检索结果-内蒙古大学图书馆

An Empirical Investigation of Speed Patterns on S-Curves Using Naturalistic Driving Data and mixed logit model

JOURNAL OF ADVANCED TRANSPORTATION 2025年第1期2025卷

作者： Lei, Cailin Shen, Yu Ji, Yuxiong Cai, Xiaoyu Du, Yuchuan Chongqing Jiaotong Univ Sch Smart City Chongqing 400074 Peoples R China Chongqing Jiaotong Univ Chongqing Key Lab Mt City Spatiotemporal Informat Chongqing 400074 Peoples R China Tongji Univ Key Lab Rd & Traff Engn Minist Educ Shanghai Peoples R China

S-curves are common and complex curves in road networks, consisting of two curves in opposite directions connected by a short segment. Drivers' behavior on S-curves reflects their ability to navigate complex environments, which is not yet fully understood. This study examines speed patterns on five S-curves using a naturalistic driving dataset of 2676 vehicle trajectories. A hierarchical clustering method is proposed to identify typical speed patterns on S-curves, and a mixed logit model is developed to analyze the influence of curve radius, slope, and lighting conditions on drivers' speed pattern choices. The empirical findings reveal that (1) each S-curve has dominant speed patterns, and these patterns vary across different S-curves;(2) speed patterns generally exhibit three types of shapes: S-shaped, U-shaped, and anti-S-shaped;and (3) the curve radius, the difference in radii between the two adjacent curves, the slope, and lighting conditions significantly influence drivers' speed pattern choices. These results provide valuable insights for S-curve alignment design, speed guidance strategies, and speed planning algorithms for autonomous vehicles.

关键词： hierarchical clustering mixed logit model naturalistic driving data S-curves speed patterns

来源：评论

学校读者我要写书评

暂无评论

Personalized Travel Recommendations Based on Asynchronous and Privacy-Preserving mixed logit model

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第2期26卷 2227-2238页

作者： Jian, Weitao He, Junshu Chen, Kunxu Xie, Jiemin Zhao, Juanjuan You, Linlin Capital Normal Univ Coll Resource Environm & Tourism Beijing 100048 Peoples R China Sun Yat Sen Univ Sch Intelligent Syst Engn Shenzhen 518107 Peoples R China Guangdong Prov Key Lab Intelligent Transportat Sys Guangzhou 510275 Peoples R China

A data-secure and cost-efficient Personalized Travel Recommendation (PTR) is necessary to develop urban intelligence in transportation. Although prevalent machine learning-based methods have gained tremendous progress on PTR, mixed logit model (MXL), as a mathematical method, is attracting much attention from industry and academia to analyze refined individual behavior for PTR. Since MXL is still in its infancy in PTR, it encounters three challenges that need to be resolved jointly, namely 1) how to use personal data to describe user preferences without violating user privacy, 2) how to utilize the idle computing resources at the edge to improve the estimation efficiency, and 3) how to coordinate devices whose capability and availability may change over time and space. To fill the gap, we propose an asynchronous and privacy-preserving mixed logit model (APMXL), which aims to integrate MXL with asynchronous federated learning (AFL), which can 1) non-intrusively exchange model parameters between the clients and the server without exposing the raw data, 2) separately perform local and global estimation at the client and server to optimize the load, and 3) collaboratively approximate the posterior of the standard MXL through a continuous asynchronous interaction mechanism. Moreover, based on a standard dataset, APMXL is evaluated, showing that the model accuracy is about 13% higher compared to a flat logit model. Meanwhile, the estimation time has been reduced by about 60% compared to a centralized MXL model, and the robustness of the model has been improved compared with the synchronous and privacy-preserving mixed logit model (SPMXL).

