• Journal of Digital Convergence
• /
• v.19 no.4
• /
• pp.25-31
• /
• 2021

Moving toward an aged society, traffic accidents involving elderly drivers have also attracted broader public attention. A rapid increase of senior involvement in crashes calls for developing appropriate crash-severity prediction models specific to senior drivers. In that regard, this study leverages machine learning (ML) algorithms so as to predict the severity of vehicle-pedestrian collisions induced by elderly drivers. Specifically, four ML algorithms (i.e., Logistic model, K-nearest Neighbor (KNN), Random Forest (RF), and Support Vector Machine (SVM)) have been developed and compared. Our results show that Logistic model and SVM have outperformed their rivals in terms of the overall prediction accuracy, while precision measure exhibits in favor of RF. We also clarify that driver education and technology development would be effective countermeasures against severity risks of senior driver-induced collisions. These allow us to support informed decision making for policymakers to enhance public safety.

• International Journal of Highway Engineering
• /
• v.13 no.1
• /
• pp.119-127
• /
• 2011

The main purpose of this paper is to apply Zone 30 system which is being experimented in advanced country for the solution of controlling the residential street's speed to our country with the consideration of the real condition of our street and traffic and to run this system as an example to analyze the effect and at the same time, analyze the problem and get appropriate preparation for this system to be widespread. The area to run this model project is Goyang City Ilsan-Gu.($0.65km^2$) which is close with the commercial area reflecting the opinion of experts and an on-site verification by the National Police Agency T/F and is having a heavy pedestrian traffic and the risk of pedestrian accident. Firstly we defined residential street and residential street area to review the system and devided the residential street type to establish a plan of operation. Afterwards, we thoroughly examined the model project area and analyzed the problem and solution. We finally completed establishing a facilities by conference with a local autonomous entity with the improvement of facility's sketch at the analysis of the model project area. The result of effects analysis which we devided after and before of establishment is that vehicle speed be reduced 5~15km/h, and traffic accidents has decreased by 24 percent.

• Journal of Digital Convergence
• /
• v.14 no.6
• /
• pp.439-448
• /
• 2016

The population over 65 years old is 12.7% of total population in 2014 and Korea is going to be an aged society in the near future. The transportation vulnerable including the aged should be guaranteed in walking mobility under safe and comfortable environment for their socio-economic activities. For the era of fusion and convergence this paper investigated the characteristics of walking accidents related to the aged pedestrians and analyzed the aged-oriented walking factors with a reaction time and a walking speed at crosswalks in Yeosu. In the results, the crashes for the aged occur at 9.9% of total crashes and the fatalities of the aged are 40.3% of total fatalities in 2014. The 47.4% of the aged fatalities is also attributed to vehicle-to-pedestrian accidents. The 49.3% of all pedestrian fatalities occurs at the aged pedestrians with a very high proportion. The reaction time and walking speed for the aged were determined as the values located at the lower 15%-tile of the elderly physical ability. It is shown that the reaction time is 4.56 seconds and the walking speed is 0.76 m/s in the case of Yeosu. From two factors' standpoint, the walking environment at crosswalks in Yeosu is inappropriate for the aged.