• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.93-108
• /
• 2014

To support business decision making, interests and efforts to analyze and use transaction data in different perspectives are increasing. Such efforts are not only limited to customer management or marketing, but also used for monitoring and detecting fraud transactions. Fraud transactions are evolving into various patterns by taking advantage of information technology. To reflect the evolution of fraud transactions, there are many efforts on fraud detection methods and advanced application systems in order to improve the accuracy and ease of fraud detection. As a case of fraud detection, this study aims to provide effective fraud detection methods for auction exception agricultural products in the largest Korean agricultural wholesale market. Auction exception products policy exists to complement auction-based trades in agricultural wholesale market. That is, most trades on agricultural products are performed by auction; however, specific products are assigned as auction exception products when total volumes of products are relatively small, the number of wholesalers is small, or there are difficulties for wholesalers to purchase the products. However, auction exception products policy makes several problems on fairness and transparency of transaction, which requires help of fraud detection. In this study, to generate fraud detection rules, real huge agricultural products trade transaction data from 2008 to 2010 in the market are analyzed, which increase more than 1 million transactions and 1 billion US dollar in transaction volume. Agricultural transaction data has unique characteristics such as frequent changes in supply volumes and turbulent time-dependent changes in price. Since this was the first trial to identify fraud transactions in this domain, there was no training data set for supervised learning. So, fraud detection rules are generated using outlier detection approach. We assume that outlier transactions have more possibility of fraud transactions than normal transactions. The outlier transactions are identified to compare daily average unit price, weekly average unit price, and quarterly average unit price of product items. Also quarterly averages unit price of product items of the specific wholesalers are used to identify outlier transactions. The reliability of generated fraud detection rules are confirmed by domain experts. To determine whether a transaction is fraudulent or not, normal distribution and normalized Z-value concept are applied. That is, a unit price of a transaction is transformed to Z-value to calculate the occurrence probability when we approximate the distribution of unit prices to normal distribution. The modified Z-value of the unit price in the transaction is used rather than using the original Z-value of it. The reason is that in the case of auction exception agricultural products, Z-values are influenced by outlier fraud transactions themselves because the number of wholesalers is small. The modified Z-values are called Self-Eliminated Z-scores because they are calculated excluding the unit price of the specific transaction which is subject to check whether it is fraud transaction or not. To show the usefulness of the proposed approach, a prototype of fraud transaction detection system is developed using Delphi. The system consists of five main menus and related submenus. First functionalities of the system is to import transaction databases. Next important functions are to set up fraud detection parameters. By changing fraud detection parameters, system users can control the number of potential fraud transactions. Execution functions provide fraud detection results which are found based on fraud detection parameters. The potential fraud transactions can be viewed on screen or exported as files. The study is an initial trial to identify fraud transactions in Auction Exception Agricultural Products. There are still many remained research topics of the issue. First, the scope of analysis data was limited due to the availability of data. It is necessary to include more data on transactions, wholesalers, and producers to detect fraud transactions more accurately. Next, we need to extend the scope of fraud transaction detection to fishery products. Also there are many possibilities to apply different data mining techniques for fraud detection. For example, time series approach is a potential technique to apply the problem. Even though outlier transactions are detected based on unit prices of transactions, however it is possible to derive fraud detection rules based on transaction volumes.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.93-111
• /
• 2013

