• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.2
• /
• pp.354-368
• /
• 2020

Accurate and versatile image data-sets are essential for fashion AI research and AI-based fashion businesses based on a systematic attribute classification system. This study constructs a color and texture attribute hierarchical classification system by collecting fashion item images and analyzing the metadata of fashion items described by consumers. Essential dimensions to explain color and texture attributes were extracted; in addition, attribute values for each dimension were constructed based on metadata and previous studies. This hierarchical classification system satisfies consistency, exclusiveness, inclusiveness, and flexibility. The image tagging to confirm the usefulness of the proposed classification system indicated that the contents of attributes of the same image differ depending on the annotator that require a clear standard for distinguishing differences between the properties. This classification system will improve the reliability of the training data for machine learning, by providing standardized criteria for tasks such as tagging and annotating of fashion items.

• Journal of architectural history
• /
• v.6 no.3 s.13
• /
• pp.61-76
• /
• 1997

A study on the traditional houses of North Korea(I) have been published in 1996. This paper is written to supplement the preceding paper. This paper aims at collecting new data of traditional house in North Korea. But still being prohibited for the researchers of South Korea to approach to the field, I had to depend on the memories and experiences of the immigrants from North Korea who are now living in Kangwon and Incheon Province. Through the questionnaire and drawings, they described vivid memory of their old houses. I was able to add new data of 70 cases, which are significant and valuable as much as those of the real field are. Those data, including the exisiting data, are enough for me to analize statstically the regional charateristics, the differnces among economical classes, and the periodical change. It opens the way for verfying the existing theory. Regional charateristics of house in North Korea can be described as followings: a. Hamkyong-do ; Concentrating spaces into one building, Double-fold type plan, Including 'cheongju-kan' space, Weak fences b. Pyongan-do ; Concentrating spaces into two buildings, 二 shape buildings , Single-fold type plan, Strong fence c. Pyongannam-do to Myolak mountains; Concentraing spaces into two buildings, ㄱ, ㄷ shape buildings, Single-fold type plan, Strong fence d. Southern area of Myolak mountains; Concentrating spaces into one building ㅁ shape building, Single-fold type plan with wooden floor space

• Journal of the Korean Society of Safety
• /
• v.13 no.1
• /
• pp.98-104
• /
• 1998

Recently, industrial accidents have occurred in various patterns due to the diversity of industries and the integration of facilities. Especially, the major accidents affect broad area and result in huge loss of lives and properties. Domestic researches on techniques for keeping away from such hazardous danger have been actively performed but their activities are limited in some institutes and universities. In advanced countries, integrated management systems like Seveso Directive of EU and OSHA(Occupational Safety and Health Act) of U.S.A. have been legislated along with the systematic research activities. In Korea, the integrated safety management systems called SMS(Safety Management System) and PSM(Process Safety Management) have been applied to major industries. These systems made chemical industries manage the process safety information by collecting and arranging safety data by themselves. In order to implement the system successfully, it is urgently required to prepare a tool for searching and accumulating process safety data systematically. In this study, a computerized prototype of Risk Assessment System which is essential to SMS and PSM was developed as a main system and data base as subsystem to handle safety information.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.45-52
• /
• 2018

With the advent of BCI technology in recent years, various BCI products have been released. BCI technology enables brain information to be transmitted directly to a computer, and it will bring a lot of convenience to life. However, there is a problem with information protection. In particular, EEG data can raise issues about personal privacy. Collecting and analyzing big data on EEG reports raises serious concerns about personal information exposure. In this paper, we propose a secure privacy-preserving BCI model in a big data environment. The proposed model could prevent personal identification and protect EEG data in the cloud environment.

• International Journal of Contents
• /
• v.16 no.3
• /
• pp.33-44
• /
• 2020

Small and medium enterprises need a wide range of information regarding technologies, industries, market conditions, other companies, and products to facilitate identification of new growth opportunities and to respond quickly to changes in the business environment. Collecting such information, however, requires the input of resources (human resources, cost, and time), and the lack of marketability resulting from the shortage of such resources is often cited as the reason small and medium often fail in their effort to commercialize their technology. The purpose of this study was to analyze the environmental factors such as market concentration and the current level of competition to enable companies to make the necessary decisions when considering market entry following R&D planning and technology commercialization, or after the development of a new product. Also, an expert-based 5FORCE analysis can be performed using the KMAPS, an industry and market intelligence system: this facilitates automatic production of analyses based on the corporate finance and transaction data. The key contribution of the study is that it facilitates conveniently and quickly analyzing the 5 Forces, which had been a difficult task in the environmental analysis, and that the outcomes of this study empower companies in the decision-making process.

