• The Korean Journal of Archival Studies
• /
• no.71
• /
• pp.237-272
• /
• 2022

In 2019, the pilot project to establish a record management system for administrative information datasets started in earnest under the leadership of the National Archives. Based on the results of the three-year project by 2021, the improved administrative information dataset management plan will be reflected in public records-related laws and guidelines. Through this, the administrative information dataset becomes the target of full-scale public record management. Although public records have been converted to electronic documents and even the datasets of administrative information systems have been included in full-scale public records management, research on the quality requirements of data itself as raw data constituting records is still lacking. If data quality is not guaranteed, all four properties of records will be threatened in the dataset, which is a structure of data and an aggregate of records. Moreover, if the reliability of the quality of the data of the administrative information system built by reflecting the various needs of the working departments of the institution without considering the standards of the standard records management system is insufficient, the reliability of the public records itself can not be secured. This study is based on the administrative information dataset management plan presented in the "Administrative Information Dataset Recorded Information Service and Utilization Model Study" conducted by the National Archives of Korea in 2021. A study was conducted. By referring to various data, especially public data-related policies and guides, which are being promoted across the government, we would like to derive quality evaluation requirements in terms of records management and present specific indicators. Through this, it is expected that it will be helpful for record management of administrative information dataset which will be in full swing in the future.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.1
• /
• pp.67-74
• /
• 2022

In recent, the number of real-time traffic information sources and providers has increased as increasing smartphone users and intelligent transportation system facilities installed at roadways including vehicle detection system (VDS), dedicated short-ranged communications (DSRC), and global positioning system (GPS) probe vehicle. The accuracy of such traffic information would vary with these heterogeneous information sources or spatiotemporal traffic conditions. Therefore, the purpose of this study is to propose an empirical strategy of heterogeneous information fusion to improve the accuracy of real-time traffic information. To carry out this purpose, travel speed data collection based on the floating car technique was conducted on 227 freeway links (or 892.2 km long) and 2,074 national highway links (or 937.0 km long). The average travel speed for 5 probe vehicles on a specific time period and a link was used as a ground truth measure to evaluate the accuracy of real-time heterogeneous traffic information for that time period and that link. From the statistical tests, it was found that the proposed fusion strategy improves the accuracy of real-time traffic information.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.419-437
• /
• 2023

As the number of thin filers in Korea surpasses 12 million, there is a growing interest in enhancing the accuracy of assessing their credit default risk to generate additional revenue. Specifically, researchers are actively pursuing the development of default prediction models using machine learning and deep learning algorithms, in contrast to traditional statistical default prediction methods, which struggle to capture nonlinearity. Among these efforts, Graph Neural Network (GNN) architecture is noteworthy for predicting default in situations with limited data on thin filers. This is due to their ability to incorporate network information between borrowers alongside conventional credit-related data. However, prior research employing graph neural networks has faced limitations in effectively handling diverse categorical variables present in credit information. In this study, we introduce the Transformer embedded Graph Convolutional Network (TeGCN), which aims to address these limitations and enable effective default prediction for thin filers. TeGCN combines the TabTransformer, capable of extracting contextual information from categorical variables, with the Graph Convolutional Network, which captures network information between borrowers. Our TeGCN model surpasses the baseline model's performance across both the general borrower dataset and the thin filer dataset. Specially, our model performs outstanding results in thin filer default prediction. This study achieves high default prediction accuracy by a model structure tailored to characteristics of credit information containing numerous categorical variables, especially in the context of thin filers with limited data. Our study can contribute to resolving the financial exclusion issues faced by thin filers and facilitate additional revenue within the financial industry.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.219-239
• /
• 2019

