• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.2
• /
• pp.321-327
• /
• 2023

With the development of artificial intelligence, the prediction system has become one of the essential technologies in our lives. Despite the growth of these technologies, traffic congestion at intersections in the 21st century has continued to be a problem. This paper proposes a system that predicts intersection traffic jams using a Convolutional LSTM (Conv-LSTM) algorithm. The proposed system models data obtained by learning traffic information by time zone at the intersection where traffic congestion occurs. Traffic congestion is predicted with traffic volume data recorded over time. Based on the predicted result, the intersection traffic signal is controlled and maintained at a constant traffic volume. Road congestion data was defined using VDS sensors, and each intersection was configured with a Conv-LSTM algorithm-based network system to facilitate traffic.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.5D
• /
• pp.763-769
• /
• 2006

Gravity Model estimates target year's distributed trips using three variables like as origin zone's trip production, destination zone's trip attraction and traffic impedance between origin zone centroid and destination zone centroid. Estimating inner zone trip by gravity model is impossible because traffic impedance of inner zone has "0" value. So till today, for estimating inner zone trips, other methods like growth factor model are used. This study proposed inner zone trip estimation method that calculates inner zone's traffic impedance using established gravity model and estimates inner zone trips by putting calculated traffic impedance into the gravity model. 1988 year's surveyed O-D as basic year's O-D, proposed method's and existing methods(growth factor method and regression model)'s estimated results of 1992 year's and 2004 year's were compared with each year's real O-D by $x^2$, RMSE, Correlation coefficient. And resulted that the proposed method is superior than other existing methods.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.3
• /
• pp.10-18
• /
• 2007

According to the recent growth of the internet commercialization and differentiated QoS(quality of service), statistical traffic modeling is necessary for forecasting and controlling future network capacity. This paper reviews tile essential components in web workloads. And I propose adjusted internet traffic modeling using heavy-tailed distributions and intervention techniques.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.16 no.1
• /
• pp.46-57
• /
• 2008

Since the 90's, Korean Air transport market has been more expanded because of economic growth, the construction of airport infrastructure, and the advent of low cost carrier. Especially, the air traffic demand in Busan metropolitan area has been increasing steadily. Therefore, in this paper, we developed a new forecasting model which could expect the future air traffic demand in Busan area. This model is developed by regression analysis using social-economic variables such as GRDP, income, and the number of people, and dummy variables, for instance, KTX opening, Japan economic depression, SARS and so on. Result from demand forecasting by this new model suggests that the new airport system is needed in order to sustain the increasing air traffic demand in Busan area.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.8
• /
• pp.403-410
• /
• 2008

The noise problem became more serious by the rapid urban population growth and traffic. This study estimates the noise level considering actual traffic volume and building shape and location. Based on the state of the arts noise level, changing amount of noise that was controlled by the speed control and truck and passenger car restriction is calculated. Some conclusion is found out. The 2-D type more than 3-D type is more than over standard of noise pollution and night time's over rate is larger than day time. And in the case of various solutions are used instead of applying one solution, noise pollution is effectively reduced.

• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.8
• /
• pp.335-342
• /
• 2013

Nowadays, the traffic type and behavior are extremely diverse due to the growth of network speed and the appearance of various services on Internet. For efficient network operation and management, the importance of application-level traffic identification is more and more increasing in the area of traffic analysis. In recent years traffic identification methodology using statistical features of traffic flow has been broadly studied. However, there are several problems to be considered in the identification methodology base on statistical features of flow to improve the analysis accuracy. In this paper, we recognize these problems by analyzing the ground-truth traffic and propose the solution of these problems. The four problems considered in this paper are the distance measurement of features, the selection of the representative value of features, the abnormal behavior of TCP sessions, and the weight assignment to the feature. The proposed solutions were verified by showing the performance improvement through experiments in campus network.

• Journal of the Korean Institute of Rural Architecture
• /
• v.8 no.1
• /
• pp.70-79
• /
• 2006

This study deals with analysing the growth prospect and development direction of Donghae city with two international ports. To do so, it is progressed, firstly, to examine the general discovery about port since the late nineteenth century, secondly, to unfold it's theory with Mukho and Donghae port as Donghae city development element as the central figure, thirdly, to analyse Donghae city as the important place of traffic, the location of industry and the resource base in a spatial planning side.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.1
• /
• pp.1-10
• /
• 2014

The characteristics of internet traffic was dramatically changed recently. Especially, the ratio of video traffic in internet network is highly increased. Because the video traffic changes the traditional interactive traffic transport into one way contents delivery, internet network pricing structure is not efficient to reflect this changes. The fundamental reason for these is the discontinuity between the cost and revenue of the internet traffic. Although the internet traffic is forecasted to grow highly, the revenue of network provider is not expected to increase as such. The present paper investigates various alternatives to improve the present business model and to accommodate traffic growth. Then, the desirable options is proposed to invoke the innovation and to reflect the price signal according to some criteria.

• Proceedings of the Korea Contents Association Conference
• /
• 2010.05a
• /
• pp.200-203
• /
• 2010

The obstructive factors of the smoothly running traffic are street improvement, major commercial buildings like department stores, the large markets, the stadiums, the concert buildings, a lot of steady cars for using parking lot. The accident of cost many lives and traffic congestion from these factors cause the result that it enables to pay the enormous expenditure socially and financially. For solving these problems, Japan adopts the Traffic Flagger System in 1972. This task has the effects of improving traffic flow in the traffic jam and mitigating risk of car accidents as leading pedestrians and vehicles thereby the task carries into effect in the area where the accident took place. Moreover, this security task is rapid growth after adopting and 59.6%(5,317) of the whole security company 8,924 in Japan based on December 2009 registered as the traffic leading security business. While South Korea is demanded of the measures about obstructive factors of the smoothly running traffic, it represents the limitation of the system and the safety management. Thus the current study suggests the we will analyze South Korea's actual condition and then discuss the law and education system for a realizable plan reached the public-Private cooperation for adopting Japan's Traffic Leading Security System.

• International journal of advanced smart convergence
• /
• v.10 no.3
• /
• pp.72-80
• /
• 2021

Metaverse is an immersive 3D virtual environment, a true virtual artificial community in which avatars act as the user's alter ego and interact with each other. If we do not manage the hype for the metaverse, which has recently been receiving a surge in interest, the metaverse will fail to cross the chasm. In this study, to provide stakeholders with insights for the successful introduction and growth of the 3D immersive next-generation virtual world, metaverse, we analyzed user-side interest, media-side interest, and research-side interest. For this purpose, in this study, search traffic, news frequency and topic, and research article frequency and topic were analyzed. The methodology and results of this study are expected to provide insight for the stable success of metaverse transformation and the coexistence of the real world and the virtual world through hyper-connection and hyper-convergence.