关键词： Estimation Data models Servers Mathematical models Logistic regression Computational modeling Data privacy Transportation Training Federated learning Personalized travel recommendation federated learning mixed logit model asynchronous federated learning privacy-preserving

来源：评论

学校读者我要写书评

暂无评论

mixed logit model based diagnostic analysis of bicycle-vehicle crashes at daytime and nighttime

引用

INTERNATIONAL JOURNAL OF TRANSPORTATION SCIENCE AND TECHNOLOGY 2022年第4期11卷 738-751页

作者： Liu, Shaojie Li, Yang Fan, Wei (David) Univ N Carolina Dept Civil & Environm Engn Charlotte NC 28223 USA

Cycling provides an important alternative to environmental-friendly transportation modes in urban areas. However, cyclists are vulnerable road users and often suffer severe injuries once crashes occur, which has impeded the growth of bicycle uses. Identification of factors that influence injury severities of crashes involving cyclists can help policy-makers form efficient strategies to mitigate crashes. Moreover, crashes involving cyclists at daytime and nighttime are very likely to present different patterns. Hence, the objective of this study is to explore the underlying factors to injury severity in crashes involving cyclists in the daytime and nighttime separately. mixed logit model approach is employed due to its advantage of accounting for heterogeneity in observations and four factors are found to have random effects in the mixed logit model for daytime. The differences of crash mechanisms at daytime and nighttime are discussed, and the results of this research would help to develop effective policies that aim to mitigate the injury severities of cyclists while promoting the use of bicycles.& COPY;2021 Tongji University and Tongji University Press. Publishing Services by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://***/ licenses/by-nc-nd/4.0/).

关键词： Bicycle-vehicle crashes Cyclists mixed logit model

来源：评论

学校读者我要写书评

暂无评论

Impact of incentives to purchase energy-efficient products: evidence from Chinese households based on a mixed logit model

引用

ENERGY EFFICIENCY 2023年第7期16卷 81页

作者： Wang, Jiaxing Sapporo Gakuin Univ Fac Econ & Business Adm 5-1-1 Atsubetsuchuo 1 joAtsubetsu Sapporo Hokkaido 0048666 Japan

Similar to many countries, China has introduced a variety of incentives to promote the use of energy-efficient appliances. The Chinese government introduced the energy-efficiency labeling program in 2005, and three types of subsidies (i.e., the countryside subsidy, trade-in subsidy, and eco-product subsidy programs) were implemented from 2007 to 2013. In this study, we examine households' selection of refrigerator energy efficiency and apply a mixed logit model to micro-level data from the Chinese General Social Survey to evaluate the impact of these policies. The analysis demonstrates that the energy-efficiency labeling program as well as the three subsidy programs promoted households' choice of energy-efficient refrigerators;however, the effects of the various subsidy programs differed. These results suggest that the countryside subsidy has a similar effect as the eco-product subsidy in terms of promoting the purchase of highly energy-efficient refrigerators, although the countryside subsidy's main objective was to promote appliances being disseminated in rural areas. The trade-in subsidy was less effective in promoting the sale of energy-efficient refrigerators. These findings provide implications for designing future incentive and subsidy policies, particularly for developing countries.

关键词： Energy efficiency Chinese households Micro data Refrigerators mixed logit model

来源：评论

学校读者我要写书评

暂无评论

Exploring the main and interaction effects of traffic flow characteristics, roadway design and weather conditions on the real-time crash risk for urban roads with mixed logit model

引用

JOURNAL OF TRANSPORTATION SAFETY & SECURITY 2024年第5期16卷 467-481页

作者： Liu, Xian Lu, Jian Wang, Boqing Zhu, Maoying Zhang, Fang Chen, Xiang Southeast Univ Jiangsu Key Lab Urban ITS Nanjing Peoples R China Southeast Univ Jiangsu Prov Collaborat Innovat Ctr Modern Urban T Nanjing Peoples R China Southeast Univ Sch Transportat Nanjing Peoples R China Nanjing Univ Sch Govt Nanjing Peoples R China Univ Leeds Sch Comp Leeds England

The present study aims at investigating the main and interaction effects of contributing factors from multiple risk sources (i.e. traffic flow characteristics, roadway design and weather conditions) on the real-time crash risk for urban roads. A mixed logit model is used to characterise heterogeneity induced by unobservable factors, and result shows that the mixed logit model achieves better goodness-of-fit than the binary logit model. It is found that the multiple risk sources such as roadway design (i.e. length of road segment, road hierarchy), traffic flow characteristics (i.e. average speed, average travel time, congestion level), and weather conditions (i.e. wind speed) have significant effects on the real-time crash risk. Moreover, interactions between the multiple risk sources such as roadway design and traffic flow characteristics (i.e. SD of speed and length of road segment, road hierarchy and average travel time), traffic flow characteristics and weather conditions (i.e. average travel time, temperature and wind speed), and roadway design and weather conditions (i.e. length of road segment and wind speed) are found to be significantly correlated to the real-time crash risk. Such findings can be potentially used for the development of real-time management measures that could mitigate the high-risk situations of urban roads.

