data, the proposed pre-fetching algorithm and the collaborative cache replacement algorithm can reduce the response time for user requests substantially.

• Journal of Korea Society of Industrial Information Systems
• /
• v.8 no.3
• /
• pp.51-60
• /
• 2003

In the radical char]go of the business environments that the existing facilities can not guarantee the business-frosts anymore, enterprises have been importing ERP system. In Korea, Sam-sung Electronics did it for the first tin in the latter half of 1994 and other enterprises succeeded. Currently, government and public enterprises as well as most of the large enterprises are employing ERP system to sharpen the competitiveness and to win the business transparency. On the other hand, it is harder for small and medium enterprises shaded by the large enterprises to be well-equipped with information system such as ERP, because they have already suffered from chronic financial difficulties and shortage of many resources. Most of all, they prefer the short-term project that does not need much tine for them to make decisions and to carry out fully. Grounded on the above factors, in this work, I suggest the suitable ERP model for the small and medium enterprises and the successful importing process of ERP, which is derived from the previous researches made by other masters' thesis. If necessary information and human resources are interchanged pertinently between local education institute and small and medium enterprise, the latter could not only deal with the confronted difficulties successfully inside and outside but attain the goal of being proficient in up-to-minute high technology. Besides, giving the students the opportunity of researching into the practice of the business they have not ever known, local universities could help their students accumulate knowledges and acquire ideas which could not be achieved in pure academic studies. When the above-mentioned procedure is over, the students might get the intellectual faculty to ponder on the future more concretely and enter a profession more carefully. In the result, we would raise up the percentage of the employment among the graduates. And active participation of university professors is the last important factor that assists the small and medium enterprises for introducing ERP system successfully. Their scholarly attainments play an important role in strengthening local economy and make the business competitiveness balanced between the capital and the local economy.

• Management & Information Systems Review
• /
• v.35 no.4
• /
• pp.99-122
• /
• 2016

The social networking services (SNSs) have become popular among smartphone users, and one of the most popular services. In order to explain users' motivations toward SNS, this study considers uses and gratification theory which can explain individuals' motivations to select certain media channels. The purposes of this study is to investigate the relationships between motivations and addiction of SNS, and between addiction of SNS and decline in the subjective wellbeing. We examine moderating effects of social tie based on the social capital theory in the relationships between SNS addiction and decline in the subjective wellbeing. The motivations of SNS are subdivided into emotional motive (entertainment and fantasy) and cognitive motive (information share burden and challenge burden) based on the use and gratifications theory. The addiction of SNS is subdivided into time tolerance, withdrawal symptoms, interruption, and barrier of living. The data used in this study were collected from 286 SNS users through surveys. The data analysis in this study was performed using AMOS 17.0, and we used SEM(Structural Equation Modeling) methods in order to test the research model. The result shows that the emotional motive(entertainment and fantasy) and cognitive motive(information share burden and challenge burden) have an effect on the addiction of SNS. Especially emotional motive such as entertainment and users' fantasy toward SNS is an important factor that can cause SNS addiction. The addiction of SNS such as time tolerance, withdrawal symptoms, interruption, and barrier of living has an effect on the decline in the subjective wellbeing. Our result show that social tie partially moderates the relationship SNS addiction and decline in the subjective wellbeing. In addition, social tie between interruption of SNS and decline in the subjective wellbeing is an important moderating factor. The results focuses on the understanding toward relationship between SNS addiction based on the online and decline in the subjective wellbeing in the real world. The findings of this study also provides theoretical as well as practical implications which reflect the major features of SNS, and moderating effects of social tie based on the social capital.

