• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.37-44
• /
• 2020

AI technology has developed in the form of decision support technology in law, patent, finance and national defense and is applied to disease diagnosis and legal judgment. To search real-time information with Deep Learning, Big data Analysis and Deep Learning Algorithm are required. In this paper, we try to predict the entrance rate to high-ranking universities using a Deep Learning model, RNN(Recurrent Neural Network). First, we analyzed the current status of private academies in administrative districts and the number of students by age in administrative districts, and established a socially accepted hypothesis that students residing in areas with a high educational fever have a high rate of enrollment in high-ranking universities. This is to verify based on the data analyzed using the predicted hypothesis and the government's public data. The predictive model uses data from 2015 to 2017 to learn to predict the top enrollment rate, and the trained model predicts the top enrollment rate in 2018. A prediction experiment was performed using RNN, a Deep Learning model, for the high-ranking enrollment rate in the special education zone. In this paper, we define the correlation between the high-ranking enrollment rate by analyzing the household income and the participation rate of private education about the current status of private institutes in regions with high education fever and the effect on the number of students by age.

• The Journal of Society for e-Business Studies
• /
• v.25 no.3
• /
• pp.95-108
• /
• 2020

The development of 5G technology, which is a next-generation communication technology capable of processing large amounts of data in real-time and solving delays, is drawing attention. Not only in the United States but also Korea, 5G is focused on supporting R&D as a national strategic technology. The strategy for the smart factory, one of the core services of the 5G, aims to increase the flexibility of manufacturing production lines. The existing wired communications devices can be replaced into wireless ones with the ultra-low-delay and ultra-high-speed characteristics of 5G. For the efficient development of 5G technology, it is necessary to keep abreast of the status and trend. In this study, based on the collected data of 1517 Korea patents and 1928 US patents, 5G technologies trend was analyzed and key technologies were identified by network analysis and topic modeling. We expect that it will be used for decision making for policy establishment and technology strategy of related industries to provide the trends of technology development related to the introduction of 5G technology to smart factories.

• Journal of Digital Convergence
• /
• v.15 no.11
• /
• pp.261-269
• /
• 2017

The purpose of this paper is to provide a search system using a method of accessing the web in real time without using a database server in order to guarantee the up-to-date information in a single network, rather than using a plurality of bots connected by a wide area network Design. The method of the research is to design and analyze the system which can search the person and keyword quickly and accurately in crepe system. In the crepe server, when the user registers information, the body tag matching conversion process stores all the information as it is, since various styles are applied to each user, such as a font, a font size, and a color. The crepe server does not cause a problem of body tag matching. However, when executing the crepe retrieval system, the style and characteristics of users can not be formalized. This problem can be solved by using the html_img_parser function and the Go language html parser package. By applying queues and multiple threads to a general-purpose web crawler, rather than a web crawler design that targets a specific site, it is possible to utilize a multiplier that quickly and efficiently searches and collects various web sites in various applications.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.7
• /
• pp.1342-1354
• /
• 2016

As Internet, and hardware technology are in rapid process, using rate and penetration rate of Internet of Things are increasing. Internet of Things is the physical objects with network which embedded with electronics, software, sensors, and network. Smart Home-kit to operate refrigerators, washing machines, light bulbs, and such internet of things by a smartphone has been realized. However, it is difficult to use a good quality of software based on IoT. It is because that the study related to quality evaluation of software based on IoT is deficient compared with increase amount of IoT devices. Software based on IoT includes mobility, transportability, real time accessibility and hardware characteristics. Therefore, it is necessary to have differentiated quality standards and quality model. Software quality evaluation model for IoT is proposed to satisfy these needs. Evaluation model is mapped by characteristics of IoT software based on ISO/IEC 25000's quality characteristics. Scenario based studies were applied to quality model for verification.

• Journal of Korean Society of Transportation
• /
• v.17 no.4
• /
• pp.59-69
• /
• 1999

A Freeway corridor is a network consisting of a few Primary longitudinal roadways (freeway or major arterial) carrying a major traffic movement with interconnecting roads which offer the motorist alternative paths to his/her destination. Control measures introduced to ameliorate traffic performance in freeway corridors typically include ramp metering at the freeway entrances, and signal control at each intersections. During a severe freeway incident, on-ramp metering usually is not adequate to relieve congestion effectively. Diverting some traffic to the Parallel surface street to make full use of available corridor capacity will be necessary. This is the purpose of the traffic management system. So, an integrated traffic control scheme should include three elements. (a)on-ramp metering, (b)off-ramp diversion and (c)signal timing at surface street intersections. The purpose of this study is to develop an integrated optimal control model in a freeway corridor. By approximating the flow-density relation with a two-segment linear function. the nonlinear optimal control problem can be simplified into a set of Piecewise linear programming models. The formulated optimal-control Problem can be solved in real time using common linear program. In this study, program MPL(ver 4.0) is used to solve the formulated optimal-control problem. Simulation results with TSIS(ver 4.01) for a sample network have demonstrated the merits of the Proposed model and a1gorithm.