关键词： urban roads crash risk multiple risk sources interaction effects mixed logit model

来源：评论

学校读者我要写书评

暂无评论

Factors affecting pedestrian injury severity in pedestrian-vehicle crashes: Insights from a data mining and mixed logit model approach

引用

JOURNAL OF TRANSPORTATION SAFETY & SECURITY 2024年第9期16卷 1015-1038页

作者： Ouyang, Huijie Han, Yin Liu, Pengfei Zhao, Jing Univ Shanghai Sci & Technol Dept Traff Engn Shanghai Peoples R China

There has been a concerning rise in pedestrian fatalities resulting from traffic accidents. This study conducts an in-depth analysis of the factors that contribute to the injury severity of pedestrians considering human, vehicle, roadway, and environmental characteristics of the crashes. A novel approach is proposed by combing a data mining technique and mixed logit models. First, the Apriori algorithm is employed to uncover patterns between fatal and incapacitating injury outcomes and their influencing factors. Then, mixed logit models are developed to investigate heterogeneity across all observations under two different lighting conditions. It is found that eight variables show heterogeneity affecting the injury severity of crash outcomes. Results also indicate that drivers older than 65 years old will increase the probability of pedestrian injury severity at dark-unlighted roads. Additionally, the present of signal and double yellow line has could increase the injury severity. Creating optimal lighting conditions at pedestrian crossings during nighttime hours and enhancing safety education initiatives for pedestrians are critical factors to improve pedestrian safety. The finding of this study will benefit policymakers and road safety professionals develop more effective strategies for preventing pedestrian injuries in vehicle crashes.

关键词： pedestrian safety injury severity Apriori algorithm mixed logit model

来源：评论

学校读者我要写书评

暂无评论

Analysis of distracted driving crashes in New Jersey using mixed logit model

引用

JOURNAL OF SAFETY RESEARCH 2022年 81卷 166-174页

作者： Hasan, Ahmed Sajid Orvin, Muntahith Mehadil Jalayer, Mohammad Heitmann, Eric Weiss, Joseph Rowan Univ Dept Civil & Environm Engn Glassboro NJ 08028 USA Univ British Columbia Dept Civil Engn Okanagan Campus3333 Univ Way Kelowna BC V1V 1V7 Canada Rowan Univ Ctr Res Educ Adv Transportat Engn Syst Dept Civil & Environm Engn Glassboro NJ 08028 USA New Jersey Div Highway Traff Safety Trenton NJ 08625 USA New Jersey Div Highway Traff Safety Piscataway NJ 08854 USA

Introduction: Distracted driving is a concern for traffic safety in the 21st century, and can be held responsible for the increasing propensity and severity of traffic crashes. With the advent of mobile technologies, distractions involving the use of cellphones while driving have emerged, and young drivers in particular are getting more and more engaged in these distractions. Texting or receiving phone calls while driving are offenses in most states, and they are punished with fiscal penalties. Awareness campaigns have also been arranged over recent decades across the United States in order to minimize crashes due to distracted driving. The severity of such crashes depends on driver behavior, which can also be affected by various factors like the geometric design of the roadway, lighting and environmental conditions, and temporal variables. Method: In this study, we analyzed data on five years (2015-2019) of crashes involving cellphone use in New Jersey using a mixed logit model. As estimated model parameters can vary randomly across roadway segments in this approach, this allowed us to account for unobserved heterogeneities relating to roadway characteristics, environmental factors, and driver behavior. A pseudo-elasticity analysis was further employed to observe the sensitivity of the significant explanatory variables to crash severity. Results: We found that higher speed limits and a larger total number of vehicles involved both increased crash severity, while higher annual average daily traffic (AADT) levels and the presence of an urban road setting reduced it. Practical Applications: These findings will help decision-makers to comprehend what the significant contributing factors associated with crash injury severity due to distracted driving are, and how to implement necessary interventions to reduce this severity.(c) 2022 National Safety Council and Elsevier Ltd. All rights reserved.

