王华

基本信息 科学研究 教育教学 论文专著 新建主栏目 基本信息 名称 王华，男，汉族，1975年生。 职称：教授 职务：交通信息与控制工程 学科带头人。 哈尔滨工业大学教授、博士生导师，学科带头人，美国华盛顿大学、英国伦敦大学学院访问学者，哈尔滨市智能交通系统专家，“985工程”建设“青年学者基础科研能力建设项目”获得者，中国公路协会自动驾驶工作委员会会员，中国智能交通协会会员，中国自动化学会会员，主要从事智能交通系统、先进交通感知技术、交通数据处理与分析、面向土木工程的健康监测等方面的教学和科研工作。发表学术论文40余篇，其中SCI和EI论文30余篇；获得发明专利授权30项；主持和参与国家重点研发计划、国家自然科学基金、国家“863计划”和科技支撑计划等国家级项目10余项，省部级科研项目20余项，出版专著1部；先后获黑龙江省高校科学技术三等奖、黑龙江省科学技术三等奖、黑龙江省教学成果二等奖、中国智能交通协会科技进步奖二等奖。 工作经历 名称 时间 工作经历 2012年12月－至今 哈尔滨工业大学 交通科学与工程学院 教授 2012年3月－至今 美国 华盛顿大学 兼职副教授 2006年12月－2012年12月 哈尔滨工业大学 交通科学与工程学院 副教授 2004年5月－2006年9月 哈尔滨工业大学 土木工程学院 博士后 2002年7月－2006年12月 哈尔滨工业大学 电气工程及自动化学院 讲师 1999年12月－2002年7月 哈尔滨工业大学 电气工程及自动化学院 助教 教育经历 名称 2000年-2004年, 就读于哈尔滨工业大学, 电气工程及自动化学院，工学博士 1998年-2000年, 就读于哈尔滨工业大学, 电气工程及自动化学院，工学硕士 1994年-1998年, 就读于哈尔滨工业大学, 电气工程及自动化学院，工学学士 主要任职 名称 2009年－2018 哈尔滨工业大学 交通科学与工程学院 交通信息与控制工程系 系主任 研究领域 名称 研究领域： 智能交通系统 先进交通路网状态感知技术 交通数据处理与分析 面向土木工程结构的无线传感技术 主要研究方向: 1、面向多源交通数据的交通主动控制研究； 2、基于多传感器的交通信息采集与无线传输技术研究； 3、基于浮动车数据的路网状态实时感知技术研究； 4、路面表面三维重构与损坏检测技术研究。 科研项目 项目名称 路面表面功能评价指标动态高精度计量标准装置 项目来源 科技部 开始时间 2017.07 结束时间 2020.12 项目经费 105万元 担任角色 负责 项目类别 纵向项目 项目状态 进行中 简单介绍 项目名称 基于多源轨迹信息的动态交通瓶颈感知理论与识别分析方法 项目来源 国家自然科学基金委 开始时间 2016.01 结束时间 2019.12 项目经费 71.2万元 担任角色 负责 项目类别 纵向项目 项目状态 进行中 简单介绍 项目名称 新形势下城市公共交通资源的优化配置与政策保障研究 项目来源 世界银行 开始时间 2018.01 结束时间 2019.9 项目经费 168万元 担任角色 负责 项目类别 横向项目 项目状态 进行中 简单介绍 项目名称 基于多源检测数据的城市交通多目标大系统运行优化和可持续性决策支持理论研究（51329801） 项目来源 国家自然科学基金 海外及港澳学者合作研究基金 开始时间 2014-01-01 结束时间 2017-12-01 项目经费 200万元 担任角色 参与 项目类别 横向项目 项目状态 完成 简单介绍 项目名称 高海拔高寒地区高速公路建设技术(2014BAG05B00) 项目来源 国家科技支撑计划 开始时间 2014-01-01 结束时间 2016-12-01 项目经费 960万元 担任角色 参与 项目类别 横向项目 项目状态 完成 简单介绍 项目名称 基于多源检测数据的城市路网交通流主动式管理与控制理论研究（51138003） 项目来源 国家自然科学基金 重点项目 开始时间 2012-01-01 结束时间 2016-12-01 项目经费 290万元 担任角色 参与 项目类别 横向项目 项目状态 完成 简单介绍 项目名称 道路平整度的多重分形维数谱分析及分形特征评价研究（50808057） 项目来源 国家自然基金 青年基金 开始时间 2009-01-01 结束时间 2011-12-01 项目经费 20万元 担任角色 负责 项目类别 纵向项目 项目状态 完成 简单介绍 项目名称 哈尔滨市智能交通顶层设计规划方案 项目来源 哈尔滨市工信委 开始时间 2013-07-01 结束时间 2014-07-01 项目经费 46.8万元 担任角色 负责 项目类别 横向项目 项目状态 进行中 简单介绍 项目名称 面向多数据源的高速公路网交通信息融合与利用技术研究 项目来源 吉林省交通厅 开始时间 2011-01-01 结束时间 2013-06-01 项目经费 85万元 担任角色 参与 项目类别 纵向项目 项目状态 进行中 简单介绍 项目名称 公路技术状况评定 项目来源 黑龙江收费公路管理局 开始时间 2009-06-01 结束时间 2011-06-01 项目经费 96万元 担任角色 参与 项目类别 纵向项目 项目状态 进行中 简单介绍 项目名称 便携式超声相控阵检测成像仪技术 项目来源 广东省科技项目 开始时间 2010-04-01 结束时间 2013-04-01 项目经费 100万元 担任角色 负责 项目类别 纵向项目 项目状态 进行中 简单介绍 项目名称 便携式水下超声相控阵检测成像系统 项目来源 国家863高科技项目 开始时间 2007-01-01 结束时间 2009-12-01 项目经费 84万元 担任角色 参与 项目类别 纵向项目 项目状态 完成 简单介绍 科学研究 名称 研制成功多功能道路检测车，该检测车拥有4项发明专利，具有独立自主知识产权，达到国内领先水平。已为全国道路养护部门提供5万余公里的检测服务，并与辽宁鞍山森远公司达成产品转化协议，促进道路快速检测和养护领域向高水平智能化发展。 在“863”项目支持下，完成了超声相控阵检测设备关键技术的研究，获得了3项发明专利，打破了国外同类产品的长期技术垄断，为推进国内无损结构探伤的检测技术发展打下基础。采用该技术的检测设备已经产品化，并占有全国30%以上的份额，且正在逐年增长。 带领智能交通信息团队，发明和研制成功了基于智能道钉的智能车路协同系统，该系统集成了先进微传感技术、微功耗处理器技术、低功耗无线通讯技术和高效太阳能收集和管理技术，利用智能道钉之间、智能道钉与车辆之间的主动无线信息交互、车辆被动感知等，实现车辆行驶诱导、安全辅助和智能停车管理等应用。该系统已在深圳、青岛、平度、哈尔滨、宁波等地被应用，其中为哈尔滨交警部门安装的智能斑马线受到了社会广泛关注，被中央电视台等多家媒体报道。 发明专利情况 名称 发明专利情况-授权专利 序号 专利名称 授权号 专利类别 发明人排序 授权时间 授权国别或组织 1 一种基于多维信息警示的城市交叉路口安全保障系统 CN 106981208 B 发明专利 1 2023.06.23 中国 2 一种基于多个震动检测传感器的车辆检测装置 ZL201410173172.9 发明专利 1 2016.8.24 中国 3 一种基于多种传感器信息的车辆检测装置 ZL201410173173.3 发明专利 2 2016.1.27 中国 4 一种基于加速度传感器和光敏原件的车辆检测装置 ZL201410173171.4 发明专利 1 2016.1.20 中国 5 一种公路路面三维检测系统 ZL201410066663.3 发明专利 1 2015.11.25 中国 6 一种柔性关节角度传感器 CN201310244292.9 发明专利 2 2016.02.10 中国 7 一种多维关节姿态检测传感器 CN201310244293.3 发明专利 2 2016.02.10 中国 8 超声相控阵检测仪器 ZL 200610009691.7 发明专利 2 2011.3.23 中国 9 车辙检测仪器及其检测方法 ZL 200810064863.X 发明专利 1 2011.11.2 中国 10 管节点焊缝超声相控阵检测成像系统 ZL 200610009690.2 发明专利 3 2010.9.8 中国 11 一种可折叠车辙检测仪器 ZL 200810209873.8 发明专利 1 2010.9.15 中国 12 公路路面状况自动采集设备及其采集方法 ZL 200810209872.3 发明专利 1 2010.12.15 中国 13 电压至电流转换电路装置 ZL 200610150934.9 发明专利 1 2009.3.4 中国 发明专利情况-受理专利 序号 专利名称 受理号 专利类别 发明人排序 受理时间 授权国别或组织 1 一种公交客流采集装置及客流统计方法 