• 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.25 no.4
• /
• pp.53-65
• /
• 2019

Object tracking is one of important steps to achieve video-based surveillance systems. Object tracking is considered as an essential task similar to object detection and recognition. In order to perform object tracking, various machine learning methods (e.g., least-squares, perceptron and support vector machine) can be applied for different designs of tracking systems. In general, generative methods (e.g., principal component analysis) were utilized due to its simplicity and effectiveness. However, the generative methods were only focused on modeling the target object. Due to this limitation, discriminative methods (e.g., binary classification) were adopted to distinguish the target object and the background. Among the machine learning methods for binary classification, total error rate minimization can be used as one of successful machine learning methods for binary classification. The total error rate minimization can achieve a global minimum due to a quadratic approximation to a step function while other methods (e.g., support vector machine) seek local minima using nonlinear functions (e.g., hinge loss function). Due to this quadratic approximation, the total error rate minimization could obtain appropriate properties in solving optimization problems for binary classification. However, this total error rate minimization was based on a batch mode setting. The batch mode setting can be limited to several applications under offline learning. Due to limited computing resources, offline learning could not handle large scale data sets. Compared to offline learning, online learning can update its solution without storing all training samples in learning process. Due to increment of large scale data sets, online learning becomes one of essential properties for various applications. Since object tracking needs to handle data samples in real time, online learning based total error rate minimization methods are necessary to efficiently address object tracking problems. Due to the need of the online learning, an online learning based total error rate minimization method was developed. However, an approximately reweighted technique was developed. Although the approximation technique is utilized, this online version of the total error rate minimization could achieve good performances in biometric applications. However, this method is assumed that the total error rate minimization can be asymptotically achieved when only the number of training samples is infinite. Although there is the assumption to achieve the total error rate minimization, the approximation issue can continuously accumulate learning errors according to increment of training samples. Due to this reason, the approximated online learning solution can then lead a wrong solution. The wrong solution can make significant errors when it is applied to surveillance systems. In this paper, we propose an exactly reweighted technique to recursively update the solution of the total error rate minimization in online learning manner. Compared to the approximately reweighted online total error rate minimization, an exactly reweighted online total error rate minimization is achieved. The proposed exact online learning method based on the total error rate minimization is then applied to object tracking problems. In our object tracking system, particle filtering is adopted. In particle filtering, our observation model is consisted of both generative and discriminative methods to leverage the advantages between generative and discriminative properties. In our experiments, our proposed object tracking system achieves promising performances on 8 public video sequences over competing object tracking systems. The paired t-test is also reported to evaluate its quality of the results. Our proposed online learning method can be extended under the deep learning architecture which can cover the shallow and deep networks. Moreover, online learning methods, that need the exact reweighting process, can use our proposed reweighting technique. In addition to object tracking, the proposed online learning method can be easily applied to object detection and recognition. Therefore, our proposed methods can contribute to online learning community and object tracking, detection and recognition communities.

• Asia pacific journal of information systems
• /
• v.23 no.4
• /
• pp.103-128
• /
• 2013

