检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hickert, Cameron Yan, Zhongxia Wu, Cathy The Institute for Data Systems and Society Massachusetts Institute of Technology CambridgeMA02139 United States The Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States The Laboratory for Information & Decision Systems The Institute for Data Systems and Society The Department of Civil and Environmental Engineering Massachusetts Institute of Technology CambridgeMA02139 United States

Autonomous driving is a highly anticipated approach toward eliminating roadway fatalities. At the same time, the bar for safety is both high and costly to verify. This work considers the role of remotely-located human operators supervising a fleet of autonomous vehicles (AVs) for safety. Such a 'scalable supervision' concept was previously proposed to bridge the gap between still-maturing autonomy technology and the pressure to begin commercial offerings of autonomous driving. The present article proposes DISCES, a framework for Data-Informed Safety-Critical Event Simulation, to investigate the practicality of this concept from a dynamic network loading standpoint. With a focus on the safety-critical context of AVs merging into mixed-autonomy traffic, vehicular arrival processes at 1,097 highway merge points are modeled using microscopic traffic reconstruction with historical data from interstates across three California counties. Combined with a queuing theoretic model, these results characterize the dynamic supervision requirements and thereby scalability of the teleoperation approach. Across all scenarios we find reductions in operator requirements greater than 99% as compared to in-vehicle supervisors for the time period analyzed. The work also demonstrates two methods for reducing these empirical supervision requirements: (i) the use of cooperative connected AVs - which are shown to produce an average 3.67 orders-of-magnitude system reliability improvement across the scenarios studied - and (ii) aggregation across larger regions. Copyright © 2024, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Value Stream Assessment of the Sustainable Concrete Recycling Process with Flue Gas Sources: Hong Kong Case

SSRN

引用

SSRN 2023年

作者： Kravchenko, Ekaterina Besklubova, Svetlana Department of Civil and Environmental Engineering the Hong Kong University of Science and Technology Clear Water Bay Hong Kong Department of Industrial and Manufacturing Systems Engineering The University of Hong Kong Pok Fu Lam Hong Kong

The escalating production of construction and demolition waste (CDW), including waste concrete powder (WCP) and recycled concrete aggregates (RA), poses significant environmental challenges. Concurrently, the construction industry is a major contributor to increasing levels of greenhouse gas emissions. To address these two concerns, this study explores the possibility of using active carbonation methods on WCP and RA. Instead of traditional methods, this study investigates the use of flue gases as an alternative source of CO2. This is done through the application of value stream assessment in conjunction with cost-benefit analysis to develop a value assessment model. A case study conducted in Hong Kong illustrates the practicality and feasibility of the developed model. The results demonstrate an approximately 28.6% greater economic efficiency of the proposed alternative concrete waste recycling method compared to the traditional method. The findings offer valuable insights into the potential for enhanced sustainability in construction material cycles. © 2023, The Authors. All rights reserved.

关键词： Carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

Generalizing Homophily to Simplicial Complexes

arXiv

引用

arXiv 2022年

作者： Sarker, Arnab Northrup, Natalie Jadbabaie, Ali Institute for Data Systems and Society MIT United States Department of Civil and Environmental Engineering MIT United States

Group interactions occur frequently in social settings, yet their properties beyond pairwise relationships in network models remain unexplored. In this work, we study homophily, the nearly ubiquitous phenomena wherein similar individuals are more likely than random to form connections with one another, and define it on simplicial complexes, a generalization of network models that goes beyond dyadic interactions. While some group homophily definitions have been proposed in the literature, we provide theoretical and empirical evidence that prior definitions mostly inherit properties of homophily in pairwise interactions rather than capture the homophily of group dynamics. Hence, we propose a new measure, k-simplicial homophily, which properly identifies homophily in group dynamics. Across 16 empirical networks, k-simplicial homophily provides information uncorrelated with homophily measures on pairwise interactions. Moreover, we show the empirical value of k-simplicial homophily in identifying when metadata on nodes is useful for predicting group interactions, whereas previous measures are uninformative. Copyright © 2022, The Authors. All rights reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

A Integrated Estimation Scheme for Tire Road Friction Coefficient Using EKHF and AUKF

