• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.21 no.1
• /
• pp.11-17
• /
• 2015

The increase of international and domestic trade according to global industrialization and economic growth has raised the national logistic cost in connection with physical distribution of articles. In order to reduce these costs and rise up national industrial competitiveness, Korea has also tried to improve the efficiency of logistics with various methods as advanced countries did. Especially, Korea government has decided standard dimension of pallets with T11 ($1100{\times}1100mm$) on the basis of unit load system in early 2000s, and certification program for logistics equipments has been operated to keep up the compatibility for the equipments and packaging with modulation of T11. Consequently, this certification program has contributed to extend standardization for logistics and to grow up 3 party logistics, but compared with advanced countries, the rate of national logistics cost to GDP (gross domestic product) still shows about 3% gap as demands for certification have been decreased in the recent. In this study, therefore, we proposed the development of logistics certification system based on social needs as a policy device to activate logistic industry as well as improve the efficiency of national logistics after we had analyzed all of certification programs for logistics being run in Korea. Namely, the first is the development of certification project for Northeast Asia's logistics corresponding to necessity for applying returnable transport system according to increasing the amount of trade between Northeast Asia's countries. The second is the development of certification project for safe transportation of packaging corresponding to costumer's needs for safe transit according to the growth of electronic commerce and the increase of global distribution.

• Journal of Internet of Things and Convergence
• /
• v.7 no.1
• /
• pp.79-89
• /
• 2021

This study attempted to identify the information gap about Internet of Things (IoT) devices and services in the era of digital transformation. To this end, we analyzed differences in perception of predicting future issues about IoT devices and services, and analyzed differences in the need for digital technology and help in life according to perceptions and experience of using IoT devices and services. Also, the level of education and demand for education were analyzed. A survey was conducted from February 15th to March 7th, 2021 for residents in Gwangju Metropolitan City and Jeollanam-do, and 232 respondents responded. Analysis was performed using SPSS 21.0, and all statistical values were presented as average values. The results of the study are as follows. First, the future issues of the intelligent information society according to the recognition of the intelligent information society, the help of life provided by artificial intelligence devices and services, and the need for intelligent information technology were presented. Second, the difference in Life help provided by artificial intelligence according to the recognition and use experience of artificial intelligence devices was presented. Third, the difference in life help provided by artificial intelligence according to the recognition and use experience of artificial intelligence service was presented. Fourth, the difference in necessity according to artificial intelligence technology recognition and use experience was presented. Fifth, the educational level and educational demand of the intelligent information society were investigated and presented. Through the results of this study, a suggestion for resolving the information gap in the era of digital transformation was suggested.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.97-117
• /
• 2020

Product evaluation criteria is an indicator describing attributes or values of products, which enable users or manufacturers measure and understand the products. When companies analyze their products or compare them with competitors, appropriate criteria must be selected for objective evaluation. The criteria should show the features of products that consumers considered when they purchased, used and evaluated the products. However, current evaluation criteria do not reflect different consumers' opinion from product to product. Previous studies tried to used online reviews from e-commerce sites that reflect consumer opinions to extract the features and topics of products and use them as evaluation criteria. However, there is still a limit that they produce irrelevant criteria to products due to extracted or improper words are not refined. To overcome this limitation, this research suggests LDA-k-NN model which extracts possible criteria words from online reviews by using LDA and refines them with k-nearest neighbor. Proposed approach starts with preparation phase, which is constructed with 6 steps. At first, it collects review data from e-commerce websites. Most e-commerce websites classify their selling items by high-level, middle-level, and low-level categories. Review data for preparation phase are gathered from each middle-level category and collapsed later, which is to present single high-level category. Next, nouns, adjectives, adverbs, and verbs are extracted from reviews by getting part of speech information using morpheme analysis module. After preprocessing, words per each topic from review are shown with LDA and only nouns in topic words are chosen as potential words for criteria. Then, words are tagged based on possibility of criteria for each middle-level category. Next, every tagged word is vectorized by pre-trained word embedding model. Finally, k-nearest neighbor case-based approach is used to classify each word with tags. After setting up preparation phase, criteria extraction phase is conducted with low-level categories. This phase starts with crawling reviews in the corresponding low-level category. Same preprocessing as preparation phase is conducted using morpheme analysis module and LDA. Possible criteria words are extracted by getting nouns from the data and vectorized by pre-trained word embedding model. Finally, evaluation criteria are extracted by refining possible criteria words using k-nearest neighbor approach and reference proportion of each word in the words set. To evaluate the performance of the proposed model, an experiment was conducted with review on '11st', one of the biggest e-commerce companies in Korea. Review data were from 'Electronics/Digital' section, one of high-level categories in 11st. For performance evaluation of suggested model, three other models were used for comparing with the suggested model; actual criteria of 11st, a model that extracts nouns by morpheme analysis module and refines them according to word frequency, and a model that extracts nouns from LDA topics and refines them by word frequency. The performance evaluation was set to predict evaluation criteria of 10 low-level categories with the suggested model and 3 models above. Criteria words extracted from each model were combined into a single words set and it was used for survey questionnaires. In the survey, respondents chose every item they consider as appropriate criteria for each category. Each model got its score when chosen words were extracted from that model. The suggested model had higher scores than other models in 8 out of 10 low-level categories. By conducting paired t-tests on scores of each model, we confirmed that the suggested model shows better performance in 26 tests out of 30. In addition, the suggested model was the best model in terms of accuracy. This research proposes evaluation criteria extracting method that combines topic extraction using LDA and refinement with k-nearest neighbor approach. This method overcomes the limits of previous dictionary-based models and frequency-based refinement models. This study can contribute to improve review analysis for deriving business insights in e-commerce market.