As Internet and information technology (IT) continues to develop and evolve, the issue of big data has emerged at the foreground of scholarly and industrial attention. Big data is generally defined as data that exceed the range that can be collected, stored, managed and analyzed by existing conventional information systems and it also refers to the new technologies designed to effectively extract values from such data. With the widespread dissemination of IT systems, continual efforts have been made in various fields of industry such as R&D, manufacturing, and finance to collect and analyze immense quantities of data in order to extract meaningful information and to use this information to solve various problems. Since IT has converged with various industries in many aspects, digital data are now being generated at a remarkably accelerating rate while developments in state-of-the-art technology have led to continual enhancements in system performance. The types of big data that are currently receiving the most attention include information available within companies, such as information on consumer characteristics, information on purchase records, logistics information and log information indicating the usage of products and services by consumers, as well as information accumulated outside companies, such as information on the web search traffic of online users, social network information, and patent information. Among these various types of big data, web searches performed by online users constitute one of the most effective and important sources of information for marketing purposes because consumers search for information on the internet in order to make efficient and rational choices. Recently, Google has provided public access to its information on the web search traffic of online users through a service named Google Trends. Research that uses this web search traffic information to analyze the information search behavior of online users is now receiving much attention in academia and in fields of industry. Studies using web search traffic information can be broadly classified into two fields. The first field consists of empirical demonstrations that show how web search information can be used to forecast social phenomena, the purchasing power of consumers, the outcomes of political elections, etc. The other field focuses on using web search traffic information to observe consumer behavior, identifying the attributes of a product that consumers regard as important or tracking changes on consumers' expectations, for example, but relatively less research has been completed in this field. In particular, to the extent of our knowledge, hardly any studies related to brands have yet attempted to use web search traffic information to analyze the factors that influence consumers' purchasing activities. This study aims to demonstrate that consumers' web search traffic information can be used to derive the relations among brands and the relations between an individual brand and product attributes. When consumers input their search words on the web, they may use a single keyword for the search, but they also often input multiple keywords to seek related information (this is referred to as simultaneous searching). A consumer performs a simultaneous search either to simultaneously compare two product brands to obtain information on their similarities and differences, or to acquire more in-depth information about a specific attribute in a specific brand. Web search traffic information shows that the quantity of simultaneous searches using certain keywords increases when the relation is closer in the consumer's mind and it will be possible to derive the relations between each of the keywords by collecting this relational data and subjecting it to network analysis. Accordingly, this study proposes a method of analyzing how brands are positioned by consumers and what relationships exist between product attributes and an individual brand, using simultaneous search traffic information. It also presents case studies demonstrating the actual application of this method, with a focus on tablets, belonging to innovative product groups.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.141-154
• /
• 2019

Rapid growth of internet technology and social media is progressing. Data mining technology has evolved to enable unstructured document representations in a variety of applications. Sentiment analysis is an important technology that can distinguish poor or high-quality content through text data of products, and it has proliferated during text mining. Sentiment analysis mainly analyzes people's opinions in text data by assigning predefined data categories as positive and negative. This has been studied in various directions in terms of accuracy from simple rule-based to dictionary-based approaches using predefined labels. In fact, sentiment analysis is one of the most active researches in natural language processing and is widely studied in text mining. When real online reviews aren't available for others, it's not only easy to openly collect information, but it also affects your business. In marketing, real-world information from customers is gathered on websites, not surveys. Depending on whether the website's posts are positive or negative, the customer response is reflected in the sales and tries to identify the information. However, many reviews on a website are not always good, and difficult to identify. The earlier studies in this research area used the reviews data of the Amazon.com shopping mal, but the research data used in the recent studies uses the data for stock market trends, blogs, news articles, weather forecasts, IMDB, and facebook etc. However, the lack of accuracy is recognized because sentiment calculations are changed according to the subject, paragraph, sentiment lexicon direction, and sentence strength. This study aims to classify the polarity analysis of sentiment analysis into positive and negative categories and increase the prediction accuracy of the polarity analysis using the pretrained IMDB review data set. First, the text classification algorithm related to sentiment analysis adopts the popular machine learning algorithms such as NB (naive bayes), SVM (support vector machines), XGboost, RF (random forests), and Gradient Boost as comparative models. Second, deep learning has demonstrated discriminative features that can extract complex features of data. Representative algorithms are CNN (convolution neural networks), RNN (recurrent neural networks), LSTM (long-short term memory). CNN can be used similarly to BoW when processing a sentence in vector format, but does not consider sequential data attributes. RNN can handle well in order because it takes into account the time information of the data, but there is a long-term dependency on memory. To solve the problem of long-term dependence, LSTM is used. For the comparison, CNN and LSTM were chosen as simple deep learning models. In addition to classical machine learning algorithms, CNN, LSTM, and the integrated models were analyzed. Although there are many parameters for the algorithms, we examined the relationship between numerical value and precision to find the optimal combination. And, we tried to figure out how the models work well for sentiment analysis and how these models work. This study proposes integrated CNN and LSTM algorithms to extract the positive and negative features of text analysis. The reasons for mixing these two algorithms are as follows. CNN can extract features for the classification automatically by applying convolution layer and massively parallel processing. LSTM is not capable of highly parallel processing. Like faucets, the LSTM has input, output, and forget gates that can be moved and controlled at a desired time. These gates have the advantage of placing memory blocks on hidden nodes. The memory block of the LSTM may not store all the data, but it can solve the CNN's long-term dependency problem. Furthermore, when LSTM is used in CNN's pooling layer, it has an end-to-end structure, so that spatial and temporal features can be designed simultaneously. In combination with CNN-LSTM, 90.33% accuracy was measured. This is slower than CNN, but faster than LSTM. The presented model was more accurate than other models. In addition, each word embedding layer can be improved when training the kernel step by step. CNN-LSTM can improve the weakness of each model, and there is an advantage of improving the learning by layer using the end-to-end structure of LSTM. Based on these reasons, this study tries to enhance the classification accuracy of movie reviews using the integrated CNN-LSTM model.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.7
• /
• pp.554-564
• /
• 2017