• Management & Information Systems Review
• /
• v.38 no.1
• /
• pp.23-41
• /
• 2019

Smart Factory is different from existing factory automation in that it aims to produce personalized products with minimum time and cost through ICT. However, previous researches, not from consumers but from product suppliers, have focused on technology trends and technology application methods. In order for Smart Factory to be successful, it must go beyond supplier-focus to meet the needs of consumers. In this study, we surveyed the purchase intention of the personalized product manufactured by smart factory. Influencing factors of purchase intention were drawn as consumers' need for uniqueness, innovativeness, need for touch, and privacy concern, based on previous research. As results of data analysis, it was confirmed that respondents were willing to purchase personalized products, and that consumers' need for uniqueness, innovativeness, and need for touch had a significant impact on purchase intention of personalized products. Our findings can be summarized as follows. First, Consumers' need for uniqueness was found to have positive effects(${\beta}=0.168$) on purchase intention of personalized products. The desire to differentiate themselves from others will be reflected in their personalized products. Therefore, consumers with a higher desire for uniqueness tend to be more willing to purchase personalized products. Second, consumer innovativeness was found to have positive effects(${\beta}=0.233$) on purchase intention of personalized products. Personalized shoes suggested in this study is a new type of personalized product that is manufactured by the latest information and communication technologies such as multi-function robots and 3D printing. Therefore, consumers seeking innovative new experiences are more willing to purchase personalized products. Third, need for touch was found to have positive effects(${\beta}=0.299$) on purchase intention of personalized products. In a smart factory environment, prosuming participation is given to consumers. If consumers participate in the product development process and reflect their requirements on the product, they are expected to increase their purchase intention by virtually satisfying the need for touch. Fourth, privacy concern was found to have no significantly related to purchase intention of personalized products. This is interpreted as a willingness to tolerate the risk of exposing personal information such as home address, telephone number, body size, and preference for consumers who feel highly useful in personalized products.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.12
• /
• pp.157-167
• /
• 2009

Recently, the leakage of confidential information and personal information is taking place on the Internet more frequently than ever before. Most of such online security incidents are caused by attacks on vulnerabilities in web applications developed carelessly. It is impossible to detect an attack on a web application with existing firewalls and intrusion detection systems. Besides, the signature-based detection has a limited capability in detecting new threats. Therefore, many researches concerning the method to detect attacks on web applications are employing anomaly-based detection methods that use the web traffic analysis. Much research about anomaly-based detection through the normal web traffic analysis focus on three problems - the method to accurately analyze given web traffic, system performance needed for inspecting application payload of the packet required to detect attack on application layer and the maintenance and costs of lots of network security devices newly installed. The UTM(Unified Threat Management) system, a suggested solution for the problem, had a goal of resolving all of security problems at a time, but is not being widely used due to its low efficiency and high costs. Besides, the web filter that performs one of the functions of the UTM system, can not adequately detect a variety of recent sophisticated attacks on web applications. In order to resolve such problems, studies are being carried out on the web application firewall to introduce a new network security system. As such studies focus on speeding up packet processing by depending on high-priced hardware, the costs to deploy a web application firewall are rising. In addition, the current anomaly-based detection technologies that do not take into account the characteristics of the web application is causing lots of false positives and false negatives. In order to reduce false positives and false negatives, this study suggested a realtime anomaly detection method based on the analysis of the length of parameter value contained in the web client's request. In addition, it designed and suggested a WAF(Web Application Firewall) that can be applied to a low-priced system or legacy system to process application data without the help of an exclusive hardware. Furthermore, it suggested a method to resolve sluggish performance attributed to copying packets into application area for application data processing, Consequently, this study provide to deploy an effective web application firewall at a low cost at the moment when the deployment of an additional security system was considered burdened due to lots of network security systems currently used.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.53-74
• /
• 2018

