检索结果-南通市图书馆

road Safety Performance Function Analysis With Visual Feature Importance of Deep Neural Nets

IEEE/CAA Journal of Automatica Sinica 2020年第3期7卷 735-744页

作者： Guangyuan Pan Liping Fu Qili Chen Ming Yu Matthew Muresan Department of Civil and Environmental Engineering University of WaterlooON N2L5G1Canada Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Electronic Engineering the Chinese University of Hong KongHong Kong 999077China

road safety performance function(SPF) analysis using data-driven and nonparametric methods, especially recent developed deep learning approaches, has gained increasing achievements. However, due to the learning mechanisms are hidden in a"black box" in deep learning, traffic features extraction and intelligent importance analysis are still unsolved and hard to *** paper focuses on this problem using a deciphered version of deep neural networks(DNN), one of the most popular deep learning models. This approach builds on visualization, feature importance and sensitivity analysis, can evaluate the contributions of input variables on model's "black box" feature learning process and output decision. Firstly, a visual feature importance(Vi FI) method that describes the importance of input features is proposed by adopting diagram and numerical-analysis. Secondly,by observing the change of weights using Vi FI on unsupervised training and fine-tuning of DNN, the final contributions of input features are calculated according to importance equations for both steps that we proposed. Sequentially, a case study based on a road SPF analysis is demonstrated, using data collected from a major Canadian highway, Highway 401. The proposed method allows effective deciphering of the model's inner workings and allows the significant features to be identified and the bad features to be eliminated. Finally, the revised dataset is used in crash modeling and vehicle collision prediction, and the testing result verifies that the deciphered and revised model achieves state-of-theart performance.

关键词： Deep learning deep neural network(DNN) feature importance road safety performance function

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Determination of critical parameters in the analysis of road tunnel fires

引用

International Journal of Mining Science and Technology 2019年第2期29卷 187-198页

作者： Ali Haghighat Kray Luxbacher Department of Mining & Minerals Engineering Virginia Tech Fire Life Safety Tunnel Ventilation GroupAECOM

The analysis of the fluid characteristics downstream of a fire source in transportation tunnels is one the most important factor in the emergency response, evacuation, and the rescue service studies. Some crucial parameters can affect the fluid characteristics downstream of the fire. This research develops a statistical analysis on the computational fluid dynamics(CFD) data of the road tunnel fire simulations in order to quantify the significance of tunnel dimensions, inlet air velocity, heat release rate, and the physical fire size(fire perimeter) on the fluid characteristics downstream of the fire source. The selected characteristics of the fluid(response variables) were the average temperature, the average density, the average viscosity, and the average velocity. The prediction of the designed statistical models was assessed; then the significant parameters' effects and the parameters interactive effects on different response variables were determined individually. Next, the effect of computational domain length on the selection of the significant parameters downstream of the fire source was analyzed. In this statistical analysis, the linear models were found to provide the statistically good prediction. The effect of the fire perimeter and the parameters interactive effects on the selected response variables downstream of the fire, were found to be insignificant.

关键词： road tunnel fire Two-level fractional factorial design Statistical two-level design CFD Fire dynamics

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Durability and microstructure analysis of the road base material prepared from red mud and flue gas desulfurization fly ash

引用

International Journal of Minerals,Metallurgy and Materials 2020年第4期27卷 555-568页

作者： Emile Mukiza Ling-ling Zhang Xiao-ming Liu School of Metallurgical and Ecological Engineering University of Science and Technology BeijingBeijing 100083China School of Energy and Environmental Engineering University of Science and Technology BeijingBeijing 100083China

The present study aimed to investigate the durability and microstructure evolution of road base materials(RBM)prepared from red mud and flue gas desulfurization fly *** durability testing showed that the strength of RBM with the blast furnace slag addition of 1wt%,3wt%and 5wt%reached 3.81,4.87,and 5.84 MPa after 5 freezing–thawing(F–T)cycles and reached 5.21,5.75,and 6.98 MPa after 20 weting–drying(W–D)cycles,*** results also indicated that hydration products were continuously formed even during W–D and F–T exposures,resulting in an increase of the strength and durability of *** observed increase of macropores(>1μm)after F–T and W–D exposures suggested that the mechanism of RBM deterioration is pore enlargement due to cracks that develop inside their ***,the F–T exposure showed a greater negative effect on the durability of RBM compared to the W–D *** leaching tests showed that sodium and heavy metals were solidified below the minimum requirement,which indicates that these wastes are suitable for use as a natural material replacement in road base construction.