A Integrated Estimation Scheme for Tire Road Friction Coeffi...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Fengjiao Zhang Shile Zhang Hui Zhang Hongtu Yang Hongdang Zhang Yan Wang College of Transportation Engineering Changzhou Vocational Institute of Mechatronic Technology Changzhou China Department of Civil and Environmental Engineering The Hong Kong Polytechnic University Hong Kong China School of Computer and Information Technology Beijing Jiaotong University Beijing China Department of Industrial and Systems Engineering Hongkong Polytechnic University Hongkong China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

The tire-road friction coefficient (TRFC) is essential for vehicle stability control and motion planning, particularly in four-wheel distributed drive electric vehicles. Estimating the TRFC typically requires obtaining the tire force first. However, onboard sensors usually do not directly measure tire force, making it common practice to use a tire model for calculation. The accuracy of tire force calculation is affected by time-varying sensor noise, which in turn impacts the TRFC estimation. To address this, we propose a method that combines the extended H-infinity Kalman filter (EHKF) with the adaptive Unscented Kalman filter (AUKF). The EHKF is used to obtain the tire force, and then the AUKF, along with the vehicle model, estimates the TRFC. Empirical data reveal that the Suggested algorithm surpasses the traditional UKF in terms of estimation accuracy and has lower volatility.

关键词： Accuracy Heuristic algorithms Friction Roads Force Noise Estimation Tires Sensors Kalman filters

来源：评论

学校读者我要写书评

暂无评论

A Novel Interpretability Evaluation Framework to Understand Deep Learning Traffic Prediction Models

SSRN

引用

SSRN 2022年

作者： Zhai, Xuehao Guo, Fangce Sivakumar, Aruna Urban Systems Lab Imperial College London United Kingdom Department of Civil and Environmental Engineering United Kingdom

Emerging Machine Learning-based models are increasingly being deployed in critical traffic prediction problems. Due to the ‘black box’ nature of these models, there is an increasing emphasis on understanding their working process and analysing the physical meaning of their hidden layers. Most existing academic studies on Deep Learning (DL) tools in transportation engineering, however, are over-focusing on statistical accuracy, while little attention has been paid to analysing model interpretability. To address this limitation, we propose a novel two step interpretability evaluation framework with land-use Probing Tasks to facilitate understanding the internal functions of a given DL-based traffic prediction model. This framework is built to understand if one or several hidden layers inside a DL-based traffic prediction model can spontaneously capture the spatial characteristics and if such spatial characteristics significantly affect the predicted outcome. In the case study, the interpretability of three types of self-supervised pre-training models (i.e., Auto-encoders, Variational Autoencoders and Graph Convolutional Auto-encoders) is evaluated within the proposed framework. These DL models are trained and tested using parking and land-use data collected from the San Francisco Bay Area, California. The results of the experiments justify the reasonability of the proposed framework from both a global and a local perspective. All the land use indexes used in the testing are spontaneously captured in the hidden layers and the indexes of office and retail land use are the main contributors to prediction accuracy. Based on the measurements of spatial interpretability from different dimensions, we also provide a hidden layer-level post-hoc explanation for why the Graph Convolutional Network outperforms traditional DL-based models. © 2022, The Authors. All rights reserved.

关键词： Land use

来源：评论

学校读者我要写书评

暂无评论

A Feedback Linearization Approach for Coordinated Traffic Flow Management in Highway systems

TechRxiv

引用

TechRxiv 2022年

作者： Chavoshi, Kimia Kouvelas, Anastasios Institute for Transport Planning and Systems Department of Civil Environmental and Geomatic Engineering ETH Zurich CH-8093 Switzerland

This paper aims to develop a traffic control approach that provides an optimal real-time solution for large-scale highway networks. The traffic flow model’s nonlinearity is the main reason for the complex optimization problems that consequently require high computational effort. Feedback linearization is a well-known approach in nonlinear systems control. It can provide an exact linear representation of the original nonlinear system. Thus, it facilitates further steps in the controller design. This research combines the feedback linearization method and linear MPC to simultaneously guarantee optimal performance and real-time feasibility. While developing feedback linearization for METANET model, we discovered a pattern that describes the expansion of the control signals (ramp metering and variable speed limits) and disturbances effects through the highway networks. Utilizing this pattern, we design a generic feedback linearization control law for METANET model. The control law provides the key connection between the linearized and original model. Finally, we complete the methodology by employing a linear MPC to regulate the linearized model. The performance of the designed method is evaluated by conducting comprehensive simulation studies, including a large-scale network. The simulation results are promising. Eventually, comparing the developed methodology with an equivalent nonlinear MPC verifies a substantial improvement in computational costs. © 2022, CC BY.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Estimating leaf area index and coverage of dominant vegetation on an extensive green roof in Syracuse, NY