CN201810264530.5 发明专利 2 2018.09.18 中国 2 一种基于视频投影的内轮差智能预警系统及预警方法 CN201810457525.6 发明专利 1 2018.09.14 中国 3 一种利用移动终端支付的地铁支付系统及支付方法 CN201710261139.5 发明专利 1 2017.09.05 中国 4 一种基于多维信息警示的城市交叉路口安全保障系统 CN201710379160.5 发明专利 1 2017.07.25 中国 5 一种利用移动终端支付的支付系统及支付方法 CN201710260952.0 发明专利 1 2017.07.21 中国 6 基于无线传感器和无线电信号定位的智能反向寻车系统 CN201610343939.7 发明专利 1 2016.09.07 中国 7 实现车路协同的链状拓扑无线通信系统 CN201610117124.7 发明专利 1 2016.05.18 中国 8 基于地磁传感器阵列的车辆检测装置 CN201510909465.3 发明专利 1 2016.03.30 中国 9 用于分布测量系统的传感器节点间的冗余布线方法 CN201510909506.9 发明专利 1 2016.02.24 中国 10 一种离线支付方法及离线支付系统 CN201810612910.3 发明专利 1 2018.6.14 中国 学术会议 名称 序号 报告名称 会议名称 主办方 时间 地点 1 面向未来交通安全的路网全息感知与多模式安全诱导技术 第十四届智能交通年会 智能交通协会 2019年11月1日 青岛 2 智能道钉-让公路更聪明更安全的道路基础设施 首届车路协同自动驾驶国际论坛 中国公路学会 2018年11月2日 北京 3 物联网感知的道路智能基础设施技术与应用 2018 第七届（2018）中国智能交通市场年会 赛文交通网 2018年4月11日 北京 4 面向未来智能交通的路内智能基础设施 2017第十二届中国智能交通年会 中国智能交通协会 2017年11月 中国常熟 5 Full-Scene Image Mosaic Algorithm of Concrete Pavement Surface The 91rd Annual Meeting of Transportation Research Board Transportation Research Board 2011.1 美国华盛顿DC 6 Research on the safety distance model based on car-car communication 18th World Congress on Intelligent Transport Systems and ITS America Annual Meeting Intelligent Transportation Society of America 2011.10 美国纽约 科研及学术奖励 名称 序号 获奖项目名称 奖励名称 等级 排序 获奖时间 授予机构 1 路面表面状况自动化采集与分析系统的研制与开发 黑龙江省科学技术奖 三等奖 2 2012 黑龙江省 2 路面表面状况自动化采集与分析系统的研制与开发 黑龙江省高校科学技术奖 三等奖 2 2009 黑龙江省高校科学技术奖励委员会 3 利用学科交叉优势培养交通运输学科复合型创新人才 黑龙江省教学成果奖 二等奖 4 2011 黑龙江省教育厅 4 首届研究生课程青年教师教学竞赛 教学竞赛 一等奖 1 2012 哈尔滨工业大学 团队成员 名称 全威，哈尔滨工业大学 交通科学与工程学院 交通信息与控制工程系 副教授 李先通，哈尔滨工业大学 交通科学与工程学院 交通信息与控制工程系 讲师 李奎，哈尔滨工业大学 交通科学与工程学院 交通信息与控制工程系 讲师 讲授课程 名称 热爱教学，乐在其中。荣获黑龙江省教学成果奖二等奖、哈工大首届研究生青年教师教学竞赛一等奖（全校仅3名），两次荣获校“优秀专兼职工作者标兵”称号和一次校“优秀专兼职工作者”称号。 数字信号处理及其工程应用硕士研究生 学位课 36学时课程简介:自2007年起，每年开设《数字信号处理及应用》硕士研究生课程，32学时，累计授课人数200多人次。各种信号在我们的日常生活和工作中具有非常重要的作用。我们经常接触的信号包括语音、音乐、图片和视频信号。这些信号都是时间、空间、位置、温度或压力的自变量函数。在过去的四十多年里，数字信号处理领域得到了极大的发展，其显著进展已经在研究和应用领域得到很好的体现。而数字计算机技术和软件的发展，更加促进了数字信号处理领域的发展。本课程讲授信号的概述和信号处理方法。首先根据信号的分类讨论信号的数学特性，然后讨论离散时间信号和离散时间系统的时域表示方法及其所遇到的问题。进一步介绍离散时间序列的离散时间傅立叶变换表示。该课程同时讲授连续时间信号的离散时间处理和离散傅立叶变换、Z变换和各种形式的数字滤波器。 交通智能检测原理及应用本科生 必修课 24学时课程简介：自2007年起，每年为大三交通工程和交通设备与控制工程专业两个专业学生开设《交通智能检测原理及应用》，24学时，累计授课人数500多人次。主旨在于深入浅出地向学生讲授在交通工程中，应用的各种典型智能传感器的原理，智能控制器的应用实例，以及典型的数据处理方法，为以后的深入学习本专业知识和科学研究打好基础。通过本课程教学，使学生学习检测技术的理论基础，传感器及智能传感器，交通工程中常用传感器原理，智能检测系统的基本结构，智能检测中常用数据处理方法，分析交通工程中智能检测系统应用实例，使学生初步了解智能检测技术的基本概念、内容与方法；培养观察问题、解决问题、调查分析、初步设计等能力。 信号完整性及高速PCB应用与实践本科生 创新研修课 32学时课程简介：自2011年起，每年开设《信号完整性及高速PCB应用与实践》本科创新研修课，24学时，累计授课人数200多人次。随着主频的提高、布线密度的增加、大量数模混合电路的应用以及产品体积的缩小，PCB的设计要求越来越高。传输时延、反射、串扰、电磁干扰、地/电层噪声、热辐射等，可以严重影响设计系统的功能正确性。同时由于大量采用了地电平面的分割以及地电平面上有过孔、通孔等，导致信号回流路径的不确定性，产生共模噪声，并由此可能会产生Delta-I噪声、地弹或瞬态交换噪声。同时由于辐射噪声的增加，产生的信号与信号间、系统与系统间的电磁干扰问题也日趋严重。这种干扰会影响系统的稳定性甚至导致功能失效。为此，设计系统的电磁兼容性（EMC）指标已经成为产品能否走向市场的关键。所以，在现代电子系统设计中，信号完整性问题和电磁干扰问题已经成为工程师们必须考虑的问题。本课程主要教授以下内容：1）信号完整性原理及分析；2）电磁兼容性原理及分析；3）印刷线路板设计的基本理论、相关问题的分析与设计。授课方式采用课堂多媒体教学与实验教学相结合的方式，其中课堂教学30学时，实验教学6学时。 《现代交通检测技术原理》本科生 30学时课程简介：自2012年起，每年与美国知名学者LAWRENCE A. KLEIN博士共同开设《现代交通检测技术原理》本科课程，30学时，累计授课人数800多人次。 《现代交通检测原理》博士研究生课程 24学时课程简介：自2013年起，每年开设《现代交通检测原理》博士研究生课程，24学时，累计授课人数50人次。 《交通系统控制与微观仿真》本科生 16学时课程简介：自2015年起，每年与美国夏威夷大学交通控制知名学者张国惠教授共同开设课程，16学时，累计授课人数200多人次。《交通影响分析与可持续交通》自2016年起，每年与美国南佛罗里达大学交通影响知名学者张瑜教授共同开设《交通影响分析与可持续交通》课程，16学时，累计授课人数400多人次。 学科竞赛 名称 作为大学生先进交通创新创业基地主任，承担本科生创新研修课一门（24学时），指导学生参加全国高校智能交通创新与创业大赛等创业赛事，引导学生积极参与创新创业活动和比赛，提升学生的创新意识和创新能力，被评为哈工大学生活动优秀指导教师。 累计指导了10余支学生创新团队，其中指导大学生创新项目6项，其中国家级立项4项，获一等奖1项；指导学生参加全国学科竞赛150多人，获国家级竞赛一等奖3项、二等奖1项，获校级创意创新创业大赛金奖2项、银奖1项，并开创交通学院学生科技创新的多个“第一”。 