This page has only limited features, please log in for full access.
Ku-Lin Wen majors in traffic engineering and motorcycle safety, and he is now a Ph.D. candidate at National Taiwan University. His research works are mainly related to motorcycle safety.
The mixed traffic environment often has high accident rates. Therefore, many motorcycle-related traffic improvements or control methods are employed in countries with mixed traffic, including slow-traffic lanes, motorcycle two-stage left turn areas, and motorcycle waiting zones. In Taiwan, motorcycles can ride in only the two outermost lanes, including the curb lane and a mixed traffic lane. This study analyzed the new motorcycle-riding space control policy on 27 major arterial roads containing 248 road segments in Taipei by analyzing before-and-after accident data from the years 2012–2018. In this study, the equivalent-property-damage-only (EPDO) method was used to evaluate the severity of crashes before and after the cancelation of the third lane prohibition of motorcycles (TLPM) policy. After EPDO analysis, the random forest analysis method was used to screen the crucial factors in accidents for specific road segments. Finally, a classification and regression tree (CART) was created to predict the accident improvement effects of the road segments with discontinued TLPM in different situations. Furthermore, to provide practical applications, this study integrated the CART results and the needs of traffic authorities to determine four rules for canceling TLPM. In the future, on the accident-prone road segment with TLPM, the inspection of the four rules can provide the authority to decide whether to cancel TLPM to improve the accident or not.
Tien-Pen Hsu; Ku-Lin Wen; Taiyi Zhang. Applying Machine Learning to Develop Lane Control Principles for Mixed Traffic. Sustainability 2021, 13, 7656 .
AMA StyleTien-Pen Hsu, Ku-Lin Wen, Taiyi Zhang. Applying Machine Learning to Develop Lane Control Principles for Mixed Traffic. Sustainability. 2021; 13 (14):7656.
Chicago/Turabian StyleTien-Pen Hsu; Ku-Lin Wen; Taiyi Zhang. 2021. "Applying Machine Learning to Develop Lane Control Principles for Mixed Traffic." Sustainability 13, no. 14: 7656.
Introduction: In Taiwan, segregated traffic flow countermeasures have long been in place. Although these facilities have decreased the numbers of motorcycle left-turn collisions, right-angle collisions, and sideswipe collisions, they have also induced serious right-turn accidents. The purpose of this research was to evaluate an intervention intended to decrease conflicts and motorcycle-involved crashes. In this study, the reasons why the motorcycle accident rate is higher at intersections with slow lanes than at those without slow lanes are presented, and the theory of the self-explaining road was applied to create divergence markings for a mixed traffic flow environment. An intervention that guides motorcycles and cars into appropriate locations at intersections was applied to three intersection approaches. Method: The intervention effectiveness was evaluated by comparing the number of accidents at the intersections before and after the implementation of improvement measures. Moreover, video recordings were used to analyze the traffic distributions at the cross-sections of intersections. T-test was adopted to examine whether the traffic flows at the cross-sections of the intersections before and after the intervention were statistically different. In addition, this research applied the post-encroachment time (PET), the time between the first road user leaving the encroachment zone and the second road user arriving in it, to evaluate traffic conflicts. Finally, the PET and severity index between a straight-through motorcycle and a right-turn vehicle were analyzed. Results: PET increased by 3.2%–20.4%, and the rates of right-turn collisions, sideswipe collisions, and rear-end collisions decreased by 64.3%, 77.3%, and 61.5% respectively. Conclusions: Eliminating the slow traffic lane and setting divergence markings may not effectively cause vehicles in different driving directions to drive in the proper locations in the lanes. However, divergence markings both reduce the rate of right-turn collisions and decrease the incidence of sideswipe and rear-end collisions. Practical applications: The proposed design method may be a good design reference for countries having a high motorcycle density.
Tien-Pen Hsu; Ku-Lin Wen. Effect of novel divergence markings on conflict prevention regarding motorcycle-involved right turn accidents of mixed traffic flow. Journal of Safety Research 2019, 69, 167 -176.
AMA StyleTien-Pen Hsu, Ku-Lin Wen. Effect of novel divergence markings on conflict prevention regarding motorcycle-involved right turn accidents of mixed traffic flow. Journal of Safety Research. 2019; 69 ():167-176.
Chicago/Turabian StyleTien-Pen Hsu; Ku-Lin Wen. 2019. "Effect of novel divergence markings on conflict prevention regarding motorcycle-involved right turn accidents of mixed traffic flow." Journal of Safety Research 69, no. : 167-176.