• Journal of Korea Spatial Information System Society
• /
• v.1 no.2 s.2
• /
• pp.63-80
• /
• 1999

This study presents NGDM(National Geospatial Information Distribution Model) in order to effectively utilize and differently apply geospatial information which is important in the dispersion of GIS. In order to establish the NGDM, this study draws the guideline of NGDM in Korea by analyzing its present condition of domestic and foreign geospatial information distribution. It also investigates some major factors forming the infrastructure of NGDM in regulative, technical, physical, and social aspects. Based on these factors, this study presents a three-staged NGDM that is applicable in Korea. The NGDM consists of four components that are the consumer, supplier, gateway for the clearinghouse and the clearinghouse of the geospatial information. According to the management form of geospatial information, the types of NGDM are classified as the concentration type, the distribution type, and compound type. Also, this study explains the mutual relationship between the NGDM's components and suggests a three-staged NGDM of planting, growth, and maturity period considering comparison results of classified models and development direction of regulation, protocol, communication network, electronic commerce, and etc.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.139-155
• /
• 2016

The purpose of this study is to find the research identity of the Korea Intelligent Information Systems Society through the profiling methods and co-word analysis in the most recent three-year('2014~'2016) study to collect keyword. In order to understand the research identity for intelligence information system, we need that the relative position of the study will be to compare identity by collecting keyword and research methodology of The korea Society of Management Information Systems and Korea Association of Information Systems, as well as Korea Intelligent Information Systems Society for the similar. Also, Korea Intelligent Information Systems Society is focusing on the four research areas such as artificial intelligence/data mining, Intelligent Internet, knowledge management and optimization techniques. So, we analyze research trends with a representative journals for the focusing on the four research areas. A journal of the data-related will be investigated with the keyword and research methodology in Korean Society for Big Data Service and the Korean Journal of Big Data. Through this research, we will find to research trends with research keyword in recent years and compare against the study methodology and analysis tools. Finally, it is possible to know the position and orientation of the current research trends in Korea Intelligent Information Systems Society. As a result, this study revealed a study area that Korea Intelligent Information Systems Society only be pursued through a unique reveal its legitimacy and identity. So, this research can suggest future research areas to intelligent information systems specifically. Furthermore, we will predict convergence possibility of the similar research areas and Korea Intelligent Information Systems Society in overall ecosystem perspectives.

• Journal of Internet of Things and Convergence
• /
• v.7 no.4
• /
• pp.85-94
• /
• 2021

This study verified what differences in screen golf content characteristics, intention to reuse, customer satisfaction and economic value experienced by consumers according to the image feeling, expression method, and image color provided by screen golf graphic content. In addition, the purpose of this study was to analyze what kind of influence the content characteristics of screen golf have on the economic value and what kind of influence the intention to reuse and customer satisfaction have in this process. From September 1, 2021 to September 30, 2021, a survey of 225 copies of consumers using the screen golf course was conducted. For data processing, frequency analysis, factor analysis, reliability analysis, cluster analysis, chi-square analysis and 3-step mediated regression analysis were performed. The research results are as follows. First, the preferred image feeling showed a high level of clean and sophisticated feeling and the preferred expression method showed a high realistic image. In addition, the preferred image color showed a high level of green color. Second, there were differences in competitiveness, ease of use, sense of solidarity and realism according to the degree of consideration of graphic content and differences in consumer's intention to reuse, customer satisfaction, and economic value. Third, in the relationship between screen golf content characteristics and economic value, customer satisfaction and re-use intention had a mediating effect. Through this study, by providing basic data to derive the graphic design model of screen golf, the operating entity suggested a way to improve economic benefits and tried to contribute to the growth of the screen golf industry.