论文期刊 论文标题 Smart Road Stud-Empowered Vehicle Magnetic Field Distribution and Vehicle Detection 作者 Sun, Yanli; Wang, Hua; Quan, Wei; Ma, Xiaolong; Tao, Zhimin; Elhajj, Mireille; Ochieng, Washington Yotto 发表时间 2023.3 期刊名称 IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 期卷 Early Access 简单介绍 A self-designed AMR detector named Smart Road Stud (SRS) is proposed. SRS, installed along lane markings, is not only a detector but also a lane markings enhancement device. Because a single SRS needs to detect vehicles on two lanes, the vehicle detection method for SRS is different from the AMR detectors installed in the middle of the lane or at the roadside. Based on SRS, an innovative mathematical model based on the magnetic dipole is developed to simulate vehicle magnetic field. According to the model, lane information can be inferred to achieve traffic volume detection. Results show that a single SRS delivers traffic volume detection accuracy of 97%, providing a strong foundation for future research to achieve higher detection performance based on multi-SRS linkage. The significance of this paper is to meet the detection requirements of warning equipment installed on lane markings. 论文标题 Evaluation of road roughness based on multi-fractal theory 作者 Wei Quan, Hua Wang ; Chaoyi Wang ; Xiangchen Hou 发表时间 期刊名称 IEEE Conference on Intelligent Transportation Systems 期卷 The Hague, 简单介绍 The paper investigates a novel evaluation method of road roughness to overcome the shortages of the current used road roughness indices which cannot fine depict the characteristics of the road locally. Multi-fractal theory is employed to systematically research into appraising the road profile, which provides obvious multi-fractal characteristics. But the results of road surface simulation in each grades based on Fourier inverse transformation show there is no unique relation between multi-fractal spectral width and road roughness in different grades. However, in logarithmic distribution diagram, the vertical axis of the road intercept which have the same multi-fractal spectral width was different. Experimental results proved the IRI and multi-fractal spectrum width values are complementary to describe the road roughness. We proposed to signify the road roughness by combining multi-fractal spectral width and the IRI as a supplement of current indices. 论文标题 Vehicle Trajectory Reconstruction for Signalized Intersections with Low-Frequency Floating Car Data 作者 Hua Wang, Changlong Gu, Washington Yotto, Ochieng 发表时间 2019.05.20 期刊名称 Journal of Advanced Transportation 期卷 2019(4) 简单介绍 Floating car data are beneficial in estimating traffic conditions in wide areas and are playing an increasing role in traffic surveillance. However, widespread application is limited by low-sample frequency which makes it hard to get a complete picture of a vehicle’s motion. An accurate and reliable reconstruction of a vehicle’s trajectory could effectively result in a higher sampling frequency enabling a more accurate estimation of road traffic parameters. Existing methods require additional information such as nearby vehicles, signal timing strategies, and queue patterns which are not always available. To address this problem, this paper presents a method used with low-sample frequency data to reconstruct vehicle trajectories through intersections, without the need for extra information. Furthermore, the additional parameters for the speed-time curve distributions for deceleration rate and acceleration rate are generated. A piecewise deceleration and acceleration model is developed to calculate the acceleration rate for different travel modes in the trajectory. Te distribution parameters of the acceleration data for each travel mode are then estimated using a new Expectation Maximization (EM) algorithm. Te acceleration statistics are then used to reconstruct the corresponding parts of the trajectory. Compared to the reference trajectories (truth), the test results show that the method developed in this paper achieves improvement in accuracy ranging from 16 to 67% over the commonly used linear interpolation method. In addition, the proposed method is not very sensitive to the sampling interval of the floating car data, unlike the linear interpolation method where the error grows rapidly with increasing sampling interval. 