关键词： red mud road base material durability microstructure damage mechanism

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Cognition-Driven Traffic Simulation for Unstructured road Networks

引用

Journal of Computer Science & Technology 2020年第4期35卷 875-888页

作者： Hua Wang Xiao-Yu He Liu-Yang Chen Jun-Ru Yin Li Han Hui Liang Fu-Bao Zhu Rui-Jie Zhu Zhi-Min Gao Ming-Liang Xu School of Information Engineering Zhengzhou UniversityZhengzhou 450001China School of Computer and Communication Engineering Zhengzhou University of Light IndustryZhengzhou 450002China School of Software Zhengzhou University of Light IndustryZhengzhou 450002China

Dynamic changes of traffic features in unstructured road networks challenge the scene-cognitive abilities of drivers,which brings various heterogeneous traffic *** traffic with these heterogeneous behaviors would have significant impact on realistic traffic *** existing traffic methods generate traffic behaviors by adjust-ing parameters and cannot describe those heterogeneous traffic flows in *** this paper,a cognition-driven traffic-simulation method inspired by the theory of cognitive psychology is *** first present a visual-filtering model and a perceptual-information fusion model to describe drivers'heterogeneous cognitive ***,logistic regression is used to model drivers'heuristic decision-making processes based on the above cognitive ***,we apply the high-level cognitive decision-making results to low-level traffic *** experimental results show that our method can provide realistic simulations for the traffic with those heterogeneous behaviors in unstructured road networks and has nearly the same efficiency as that of existing methods.

关键词： unstructured road network traffic simulation cognition-driven heterogeneous

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Elemental composition and risk assessment of heavy metals in the PM10 fractions of road dust and roadside soil

引用

Particuology 2019年第3期17卷 146-152页

作者： Jing Zhang Lin Wu Yanjie Zhang Fenghua Li Xiaozhen Fang Hongjun Mao Center for Urban Transport Emission Research (CUTER) College of Environmental Science and Engineering Nankai University Tianjin 300071 China Tianjin Eco-Environmental Monitoring Center Tianjin 300191 China Tianjin-Tianbinruicheng Environmental Technology and Engineering Co. Ltd. Tianjin 300190 China Nankai University Weijin Road 94. Tianjin 300071 China

A total of 64 dust samples were analyzed to determine the size distribution and elemental composition of the PM10 fraction, including42 road dust(RD), 12 roadside soil(RSD), and 10 park road dust(PRD) samples. The mass of dust smaller than 20μm was dominated by particles sized 2.5-16 μm, which accounted for 85%, 88%, and 87% of the RD, PRD, and RSD, respectively. Additionally, crustal elements accounted for 30.14%, 36.35%, and 37.14% of the PMio fractions of the RD, RSD, and PRD, respectively. The most abundant trace elements in RD, RSD, and PRD were Zn, Mn, and Cu (range, 277 to 874 mg/kg). Moreover, the /geo values revealed all dusts were contaminated with Pb, Zn, Cu, Sb, Sn, and Cd. Health risk assessment showed that Mn, Ni, Cu, Zn, Cd, Sb, and Pb in the PM10 fraction of three types of dusts posed non-cancer risks to children but posed no non-cancer risk to adults. Additionally, As, Ni, and Cd posed no cancer risk to inhabitants.

关键词： road dust Mass size distribution PM10 Elemental composition Health risk assessment

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Progressive LiDAR Adaptation for road Detection

引用

IEEE/CAA Journal of Automatica Sinica 2019年第3期6卷 693-702页

作者： Zhe Chen Jing Zhang Dacheng Tao IEEE the UBTECH Sydney Artificial Intelligence Centre and the School of Computer Science Faculty of Engineering and Information Technologies University of Sydney the School of Automation Hangzhou Dianzi University the University of Technology Sydney

