• International Journal of Highway Engineering
• /
• v.13 no.1
• /
• pp.69-77
• /
• 2011

This study is to suggest a methodology to overcome the uncertainty and lack of reliability of data. The fuzzy reasoning model and the neural network model were developed in order to overcome the potential lack of reliability which may occur during the process of data collection. According to the result of comparison with the Poisson regression model, the suggested models showed better performance in the accuracy of the accident frequency prediction. It means that the more accurate accident frequency prediction model can be developed by the process of the uncertainty of raw data and the adjustment of errors in data by learning. Among the suggested models, the performance of the neural network model was better than that of the fuzzy reasoning model. The suggested models can evaluate the safety of signalized intersections in operation and/or planning, and ultimately contribute the reduction of accidents.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.1
• /
• pp.90-100
• /
• 2017

This paper investigates pedestrian-thrown distance pattern by pedestrian-vehicle collision position by madymo-simulation. The simulation were performed for every 2.5 cm interval between center and edge of bumper for various vehicle speeds and vehicle shapes. As a result, two critical points where thrown distance change rapidly were found. First critical point locate where pedestrian's shoulder do not contact the vehicle. Second point locate where the center of gravity of pedestrian are close to edge of bumper. Between 1st and 2nd critical points, thrown distance decrease rapidly where collision points move to the edge of vehicle. In other cases, the thrown distance does not change rapidly. This result gives more accurate guideline for pedestrian collision in traffic safety.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.3
• /
• pp.102-111
• /
• 2012

Expresway traffic accident is fatal accident by high speed, especially human injury is a great social issue. This paper aims to identify characteristic differences of highway accidents that involve human injuries or not. To analysis the elements that affect the two types of accidents used the logistic regression model. The analysis showed that human injury accident rate is increased in case of straight road, flat, or cut-slope areas, barriers, male driver, and older driver. These results provide the ground for actions to counter the problems. By discovering factors for accidents leading to fatality, this study can provide important implications for authorities that establish highway safety measures and policies in preventing human injuries or deaths from car accidents.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.3
• /
• pp.1105-1113
• /
• 2013

Understanding the characteristics of truck-involved crashes is of keen interest because such crashes are highly associated with greater potential leading to severer injury. The purpose of this study is to identify factors affecting injury severity of truck-involved crashes on freeways. In addition, a binary logistic regression technique is applied to identify causal factors affecting truck crash severity under normal and adverse weather conditions. Major findings from the analyses are discussed with truck operations strategies including speed enforcement, variable speed limit, and truck lane restriction, from the safety enhancement point of view. The results of this study would be useful for developing traffic control and operations strategies to reduce truck-involved crashes and injury severity in practice.

• International Journal of Highway Engineering
• /
• v.14 no.2
• /
• pp.83-91
• /
• 2012

This study deals with the operational efficiency of roundabout. The roundabouts generally have such the merits as high capacity, delay reduction, safety improvement, and others. Circular intersection can be divided into the rotary and roundabout according to travelling priority. The objective of this study is to comparatively analyze the operational efficiency of rotary and roundabout by scenario. In pursuing the above, this study gives the particular attentions to developing 256 scenarios according to the directional and entering traffic volume and analyzing the delay using VISSIM. The main results are as follows. First, the average delay of rotary was analyzed to be 1.56-8.74 times of roundabout. Second, the operational efficiencies of rotary and roundabout were analyzed to be better in the case of bigger differences in the traffic volumes between the main and minor roads. Third, the average delay of the 4-legged was evaluated to be 1.77-11.70 times of 3-legged intersection. Finally, 2-lane intersection (3-legged & 4-legged) was analyzed to be 2.02-2.23 times of 1-lane intersection.

• Journal of Preventive Medicine and Public Health
• /
• v.37 no.3
• /
• pp.274-281
• /
• 2004

Objectives : This study was performed to investigate the injury rates and risk factors for preschool children in Daegu city and Kyungpook province. Method : A questionnaire survey about medically attended injuries during the preschool period was performed in nine primary schools located in Daegu city, Pohang city and Goryung County. The overall injury rate was estimated using person-year. The causes and patterns of the injuries, and their risk factors were examined. Result : A total of 469 medically attended injuries were reported in 330 of the 959 study subjects during the preschool period. The overall annual injury rate was 7.5 per 100 children. The injury rate increased sharply during the period from infant (2.4) to 1 year of age (7.5), and the peak injury rate (9.2) was reported for 5 year olds. The most common causes of injuries were falling (36.0%), followed by being struck by an object (23.7%), and traffic accidents (14.1%). Among the traffic accidents, 72.8% occurred while playing on the road, riding a bicycle or roller-skating. A proportional hazard model showed that males (hazard ratio=1.49, p<0.001 compared with female) and the mother's higher education level (hazard ratio of college or higher= 1.51, p=0.013; high school=1.32, p=0.085 compared with those of middle school or lower) were significant risk factors of childhood injury. Conclusion : The results of this study suggested that efforts for children's safety should be made, especially from the toddler stage, and in male children. To develop a more specific childhood injury prevention program, a surveillance system for injuries should be established. Further study of the relationship between mother's occupation and injury rates is also needed.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.21 no.3
• /
• pp.60-68
• /
• 2017