论文标题 Smart road stud based two-lane traffic surveillance 作者 Hua Wang, Wei Quan, Washington Yotto Ochieng 发表时间 2019.05.15 期刊名称 Journal of Intelligent Transport Systems 期卷 vol 2019 简单介绍 This paper develops the two-lane traffic surveillance function of a smart road stud (SRS), which has the capabilities of high-resolution traffic data collection and transmission, and a light-based traffic guidance. The SRS addresses the limitations of the current systems with the potential for high performance and usage for a variety of applications. SRS nodes are mounted on the road surface along the lane separation lines instead of the intrusive middle of the lane detection sensors. The key innovation in SRS design is its ability to detect vehicles in two adjacent lanes in real time by employing a three-axis geomagnetic sensor mounting on the lane line, which is the basis of advanced applications such as traffic surveillance, driving guidance, and congestion monitoring. Multiple vehicles are recognized based on the superposition of the disturbance of the geomagnetic fields. Magnetic field changes along the axes are simulated and analyzed with vehicles modeled as magnet dipoles to determine the criteria for the detection of vehicles in adjacent lanes, which are verified by actual waveforms. Extended dual-window and two-lane vehicle detection algorithms are developed, enabling to distinguish five detection scenarios and count vehicles in two lanes. Field test results show that one SRS can detect traffic in adjacent lanes with a correct vehicle detection rate of over 98%, the same level achievable by intrusive middle of the lane detectors. Based on the enhanced features, high performance, cost-effectiveness, and value-added services, the SRS is a significant improvement on the conventional studs for intelligent transport system applications. 论文标题 Vehicle detection using three-axis AMR sensors deployed along travel lane markings 作者 Meng Liu, Wang Hua, Quan Wei 发表时间 期刊名称 IET Intelligent Transport Systems 期卷 2017,11(9):581-587 简单介绍 A vehicle detection method is developed based on three-axis anisotropic magneto resistive (AMR) sensors along travel lane markings. The method integrates multiple algorithms and uses different geomagnetic waveforms which are disturbed by vehicles passing a single AMR sensor. This method comprehensively analyses X-, Y-, and Z-axis information and applies a double-window algorithm to extract a single vehicle waveform. The vehicle mixed algorithm (VMA) is developed to differentiate vehicles driving by the AMR sensor simultaneously and determine vehicle flow rates. In addition, the vehicle motion-state discrimination algorithm (VMSDA) is developed to distinguish the vehicle operating status (i.e. driving on the left lane, the lane line, or the right lane). The field experimental tests verified the effectiveness of the both algorithms. Results indicate that the average accuracy rates of VMA and VMSDA can, respectively, be up to 98.0 and 96.4%. 