• International Journal of Highway Engineering
• /
• v.15 no.2
• /
• pp.121-129
• /
• 2013

PURPOSES : This study deals with the traffic accidents of rotary in Korea. The objective of this study is to develop the accident models by age group based on the various data of rotaries. METHODS : In pursuing the above, this study gives particular attentions to classifying the accident data of 17 rotaries by age, collecting the data of geometric structure, traffic volume and others, and developing the models using SPSS 17.0 and EXCEL. RESULTS : First, 3 multiple linear regression models which were all statistically significant were developed. The value of model of under 30-49 age group were, however, evaluated to be 0.688 and be less than those of other models. Second, the most powerful variables were analyzed to be traffic volume in the model of under 30 age group, circulatory roadway width in the model of 30-49 age group, and the number of approach lane in the model of above 50 age group. Finally, the test results of accident models using RMSE were all evaluated to be fitted to the given data. CONCLUSIONS : This study propose install streetlights, speed humps and widen Circulatory as effective improvements for reduction of accident in rotary.

• Journal of Korea Water Resources Association
• /
• v.34 no.3
• /
• pp.253-263
• /
• 2001

It is very important to select appropriate methods of collecting, predicting, and analyzing information for the development of urban water resources and the prevention of disasters. Thus, in this study an accurate data generation method is developed using Geographic Information System (GIS) and Remote Sensing (RS). The methods of development and application of an expert system are suggested to solve more efficiently the problems of water resources and quality induced by the rapid urbanization. The time-varying data in a large region, the An-Yang cheon watershed, were reasonably obtained by the application of the GIS using ARC/INFO and RS data. The ESPE (Expert System for Parameter Estimation), an expert system is developed using the CLIPS 6.0. The simulated results showed agreement with the measured data globally. These methods are expected to efficiently simulate the runoff and water quality in the rapidly varying urban area.

• Solar Energy
• /
• v.20 no.2
• /
• pp.19-30
• /
• 2000

Since the solar radiation is the main input for sizing any solar system, it will be necessary to understand and evaluate the insolation data. The Korea Institute of Energy Research(KIER) has began collecting horizontal global insolation data since May, 1982 at 16 different locations. Because of a poor reliability of existing data, KIER's new data will be extensively used by solar system users as well as by research institutes. From the results, we can conclude that 1) The yearly averaged horizontal global insolation of Korea was turned out $3,042kcal/m^2.day$ in the periods of $1982\sim1999$. 2) Horizontal global insolation of spring and summer were 24 % and 21 %, higher than the yearly average value, respectively, and for fall and winter, their values were 12 % and 34 % lower than the yearly average value, respectively.

• Solar Energy
• /
• v.20 no.2
• /
• pp.31-42
• /
• 2000

Since the direct normal insolation is a main factor for designing any focusing solar system, it is necessary to evaluate its characteristics all over the country. We have begun collecting direct normal insolation data since December 1990 at 16 different locations and considerable effort has been made for constructing a standard value from measured data at each station. KIER(Korea Institute of Energy Research)'s new data will be extensively used by concentrating system users or designers as well as by research institutes. From the results, we can conclude that 1) Yearly mean $4,576kcal/m^2.day$ of the direct normal insolation was evaluated for clear day all over 16 areas in Korea. 2) Clear day's direct normal insolation of spring and summer were $4,710kcal/m^2.day$ and $4,960kcal/m^2.day$, and for fall and winter their values were $4,484kcal/m^2.day$ and $4,151kcal/m^2.day$ respectively. So, spring and summer were higher, and fall and winter were lower than the yearly mean value.

• Food Science of Animal Resources
• /
• v.33 no.4
• /
• pp.463-473
• /
• 2013

Through the development of efficient data collecting technologies like RFID, and inter-enterprise collaboration platforms such as web services, companies which participate in supply chains can acquire visibility over the whole supply chain, and can make decisions to optimize the overall supply chain networks and processes, based on the extracted knowledge from historical data collected by the visibility system. Although not currently active, the MeatWatch system has been developed, and is used in part for this purpose, in the imported beef distribution network in Korea. However, the imported beef distribution network is too complicated to analyze its various aspects using ordinary process analysis approaches. In this paper, we suggest a novel approach, called RFID-based supply chain process mining, to automatically discover and analyze the overall supply chain processes from the distributed RFID event data, without any prior knowledge. The proposed approach was implemented and validated, by using a case study of the imported beef distribution network in Korea. Specifically we demonstrated that the proposed approach can be successfully applied to discover supply chain networks from the distributed event data, to simplify the supply chain networks, and to analyze anomaly of the distribution networks. Such novel process mining functionalities can reinforce the capability of traceability services like MeatWatch in the future.