• Journal of Internet of Things and Convergence
• /
• v.8 no.3
• /
• pp.1-10
• /
• 2022

The purpose of this study was to investigate how the characteristics of mobile-based financial platforms have an impact on the intention to use loan service users. In addition, it was attempted to investigate whether usefulness and ease of use had a mediating effect in the relationship between each characteristic of the mobile financial platform on the intention to use the loan service. Data collection was conducted from March 1 to April 30, 2022, and 200 people participated in the study. Analysis methods were frequency analysis, exploratory factor analysis, reliability analysis, correlation analysis, hierarchical multiple regression analysis, and three-step mediation regression analysis. The research results are as follows. First, the influence of user factors, technical factors, and environmental factors of a financial platform on the intention to use a mobile loan service was found to be ubiquity in user factors, reliability in technical factors, and facilitation conditions in environmental factors. Second, in the relationship between convenience and intention to use user factors, usefulness had a completely mediating effect. Third, in the relationship between reliability of technical factors and intention to use, usefulness showed a partial mediating effect. Fourth, in the relationship between the social impact of environmental factors and facilitation conditions and intention to use, the usefulness showed a partial mediating effect. Fifth, ease of use showed a completely mediating effect in the relationship between convenience and intention of use of user factors. Sixth, in the relationship between reliability of technical factors and intention to use, ease of use showed a partial mediating effect. Seventh, in the relationship between the social impact of environmental factors and intention to use, ease of use showed a partial mediating effect, and in the relationship between facilitation conditions and intention to use, ease of use showed a fully mediating effect. Through this study, we tried to present basic data on the determinants of the user's acceptable intention to use the mobile loan service.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.29-56
• /
• 2021

Recently, various types of products have been launched with the rapid growth of the e-commerce market. As a result, many users face information overload problems, which is time-consuming in the purchasing decision-making process. Therefore, the importance of a personalized recommendation service that can provide customized products and services to users is emerging. For example, global companies such as Netflix, Amazon, and Google have introduced personalized recommendation services to support users' purchasing decisions. Accordingly, the user's information search cost can reduce which can positively affect the company's sales increase. The existing personalized recommendation service research applied Collaborative Filtering (CF) technique predicts user preference mainly use quantified information. However, the recommendation performance may have decreased if only use quantitative information. To improve the problems of such existing studies, many studies using reviews to enhance recommendation performance. However, reviews contain factors that hinder purchasing decisions, such as advertising content, false comments, meaningless or irrelevant content. When providing recommendation service uses a review that includes these factors can lead to decrease recommendation performance. Therefore, we proposed a novel recommendation methodology through CNN-based review usefulness score prediction to improve these problems. The results show that the proposed methodology has better prediction performance than the recommendation method considering all existing preference ratings. In addition, the results suggest that can enhance the performance of traditional CF when the information on review usefulness reflects in the personalized recommendation service.

• The Journal of Society for e-Business Studies
• /
• v.25 no.4
• /
• pp.33-60
• /
• 2020

Along with the rapid advance in internet technologies, ubiquitous mobile device usage has enabled consumers to access real-time information and increased interaction with others through various social media. Consumers can now get information more easily when making purchase decisions, and these changes are affecting the brand landscape. In a digitally connected world, brand image is not communicated to the consumers one-sidedly. Rather, with consumers' growing influence, it is a result of co-creation where consumers have an active role in building brand image. This explains a reality where people no longer purchase products just because they know the brand or because it is a famous brand. However, there has been little discussion on the matter, and many practitioners still rely on the traditional measures of brand indicators. The goal of this research is to present the limitations of traditional definition and measurement of brand and brand image, and propose a more direct and adequate measure that reflects the nature of a connected world. Inspired by the proverb, "A man is known by the company he keeps," the proposed measurement offers insight to the position of brand (or brand image) through co-purchased product networks. This paper suggests a framework of network analysis that clusters brands of cosmetics by the frequency of other products purchased together. This is done by analyzing product networks of a brand extracted from actual purchase data on Amazon.com. This is a more direct approach, compared to past measures where consumers' intention or cognitive aspects are examined through survey. The practical implication is that our research attempts to close the gap between brand indicators and actual purchase behavior. From a theoretical standpoint, this paper extends the traditional conceptualization of brand image to a network perspective that reflects the nature of a digitally connected society.

• Journal of KIISE:Databases
• /
• v.28 no.3
• /
• pp.279-300
• /
• 2001

Data mining plays an important role in knowledge discovery process and usually various existing algorithms are selected for the specific purpose of the mining. Currently, data mining techniques are actively to the statistics, business, electronic commerce, biology, and medical area and currently numerous algorithms are being researched and developed for these applications. However, in a long run, only a few algorithms, which are well-suited to specific applications with excellent performance in large database, will survive. So it is reasonable to focus our effort on those selected algorithms in the future. This paper classifies about 30 existing algorithms into 7 categories - association rule, clustering, neural network, decision tree, genetic algorithm, memory-based reasoning, and bayesian network. First of all, this work analyzes systematic hierarchy and characteristics of algorithms and we present 14 criteria for classifying the algorithms and the results based on this criteria. Finally, we propose the best algorithms among some comparable algorithms with different features and performances. The result of this paper can be used as a guideline for data mining researches as well as field applications of data mining.