When a consumer needs a product or service and multiple sellers are available online, the process of selecting a seller to buy online from is complex since the process involves many behavioral dimensions that have to be taken into account. As a part of this selection process, consumers may set minimum trust expectation that can be used to screen out less trustworthy sellers. In the previous research, the level of consumers' trust expectation has been anchored on two important factors: product involvement and perceived risk. Product involvement refers to the extent to which a consumer perceives a specific product important. Thus, the higher product involvement may result in the higher trust expectation in sellers. On the other hand, other related studies found that when consumers perceived a higher level of risk (e.g., credit card fraud risk), they set higher trust expectation as well. While abundant research exists addressing the relationship between product involvement and perceived risk, little attention has been paid to the integrative view of the link between the two constructs and their impacts on the trust expectation. The present paper is a step toward filling this research gap. The purpose of this paper is to understand the process by which a consumer chooses an online merchant by examining the relationships among product involvement, perceived risk, trust expectation, and intention to buy from an e-tailer. We specifically focus on the mediating role of perceived risk in the relationships between enduring product involvement and the trust expectation. That is, we question whether product involvement affects the trust expectation directly without mediation or indirectly mediated by perceived risk. The research model with four hypotheses was initially tested using data gathered from 635 respondents through an online survey method. The structural equation modeling technique with partial least square was used to validate the instrument and the proposed model. The results showed that three out of the four hypotheses formulated were supported. First, we found that the intention to buy from a digital storefront is positively and significantly influenced by the trust expectation, providing support for H4 (trust expectation ${\rightarrow}$ purchase intention). Second, perceived risk was found to be a strong predictor of trust expectation, supporting H2 as well (perceived risk ${\rightarrow}$ trust expectation). Third, we did not find any evidence of direct influence of product involvement, which caused H3 to be rejected (product involvement ${\rightarrow}$ trust expectation). Finally, we found significant positive relationship between product involvement and perceived risk (H1: product involvement ${\rightarrow}$ perceived risk), which suggests that the possibility of complete mediation of perceived risk in the relationship between enduring product involvement and the trust expectation. As a result, we conducted an additional test for the mediation effect by comparing the original model with the revised model without the mediator variable of perceived risk. Indeed, we found that there exists a strong influence of product involvement on the trust expectation (by intentionally eliminating the variable of perceived risk) that was suppressed (i.e., mediated) by the perceived risk in the original model. The Sobel test statistically confirmed the complete mediation effect. Results of this study offer the following key findings. First, enduring product involvement is positively related to perceived risk, implying that the higher a consumer is enduringly involved with a given product, the greater risk he or she is likely to perceive with regards to the online purchase of the product. Second, perceived risk is positively related to trust expectation. A consumer with great risk perceptions concerning the online purchase is likely to buy from a highly trustworthy online merchant, thereby mitigating potential risks. Finally, product involvement was found to have no direct influence on trust expectation, but the relationship between the two constructs was indirect and mediated by the perceived risk. This is perhaps an important theoretical integration of two separate streams of literature on product involvement and perceived risk. The present research also provides useful implications for practitioners as well as academicians. First, one implication for practicing managers in online retail stores is that they should invest in reducing the perceived risk of consumers in order to lower down the trust expectation and thus increasing the consumer's intention to purchase products or services. Second, an academic implication is that perceived risk mediates the relationship between enduring product involvement and trust expectation. Further research is needed to elaborate the theoretical relationships among the constructs under consideration.

• Journal of the Korean Society for Library and Information Science
• /
• v.55 no.4
• /
• pp.5-22
• /
• 2021

This study aimed to understand how people perceive the transition from offline to online classes at universities during the COVID-19 pandemic. To achieve the goal, we collected tweets related to online classes on Twitter and performed sentiment and time series topic analysis. We have the following findings. First, through the sentiment analysis, we found that there were more negative than positive opinions overall, but negative opinions had gradually decreased over time. Through exploring the monthly distribution of sentiment scores of tweets, we found that sentiment scores during the semesters were more widespread than the ones during the vacations. Therefore, more diverse emotions and opinions were showed during the semesters. Second, through time series topic analysis, we identified five main topics of positive tweets that include class environment and equipment, positive emotions, places of taking online classes, language class, and tests and assignments. The four main topics of negative tweets include time (class & break time), tests and assignments, negative emotions, and class environment and equipment. In addition, we examined the trends of public opinions on online classes by investigating the changes in topic composition over time through checking the proportions of representative keywords in each topic. Different from the existing studies of understanding public opinions on online classes, this study attempted to understand the overall opinions from tweet data using sentiment and time series topic analysis. The results of the study can be used to improve the quality of online classes in universities and help universities and instructors to design and offer better online classes.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.33-49
• /
• 2018

The impact of TV Drama success on TV Rating and the channel promotion effectiveness is very high. The cultural and business impact has been also demonstrated through the Korean Wave. Therefore, the early prediction of the blockbuster success of TV Drama is very important from the strategic perspective of the media industry. Previous studies have tried to predict the audience ratings and success of drama based on various methods. However, most of the studies have made simple predictions using intuitive methods such as the main actor and time zone. These studies have limitations in predicting. In this study, we propose a model for predicting the popularity of drama by analyzing the customer's viewing pattern based on various theories. This is not only a theoretical contribution but also has a contribution from the practical point of view that can be used in actual broadcasting companies. In this study, we collected data of 280 TV mini-series dramas, broadcasted over the terrestrial channels for 10 years from 2003 to 2012. From the data, we selected the most highly ranked and the least highly ranked 45 TV drama and analyzed the viewing patterns of them by 11-step. The various assumptions and conditions for modeling are based on existing studies, or by the opinions of actual broadcasters and by data mining techniques. Then, we developed a prediction model by measuring the viewing-time distance (difference) using Euclidean and Correlation method, which is termed in our study similarity (the sum of distance). Through the similarity measure, we predicted the success of dramas from the viewer's initial viewing-time pattern distribution using 1~5 episodes. In order to confirm that the model is shaken according to the measurement method, various distance measurement methods were applied and the model was checked for its dryness. And when the model was established, we could make a more predictive model using a grid search. Furthermore, we classified the viewers who had watched TV drama more than 70% of the total airtime as the "passionate viewer" when a new drama is broadcasted. Then we compared the drama's passionate viewer percentage the most highly ranked and the least highly ranked dramas. So that we can determine the possibility of blockbuster TV mini-series. We find that the initial viewing-time pattern is the key factor for the prediction of blockbuster dramas. From our model, block-buster dramas were correctly classified with the 75.47% accuracy with the initial viewing-time pattern analysis. This paper shows high prediction rate while suggesting audience rating method different from existing ones. Currently, broadcasters rely heavily on some famous actors called so-called star systems, so they are in more severe competition than ever due to rising production costs of broadcasting programs, long-term recession, aggressive investment in comprehensive programming channels and large corporations. Everyone is in a financially difficult situation. The basic revenue model of these broadcasters is advertising, and the execution of advertising is based on audience rating as a basic index. In the drama, there is uncertainty in the drama market that it is difficult to forecast the demand due to the nature of the commodity, while the drama market has a high financial contribution in the success of various contents of the broadcasting company. Therefore, to minimize the risk of failure. Thus, by analyzing the distribution of the first-time viewing time, it can be a practical help to establish a response strategy (organization/ marketing/story change, etc.) of the related company. Also, in this paper, we found that the behavior of the audience is crucial to the success of the program. In this paper, we define TV viewing as a measure of how enthusiastically watching TV is watched. We can predict the success of the program successfully by calculating the loyalty of the customer with the hot blood. This way of calculating loyalty can also be used to calculate loyalty to various platforms. It can also be used for marketing programs such as highlights, script previews, making movies, characters, games, and other marketing projects.