论文标题 Estimating control delays at signalised intersections using low-resolution transit bus based global positioning system data 作者 Hua Wang, Guohui Zhang, Zhisong Zhang, Yinhai Wang 发表时间 期刊名称 IET Intelligent Transport Systems 期卷 2016,Vol.10,No.2,73-78 简单介绍 Intersection control delay is one of the most important performance indicators for evaluating the traffic level of service and intersection capacities. In current traffic data detection infrastructure, control delay is not directly measurable. Although video-based detection approaches have been applied, their detection accuracy and reliability are constrained by application conditions and detection environments. Manual control delay data collection is labour-intensive, tedious, and time-consuming. High-resolution global positioning system (GPS) data provide an effective means of estimating control delays at intersections, but computationally intensive algorithms and hardware support are needed to handle a large network and impede their wide applications. 论文标题 Traffic flow prediction based on hybrid model using double exponential smoothing and support vector machine 作者 Jinjun Tang; Guangning Xu ; Yinhai Wang ; Hua Wang ; Shen Zhang ; Fang Liu 发表时间 期刊名称 期卷 The Hague, 简单介绍 This study develops a hybrid model that combines double exponential smoothing (DES) and support vector machine (SVM) to implement a traffic flow predictor. In the hybrid model, DES is used firstly to predict the future data, and the smoothing parameters of the DES are determined by Levenberg-Marquardt algorithm. Then, SVM is employed to fit the residual series between the predicting results of DES model and actual measured data for its powerful no-linear fitting ability. Finally, a practical application is used to testify the proposed model. In the application, data smoothing and wavelet de-noising technology are applied as data pre-treatment before prediction. In addition, the data smoothing contains difference and ratio smoothing strategy. It is demonstrated the superiority of the new hybrid model and the effectiveness of data pre-treatment through the comparison between the prediction results of DES, autoregressive integrated moving average (ARIMA) and DES-SVM model. 论文标题 Dual Roadside Seismic Sensor for Moving Road Vehicle Detection and Characterization 作者 Wang H, Quan W, Wang Y, Miller GR 发表时间 期刊名称 Sensors 期卷 Vol. 14, N 简单介绍 This paper presents a method for using a dual roadside seismic sensor to detect moving vehicles on roadway by installing them on a road shoulder. Seismic signals are split into fixed time intervals in recording. In each interval, the time delay of arrival (TDOA) is estimated using a generalized cross-correlation approach with phase transform (GCC-PHAT). Various kinds of vehicle characterization information, including vehicle speed, axle spacing, detection of both vehicle axles and moving direction, can also be extracted from the collected seismic signals as demonstrated in this paper. The error of both vehicle speed and axle spacing detected by this approach has been shown to be less than 20% through the field tests conducted on an urban street in Seattle. Compared to most existing sensors, this new design of dual seismic sensor is cost effective, easy to install, and effective in gathering information for various traffic management applications. 论文标题 面向欠采样公交 GPS 数据的信号交叉口延误估计 作者 王华，张志松，张瞫，刘昕 发表时间 期刊名称 交通运输系统工程与信息 期卷 交通运输系统工程与信 简单介绍 许多大城市公交车均配备GPS 定位系统，系统收集的数据为城市交通规划与管控提供决策支持.然而考虑到数据的传输、存储成本及功能需求，目前公交GPS 数据的采样间隔多为30 秒，由于公交GPS 数据的低采样率问题，其很少被用来估计信号交叉口的延误.为有效利用现有数据，降低交叉口延误获取成本，本文针对欠采样的公交GPS 数据，提出了一种获得交叉口车辆平均控制延误的新方法.在研究欠采样GPS 数据的基础上，通过对车辆在交叉口运行特性的分析，建立欠采样数据下车辆在交叉口的加减速模型，估算交叉口延误值.利用交叉口直行方向公交车的数据验证了该方法的实用性与有效性. 