• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.3
• /
• pp.87-97
• /
• 2018

The traffic accident reports that are generated by the Traffic Broadcasting Networks(TBN) are unstructured data. It, however, has the value as some sort of real-time traffic information generated by the viewpoint of the drives and/or pedestrians that were on the roads, the time and spots, not the offender or the victim who caused the traffic accidents. However, the traffic accident reports, which are big data, were not applied to traffic accident analysis and traffic related research commonly. This study adopting text-mining technique was able to provide a clue for utilizing it for the impacts of traffic accidents. Seven years of traffic reports were grasped by this analysis. By analyzing the reports, it was possible to identify the road names, accident spot names, time, and to identify factors that have the greatest influence on other drivers due to traffic accidents. Authors plan to combine unstructured accident data with traffic reports for further study.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.264-283
• /
• 2023

Unlike conventional vehicle traffic accidents, autonomous vehicles traffic accidents can be caused by various factors, including technical problems, the environment, and driver interaction. With the future advances in autonomous driving technology, new issues are expected to emerge in addition to the existing accident causes, and various scenario-based approaches are needed to respond to them. This study developed autonomous vehicle traffic accident scenarios by collecting autonomous driving accident reports, CA DMV collision reports, autonomous driving mode disengagement reports, and autonomous driving actual accident videos. The scenarios were derived based on the functional safety system failure modes of ISO 26262 and attempted to reflect the various issues of autonomous driving functions. The autonomous vehicle scenarios derived through this study are expected to play an essential role in preventing and preparing for various autonomous vehicle traffic accidents in the future and improving the safety of autonomous driving technology.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.841-854
• /
• 2020

The paper explains the method to process, analyze and predict traffic patterns in Los Angeles county using Big Data and Machine Learning. The dataset is used from a popular navigating platform in the USA, which tracks information on the road using connected users' devices and also collects reports shared by the users through the app. The dataset mainly consists of information about traffic jams and traffic incidents reported by users, such as road closure, hazards, accidents. The major contribution of this paper is to give a clear view of how the large-scale road traffic data can be stored and processed using the Big Data system - Hadoop and its ecosystem (Hive). In addition, analysis is explained with the help of visuals using Business Intelligence and prediction with classification machine learning model on the sampled traffic data is presented using Azure ML. The process of modeling, as well as results, are interpreted using metrics: accuracy, precision and recall.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.6 no.2
• /
• pp.217-224
• /
• 2002

This paper is proposed a reasonable method for determining the dynamic properties, the impact factors caused by traffic loads on highway bridges. In addition, the impact factors obtained in previous inspection reports were classified by the span length of the bridge, kind of bridge and type of bridge and the result of the impact factor was adjusted by a statistical method and presented problems. Also, the method for determining the impact factor using traffic load is proposed and the proposed method is compared with the specification code. The method estimating the impact factors due to the traffic loads can efficiently recognize the response of the structure by providing the impact factors and help to save the investigation cost, and also it can be used for the maintenance of structures using the usual test of bridges.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.21 no.1
• /
• pp.107-112
• /
• 2013

Base on insurance vehicle collision and bodily injury claim reports, 23,655 cases of vehicle to vehicle accidents occurred in Korea 2010 are investigated in order to understand vehicle damage severities, repair costs and occupant injury types. The results of our statistical analysis reveal that minor damages with small dent or scratches on vehicle body panels which is assumed to imply during very low speed crashes are major portion of accident severities types. The most vulnerable body regions due to the real-world accident are neck. The 86.3% of total injured driver in minor rear damaged vehicles has reported neck pains and they are followed by whole bodies and head but with much lower occurrence rates.

• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.1-9
• /
• 2022

To provide real-time traffic conditions, crowd sourcing based traffic information services in which users directly report and share traffic conditions are being developed. However, the existing traffic information service provides limited traffic conditions because it only shares information reported by specific service participants. In this paper, we design and develop a crowd sourcing based traffic information service that provides real-time traffic conditions by collecting direct reports from users and public traffic conditions. The proposed service allows users to directly report traffic conditions by voice and text, and collects and integrates traffic conditions published by external organizations. The collected traffic conditions are provided in real time through a push service, and new traffic conditions are transmitted when the user's location changes. The proposed service can report traffic conditions and share real-time traffic conditions through an Android app.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2001.11a
• /
• pp.809-814
• /
• 2001

In this paper, dynamic properties of a bridge by traffic loads, is proposed as a reasonable method for the determining the impact factor. In addition, impact factors obtained from previous inspection reports were classified by the span length of the bridge, kind of the bridge and type of the bridge and adjusted the result of the impact factor by the statistical method and presented problems. Also, the determining method of the impact fatter using traffic load is proposed and compared the proposed method with the specification code. The method estimating the impact factor by the traffic loads can be efficiently concluded to the response of structure as reflecting the impact factor and saving the investigation cost. Also it is expected to use to maintenance of structures using the usual test of the bridge.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.6
• /
• pp.1339-1345
• /
• 2015

Korean government annually estimates and reports the traffic safety index to evaluate the traffic safety of 228 Gu Gun. However, since the traffic safety index is derived from the spatially macroscopic perspective based on collected relative data, there are a couple of problems such as inability to investigate the individual traffic accidents on the spot, insecurity of accuracy and reliability of traffic safety index estimation method, and absence of establishing temporal relationship of traffic accidents. Thus, this study investigated temporal traffic safety in macroscopic manner for Gu Gun in Busan depending on the installation of the traffic safety facility (i.e., urban median), employing meta analysis. As a result, all Gu Gun in Busan except Saha, Buk, Dong, and Busanjin experienced more traffic accidents after installing the urban median, indicating that there are more rooms for improvement of macroscopic traffic safety evaluation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.2
• /
• pp.264-270
• /
• 2006

In this paper we verified that the window based TCP performance of throughput can be improved by the traffic connection efficiency. and have studied the performance of traffic congestion control that is controlling transmission rate. In wireless network, the bidirectional node is run by estimating the usage rate of link of error control idle and the throughput is shown by transmitting segments. The throughput rate shows almost no delay due to the bidirectional traffic connection efficiency up to the allowable point as increasing the transport rate by the critical value, depending on the size of end-to-end node queue of the increase of transport rate. This paper reports the performance improvement as the number of feedback connection traffic congestion control increases because of the increase of the number of asynchronous transport TCP connections.

• Journal of Korean Medical Ki-Gong Academy
• /
• v.17 no.1
• /
• pp.52-63
• /
• 2017

Objectives : The purpose of this study is to report the case with pneumocranium in a traffic accident patient by korean medicine. Methods : The subject is a patient with pneumocranium in a traffic accident. This patient was treated with korean medical treatments. Results : After the treatment, pneumocranium in right cerebral convexities in brain CT is removed. The symptoms is improved significantly Conclusions : This study shows that a patient with pneumocranium was diagnosed with stroke and cured without a recurrence through holistic treatment of Korean medicine.