引用

Nature-Based Solutions 2023年 3卷

作者： Johnson, Alexander J. Davidson, Cliff I. Cibelli, Evan Wojcik, Anna Department of Civil and Environmental Engineering Syracuse University Syracuse NY United States Center of Excellence in Environmental and Energy Systems Syracuse University Syracuse NY United States

Roofs with full or partial coverage of vegetation, also known as green roofs, are perceived to restore ecosystem services in urban areas. Research investigations have been carried out to evaluate green roof performance on reducing stormwater runoff, improving runoff water quality, decreasing urban heat island effects, and several other benefits. The leaf area index (LAI) or an estimate of vegetation coverage on a roof may aid in evaluating these benefits. This study evaluates the leaf area index and plant area index as well as spatial coverage of two dominant species of vegetation on a 5550 m² extensive green roof in downtown Syracuse, NY. Stems with attached leaves within individual patches of Phedimus takesimensis and Sedum floriferum were picked to estimate leaf area index using geometric models, and a ceptometer was used to provide an approximate range of values for the plant area index (PAI). Patches were picked in the summer of 2020 when plants were flowering, but the surface area of the flowers was not included in measurements. Sizes were measured for 8522 leaves from four patches of Phedimus takesimensis and 7751 leaves from five patches of Sedum floriferum. The estimated LAI for a patch of Phedimus takesimensis is 4.97 +/- 0.52 cm² leaf area cm⁻² ground area, while the LAI for a patch of Sedum floriferum is 2.70 +/- 0.37 cm² leaf area cm⁻² ground area. Furthermore, 154 photos were taken in the fall of 2020 and late spring and summer of 2021, representing 7.1% of the roof area in several categories. Results show the following fractions of area: 0.226 (Phedimus takesimensis), 0.381 (Sedum floriferum), 0.074 (moss), 0.029 (other vegetation), and 0.290 (bare soil). Using a weighted average, the LAI of the entire area of this green roof is 4.03 cm² leaf area cm⁻² ground area if the other vegetation has an LAI of 0.92 cm² leaf area cm⁻² ground area and the moss has

关键词： Fractional vegetation cover Green roof Leaf area index Plant area index

来源：评论

学校读者我要写书评

暂无评论

Exploring the feasibility and sensitivity of deep reinforcement learning controlled traffic signals in bidirectional two-lane road work zones

引用

Expert systems with Applications 2025年 287卷

作者： Song, Li Lin, Yixuan Zhao, Xin Lyu, Nengchao Fan, Wei The School of Transportation and Logistics Engineering Wuhan University of Technology Wuhan430063 China Engineering Research Center of Transportation Information and Safety Ministry of Education Wuhan430063 China The Intelligent Transportation Systems Research Center Wuhan University of Technology Wuhan430063 China Department of Civil and Environmental Engineering University of North Carolina at Charlotte NC United States

Reconstruction of bidirectional two-lane roads typically necessitates closing one lane, with traffic signal control (TSC) implemented to prevent direct conflicts between opposing traffic flows. First, the effectiveness of 16 modified discrete and continuous deep reinforcement learning (DRL) algorithms from 4 categories (DQN, AC, PO, DDPG) was systematically investigated in virtual and real-world bidirectional two-lane road work zone scenarios by this study to explore inter-correlations between scenarios and DRL algorithms. Next, multiple sensitivity analyses, including the work zone length, average speed, and directional distribution factor, are conducted to explore the core mechanisms underlying the performance discrepancies of different algorithms. Results indicates that the discrete D3QN-PER-2s (Dueling Double Deep Q network that uses both prioritized experiences replay and double-step temporal difference methods) outperforms continuous DRL and baseline methods in both virtual and real-world scenarios. Overall, D3QN-PER-2s decreases about 68 % of the average waiting time and 15 % of the CO2 emission in three real-world scenarios, indicating the strong transferability of DRL methods. Additionally, with longer work zone distance, the better performances are observed in discrete methods. Last, the fundamental mechanisms underlying the performance divergences are explored. Furthermore, several scenario-specific traffic management approaches are suggested for implementation. These findings offer valuable guidance and insights into the development and implementation of DRL TSC in bidirectional two-lane road work zones. © 2025 Elsevier Ltd