The purpose of this study is to assist farmers in determining the optimal time for the shipment of stored apples by investigating the market trends, storage status and release dates of low-temperature stored apples. We surveyed 300 apple cultivation farms in Daegu, Gyeongbuk Province, which is the main producer of apples, and examined the cultivars, cultivation areas, storage conditions, and shipment status of apples. The main results are as follows: the proportion of apples cultivatedat different ripening times was surveyed. According to the results, the proportions of early, middle and late varieties were 78.3%, 63.7% and 96.0%, respectively. Also, 48.7% of the farm households surveyed had cold storage facilities. The average storage cost per apple box(15kg) was 978.3 won for self-storage and 1,771.8 won for consignment storage. For the six(6) months between November and April, the proportion of shipped apples was 91.6% of the total stored apples. The (average total?)annual apple shipment, including apples stored in general storage warehouses, was 744.4 boxes. The (average total?) annual shipment of cold storage apples was 616 boxes. The stored apples were mainly shipped to 'wholesale markets', which have the highest sales share, followed by 'production site collectors' and then 'supermarkets'. The most common shipping method of the apples was by general trucks, followed by low-temperature trucks, and finally by delivery services. The analysis of the factors influencing the decision to release apples by period showed that it was affected by the storage cost, loss rate, and customary shipping in the off-season(from May to August). On the other hand, in the general release season(from November to April), the statistically significant decision factors for the release of apples were the future expected price, storage cost and decision of the leading farmer groups. For farmers with a high share of general shipment, the deciding factors for the release of apples were the future expected price, storage cost, high income expectation, and decision by leading farmers.

• Archives of design research
• /
• v.19 no.4 s.66
• /
• pp.133-144
• /
• 2006

According to the latest report by the Customer Protection Board, those who moved into newly constructed buildings are complaining about unidentified pains, asking for more careful selection of constructive materials for prevention of such potential problems. It is internationally recognized today that ecological materials can serve a significant factor for users' health, environmental protection and better industrial competitiveness. This study examined eco-design aspects of each interior material through web site search, in order to help customers learn about and capitalize on eco materials in a proper manner. As a result, 1. It turned out that the domestic industry are giving an impetus to releasing new eco items focusing on lower VOCs emission or addition of functional components as part of the marketing strategy. However, it is recommended that company understand significance of life cycle, and produce eco-concept materials. 2. The reliable standard for choosing the domestic material is EL, HB, GR marks. It is desirable to enhance recycling technologies and expand the sustainable consumption. customer class, since many recycled items are not developed. 3. The sourcing is a vulnerable part in terms of the concept of being environment-friendly material. Therefore, many manufacturers should design the easy knock-down products and produce the good items using recycled materials instead of new raw materials. Also solutions for making the energy from burning material should be studied. 4. The guidebook or manual with correct information about eco-materials is required to promote production and consumption with sustainable concept. 5. Many manufacturers are emphasizing ecological materials for customers, but some of them intended to disrupt customers' proper selection by promoting even unverified items to be environment-friendly.

• Cartoon and Animation Studies
• /
• s.43
• /
• pp.151-184
• /
• 2016

In order to develop the animation industry, it is essential to encourage other related areas because all related industries can create synergy effects through exchanging their business. The magazine industry dealing with animation is one of them since the animation magazine plays an critical role in providing information and knowledge as well as analyzing market and industry from the practical viewpoint. But, there is only one magazine working in Korea, and it has never been researched so far even though over 20 years has passed since its first publication in 1995. It is Animatoon that is published by the company of Akom Production Co. who produced animation from the mid-1980s and Nelson Shin, the CEO of Akom, has worked as the Chief Editor. This research deals with Animatoon from the first issue till vol. 115 which was published in 2015, and tries to explore the characteristics. The result is as follows. First, Animatoon provides items to understand every article easily. Second, it provides original English articles written by foreign correspondents. Third, it provides different type of articles such as terminology explanation, production pipeline related knowledge, information about newly-released animation DVDs and so on. In addition, it is found out that Animatoon has small amount of advertisements. These characteristics shows that Animatoon helps subscribers to judge the contents of articles easier, tries to focus on the global trend, and provides basic and critical information. Therefore it can be said that Animatoon has enough features to be judged as the specialized magazine. First, Animatoon has its own specialized area, which is animation. Second, considering the type of articles, Animatoon tries to have all the parties concerned as its subscribers. Although, the amount of ads in Animatoon is small, only animation related ads are run through the whole issues.

