基于缓冲区重采样的LSTM林火预测模型*

为提高林火风险预测精度,挖掘地图上隐含的空间信息、时间序列上隐含的长期趋势和循环波动,提出1种基于缓冲区重采样的长短期记忆（LSTM）林火预测模型,选取15个与林火相关的影响因素,以方差膨胀因子为评价指标对其进行多重共线性检验,方差膨胀因子大于10的因素具有共线性,并采用信息增益率验证筛选结果的合理性。考虑到火灾的空间聚集特性,采用缓冲区分析与过采样相结合方法减少样本不均衡现象的影响,最终得到176 732条样本。对12个影响因素和研究时间段的火点建立LSTM预测模型,对森林火灾发生风险进行预测。研究结果表明:基于缓冲区重采样的LSTM林火预测模型有效考虑时空上隐含的信息,预测模型准确率为87.06%,特异性为97.99%,敏感度为76.12%,阳性预测率为97.43%,阴性预测率为80.41%,ROC曲线与AUC值均优于随机森林（RF）和支持向量机（SVM）这2种基准算法。维尔克松秩和检验发现,本文提出的模型与基准算法结果具有显著性差异。研究结果可为提高林火风险预测精度提供参考。     

大型公园道路网络关键节点脆弱性评价

为更加科学有效地辨识景区道路网络中的客流关键节点,以节点脆弱性为度量指标,提出1种基于FIM模型的关键节点脆弱性评价方法.以某大型公园为例,首先通过ArcGIS软件将该公园的道路网络信息转换成可编译的文本信息,经过Java枚举可行路径,然后利用嵌入FIM算法的Lingo进行优化,得出网络节点的重要度.最后综合节点容量、...     

基于云模型的城轨信号系统安全保障能力评价方法

为准确评价城轨信号系统安全保障能力及影响因素,基于云理论对定性与定量因素的良好融合优点,构建城轨信号系统安全保障能力评价云模型及评价指标体系,采用组合赋权法对各指标赋予权重,并基于专家意见,利用正向云发生器生成标准云.结果表明:该云模型具有一定稳定性和可靠性,可对城轨信号系统安全保障能力进行有效测评,同时能够发现安全运...     

An in-depth analysis of self-reported cycling injuries in single and multiparty bicycle crashes in Denmark

Introduction: Cycling is one of the main forms of transportation in Denmark. However, while the number of traffic crash fatalities in the country has decreased over the past decade, the frequency of cyclists killed or seriously injured has increased. The high rate of serious injuries and fatalities associated with cycling emphasizes the increasing need for mitigating the severity of such crashes. Method: This study conducted an in-depth analysis of cyclist injury severity resulting from single and multiparty bicycle-involved crashes. Detailed information was collected using self-reporting data undertaken in Denmark for a 12-month period between 1 November 2012 and 31 October 2013. Separate multilevel logistic (MLL) regression models were applied to estimate cyclist injury severity for single and multiparty crashes. The goodness-of-fit measures favored the MLL models over the standard logistic models, capturing the intercorrelation among bicycle crashes that occurred in the same geographical area. Results: The results also showed that single bicycle-involved crashes resulted in more serious outcomes when compared to multiparty crashes. For both single and multiparty bicycle crash categories, non-urban areas were associated with more serious injury outcomes. For the single crashes, wet surface condition, autumn and summer seasons, evening and night periods, non-adverse weather conditions, cyclists aged between 45 and 64 years, male sex, riding for the purpose of work or educational activities, and bicycles with light turned-off were associated with severe injuries. For the multiparty crashes, intersections, bicycle paths, non-winter season, not being employed or retired, lower personal car ownership, and race bicycles were directly related to severe injury consequences. Practical Applications: The findings of this study demonstrated that the best way to promote cycling safety is the combination of improving the design and maintenance of cycling facilities, encouraging safe cycling behavior, and intensifying enforcement efforts.     