Despite rapid developments in visual image-based road detection, robustly identifying road areas in visual images remains challenging due to issues like illumination changes and blurry images. To this end, LiDAR sensor data can be incorporated to improve the visual image-based road detection,because LiDAR data is less susceptible to visual noises. However,the main difficulty in introducing LiDAR information into visual image-based road detection is that LiDAR data and its extracted features do not share the same space with the visual data and visual features. Such gaps in spaces may limit the benefits of LiDAR information for road detection. To overcome this issue, we introduce a novel Progressive LiDAR adaptation-aided road detection(PLARD) approach to adapt LiDAR information into visual image-based road detection and improve detection performance. In PLARD, progressive LiDAR adaptation consists of two subsequent modules: 1) data space adaptation, which transforms the LiDAR data to the visual data space to align with the perspective view by applying altitude difference-based transformation; and 2) feature space adaptation, which adapts LiDAR features to visual features through a cascaded fusion structure. Comprehensive empirical studies on the well-known KITTI road detection benchmark demonstrate that PLARD takes advantage of both the visual and LiDAR information, achieving much more robust road detection even in challenging urban scenes. In particular, PLARD outperforms other state-of-theart road detection models and is currently top of the publicly accessible benchmark leader-board.

关键词： Autonomous driving computer vision deep learning LiDAR processing road detection

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Determining the road traffic accident hotspots using GIS-based temporal-spatial statistical analytic techniques in Hanoi,Vietnam

引用

Geo-Spatial Information Science 2020年第2期23卷 153-164页

作者： Khanh Giang Le Pei Liu Liang-Tay Lin College of Construction and Development Feng Chia UniversityTaichungTaiwanChina Faculty of Civil Engineering University of Transport and CommunicationsHanoiVietnam

This study applied GIS-based statistical analytic techniques to investigate the influence of accident Severity Index(SI)on temporal-spatial patterns of accident hotspots related to the specific time intervals of day and *** Traffic Accident(RTA)data in 3 years(2015-2017)in Hanoi,Vietnam were used to analyze and test this ***,the RTA data were divided into four seasons in accordance with Hanoi's weather conditions and the time intervals such as the daytime,nighttime,or peak ***,the Kernel Density Estimation(KDE)method was applied to analyze hotspots according to the time intervals and ***,the results were presented by using the comap *** study considered both analyses with and without *** accident SI measures the seriousness of an *** approach method is to give higher weights to the more serious accidents,but not with the extremely high values calculated on a direct rate to the accident *** results showed that both analyses determined the relatively similar hotspots,but the rankings of some hotspots were quite different due to the integration of *** is better to take into account SI in determining RTA hotspots because the gained results are more precise and the rankings of hotspots are more *** there,the traffic authorities can easily understand the causes behind each accident and provide reasonable solutions to solve the most dangerous hotspots in case of limited budget and resources *** is also the first study about this issue in Vietnam,so the contribution of the article will help the traffic authorities easily solve this problem not only in Hanoi but also in other cities.

关键词： road Traffic Accident(RTA) hotspot GIS temporal-spatial analysis Kernel Density Estimation(KDE) Severity Index(SI)

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

road Pricing Design Based on Game Theory and Multi-agent Consensus

引用

IEEE/CAA Journal of Automatica Sinica 2014年第1期1卷 31-39页

作者： Nan Xiao Xuehe Wang Lihua Xie Tichakorn Wongpiromsarn Emilio Frazzoli Daniela Rus the Singapore-MIT Alliance for Research and Technology Centre the EXQUISITUS Centre for ECity School of Electrical and Electronic Engineering Nanyang Technological University the Ministry of Science and Technology the Massachusetts Institute of Technology

Consensus theory and noncooperative game theory respectively deal with cooperative and noncooperative interactions among multiple players/agents. They provide a natural framework for road pricing design, since each motorist may myopically optimize his or her own utility as a function of road price and collectively communicate with his or her friends and neighbors on traffic situation at the same time. This paper considers the road pricing design by using game theory and consensus theory. For the case where a system supervisor broadcasts information on the overall system to each agent, we present a variant of standard fictitious play called average strategy fictitious play(ASFP) for large-scale repeated congestion *** a weighted running average of all other players actions is assumed to be available to each player. The ASFP reduces the burden of both information gathering and information processing for each player. Compared to the joint strategy fictitious play(JSFP) studied in the literature, the updating process of utility functions for each player is avoided. We prove that there exists at least one pure strategy Nash equilibrium for the congestion game under investigation, and the players actions generated by the ASFP with inertia(players reluctance to change their previous actions) converge to a Nash equilibrium almost surely. For the case without broadcasting, a consensus protocol is introduced for individual agents to estimate the percentage of players choosing each resource, and the convergence property of players action profile is still ensured. The results are applied to road pricing design to achieve socially local optimal trip timing. Simulation results are provided based on the real traffic data for the Singapore case study.

