• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.332-333
• /
• 2023

본 논문은 사람과 짐의 물체 감지를 위한 YOLO 모델을 활용하여 특정 공간 내 혼잡도를 측정하는 시스템을 제안한다. YOLO를 학습시켜 기차 내에서 사람 및 짐과 같은 객체를 탐지하는 모델을 만든다. 그리고 이 모델을 이용하여 기차 내에서 객체를 탐지하고, 객체의 위치와 개수 정보를 얻는다. 이렇게 얻은 정보를 기반으로, 혼잡도를 측정하기 위해 다양한 지표를 활용한다. 이를 인터페이스에 시각적으로 보여준다. 결과적으로, 제안된 시스템은 승객들의 안전과 편의를 보장하며, 특정 공간의 혼잡도 파악에 유용한 도구로 사용될 수 있다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.5B
• /
• pp.427-434
• /
• 2003

This paper suggests an improved TCP congestion algorithm, which is more robust to lossy wireless environment than other algorithms such as TCP-Reno. The suggested algorithm decides on the size of a congestion window depending on both PER (Packet Error Rate) and its state, which is one of fast recovery state and slow start state. Some simulations are given to validate the suggested algorithm and the algorithm is compared with other TCP congestion algorithm from the point of view of performance measures such as a congestion window and throughput. The suggested algorithm has better throughput than other algorithm over wireless links with high PER and similar throughput to others over wireless links with low BER.

• Journal of the Korean Society for Railway
• /
• v.15 no.1
• /
• pp.80-87
• /
• 2012

This study analyzed the quality of a commuter rail service of Incheon line 1 with respect to two service measures such as occupancy (crowdedness) and punctuality based on transit smart card data collected in 2009. In order to analyze the metro services by individual fleet, we aggregated the personal level card data into the fleet operated in each planned schedule. The results show a low level of service for both crowdedness and punctuality during peak hours at the line segment from 'Gyeyang' to 'International business district'. Further, a close relationship between vehicle occupancy and punctuality is found, which illustrates high passenger demand causes successive metro delay.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.3
• /
• pp.50-62
• /
• 2015

Recently, Subway Line No. 9, described as a 'hell-like' subway for its recorded load factor of max. 240% due to the opening of the 2nd phase extension section, has been causing problems of recurrent congestion in a subway station building. A recurrent congestion in the station building becomes a factor to offend rail users and to reduce the efficiency of railway management. This study aims to establish the methodology for effect evaluation of information provided to rail users, and conducts a gate metering case study considering the congested conditions at a platform among the methodologies for effect evaluation. The metering effect evaluation by load factor was conducted through selecting the micro simulation and pedestrian simulation tool grafting a gate metering. As a result, it was confirmed that, if gate metering is performed, the service level and pedestrian density of a platform by load factor would improve. In other words, if metering is conducted at a platform, it is possible to control the load factor in the waiting space of a platform. Therefore, it was judged through this study that it is possible to set up the index for effect evaluation of information provided to manage congestion of rail users, and establish the methodology for effect evaluation of information provided to rail users through a program.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• v.4 no.2
• /
• pp.161-166
• /
• 2001

Purpose: Poor living conditions such as overcrowding and sharing a bed are reported to be significant risk factors for H. pylori infection throughout childhood. We investigated the prevalence of Helicobacter pylori infection in Korean athletes who are obliged to live together in training camps over six months a year. Methods: Blood sampling and surveying through questionnaire were performed on 440 regular high school students (228 boys and 212 girls) and 220 athletes (148 boys and 72 girls) of a physical education high school. We measured serum IgG Ab to H. pylori in order to compare the prevalence of H. pylori infection between normal adolescents and athletes. In addition, we conducted a nutritional analysis and questionnaire survey for socioeconomic status in order to compare other risk factors that might influence H. pylori infection between groups. Results: The prevalence (43.2%) of H. pylori infection in athletes was higher than that (22.7%) in the controls. No significant differences in the nutritional factors or socioeconomic status, such as Hollingshead index, type of house, and crowding index, were found between the groups. Multivariate analysis showed that crowding and the difference in school type were the significant predictors of H. pylori seropositivity after controlling for dietary and socioeconomic factors. Conclusion: Living together in training camps might be a significant risk factor for H. pylori infection in athletes.