论文标题 Prediction of Multivariate Traffic Parameters under Normal and Abnormal Conditions on the Basis of Multi-Scale Online SVR 作者 Quan Wei, Wang Hua, Lin Datong, Wang Yinhai 发表时间 期刊名称 Quan, Wei Wang, Hua Lin, Datong Wang, Yinhai 期卷 2014.1, Wa 简单介绍 Short-term traffic flow prediction algorithms in ordinary condition are popular in literature. As to traffic management systems in ITS, specifically the dynamic traffic assignment, the short-term prediction of multivariate fundamental traffic parameters, especially under abnormal conditions, such as collision, work and etc. are more vital and preferable. For this purpose, the study proposes a prediction methodology based on Multi-Scale Online Support Vector Regression (MSOL-SVR) algorithm to forecast traffic flow and average speed under normal and abnormal condition. The data provided by the Vehicle Detector Station (VDS)are separated into global data and local data. In normal traffic condition, the prediction based on MSOL-SVR with global data is preferable for the traffic flow forecasting for its good accuracy and efficiency. Additionally, it can provide the whole day prediction without the limitation of short term. The MSOL-SVR with local data is suitable for the prediction of short-term traffic flow and average speed, which has a good performance even in abnormal condition. The paper presents an application of the methodology to predict freeway traffic flow and speed in normal and abnormal conditions. Additionally, the proposed algorithm also is proved to be capable of road network forecasting and provides more accurate and robust results. The results indicate the proposed methodology has an optimal performance. 论文标题 A Multifunctional Joint Angle Sensor with Measurement Adaptability 作者 Quan, W.; Wang, H.; Liu, D. 发表时间 期刊名称 Sensors 期卷 Vol. 13, N 简单介绍 The paper presents a multifunctional joint sensor with measurement adaptability for biological engineering applications, such as gait analysis, gesture recognition, etc. The adaptability is embodied in both static and dynamic environment measurements, both of body pose and in motion capture. Its multifunctional capabilities lay in its ability of simultaneous measurement of multiple degrees of freedom (MDOF) with a single sensor to reduce system complexity. The basic working mode enables 2DOF spatial angle measurement over big ranges and stands out for its applications on different joints of different individuals without recalibration. The optional advanced working mode enables an additional DOF measurement for various applications. By employing corrugated tube as the main body, the sensor is also characterized as flexible and wearable with less restraints. MDOF variations are converted to linear displacements of the sensing elements. The simple reconstruction algorithm and small outputs volume are capable of providing real-time angles and long-term monitoring. The performance assessment of the built prototype is promising enough to indicate the feasibility of the sensor. 论文标题 Modeling of Safe Driving Distance on the Basis of Vehicle-to-Vehicle Communication 作者 Wang Hua, Quan Wei, Wang Yinhai, Liu Xiaoyue 发表时间 期刊名称 Transportation Research Record 期卷 Vol.2381，p 简单介绍 Modeling of safe driving distances is one of the most important topics in collision prevention analysis. This paper presents an improved safe distance model (SDM) that is based on vehicle-to-vehicle communication technology. The technology enables on-time data collection as well as real-time intervehicle communication. A tube-like highway scenario in which vehicles enter at one end and exit at the other is presented to demonstrate the application of the SDM. By incorporation of both braking theory and a driver behavior prediction model, absolute and relative SDMs are developed to provide decision-making information to drivers in response to changing traffic conditions. The comparative analysis with four traditional SDMs confirmed that the proposed model describing the characteristics of vehicle-to-vehicle communication was able to improve the efficiency of vehicle collision prevention systems and increase road use, as well as ensure safe driving. 