• Economic and Environmental Geology
• /
• v.53 no.4
• /
• pp.441-477
• /
• 2020

There have been raised other environmental issues related to remediated soils piled up in numerous carry-out processing facilities because a considerable quantity of them have been produced every year, but most of them have not been relevantly reused or recycled. Thus, this article reports the trend of researches on the development of techniques to restore the quality of remediated soils to activate their reuse and recycling. Firstly, the tendency of change in soil properties through remediation processes was looked over, and then the degradation of soil quality was characterized according to the type of remediation processes. Besides, the direction of policy to promote the reuse and recycling of remediated soils was introduced, and finally, the future works needed were suggested. This article was prepared based on the results of the survey of domestic and foreign literature. A number of literature were reviewed to scrutinize the change of soil properties due to remediation processes and diverse techniques for the amendment and restoration of remediated soils. Furthermore, the policies related to the reuse and recycling of remediated soils were arranged with the reference of the first and second versions of the Soil Conservation Master Plan of Korea. The literature survey focused on three kinds of remediation technologies, such as land farming, soil washing, and thermal desorption, which were most frequently used so far in Korea. The results indicate that the tendency of change in soil properties was significantly different depending on the type of remediation processes applied, and the degradation characteristics of soil quality were also totally different between them. The soil amendment and restoration can be categorized as three techniques depending on the type of substances used, such as inorganic, organic, and biological ones. Diverse individual materials have been used, and the soil properties improved or enhanced were dependent on the type of specific materials utilized. However, few studies on the restoration of soil qualities degraded during the remediation processes have not been carried out so far. The second Soil Conservation Master Plan states the quality certification and target management system of remediated soils, and it is expected that their reuse and recycling will be facilitated hereafter. With the consideration of the type of remediation processes implemented and public utility, the restoration technologies of remediated soils should be developed for the vitalization of their reuse and recycling. Besides, practical and specific measures should be taken to support the policy specified in the second Soil Conservation Master Plan and to promote reuse/recycling of remediated soils.

• Tuberculosis and Respiratory Diseases
• /
• v.45 no.4
• /
• pp.766-775
• /
• 1998

Background : The prognosis of patients with lung cancer is still poor. Lung cancer exhibits a variable clinical outcome, even in those patients with same stage. Numerous reports suggest that oncogene expression might playa role in explaining the variability of response and survival But many of these reports are still under debate. So we studied the clinical relevance of oncogene expression in Korean lung cancer patients. Immunohistochemistry of p53, erbB-2, CEA expression was performed. Method: From March, 1992 until March, 1997, 120 patients with lung cancer were reviewed. p53, erbB-2, and CEA expression were detected on paraffin-embedded tumor blocks with the use of monoclonal antibodies. The survival and response has correlated with the expressibility of p53, erbB-2, and CEA oncoprotein Results: Overall, the expression rates of p53, erbB-2, and CEA were 33.7%, 59.3%, and 32.6% respectively. Expression rates were not correlated to cell type or stage. Compared with response to chemotherapy, no correlation was found. The expression of p53, erbB-2, or CEA was not correlated with 2-year survival. With simultaneous applications of p53, erbB-2, and CEA, patients with 2 or more expressions also did not show poor response to chemotherapy. Conclusion: We conclude the p53, erbB-2, and CEA expression are clinically less useful in predicting response to chemotherapy or survival.

• The Korean Journal of Air & Space Law and Policy
• /
• v.32 no.2
• /
• pp.3-31
• /
• 2017