• Journal of Korean Society of Transportation
• /
• v.30 no.3
• /
• pp.83-91
• /
• 2012

The objective of this study is to build a methodology for evaluating intelligent transportation systems (ITS) projects, by selecting measures of effectiveness (MOEs) and developing an approach to collect and process traffic data. While reviewing the existing MOEs and evaluation methodologies for ITS projects, several problems were found, such as the complication in delineating study areas, the absence of standardized evaluation methodologies, and the duplication in selecting MOEs. To tackle these problems, two MOEs capable of directly evaluating traffic conditions were chosen: i.e., average vehicle speed and traffic volume. Both MOEs can not only include all the functions of the existing MOEs, but also be simpler and more objective in evaluating real traffic conditions. The traffic volume can be measured by using either "cordon line" or "all point average" methods. On the other hand, measuring the average vehicle speed depends on site-specific characteristics such as traffic flow states (interrupted or uninterrupted) and traffic conditions (congested or uncongested). The present methodology is easily understandable for anyone and applicable for any ITS project, and is also expected to contribute to building a standardized evaluation system.

• Korean Journal of Environment and Ecology
• /
• v.25 no.1
• /
• pp.111-117
• /
• 2011

The purpose of this study is to establish trail use impact indicators, and evaluate the degree of use impact based on the understanding of the causality among the impacts on the spot. Theoretical reviews developed three indicators in terms of three ecological impacts, four physical impacts, and five sociological impacts, respectively. With this indicators, observation and questionnaire survey were employed on Gwanak Mountain Trail to measure the levels of impacts forementioned. As for the ecological impact, Some loss of ground cover vegetation was reveled near the trail due to trail use, however the level of disturbance by the naturalized and exotic plants was insignificant. Physical impacts such as soil hardness, enlargement of trail width were found intensified. The result of measuring sociological impacts showed visitors had expected higher level of crowding and encounters before their visit, therefore overall satisfaction level was positive, despite higher awareness level of actual crowding. Intensified continuing use of the trail is aggravating ecological and physical impacts on Gwanak Mountain trail, because of its location in a metropolitan area. Sociological impacts seem favorable at present, however if ecological and physical impacts were deteriorated, sociological impacts would also be affected. To maintain the quality level of use experience, managerial efforts to improve climbing culture as well as ecological and physical environment such as restoration of damaged areas are needed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.5
• /
• pp.72-84
• /
• 2017

Together with the Big Data of the 4th Industrial Revolution, the traffic information system has been changed to an section detection system by the point detection system. With DTG(Digital Tachograph) data based on Global Navigation Satellite System, the properties of raw data and data according to processing step were examined. We identified the vehicle trajectory, the link travel time of individual vehicle, and the link average travel time which are generated according to the processing step. In this paper, we proposed a application method for traffic management as characteristics of processing data. We selected the historical data considering the data management status of the center and the availability at the present time. We proposed a method to generate the Travel Time Index with historical link average travel time which can be collected all the time with wide range. We propose a method to monitor the traffic congestion using the Travel Time Index, and analyze the case of intersections when the traffic operation method changed. At the same time, the current situation which makes it difficult to fully utilize DTG data are suggested as limitations.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.5
• /
• pp.183-193
• /
• 2019

This study developed a shockwave detection and prediction of their extinction point method based on continuous wavelet transform using trajectory data from probe vehicles equipped with automotive sensors.. To analyze the effectiveness of the proposed method, this paper proposed two measures which are a distance error between the extinction points of the predictor and an time-location error of the extinction points. The proposed concept was proved using the micro simulation based experiment with three exogenous variables of traffic volume, lane-close duration, market penetration of probe vehicles. The analysis results show that the proposed method is capable of detecting the traffic shockwaves as well as predicting their extinction point, and also that the accuracy of the proposed method is highly dependent on the rate of the probe vehicles.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.4
• /
• pp.1611-1617
• /
• 2013

Information about trafficability or the condition of road with regard to its being traveled over by vehicles is one of the most critical factors for roadway operation in winter. Specifically, when traveling on snowy or icy surfaces, the traction force varies per vehicle type including tire types, geometric characteristics of roads, and conditions of road surfaces. In general, front-wheel drive or four-wheel drive vehicles have better traction performance on snowy or icy surface than rear-wheel drive vehicles, and the latter type vehicle causes more serious traffic congestion when there is unexpected snowfall. Thus, traffic information regarding trafficability with respect to vehicle types, geometric characteristics of roadway sections, and roadway surface conditions can provide a foundation to make a decision whether to use the associated roadway sections for roadway operators as well as users. Based on the preceding premise, the objective of this study is to present a methodology for developing a trafficability index with respect to vehicle types, geometric characteristics of roadway sections, and roadway surface conditions.