• Journal of the Society of Disaster Information
• /
• v.16 no.4
• /
• pp.813-823
• /
• 2020

Purpose: In order to maximize the stability and productivity of the work through simulation prior to high-risk facilities and high-cost work such as dismantling the facilities inside the reactor, we intend to use digital twin technology that can be closely controlled by simulating the specifications of the actual control equipment. Motion control errors, which can be caused by the time gap between precision control equipment and simulation in applying digital twin technology, can cause hazards such as collisions between hazardous facilities and control equipment. In order to eliminate and control these situations, prior research is needed. Method: Unity 3D is currently the most popular engine used to develop simulations. However, there are control errors that can be caused by time correction within Unity 3D engines. The error is expected in many environments and may vary depending on the development environment, such as system specifications. To demonstrate this, we develop crash simulations using Unity 3D engines, which conduct collision experiments under various conditions, organize and analyze the resulting results, and derive tolerances for precision control equipment based on them. Result: In experiments with collision experiment simulation, the time correction in 1/1000 seconds of an engine internal function call results in a unit-hour distance error in the movement control of the collision objects and the distance error is proportional to the velocity of the collision. Conclusion: Remote decomposition simulators using digital twin technology are considered to require limitations of the speed of movement according to the required precision of the precision control devices in the hardware and software environment and manual control. In addition, the size of modeling data such as system development environment, hardware specifications and simulations imitated control equipment and facilities must also be taken into account, available and acceptable errors of operational control equipment and the speed required of work.

• Korean Journal of Environmental Biology
• /
• v.38 no.4
• /
• pp.634-649
• /
• 2020

Recently, stream longitudinal connectivity has been a topic of investigation due to the frequent disconnections and the impact of aquatic ecosystems caused by the construction of small and medium-sized weirs and various artificial structures (fishways) directly influencing the stream ecosystem health. In this study, the international and domestic research trends of the longitudinal connectivity in aquatic ecosystems were evaluated and the applicability of fish-based longitudinal connectivity models used in developed countries was analyzed. For these purposes, we analyzed the current status of research on longitudinal connectivity and structural problems, fish monitoring methodology, monitoring approaches, longitudinal disconnectivity of fish movement, and biodiversity. In addition, we analyzed the current status and some technical limitations of physical habitat suitability evaluation, ecology-based water flow, eco-hydrological modeling for fish habitat connectivity, and the s/w program development for agent-based model. Numerous references, data, and various reports were examined to identify worldwide longitudinal stream connectivity evaluation models in European and non-European countries. The international approaches to longitudinal connectivity evaluations were categorized into five phases including 1) an approach integrating fish community and artificial structure surveys (two types input variables), 2) field monitoring approaches, 3) a stream geomorphological approach, 4) an artificial structure-based DB analytical approach, and 5) other approaches. the overall evaluation of survey methodologies and applicability for longitudinal stream connectivity suggested that the ICE model (Information sur la Continuite Ecologique) and the ICF model (Index de Connectivitat Fluvial), widely used in European countries, were appropriate for the application of longitudinal connectivity evaluations in Korean streams.