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

On the feasibility of producing cement-bonded particleboard panels containing agrowaste and silica fume 11

On the feasibility of producing cement-bonded particleboard ...

引用

11th International Conference on Structural Health Monitoring of Intelligent Infrastructure, SHMII 2022

作者： Meftahi, Farshad Hatami, Arman Majumdar, Kirty Dhemaied, Rahma Godbout, Stéphane Palacios, Joahnn Soliman, Ahmed Building Civil and Environmental Engineering Department Gina Cody School of Engineering and Computer Science Concordia University MontrealQCH3G 1M8 Canada Department of Civil Engineering Jadavpur University Kolkata700 032 India Energetic Systems and Advanced Technologies Department National School of Sciences and Advanced Technologies Borj Cedria Tunisia QuébecG1P 3W8 Canada

Agricultural waste disposal has become one of the most significant environmental challenges during the past decade. Consequently, agro-waste use in construction has become the subject of contemporary research. Implementing agro-waste materials for various elements in concrete mixtures had several implications on mechanical qualities, structural behavior, durability, and sustainability. Depending on its qualities, agro-waste can be replaced up to 100 percent with fine and coarse aggregates, serve as a filler, and operate as a reinforcing element. This study focused on producing cement-bonded agrowaste particle panels containing supplementary cementitious materials (silica fume and fly ash) to reduce the disposal problem while improving wall panels' surface quality significantly. For this reason, different panels with variations of agro-waste and types of supplementary cementitious materials were produced. The density of the panels and a visual inspection were carried out on the specimens. A novel method for eliminating agro-waste high-waste absorption and expansion was proposed. This paper can enlighten the in-situ engineers about the great potential of using agro-waste in cementitious wall panels. © 2022 International Conference on Structural Health Monitoring of Intelligent Infrastructure: Transferring Research into Practice, SHMII. All rights reserved.

关键词： Fly ash

来源：评论

学校读者我要写书评

暂无评论

Review on techno-socio-economic studies of electric vehicles in electrical energy systems

引用

e-Prime - Advances in Electrical engineering, Electronics and Energy 2024年 10卷

作者： Nazari-Heris, M. Asadi, S. Mohammadi-Ivatloo, B. Department of Engineering College of Engineering and Technology East Carolina University Greenville NC United States Department of Architectural Engineering Pennsylvania State University PA United States Department of Civil and Environmental Engineering School of Engineering University of Virginia Charlottesville VA United States School of Energy Systems LUT University Lappeenranta Finland

Transportation electrification is a practical solution for the world's environmental, economic, and technical challenges. During the last decades, numerous studies have focused on electric vehicles (EVs) as one of the essential energy fields due to the growth rate of EV penetration into energy systems. Researchers have investigated different operation and long-term planning models of EV charging infrastructure and prediction and uncertainty-handling approaches for EV drivers’ behavior (i.e., the arrival/departure time to/from charging stations and the associated state-of-charge) as well as fixed and mobile charging stations (MCSs) and social equity access to EV charging infrastructure. This study provides a detailed analysis and discussion of the daily operation and long-term planning of EV charging stations with economic and technical aspects. Also, the prediction of EV drivers’ behavior and approaches to dealing with uncertain EV parameters are studied. Furthermore, the role of MCSs and social equity access in planning EVs’ charging station placement is investigated. The authors also assess the applications of permanent and MCSs and the social equity access to EV infrastructure. Finally, the current study discusses EVs future trends and their effect on electrical systems as future subjects of research studies. © 2024

关键词： Economic analysis Electric vehicles (EVS) Energy systems Operation and long-term planning Social equity Transportation electrification

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：