Investigating factors affecting severity of large truck-involved crashes: Comparison of the SVM and random parameter logit model

Introduction: Reducing the severity of crashes is a top priority for safety researchers due to its impact on saving human lives. Because of safety concerns posed by large trucks and the high rate of fatal large truck-involved crashes, an exploration into large truck-involved crashes could help determine factors that are influential in crash severity. The current study focuses on large truck-involved crashes to predict influencing factors on crash injury severity. Method: Two techniques have been utilized: Random Parameter Binary Logit (RPBL) and Support Vector Machine (SVM). Models have been developed to estimate: (1) multivehicle (MV) truck-involved crashes, in which large truck drivers are at fault, (2) MV track-involved crashes, in which large truck drivers are not at fault and (3) and single-vehicle (SV) large truck crashes. Results: Fatigue and deviation to the left were found as the most important contributing factors that lead to fatal crashes when the large truck-driver is at fault. Outcomes show that there are differences among significant factors between RPBL and SVM. For instance, unsafe lane-changing was significant in all three categories in RPBL, but only SV large truck crashes in SVM. Conclusions: The outcomes showed the importance of the complementary approaches to incorporate both parametric RPBL and non-parametric SVM to identify the main contributing factors affecting the severity of large truck-involved crashes. Also, the results highlighted the importance of categorization based on the at-fault party. Practical Applications: Unrealistic schedules and expectations of trucking companies can cause excessive stress for the large truck drivers, which could leads to further neglect of their fatigue. Enacting and enforcing comprehensive regulations regarding large truck drivers’ working schedules and direct and constant surveillance by authorities would significantly decrease large truck-involved crashes.     

Investigation of injury severities in single-vehicle crashes in North Carolina using mixed logit models

IntroductionRoadway departure (RwD) crashes, comprising run-off-road (ROR) and cross-median/centerline head-on collisions, are one of the most lethal crash types. According to the FHWA, between 2015 and 2017, an average of 52 percent of motor vehicle traffic fatalities occurred each year due to roadway departure crashes. An avoidance maneuver, inattention or fatigue, or traveling too fast with respect to weather or geometric road conditions are among the most common reasons a driver leaves the travel lane. Roadway and roadside geometric design features such as clear zones play a significant role in whether human error results in a crash. Method: In this paper, we used mixed-logit models to investigate the contributing factors on injury severity of single-vehicle ROR crashes. To that end, we obtained five years' (2010–2014) of crash data related to roadway departures (i.e., overturn and fixed-object crashes) from the Federal Highway Administration's Highway Safety Information System Database. Results: The results indicate that factors such as driver conditions (e.g., age), environmental conditions (e.g., weather conditions), roadway geometric design features (e.g., shoulder width), and vehicle conditions significantly contributed to the severity of ROR crashes. Conclusions: Our results provide valuable information for traffic design and management agencies to improve roadside design policies and implementing appropriately forgiving roadsides for errant vehicles. Practical applications: Our results show that increasing shoulder width and keeping fences at the road can reduce ROR crash severity significantly. Also, increasing road friction by innovative materials and raising awareness campaigns for careful driving at daylight can decrease the ROR crash severity.     

The acceptance of personal protective equipment among Hong Kong construction workers: An integration of technology acceptance model and theory of planned behavior with risk perception and safety climate

Introduction: The phenomenon that construction workers do not use personal protective equipment (PPE) is a major reason for the high occurrence frequency of accidents in the construction industry. However, little efforts have been made to quantitatively examine the factors influencing construction workers’ acceptance of PPE. Method: In the current study, a PPE acceptance model for construction workers (PAMCW) was proposed to address the noted need. The PAMCW incorporates the technology acceptance model, theory of planned behavior, risk perception, and safety climate for explaining construction worker acceptance of PPE. 413 construction workers participated in this study to fill out a structured questionnaire. The PAMCW was analyzed using structural equation modeling. Results: Results provide evidence of the applicability of the technology acceptance model and theory of planned behavior to the PPE acceptance among construction workers. The positive influence of safety climate and risk perception-severity on attitude toward using PPE was significant. Safety climate positively influences perceived usefulness. Risk perception-worry and unsafe was found to positively affect intention to use PPE. Practical Applications: Practical suggestions for increasing construction workers’ use of PPE are also discussed.     

基于ARIMA-LOESS模型的危化品道路运输事故起数预测

文章针对危化品道路运输事故预测问题,运用差分自回归移动平均模型(Autoregressive Integrat-ed Moving Average,ARIMA)与局部加权回归模型(Locally Estimated Scatterplot Smoothing,LOESS)的组合模型,对我国危化品道路运输事故发生起数进行...     

基于云模型的富水岩溶隧道涌水风险评价

为适应风险因素不确定性、随机性及动态反馈性等特点,建立新型富水岩溶隧道涌水风险评价体系,提出1种基于云模型的模糊综合评价方法.选取5个1级指标、29个2级指标构建评价指标体系;综合层次分析、熵权与加权平均计算法合理分配各指标权重;利用云生成算法计算出云数字特征参数并生成足够数量的云滴;将方法应用于贵州省某隧道涌水风险评...