As the importance of providing customized services to individuals becomes important, researches on personalized recommendation systems are constantly being carried out. Collaborative filtering is one of the most popular systems in academia and industry. However, there exists limitation in a sense that recommendations were mostly based on quantitative information such as users' ratings, which made the accuracy be lowered. To solve these problems, many studies have been actively attempted to improve the performance of the recommendation system by using other information besides the quantitative information. Good examples are the usages of the sentiment analysis on customer review text data. Nevertheless, the existing research has not directly combined the results of the sentiment analysis and quantitative rating scores in the recommendation system. Therefore, this study aims to reflect the sentiments shown in the reviews into the rating scores. In other words, we propose a new algorithm that can directly convert the user 's own review into the empirically quantitative information and reflect it directly to the recommendation system. To do this, we needed to quantify users' reviews, which were originally qualitative information. In this study, sentiment score was calculated through sentiment analysis technique of text mining. The data was targeted for movie review. Based on the data, a domain specific sentiment dictionary is constructed for the movie reviews. Regression analysis was used as a method to construct sentiment dictionary. Each positive / negative dictionary was constructed using Lasso regression, Ridge regression, and ElasticNet methods. Based on this constructed sentiment dictionary, the accuracy was verified through confusion matrix. The accuracy of the Lasso based dictionary was 70%, the accuracy of the Ridge based dictionary was 79%, and that of the ElasticNet (${\alpha}=0.3$) was 83%. Therefore, in this study, the sentiment score of the review is calculated based on the dictionary of the ElasticNet method. It was combined with a rating to create a new rating. In this paper, we show that the collaborative filtering that reflects sentiment scores of user review is superior to the traditional method that only considers the existing rating. In order to show that the proposed algorithm is based on memory-based user collaboration filtering, item-based collaborative filtering and model based matrix factorization SVD, and SVD ++. Based on the above algorithm, the mean absolute error (MAE) and the root mean square error (RMSE) are calculated to evaluate the recommendation system with a score that combines sentiment scores with a system that only considers scores. When the evaluation index was MAE, it was improved by 0.059 for UBCF, 0.0862 for IBCF, 0.1012 for SVD and 0.188 for SVD ++. When the evaluation index is RMSE, UBCF is 0.0431, IBCF is 0.0882, SVD is 0.1103, and SVD ++ is 0.1756. As a result, it can be seen that the prediction performance of the evaluation point reflecting the sentiment score proposed in this paper is superior to that of the conventional evaluation method. In other words, in this paper, it is confirmed that the collaborative filtering that reflects the sentiment score of the user review shows superior accuracy as compared with the conventional type of collaborative filtering that only considers the quantitative score. We then attempted paired t-test validation to ensure that the proposed model was a better approach and concluded that the proposed model is better. In this study, to overcome limitations of previous researches that judge user's sentiment only by quantitative rating score, the review was numerically calculated and a user's opinion was more refined and considered into the recommendation system to improve the accuracy. The findings of this study have managerial implications to recommendation system developers who need to consider both quantitative information and qualitative information it is expect. The way of constructing the combined system in this paper might be directly used by the developers.

• Asia pacific journal of information systems
• /
• v.19 no.3
• /
• pp.125-150
• /
• 2009

RFID(Radio Frequency IDentification) is a wireless frequency of recognition technology that can be used to recognize, trace, and identify people, things, and animals using radio frequency(RF). RFID will bring about many changes in manufacturing and distributions, among other areas. In accordance with the increasing importance of RFID techniques, great advancement has been made in RFID studies. Initially, the RFID research started as a research literature or case study. Recently, empirical research has floated on the surface for announcement. But most of the existing researches on RFID adoption have been restricted to a dichotomous measure of 'adoption vs. non-adoption' or adoption intention. In short, RFID research is still at an initial stage, mainly focusing on the research of the RFID performance, integration, and its usage has been considered dismissive. The purpose of this study is to investigate which factors are important for the RFID adoption and implementation with organizational resources. In this study, the organizational resources are classified into either finance resources or IT knowledge resources. A research model and four hypotheses are set up to identify the relationships among these variables based on the investigations of such theories as technological innovations, adoption stage, and organizational resources. In order to conduct this study, a survey was carried out from September 27, 2008 until October 23, 2008. The questionnaire was completed by 143 managers and workers from physical distribution and manufacturing companies related to the RFID in South Korea. 37 out of 180 surveys, which turned out unfit for the study, were discarded and the remaining 143(adoption stage 89, implementation stage 54) were used for the empirical study. The statistics were analyzed using Excel 2003 and SPSS 12.0. The results of the analysis are as follows. First, the adoption stage shows that perceived benefits, standardization, perceived cost savings, environmental uncertainty, and pressures from rival firms have significant effects on the intent of the RFID adoption. Further, the implementation stage shows that perceived benefits, standardization, environmental uncertainty, pressures from rival firms, inter-organizational cooperation, and inter-organizational trust have significant effects on the extent of the RFID use. In contrast, inter-organizational cooperation and inter-organizational trust did not show much impact on the intent of RFID adoption while perceived cost savings did not significantly affect the extent of RFID use. Second, in the adoption stage, financial issues had adverse effect on both inter-organizational cooperation and the intent against the RFID adoption. IT knowledge resources also had a deterring effect on both perceived cost savings and the extent of the RFID adoption. Third, in the implementation stage, finance resources had a moderate effect on environmental uncertainty and extent of RFID use while IT knowledge resources had also a moderate effect on perceived cost savings and the extent of the RFID use. Limitations and future research issues can be summarized as follows. First, it is difficult to say that the sample is large enough to be representative of the population. Second, because the sample of this study was conducted among manufacturers only, it may be limited in analyzing fully the effect on the industry as a whole. Third, in consideration of the fact that the organizational resources in the RFID study require a great deal of researches, this research may deem insufficient to fulfill the purpose that it initially set out to achieve. Future studies using performance research are, therefore, needed to help better understand the organizational level of the RFID adoption and implementation.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.3 no.2 s.5
• /
• pp.19-28
• /
• 2004

