• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.53-67
• /
• 2020

This study employees a supervised learning prediction model to detect nonconformity in advance of processed food manufacturing and processing businesses. The study was conducted according to the standard procedure of machine learning, such as definition of objective function, data preprocessing and feature engineering and model selection and evaluation. The dependent variable was set as the number of supervised inspection detections over the past five years from 2014 to 2018, and the objective function was to maximize the probability of detecting the nonconforming companies. The data was preprocessed by reflecting not only basic attributes such as revenues, operating duration, number of employees, but also the inspections track records and extraneous climate data. After applying the feature variable extraction method, the machine learning algorithm was applied to the data by deriving the company's risk, item risk, environmental risk, and past violation history as feature variables that affect the determination of nonconformity. The f1-score of the decision tree, one of ensemble models, was much higher than those of other models. Based on the results of this study, it is expected that the official food control for food safety management will be enhanced and geared into the data-evidence based management as well as scientific administrative system.

• The Journal of Society for e-Business Studies
• /
• v.27 no.1
• /
• pp.63-79
• /
• 2022

Recently, various studies have been conducted on stock price prediction using machine learning and deep learning techniques. Among these studies, the latest studies have attempted to predict stock prices using limit order books, which contain buy and sell order information of stocks. However, most of the studies using limit order books consider only the trend of limit order books over the most recent period of a specified length, and few studies consider both the medium and short term trends of limit order books. Therefore, in this paper, we propose a deep learning-based prediction model that predicts stock price more accurately by considering both the medium and short term trends of limit order books. Moreover, the proposed model considers news headlines during the same period to reflect the qualitative status of the company in the stock price prediction. The proposed model extracts the features of changes in limit order books with CNNs and the features of news headlines using Word2vec, and combines these information to predict whether a particular company's stock will rise or fall the next day. We conducted experiments to predict the daily stock price fluctuations of five stocks (Amazon, Apple, Facebook, Google, Tesla) with the proposed model using the real NASDAQ limit order book data and news headline data, and the proposed model improved the accuracy by up to 17.66%p and the average by 14.47%p on average. In addition, we conducted a simulated investment with the proposed model and earned a minimum of $492.46 and a maximum of $2,840.93 depending on the stock for 21 business days.

• Journal of Digital Convergence
• /
• v.12 no.4
• /
• pp.145-155
• /
• 2014

POSCO has been chosen as the most competitive steelmaker in the world, for the 4th year in a row. It's potentials and key success points lay at technology innovation as well as effective partnerships with suppliers and customers. Partnership with suppliers is based upon the effective supply chain management. While ERP system supports the standard business work flows, the biggest impact on business performance is created by exceptions and variability. A SCM Advanced Planning System reduces the amount of exceptional situations, helping to keep business in a standard mode of operation. A case summary on SCM Advanced Planning System of POSCO as well as its impact on firm performances is presented. As a supplement to this case study, we also investigate the employees' perceived level of SCM-related factors, including information sharing, collaboration, incentive system for suppliers and their impacts on SCM performances. As a conclusion, the practical implications of these findings are discussed.

• International Commerce and Information Review
• /
• v.17 no.3
• /
• pp.133-152
• /
• 2015

Cause of the technology leakage and trade secrets can be leaked to the lack of infrastructure, lack of coping skills of SMEs. In addition, small businesses can avoid technology outflow and re-experience the same half of the damage, even when the external leak developed after the fact and does not demonstrate such technology leakage time for the technology and situation which did not take any action, security, infrastructure investments difficult, work-related knowledge, lack of security, trade secret protection dedicated staff, inadequate legal and institutional measures have been identified as such complaints to date. For subcontracting, etc. mid-sized transactions, hinder the growth of SMEs, SME cross-technology leakage to the increase in unfair practices, including useful, and this has been accompanied by growth-based business-to-business it weakened.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.21 no.4
• /
• pp.133-147
• /
• 2010

With the start of knowledge based society, there has been extinction of traditional librarian jobs, new kinds of jobs are created, differentiated, and joined. As so there has been a great change in career paths. This study is a basic research of career parhes of library and information sciences alumni to adapt field work and build powerful workforce. Through the research of 5 Universities and 190 career routes, the movement of the library information and science majors' career has been unveiled. The majority of the library and information science majored career was jobs based on culture and arts, education and researches, economy and planning related ones, marketing and sales respectively. Particularly, except the librarian, there were just few careers in artistic cultural field. Further more, because there is a great impact in career tendency based on his education, the library information and science has drawn the report that the future of career and knowledge which is demanded in working field.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.8
• /
• pp.1843-1850
• /
• 2004

If the location information of a great number of cars kept for business with telematics terminals is acquired and managed efficiently, this information forms the foundation for controlling cars and traffic flows. The studies on the pure spatial indices have focused on the efficient retrievals. However, the acquisition and management of the terminal location of moving objects are more important than the efficiency of the query processing in the moving object databases. Therefore, it will be need to adopt parallel processing system for the moving object databases which should maintain the object's current location as precise as possible. This paper proposes a location management system using CDMA communications of telematics terminals. More precisely, we propose a architecture of spatial indexing mobile objects using multiple processors, and also newly propose a method of splitting buckets using the properties of moving objects in order to minimize the number of database updates. We also propose a acquisition method for gathering the location information of moving objects and passing the information of the bucket extents in order to reduce the amount of passed messages between processors.