• Journal of the Korea Institute of Building Construction
• /
• v.11 no.3
• /
• pp.283-291
• /
• 2011

As the construction industry has recently been transformed by the emergence of ubiquitous and intelligent technology, there have been major changes in the management methods employed. Specifically, next-generation construction management systems have been developed that collect and analyze many pieces of information in real time by using various wireless sensors and networks. The purpose of this study is to understand the current status of Ubiquitous Sensor Networks (USN) in the construction sector, and to gain fundamental data for a system of measuring concrete curing temperature in a construction site that employs a USN. By investigating the application status of USN, it was confirmed that USN has mainly been applied to the maintenance of facilities, safety management, and quality control. In addition, a field experiment in which the curing temperature of concrete was measured using a USN was carried out to evaluate two systems with wireless sensor networks, and the applicability of these systems on site was confirmed. However, it is estimated that the embedded wireless sensor type is affected by metal equipment on site, internal battery of sensor and concrete depth, and studies to provide more stable system by USN are thus required.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.1D
• /
• pp.13-22
• /
• 2012

The 119 emergency rescue-aid service operated by Korean government is a very valuable in a society and its importance is growing in Korea as an aging society. Especially, the emergency vehicle's arrival time to accidents place is an important variable which affects initial emergency measure for patients and it depends on the road network attributes, such as emergency service station's location, accessibility to accidents place and so on. This study aims to analysis the emergency vehicles' arrival delay and the dispatch station in the viewpoint of efficiency utilizing the real rescue-aid activity data. We analyzed the dispatch distribution of the emergency rescue-aid service at first. And we analyzed high accident rate locations not involved in the fixed radius of rescue-aid service stations and display GIS map showing regions have been delayed. The input data of the road network speed is based on the KTDB (Korea Transportation Database) and historical rescue-aid data is from Gyeongsangbuk-do's fire service headquarters.

• Journal of Korea Water Resources Association
• /
• v.33 no.2
• /
• pp.247-262
• /
• 2000

In this paper, the WSANN(Water Stage Analysis with Neural Network) model was presented so as to predict flood water stage at Jindong which has been the major stream gauging station in Nakdong river basin. The WSANN model used the improved backpropagation training algorithm which was complemented by the momentum method, improvement of initial condition and adaptive-learning rate and the data which were used for this study were classified into training and testing data sets. An empirical equation was derived to determine optimal hidden layer node between the hidden layer node and threshold iteration number. And, the calibration of the WSANN model was performed by the four training data sets. As a result of calibration, the WSANN22 and WSANN32 model were selected for the optimal models which would be used for model verification. The model verification was carried out so as to evaluate model fitness with the two-untrained testing data sets. And, flood water stages were reasonably predicted through the results of statistical analysis. As results of this study, further research activities are needed for the construction of a real-time warning of the impending flood and for the control of flood water stage with neural network method in river basin. basin.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.948-952
• /
• 2006