This paper shows how to compensate the skew from the traffic sign included in the natural image and extract the text. The research deals with the Process related to the array image. Ail the process comprises four steps. In the first fart we Perform the preprocessing and Canny edge extraction for the edge in the natural image. In the second pan we perform preprocessing and postprocessing for Hough Transform in order to extract the skewed angle. In the third part we remove the noise images and the complex lines, and then extract the candidate region using the features of the text. In the last part after performing the local binarization in the extracted candidate region, we demonstrate the text extraction by using the differences of the features which appeared between the tett and the non-text in order to select the unnecessary non-text. After carrying out an experiment with the natural image of 100 Pieces that includes the traffic sign. The research indicates a 82.54 percent extraction of the text and a 79.69 percent accuracy of the extraction, and this improved more accurate text extraction in comparison with the existing works such as the method using RLS(Run Length Smoothing) or Fourier Transform. Also this research shows a 94.5 percent extraction in respect of the extraction on the skewed angle. That improved a 26 percent, compared with the way used only Hough Transform. The research is applied to giving the information of the location regarding the walking aid system for the blind or the operation of a driverless vehicle

• Nutrition Research and Practice
• /
• v.10 no.5
• /
• pp.555-562
• /
• 2016

BACKGROUND/OBJECTIVES: Childhood obesity has become a global epidemic. Development of effective and sustainable programs to promote healthy behaviors from a young age is important. This study developed and tested an intervention program designed to promote healthy eating and physical activity among young children in South Korea by adaptation of the US National Aeronautics and Space Administration (NASA) Mission X (MX) Program. SUBJECTS/METHODS: The intervention program consisted of 4 weeks of fitness and 2 weeks of nutrition education. A sample of 104 subjects completed pre- and post- surveys on the Children's Nutrition Acknowledgement Test (NAT). Parents were asked for their children's characteristics and two 24-hour dietary records, the Nutrition Quotient (NQ) at baseline and a 6-week follow-up. Child weight status was assessed using Korean body mass index (BMI) percentiles. RESULTS: At baseline, 16.4% (boy: 15.4%; girl: 19.2%) of subjects were overweight or obese (based on $BMI{\geq}85%tile$). Fat consumption significantly decreased in normal BMI children ($48.6{\pm}16.8g$ at baseline to $41.9{\pm}18.1g$ after intervention, P < 0.05); total NQ score significantly increased from 66.4 to 67.9 (P < 0.05); total NAT score significantly improved in normal BMI children (74.3 at baseline to 81.9 after the program), children being underweight (from 71.0 to 77.0), and overweight children (77.1 at baseline vs. 88.2 after intervention, P < 0.001). CONCLUSIONS: The 6-week South Korean NASA MX project is feasible and shows favorable changes in eating behaviors and nutritional knowledge among young children.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.7
• /
• pp.573-584
• /
• 2016