Since South Korea has an economic structure that has a characteristic which market-dependent on overseas, the tourism industry is considered as a very important industry for the national economy, such as improving the country's balance of payments or providing income and employment increases. Accordingly, the necessity of more accurate forecasting on the demand in the tourism industry has been raised to promote its industry. In the related research, economic variables such as exchange rate and income have been used as variables influencing tourism demand. As information technology has been widely used, some researchers have also analyzed the effect of media on tourism demand. It has shown that the media has a considerable influence on traveler's decision making, such as choosing an outbound destination. Furthermore, with the recent availability of online information searches to obtain the latest information and two-way communication in social media, it is possible to obtain up-to-date information on travel more quickly than before. The information in online media such as blogs can naturally create the Word-of-Mouth effect by sharing useful information, which is called eWOM. Like all other service industries, the tourism industry is characterized by difficulty in evaluating its values before it is experienced directly. And furthermore, most of the travelers tend to search for more information in advance from various sources to reduce the perceived risk to the destination, so they can also be influenced by online media such as online news. In this study, we suggested that the number of online media posting, which causes the effects of Word-of-Mouth, may have an effect on the number of outbound travelers. We divided online media into public media and private media according to their characteristics and selected online news as public media and blog as private media, one of the most popular social media in tourist information. Based on the previous studies about the eWOM effects on online news and blog, we analyzed a relationship between the volume of eWOM and the outbound tourism demand through the panel model. To this end, we collected data on the number of national outbound travelers from 2007 to 2015 provided by the Korea Tourism Organization. According to statistics, the highest number of outbound tourism demand in Korea are China, Japan, Thailand, Hong Kong and the Philippines, which are selected as a dependent variable in this study. In order to measure the volume of eWOM, we collected online news and blog postings for the same period as the number of outbound travelers in Naver, which is the largest portal site in South Korea. In this study, a panel model was established to analyze the effect of online media on the demand of Korean outbound travelers and to identify that there was a significant difference in the influence of online media by each time and countries. The results of this study can be summarized as follows. First, the impact of the online news and blog eWOM on the number of outbound travelers was significant. We found that the number of online news and blog posting have an influence on the number of outbound travelers, especially the experimental result suggests that both the month that includes the departure date and the three months before the departure were found to have an effect. It is shown that online news and blog are online media that have a significant influence on outbound tourism demand. Next, we found that the increased volume of eWOM in online news has a negative effect on departure, while the increase in a blog has a positive effect. The result with the country-specific models would be the same. This paper shows that online media can be used as a new variable in tourism demand by examining the influence of the eWOM effect of the online media. Also, we found that both social media and news media have an important role in predicting and managing the Korean tourism demand and that the influence of those two media appears different depending on the country.

• Journal of Intelligence and Information Systems
• /
• v.17 no.2
• /
• pp.119-128
• /
• 2011

The Sensor technology and portable device capability able to collect recent user information and the information about the surrounding environment haven been highly developed. A user can be made use of various contents and the option is also extending with this technology development. In particular, the initial portable device had simply a call function, but now that has evolved into 'the 4th screen' which including movie, television, PC ability. also, in the past, a portable device to provided only the services of a SMS, in recent years, it provided to interactive video service, and it include technology which providing various contents. Also, it is rising as media which leading the consumption of contents, because it can be used anytime, anywhere. However, the contents available for the nature of user's handheld devices are limited. because it is very difficult for making the contents separately according to various device specification. To find a solution to this problem, the study on one contents from several device has been progressing. The contents conversion technology making use of the profile of device out of this study comes to the force and profile study has been progressing for this. Furthermore, Demand for a user is also increased and the study on the technology collecting, analyzing demands has been making active progress. And what is more, Grasping user's demands by making use of this technology and the study on the technology analyzing, providing contents has been making active progress as well. First of all, there is a method making good use of ZigBee, Bluetooth technology about the sensor for gathering user's information. ZigBee uses low-power digital radio for wireless headphone, wireless communication network, and being utilized for smart energy, automatic home system, wireless communication application and wireless sensor application. Bluetooth, as industry standards of PAN(Personal Area Networks), is being made of use of low power wireless device for the technology supporting data transmission such as drawing file, video file among Bluetooth device. With analyzing the collected information making use of this technology, it utilizes personalized service based on network knowledge developed by ETRI to service contents tailor-made for a user. Now that personalized service builds up network knowledge about user's various environments, the technology provides context friendly service constructed dynamically on the basis of this. The contents to service dynamically like this offer the contents that it converses with utilizing device profile to working well. Therefore, this paper suggests the system as follow. It collects the information, for example of user's sensitivity, context and location by using sensor technology, and generates the profile as a means of collected information as sensor. It collects the user's propensity to the information by user's input and event and generates profile in the same way besides the gathered information by sensor. Device transmits a generated profile and the profile about a device specification to proxy server. And proxy server transmits a profile to each profile management server. It analyzes profile in proxy server so that it selects the contents user demand and requests in contents server. Contents server receives a profile of user portable device from device profile server and converses the contents by using this. Original source code of contents convert into XML code using the device profile and XML code convert into source code available in user portable device. Thus, contents conversion process is terminated and user friendly system is completed as the user transmits optimal contents for user portable device.