• 한국방재학회:학술대회논문집
• /
• 2011.02a
• /
• pp.184-184
• /
• 2011

선로의 레일은 재료적인 특성과 현장의 많은 주변 요소에 의한 불확실성이 매우 높은 시스템으로 결함의 위험이 상존한다. 결함 발생과 조치에 따라 영업손실로 이어지므로 레일 결함 발생과 동시에 적절한 조치가 요구된다. 따라서 레일결함 발생 시 레일교환시기를 파악하는 것이 선로관리비용을 줄일 수 있으며 레일교환에 대한 신속한 판단을 위함 관리기준을 정립하는 것이 요구된다. 현재 국내에서 고속선의 경우 관리 기준이 있으나, 일반철도는 없는 실정이다. 본 연구는 차후 일반철도 180km/h 속도상승을 계획하고 있는 현 시점에 국외 관리기준을 분석하여 결함관리기준을 정립에 기여하고자 한다. 국내의 경우, 2004. 4. 1 프랑스 기술을 전수받아 개통한 고속선은 프랑스 레일관리기준을 적용한 "레일손상 등급별 관리기준"을 제정하여 레일관리를 시행하고 있다. 국외의 경우, INNOTRACK프로젝트 안에서 관련된 다른 IM(Infrastructure Managers, 사회기반시설 관리자들)에게 최근의 활동과 변화의 이해를 제공하기 위해서, 선택된 결함들의 최소조치들의 조사가 Network Rail, OBB, Prorail, Banverket 그리고 DB에서 수행되고 있으며 UIC 지침에도 포함되고 있다. 모든 최소조치 원칙은 초음파나 육안에 의해 발견된 길이나 초음파 또는 와류탐상기(eddy current system)를 이용한 깊이에 대한 제한(limits)을 준다. 또한 침목과 이음매 또는 용접부에 관한 위치에 관한 결함의 제한이 있다. 명시된 기간은 즉각적일 수도 있으며, 보통 속도 제한이나 비상 죔쇠(Clamps)같은 경감시키는 수단에 적용될 수 있으며, 또는 더 긴 기간이 될 수도 있다. 더 긴 기간들은 수리나 레일 교체를 통하여 선로로부터 결함이 제거되어야 하는 최대의 시간이다. 본 연구에서는 Transverse Breaks, Squats, Head Checks 3가지 결함 유형에 대해 각 국에서 사용하는 최소 조치를 비교하여 분석하였다. 분석결과, 유럽에서는 레일결함에 대하여 깊이 있는 연구를 통하여 관리기준을 정하여 관리하고 있으며 이에 따라 상세하고 구체적인 레일 관리가 가능하므로 효율적이며 안전성이 제고되는 것으로 판단된다. 차후 일반철도의 180km/h 속도상승을 계획하고 있는 현 시점에서 국내철도 일반선 여건에 적합한 레일결함관리기준을 정립하기 위한 추가적인 연구가 필요할 것으로 판단된다.

• Journal of Digital Contents Society
• /
• v.18 no.7
• /
• pp.1357-1366
• /
• 2017

In the context of domestic consumption environment changes such as expansion of smartphones and increase of single-person households, hypermarket, which was the mainstream of the existing retail market, have recorded negative growth for the last three years due to declining sales. And it is not enough to analyze the influence relationship with other retail channels or investigate the cause of consumption movement. In this study, we analyzed the decline in the growth rate of hypermarket by demographic variables, consumption time, etc. And logistic regression analysis revealed the relationship between the decrease in consumption of hypermarket and the change in the proportion of sales of other retail channels. In addition, we surveyed consumers who have decreased consumption of hypermarket based on actual card consumption data to determine why they choose different retail channels. This is significant in that the result of quantitative analysis of changes in retail channel consumption and the result of qualitative reasoning converged to give a stereoscopic view of consumption.

• Journal of Information Technology and Architecture
• /
• v.9 no.4
• /
• pp.433-442
• /
• 2012

This paper focuses on developing a smartphone-based mobile office system for a logistics company in Korea using HTML5. Mobile office is smart working environment of working out of a company office using mobile devices such as smartphones and portable computers which are connected to the company servers via WiFi or 3G/4G. Recently many companies are introducing mobile office information systems with the smartphone wave, but they are having difficulties in maintaining and updating their systems due to the transformative mobile application platform. Therefore, we need a platform-independent implementation tools for the mobile office application and HTML5 is one of the solution tools. In this paper, we develop mobile and web applications applicable to all kinds of mobile devices such as iOS, android and windows mobile etc using HTML5. The proposed mobile office system consists of groupware, marketing management, reporting module and transportation management system.

• Journal of Energy Engineering
• /
• v.24 no.1
• /
• pp.17-23
• /
• 2015

Electrical door system is one of the most essential items for the successful commercial operation of the railway vehicles. Nowadays, reliability values of electrical door system have a tendency to be included in technical requirements for design and manufacturing of rolling stocks. Manufacturer shall meet the reliability target values of electrical door system which is proposed by railway operator in procurement contract book. Railway operator shall approve the supplier's the reliability target values based on maintenance operation data. Railway operators are in the transition stage from the framework of maintenance interval based on time to the framework of maintenance interval based on distance. In this study, failure rates of the electrical door system currently used in railway vehicles are collected from maintenance field data. Failure rates are analyzed by using Minitab. Several kinds of plan for improving reliability are also suggested. It is necessary to keep studying on reliability prediction methodology, applying it in the field and implementing on improvement of reliability through feedback as well. Further, it will be useful for determining new maintenance policies or changing maintenance intervals for existing railway vehicles.