인구의 증가와 경제의 발전으로 인해 한정된 수자원에 대한 수요가 급증하였고 향후 고도의 복지사회 구현과 지방 자치화에 따른 각종 용수 수요에 대한 심각한 물 배분 문제가 대두되고 있다. 특히 심각하게 물 배분 문제가 야기될 때 각 수요지점별로 필요한 용수를 공급하기 위해서 단지 상류에서 하류 단으로 물을 배분한다면 수리권의 공정성 문제가 제기되며 물 관리 원칙의 결여에 따른 곤란한 상황이 발생할 수 있다. 이렇게 갈수 및 가뭄 시와 같이 물 배분 문제가 생길시 에는 우선 하천유역 전체의 가용수량을 파악한 후 각 용수 사용별로 중요성을 감안하여 용수공급 우선순위를 설정하여 전 하천 유역을 통하여 일관된 배분을 실시할 수 있는 수자원 최적화 배분 시스템을 개발 할 필요성이 있다. 이러한 문제를 해결하기 위하여 본 연구에서는 한국수자원공사 수자원연구원과 콜로라도주립대학에서 공동 개발한 유역 네트워크 유량 모델(River Basin Network Flow Model)인 K-MODSIM을 이용하여 유역통합 실시간 일 저수지 운영 모델을 개발하였다. 개발된 유역통합 실시간 일운영 모델은 금강유역에 적용하였으며, 금강유역을 12개의 소유역으로 구분하고, 용담댐과 대청댐을 포함하며, 유역관리는 용수공급, 치수대책, 발전수력 및 하천 유지용수의 공급등의 유역내 수자원 관리 상황을 포함하였다. 이처럼 유역의 매우 자세한 세부사항을 고려함으로서 기존에 개발된 모델이 가지고 있던 단순화의 단점을 보완하고 유역의 특성을 최대한 반영하도록 하였다. 또한 유역통합 실시간 일운영 모델의 장기적인 저수지 운영 문제를 해결하기 위해 암시적 추계학적 동적계획법을 사용하여 도출된 월운영룰을 일운영모델에 적용할 수 있는 방법을 제시 하였다.기능으로 구성되어 있으며, 각 기능을 선택하면 해당 화면으로 GUI가 전환된다. 따라서 다량의 측정자료의 신뢰성을 유지하고 이를 모형의 입력자료로 활용하는 일련의 과정을 시스템화하기 때문에 자료의 이상적 유지 관리가 이루어지며 복잡한 2차원 수질해석 모형을 수월하게 운영할 수 있는 시스템으로 개발하였다.제외하면, 부자측정 방법에 의한 유량산정시 가장 큰 오차원인은 홍수시 측정된 유속측선의 위치와 홍수 전후로 측정된 횡단면상의 위치가 일치하지 않는 점과, 대부분 두 측정 구간의 평균값을 대푯값으로 사용한다는 점이다. 본 연구는 다년간의 유량 측정 및 검증 경험과 자료를 토대로 현장에서 부자를 이용하여 측정된 측정성과를 정확도 높은 유량자료로 산정하는데 있어서의 문제점을 도출하고, 이로 인해 발생하는 오차를 추정하여 그 개선방안을 제시해 보고자한다. 더불어 보다 정확한 유량 산정을 위한 기준과 범주를 제시하고자 한다.리적 특성을 잘 반영하며, 도시지역의 복잡한 배수시스템 해석모형과 지표범람 모형을 통합한 모형 개발로 인해 더욱 정교한 도시지역에서의 홍수 범람 해석을 실시할 수 있을 것으로 판단된다. 본 모형의 개발로 침수상황의 시간별 진행과정을 분석함으로써 도시홍수에 대한 침수위험 지점 파악 및 주민대피지도 구축 등에 활용될 수 있을 것으로 판단된다. 있을 것으로 판단되었다.4일간의 기상변화가 자발성 기흉 발생에 영향을 미친다고 추론할 수 있었다. 향후 본 연구에서 추론된 기상변화와 기흉 발생과의 인과관계를 확인하고 좀 더 구체화하기 위한 연구가 필요할 것이다.게 이루어질 수 있을 것으로 기대된다.는 초과수익률이 상승하지만, 이후로는 감소하므로, 반전거래전략을 활용하는 경우 주식투자기간은 24개월이하의 중단기가 적합함을

• The KIPS Transactions:PartC
• /
• v.15C no.5
• /
• pp.383-390
• /
• 2008

The mobile sink is most suitable to guarantee the real time processing to events in ubiquitous environment. However it brings many challenges to wireless sensor networks. In particular, the question of how to transfer the collected data to the mobile sink is an important topic in the aspect of effective management of wireless sensor nodes. In this paper, a new data dissemination model is proposed. Since this method uses the home agent and the access node concepts, it provides reliable and efficient data delivery to mobile sink with minimum overhead. In this proposed method, the information of the mobile sink which is constantly moving is informed only to the home agent node and the access node, instead of all sensor nodes. Thus, the collected data from sensor nodes are transferred to the fixed home agent and it sends these data to the mobile sink. Since the confliction phenomenon between data packets in wireless networks could be reduced, the success ratio of data arriving in the mobile sink is highly enhanced. In our experiments, the proposed method reduces the number of broadcast packets so that it saves the amount of energy consumed for transmitting and receiving the data packets. This effect contributes to prolong the lifetime of the wireless sensor networks operated by batteries.