关键词： Average strategy fictitious play(ASFP) gametheory multi-agent consensus road pricing

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Investigating the Effectiveness of road-related Mitigation Measures under Semi-controlled Conditions:A Case Study on Asian Amphibians

引用

Asian Herpetological Research 2019年第1期10卷 62-68页

作者： Yun WANG Jiayu LAN Hongping ZHOU Lei GUAN Yudi WANG Yongshun HAN Jiapeng QU Syed Asifullah SHAH Yaping KONG China Academy of Transportation Sciences Jilin Agricultural University Hunan University of Science and Technology Key Laboratory of Adaptation and Evolution of Plateau Biota Northwest Institute of Plateau Biology Chinese Academy of Sciences Qinghai Provincial Key Laboratory of Animal Ecological Genomics Department of Ornamental Horticulture and Landscape Architecture College of Horticulture China Agricultural University

road traffic is the main factor causing the decline in amphibian populations worldwide. The proper design of an amphibian tunnel is one of the most efficient measures to mitigate the negative impacts of road traffic on amphibians. However, no study has investigated the effectiveness of amphibian tunnels under semi-controlled conditions in Asian amphibians. Here, we selected two representative amphibian species, the Chinese brown frog, Rana chensinensis, and the Asiatic toad, Bufo gargarizans, which suffer the most severe road mortality along the roads in Northeast China. We placed experimental arrays of culverts of various sizes(diameters of 1.5, 1, and 0.5 m for circular culverts; side lengths of 1.5, 1, and 0.5 m for box culverts), and substrate type(soil, concrete, and metal) to examine the preferences of both species during the migratory season between May and September in 2016 and 2017. The results revealed that the Chinese brown frog preferred mid-and large-sized culverts as well as soil culverts. We concluded that culverts with a side length ≥ 1 m, lined with soil, and accompanied by a ≥ 0.4 m high guide drift fence and ≤ 45° gradient on the roadside ditch wall would best facilitate road crossings for both species and likely for other amphibian species in Northeast China.

关键词： amphibian tunnels crossing structure drift fence highway roadside ditch road ecology

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Impact of earthquake-induced bridge damage and time evolving traffic demand on the road network resilience

引用

Journal of Traffic and Transportation Engineering(English Edition) 2019年第1期6卷 35-48页

作者： Ioannis Kilanitis Anastasios Sextos Department of Civil Engineering Aristotle University of Thessaloniki Department of Civil Engineering University of Bristol

Damage from recent earthquakes has shown that substandard bridges are particularly vulnerable to strong ground motions being the weakest components of a road *** and foundation damages in bridges lead to a significant loss related to both repair process and a prolonged traffic disruption, which in turn results in large indirect loss in the affected area. Along these lines, the estimation of the overall loss related to earthquake-induced damage in highway bridges and overpasses must be based on a wider network analysis rather than on a single structural assessment. Key concept in such a comprehensive loss estimation procedure is the network resilience, expressing the extent of both direct and indirect loss, as well as the system's ability to quickly recover its preearthquake state. In this paper, a recently developed framework for assessing the loss and resilience associated with seismic impact on the structural and geotechnical components of a road network, as well as the relevant software developed are extended to further consider the implications of post-earthquake traffic demand variation. Moreover, a sensitivity analysis is conducted for a case study network to investigate the impact of traffic demand variation after a major earthquake event and the subsequent trip cancelations on the time-variant, cumulative cost at a network level. The results clearly highlight that not only the seismic resilience of a highway network should be assessed in a holistic manner coupling seismic hazard, structural and traffic analysis, but the latter shall include realistic scenarios with respect to the potential variation of origin-destination demand after the earthquake and during the recovery period.

关键词： Seismic resilience road networks Traffic analysis Bridges Earthquake damage

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：