论文标题 Research on the safety distance model based on car-car communication 作者 Wang Hua, Quan Wei, Liu Xin, Liang ZhongYan 发表时间 期刊名称 18th ITS World Congress 期卷 pp 5621-56 简单介绍 The Safety Distance Model (SDM) is one key research of the collision prevention system. The paper presents the improved SDMs based on the development of car-car communication technology characterized of its on-time measurement and communication. The research is focus on analyzing SDMs of the vehicle fleet driving in single lane under car-following status. By considering both the braking theory and driver prediction model, the absolute and relative SDMs are achieved to support decision-making information in corresponding driving conditions. The comparative analysis with tradition four SDMs confirms that the proposed models are able to increase the efficiencies of the vehicle collision prevention system, increase the utilization rate of the road on promise of ensuring the driving safety. 论文标题 Innovative Smart Road Stud Sensor Network Development for Real-Time Traffic Monitoring 作者 Tao, Zhimin; Quan, Wei; Wang, Hua 发表时间 2022-05-29 期刊名称 JOURNAL OF ADVANCED TRANSPORTATION 期卷 2022 简单介绍 Intelligent transportation infrastructure has gained significant research attention recently. In this paper, an innovative sensor network of smart road stud (SRS) is developed to enhance traffic detection infrastructure characterized by its functionality in traffic data collection, long/short range wireless data transmission, self-sustained power supply, and remote custom controlled lighting-based traffic guidance. Compared to the traditional traffic detectors and road studs, SRS nodes are installed on lane lines instead of lane center to enable the additional applications besides the detection function, such as traffic monitoring, congestion warning, routing guidance, and so on. SRS detects vehicles based on three-axis geomagnetic sensors. A vehicle detection algorithm is proposed correspondingly under different operation scenarios to count vehicles in two adjacent lanes. Its detecting accuracy can be further improved by a sensor network of multiple SRSs working cooperatively. Field test results show that the vehicle detection accuracy based on the SRS network is about 98% per lane, which is the same level as the commercial detector installed in center of lane, even under the non-standard driving behaviors such as crossing lane line. The high performance, value-added service, and low cost enable wide-range applications of SRS networks as part of intelligent traffic detection infrastructure. 论文期刊 论文标题 Spatiotemporal Features—Extracted Travel Time Prediction Leveraging Deep-Learning-Enabled Graph Convolutional Neural Network Model 作者 Xiantong Li 1 , Hua Wang 1,*, Pengcheng Sun 1 and Hongquan Zu 2 发表时间 2021.01.25 期刊名称 Sustainability 期卷 2021(13) 简单介绍 Travel time prediction is one of the most important parameters to forecast network-wide traffic conditions. Travelers can access traffic roadway networks and arrive in their destinations at the lowest costs guided by accurate travel time estimation on alternative routes. In this study, we propose a long short-term memory (LSTM)-based deep learning model, deep learning on spatiotemporal features with Convolution Neural Network (DLSF-CNN), to extract the spatial–temporal correlation of travel time on different routes to accurately predict route travel time. Specifically, this model utilizes network-wide travel time, considering its topological structure as inputs, and combines convolutional neural network and LSTM techniques to