Since the bridge is the main facility of the road that is the core of the civil infrastructure, the bridge is constructed to ensure stability and serviceability during the traffic use. In order to secure the safety of bridges, evaluating the integrity of bridges at present is an important task in the maintenance work of bridges. In general, to evaluate the load carrying capacity of bridges, it is possible to confirm the superimposed behavior and symmetric behavior of bridges by estimating the lateral load distribution factor of the bridges through vehicle loading tests. However, in order to measure the lateral load distribution factor of a commonly used bridge, a static loading test is performed. There is a difficulty in traffic control. Therefore, in this study, the static displacement component of the bridge measured in the dynamic loading test and the ambient vibration test was extracted by using empirical mode decomposition technique. The lateral load distribution was estimated using the extracted static displacement component and compared with the lateral load distribution factor measured in the static loading test.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3904-3922
• /
• 2022

As a research hotspot, pedestrian detection has a wide range of applications in the field of computer vision in recent years. However, current pedestrian detection methods have problems such as insufficient detection accuracy and large models that are not suitable for large-scale deployment. In view of these problems mentioned above, a lightweight pedestrian detection and early warning method using a new model called you only look once (Yolov5) is proposed in this paper, which utilizing advantages of Yolov5s model to achieve accurate and fast pedestrian recognition. In addition, this paper also optimizes the loss function of the batch normalization (BN) layer. After sparsification, pruning and fine-tuning, got a lot of optimization, the size of the model on the edge of the computing power is lower equipment can be deployed. Finally, from the experimental data presented in this paper, under the training of the road pedestrian dataset that we collected and processed independently, the Yolov5s model has certain advantages in terms of precision and other indicators compared with traditional single shot multiBox detector (SSD) model and fast region-convolutional neural network (Fast R-CNN) model. After pruning and lightweight, the size of training model is greatly reduced without a significant reduction in accuracy, and the final precision reaches 87%, while the model size is reduced to 7,723 KB.

• Korean Journal of Culture and Social Issue
• /
• v.12 no.1
• /
• pp.35-54
• /
• 2006

This study analysed the effect of music tempo on young drivers' driving speed. 23 male college students under age 26 were randomly assigned to one of three music conditions as follows; No Music, Slow Music and Fast Music. Every subject's travel time(sec) and driving speed(Km/h) was recorded while they were driving a computer-based driving simulator. As the results of this study, we found that 1) the fast music group's mean of travel time was the shortest and also, 2) their mean of driving speed was the fastest. The effect of music tempo on driving speed can be explained as a biological mechanism, same as the effect on our heart-beat rate or intensity of physical exercising. This result shows us that listening musics while driving can affect the driving speed instead of the driver's physical condition.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.4
• /
• pp.375-382
• /
• 2020

As the 4th Industrial Revolution era in worldwide, interest in autonomous vehicles is increasing. but due to recent safety issues such as pedestrian accidents and car accidents, as a technical model for this, the demand for 3D HD maps (High Definition maps) is increasing in including lanes, road markings, road information, traffic lights and traffic signs etc. However, since some complementary points have been continuously raised according to demand, It is necessary to collect the opinions of institutions and companies utilizing HD maps and to improve HD maps. This study was conducted by utilizing the results of the contest for usability verification of HD Maps hosted by the National Geographic Information Institute and organized by the Spatial Information Industry Promotion Institute. For this study, we researched HD maps' layers and codes for HD maps object usability to improve HD maps, constructed HD maps object usability items accordingly, and contested usability verification of HD maps according to the items The contestants conducted verification and analyzed the results. As a result, the most frequently used code for each layer was the flat intersection, and the code showing the highest usage rate was a safety sign. In addition, the use rate of the sub-section and height obstacles was 16.67% and 8.88%, respectively, showing a low ratio. In order to utilize HD maps in the future, this study is expected to require research to continuously collect opinions from customers and improve data objects and data models that are actually needed by customers.