• Knowledge Management Research
• /
• v.22 no.2
• /
• pp.119-144
• /
• 2021

Recently, as competition in the market evolves from the competition among companies to the competition among their supply chains, companies are struggling to enhance their supply chain management (hereinafter SCM). In particular, as blockchain technology with various technical advantages is combined with SCM, a lot of domestic manufacturing and distribution companies are considering the adoption of blockchain-oriented SCM (BOSCM) services today. Thus, it is an important academic topic to examine the factors affecting the use of blockchain-oriented SCM. However, most prior studies on blockchain and SCMs have designed their research models based on Technology Acceptance Model (TAM) or the Unified Theory of Acceptance and Use of Technology (UTAUT), which are suitable for explaining individual's acceptance of information technology rather than companies'. Under this background, this study presents a novel model of blockchain-oriented SCM acceptance model based on the Technology-Organization-Environment (TOE) framework to consider companies as the unit of analysis. In addition, Value-based Adoption Model (VAM) is applied to the research model in order to consider the benefits and the sacrifices caused by a new information system comprehensively. To validate the proposed research model, a survey of 126 companies were collected. Among them, by applying PLS-SEM (Partial Least Squares Structural Equation Modeling) with data of 122 companies, the research model was verified. As a result, 'business innovation', 'tracking and tracing', 'security enhancement' and 'cost' from technology viewpoint are found to significantly affect 'perceived value', which in turn affects 'intention to use blockchain-oriented SCM'. Also, 'organization readiness' is found to affect 'intention to use' with statistical significance. However, it is found that 'complexity' and 'regulation environment' have little impact on 'perceived value' and 'intention to use', respectively. It is expected that the findings of this study contribute to preparing practical and policy alternatives for facilitating blockchain-oriented SCM adoption in Korean firms.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.1
• /
• pp.55-67
• /
• 2021

Hornbeams (Carpinus spp.), which are widely distributed in South Korea, are recognized as one of the most abundant species at climax stage in the temperate forests. Although the distribution and vegetation structure of the C. laxiflora community have been reported, little ecological information of C. tschonoskii is available. Little effort was made to examine the distribution shift of these species under the future climate conditions. This study was conducted to predict potential shifts in the distribution of C. laxiflora and C. tschonoskii in 2050s and 2090s under the two sets of climate change scenarios, RCP4.5 and RCP8.5. The MaxEnt model was used to predict the spatial distribution of two species using the occurrence data derived from the 6th National Forest Inventory data as well as climate and topography data. It was found that the main factors for the distribution of C. laxiflora were elevation, temperature seasonality, and mean annual precipitation. The distribution of C. tschonoskii, was influenced by temperature seasonality, mean annual precipitation, and mean diurnal rang. It was projected that the total habitat area of the C. laxiflora could increase by 1.05% and 1.11% under RCP 4.5 and RCP 8.5 scenarios, respectively. It was also predicted that the distributional area of C. tschonoskii could expand under the future climate conditions. These results highlighted that the climate change would have considerable impact on the spatial distribution of C. laxiflora and C. tschonoskii. These also suggested that ecological information derived from climate change impact assessment study can be used to develop proper forest management practices in response to climate change.

• Korean Journal of Environment and Ecology
• /
• v.35 no.1
• /
• pp.24-36
• /
• 2021

Countries around the world, including the Republic of Korea, are participating in efforts to preserve biodiversity. Concerning species, in particular, studies that aim to find potential habitats and establish conservation plans by conducting habitat suitability analysis for specific species are actively ongoing. However, few studies on mid- to long-term changes in suitable habitat areas are based on accumulated information. Therefore, this study aimed to analyze the time-series changes in the habitat suitable area and examine the otters' changing pattern (Lutra lutra) designated as Level 1 endangered wildlife in Gangwon-do. The time-series change analysis used the data on otter species' presence points from the 2nd, 3rd, and 4th national natural environment surveys conducted for about 20 years. Moreover, it utilized the land cover map consistent with the survey period to create environmental variables to reflect each survey period's habitat environment. The suitable habitat area analysis used the MaxEnt model that can run based only on the species presence information, and it has been proven to be reliable by previous studies. The study derived the habitat suitability map for otters in each survey period, and it showed a tendency that habitats were distributed around rivers. Comparing the response curves of the environmental variables derived from the modeling identified the characteristics of the habitat favored by otters. The examination of habitats' change by survey period showed that the habitats based on the 2nd National Natural Environment Survey had the widest distribution. The habitats of the 3rd and 4th surveys showed a tendency of decrease in area. Moreover, the study aggregated the analysis results of the three survey periods and analyzed and categorized the habitat's changing pattern. The type of change proposed different conservation plans, such as field surveys, monitoring, protected area establishment, and restoration plan. This study is significant because it produced a comprehensive analysis map that showed the time-series changes of the location and area of the otter habitat and proposed a conservation plan that is necessary according to the type of habitat change by region. We believe that the method proposed in this study and its results can be used as reference data for establishing a habitat conservation and management plan in the future.