accurately predict travel time. In addition to their spatial dependence, both coarse-grained and fine-grained temporal dependences are fully considered among the road segments along a route as well. The shift problem is formulated in the coarse-grained granularity to predict the route travel time in the next time interval. The experimental tests were conducted using real route travel time obtained by taxi trajectories in Harbin. The test results show that the travel time prediction accuracy of DLSF-CNN is above 90%. Meanwhile, the proposed model outperformed the other machine learning models based on multiple evaluation criteria. The RMSE (Root Mean Squard Error) and R2 (R Squared) increased by 18.6% and 22.46%, respectively. The results indicate the proposed model performs reasonably well under prevailingtraffic conditions. 论文期刊 论文标题 Traffic volume measurement based on a single smart road stud 作者 Hua Wang *, Yanli Sun, Wei Quan, Xiaolong Ma, Washington Yotto Ochieng 发表时间 2021.09.06 期刊名称 Measurement 期卷 2022(187) 简单介绍 Anisotropic Magneto-Resistive (AMR) sensing is one of the most burgeoning techniques for traffic volume measurement to support effective traffic management. This is because of its small size, low power consumption and environmental resilience. This paper presents a vehicle detection algorithm based on a new type of AMR sensor called Smart Road Stud (SRS), which can detect the Magnetic Field Intensity (MFI) disturbance generated by passing vehicles. The proposed two-step process can extract the disturbance signal from MFI time series with a simple determination of threshold and a more widespread applicability. However, when vehicle temporal headway is short, an extracted signal may be generated by more than one vehicle. For this case, a method to recognize the number of vehicles the signal corresponds to is proposed also. The results show that the accuracy of traffic volume measurement is higher than 97% when detecting traffic volume in two adjacent lanes. 论文期刊 论文标题 基于时空特征深度学习模型的路径行程时间预测 作者 李先通，全威，王华，孙鹏程，安鹏进，满永兴 发表时间 2021-02-22 期刊名称 吉林大学学报(工学版) 期卷 2021：1-8 简单介绍 针对路径行程时间预测问题，本文提出一种时空特征深度学习网络模型，结合卷积神经网络与长短时记忆网络（LSTM），并考虑路段空间依赖、时序依赖以及粗颗粒度中时间飘移问题，对下一时隙的路径行程时间进行预测。 本文利用哈尔滨市出租车轨迹数据为实验数据，比较发现基于时空特征深度学习网络模型比机器学习模型在多个评价指标上均有提升， 其中 RMSE 和 R2 指标分别提升 18.6%和 22.46%. 结果表明，本文提出的模型预测精度达到 90%以上，且效率处于同类算法的领先水平。 论文期刊 论文标题 Spot vehicle speed detection method based on short-pitch dual-node geomagnetic detector 作者 Wei Quan, Hua Wang, Zhichao Gai 发表时间 2020.02.28 期刊名称 Measurement 期卷 2020:158 简单介绍 The paper proposed a spot vehicle speed detection method bases on a smart infrastructure called Smart Road Stud (SRS), which has functionalities of vehicle detection, wireless transmission, self-powering module and a controlled light-based traffic guidance as a compact road safety stud. Traditional dualnode speed detection system deployed two separated nodes with relative several meters long gap. The SRS integrates two identical three-axis geomagnetic sensors with a short pitch less than 10 cm on a single board to form an integrated device for speed detection, which result the low time resolution of sample points with high driving speed. The slight delay ununiformity of two raw detection waveforms can induce a big error in time difference calculation. The paper proposed standardized processing and Local-Optimization-Fitting (LOF) method for speed calculation, for solving the problem of low time signal resolution and waveform ununiformity induced by different electrical characteristics of two channels. Field testing results show the LOF method for spot vehicle speed estimation is over 93% accuracy, which is worthy of practical application. (C) 2020 Elsevier Ltd. All rights reserved.