关键词： Distracted driving Cellphone distractions New Jersey mixed logit model Pseudo-elasticity Distracted driving Cellphone distractions New Jersey mixed logit model Pseudo-elasticity

来源：评论

学校读者我要写书评

暂无评论

The Garbage Class mixed logit model: Accounting for Low-Quality Response Patterns in Discrete Choice Experiments

引用

VALUE IN HEALTH 2022年第11期25卷 1871-1877页

作者： Jonker, Marcel F. Erasmus Univ Erasmus Sch Hlth Policy & Management Rotterdam Netherlands Erasmus Univ Erasmus Choice Modelling Ctr Rotterdam Netherlands

Objectives: To introduce the garbage class mixed logit (MIXL) model as a convenient alternative to manually screening and accounting for respondents with low data quality in discrete choice experiments. Methods: Garbage classes are typically used in latent class logit analyses to designate or identify group(s) of respondents with low data quality. Yet, the same concept can be applied to MIXL models as well. Results: Based on a reanalysis of 4 discrete choice experiments that were originally analyzed using a standard MIXL model, it is shown that garbage class MIXL models can achieve the same effect as manually screening for (and excluding) respondents with low data quality based on the more commonly used root likelihood test, but with less effort and ambiguity. Conclusions: Including a garbage class in MIXL models removes the influence of respondents with a random choice pattern from the MIXL model estimates, provides an estimate of the number of low-quality respondents in the dataset, and avoids having to manually screen for respondents with low data quality based on internal or statistical validity tests. Although less versatile than the combination of standard MIXL estimates with separate assessments of data quality and sensitivity analyses, the proposed garbage class MIXL model provides an attractive alternative.

关键词： data quality discrete choice experiment garbage class mixed logit model

来源：评论

学校读者我要写书评

暂无评论

A comparison between mixed logit model and latent class logit model for multi-profile best-worst scaling: evidence from mobile payment choice dataset

引用

APPLIED ECONOMICS LETTERS 2022年第14期29卷 1300-1305页

作者： Guo, Qinxin Shen, Junyi Shanghai Lixin Univ Accounting & Finance Sch Int Econ & Trade 995 Shangchuan Rd Shanghai 201209 Peoples R China Kobe Univ Grad Sch Econ Kobe Hyogo Japan

This paper uses a multi-profile best-worst scaling dataset to compare the mixed logit model and the latent class logit model for mobile payment choice. Three non-nested tests are applied to show the comparison results... 详细信息

关键词： Multi-profile best-worst scaling mixed logit model latent class model non-nested test

来源：评论

学校读者我要写书评

暂无评论

Analyzing injury severity of rear-end crashes involving large trucks using a mixed logit model: A case study in North Carolina

引用

JOURNAL OF TRANSPORTATION SAFETY & SECURITY 2022年第5期14卷 723-736页

作者： Liu, Pengfei Fan, Wei (David) Univ North Carolina Charlotte USDOT Ctr Adv Multimodal Mobil Solut & Educ CAMMS Dept Civil & Environm Engn EPIC BldgRoom 32619201 Univ City Blvd Charlotte NC 28223 USA

As one of the most frequently occurring crashes, rear-end crashes often result in injuries and property damage, especially when large trucks are involved. To investigate the contributing factors and the unobserved heterogeneity in such factors, a mixed logit model is developed to analyze rear-end crashes involving large trucks. A dataset containing 7,976 rear-end crashes involving large trucks is collected from Highway Safety Information System (HSIS) in North Carolina between 2005 and 2013. Driver, roadway, and environmental related characteristics are considered in the analysis. Speed limit over 50 mph is found to be better modeled as a random-parameter at specific injury severity levels. Results also indicate that driving under the influence of alcohol or drugs, rural roadways, dark light condition, grade roadway configuration, speed limit over 50 mph will significantly increase the injury severity of large truck involved rear-end crashes. Roadway with traffic control will significantly decrease the injury severity of such crashes. The findings in this study can greatly help traffic agencies and truck companies develop better large truck-involved rear-end crash prevention strategies.

关键词： injury severity analysis large truck mixed logit model rear-end crash

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：