The train control system is a facility to ensure model-based design and safe train operation, and its safety is the most important factor for system introduction, complexity of the design information and traceability etc. Therefore, the model-based design and safety activities regarding the way-side equipment of a train control system is also highlighted. To solve this problem, In this paper, model-based design was carried out first to develop an effective train control system, which is represented by SysML(System Modeling Language). The test scenarios that can take advantage of the design model were created to improve the train safety control system. Case studies of a model-based design of a train-centric train control system were applied to the test scenarios; the results demonstrated its usability. The improved activity over the test highlighted the safety improvement approach, and it is expected to reduce the cost and time in the conceptual design of a future development model-based train control system.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.4
• /
• pp.55-66
• /
• 2020

This study developed four algorithms and their associated indices that can quantify and qualify road hazards along roadways. Initially, relevant raw data can be collected from commercial vehicles by camera and DTG. Well-processed data, such as potholes, road freezing, and fog, can be generated from the Integrated management system. Road hazard algorithms combine these data with road inventory data in the Data Sharing Platform. Depending on well-processed data, four different road hazard algorithms and their associated indices were developed. To test the algorithms, an experimental plan based on passive DTG attached in probe vehicles was performed at two different test locations. Selection of the test routes was based on historical data. Although there were limitations using random data for commercial vehicles, hazardous roadways sections, such as fog, road freezing, and potholes, were generated based on actual historical data. As a result, no algorithm error was found in the entire test. Because this study provides road hazard information according to a section, not a point, it can be practically helpful to road users as well as road agencies.

• Journal of Distribution Science
• /
• v.9 no.1
• /
• pp.49-59
• /
• 2011

Although the South Korean organic food market is in the infancy compared to other industrialized countries, Korean consumers'interest in organic food and retail stores devoting space to organic products have been rapidly increasing. Despite the fact of organic food popularity, the term "organic" is interpreted differently by individuals. As opposed to the US, Japan and the EU where have operated an integrated organic food labelling system, Korea has adopted complex organic labelling systems regulated by several different government bodies. As a result, complicated food labelling standards make consumers confused when purchasing organic foods. Furthermore, in terms of country of origin (COO), it is argued by a lot of researchers that COO effects vary from product to product and from country to country; moreover, other informational cues such as brand and price can influence COO effects. In modern society, COO labelling has been complicated, due to the sourcing, manufacturing and market locations of merchandise spread over the world. Accordingly, the evaluation of COO effects has become complex. In order to examine these issues, a quantitative research was selected to classify the commonfeatures of organic food consumers and construct statistics such as the extent to which people are aware of organic food and COO labellingvia a questionnaire which took place in two cities in Korea with a cluster sample of 161 organic food purchasers. As for the data analysis, one-way analysis of variance (ANOVA), T-tests, bivariate crosstatulations with Cramer's V were conducted,depending on the characteristics of variables and the assumptions the research data need to fit. It has been concluded that in general, Korean organic consumers comprehend the term "organic"in a closer way to the general concept rather than technical term, thus people do not appreciate environmentally labels which include organic food labels, although marital status influence the degree of label awareness, regardless of gender, age, education level and so on. Regarding COO effects on organic food, home organic products were Korean consumers'first choice over those from industrialized countries and developing nations. Specifically, in processed organic product category, domestically cultivated and processed organic products were absolutely preferred to leading national brands produced with imported ingredients and international brands. However, due to a lack of checks of ingredients' COO, consumers tend to purchase a leading national organic food brand, believing that it is a pure organic food sourced domestically. As a consequence, this research has suggested some important managerial implications and future research directions. In order to prevent consumer confusion when buying organic foods, it should be noted that consumers do not comprehend the organic food certifications, due to complicated labelling systems for organic produce and processed organic foods. Therefore, government bodies related to organic food distribution have to know consumers' perception of organic food labels and the significance of customer-oriented labels and reestablish labelling standards. Similarly, public advertising should be followed to raise public awareness of the labelling to enable customers to have the correct information. In addition, not only international marketers but also domestic marketers need to understand COO images and also the influence COO of ingredients has on the image of an organic product.