On 12 October 2017, the English Royal Courts of Justice delivered its decision about air carrier's compensation liability for the flight delay. In the cases the passengers suffered delays at a connecting point and, consequently, on arrival at their final destination. They claimed compensation under Regulation 261/2004 (the "Regulation"), as applied by the Court of Justice of the European Union (the "CJEU") in Sturgeon v. Condor [2009]. The principal issues were whether delays suffered by the passengers during the second leg of their respective journeys were compensable under the Regulation, whether there was jurisdiction under the Regulation and whether the right to compensation under the Regulation is, insofar as non-Community air carriers are concerned, excluded by virtue of the exclusive liability regime established under the Montreal Convention 1999. The passengers, the plaintiff, argued that the relevant delay was not that on flight 1 but that suffered at the "final destination". They maintained that there was no exercise by the EU of extraterritorial jurisdiction as the delay on flight 2 was merely relevant to the calculation of the amount of compensation due under the Regulation. The air carrier, the defendant, however argued that the only relevant flights for the purpose of calculating any delay were the first flights (flights 1) out of EU airspace, as only these flights fell within the scope of the Regulation; the connecting flights (flights 2) were not relevant since they were performed entirely outside of the EU by a non-Community carrier. Regarding the issue of what counts as a delay under the Regulation, the CJEU held previously on another precedents that the operating carrier's liability to pay compensation depends on the passenger's delay in arriving at the "final destination". It held that where the air carrier provides a passenger with more than one directly connecting flight to enable him to arrive at their destination, the flights should be taken together for the purpose of assessing whether there has been three hours' or more delay on arrival; and that in case of directly connecting flights, the final destination is the place at which the passenger is scheduled to arrive at the end of the last component flight. In addition, the Court confirmed that the Regulation applied to flights operated by non-Community carriers out of EU airspace even if flight 1 or flight 2 lands outside the EU, since the Regulation does not require that a flight must land in the EU. Accordingly, the passengers' appeal from the lower Court was allowed, while that of air carrier was dismissed. The Court has come down firmly on the side of the passengers in this legal debate. However, this result is not a great surprise considering the recent trends of EU member states' court decisions in the fields of air transport and consumer protection. The main goal of this article is to review the Court's decision and to search historical trend of air consumer protection especially in EU area.

• Journal of Gifted/Talented Education
• /
• v.16 no.1
• /
• pp.21-42
• /
• 2006

The object of this research is to analyze the contents and amount of articles on gifted education in major daily newspapers dated January 1990 to December 2003, and to review the trend of social perception of gifted education with the passage of time. Following are the research question : 1. How many articles belonging to the same category appeared in the newspapers within the period of time covered by the study? 2. What kinds of articles appeared in the newspapers within the period of time covered by the study? To arrive at the answers to the problems mentioned above, 714 articles on gifted education. The period from 1990 to 2003 were divided into time frames of 5 years to facilitate the analysis of social consciousness regarding gifted education before and after the enforcement of the Early School Entering Law in 1995 and the Law for Promotion of Gifted Education in 2000. The researcher defined Period I as the years from 1990 to 1994, Period II from 1995 to 1999, and Period III from 2000 to 2003. The articles were classified by content which were significance and trend of gilled education, current policies on gifted education, information on gifted education, and social environment of gifted education. The results of the analysis are as follows: (1) The articles from 1990 to 2003 totalled 714. 130 articles were found within Period I, 213 within Period II, and 371 within Period III. Since the year 2000, when the Law for Promotion of gifted education was enforced, the amount of articles considerably increased. The articles on the trend of gifted education numbered 42 within Period I, 49 within Period II, and 81 within Period III, showing a huge increase in the last period. The articles on current policies numbered 56 within Period I, 77 within Period II, and 143 within Period III, numbering the most in the last period. This means that, even before the Law for Promotion of gifted education was enforced, there has been much interest in and discussion of the appropriate educational system for gifted children in preparation for the legal and institutional foundation of such system. Since the enforcement of the law, many institutions were established and the problem became an important social issue. The articles that most frequently appeared were about current policies on and status of gifted education. This category showed the largest numbers through all the three periods and on all the subjects. This subject represented 43.1% of the articles on gifted children within Period I, 36.2% within Period II, and 38.6% within Period III. As to the significance and trend of gifted education, this subject showed a decrease from 32.3% within Period I, 23% within Period II, and 21.8% within Period III. However, the articles in the category of information on gifted education gradually increased from they represented 5.4% of the articles on brilliant children within Period I, 7.5% within Period II, and 8.4% within Period III. The social environment articles showed an increase from Period I to Period II-- from 19.2% to 33.3%, but it went down to 31.3% within Period III. (2) As to articles on the trend of gifted education, there were many such articles found, mainly on researches and trends in other countries. As greater importance is accorded to gifted children and as the recognition of the necessity of providing specific education for them grows, more related studies are conducted and people try to adopt new trends from other countries. For the articles on the current policies of gifted education, most of them were about institutions. This means that many educational institutions have been established since the Law for Promotion of Gifted Education was enforced. Informative articles on gilled education were mostly about distinctive features of gifted children and how to tell who the brilliant children are. This fact shows the importance of identifying gifted children in order to educate them systemically and effectively.