讲座预告 | 第五届中国系统科学大会-智能交通前沿论坛

作者:发布时间:2021-11-16浏览次数:46


     2021年5月21日下午,将于江苏省会议中心(南京钟山宾馆)举办第五届中国系统科学大会-智能交通前沿论坛(会前专题讲座),欢迎大家参会交流。
     中国系统科学大会(CSSC)由上海系统科学研究院,中国科学院数学与系统科学研究院系统科学研究所、北京师范大学系统科学学院、北京交通大学交通系统科学与工程研究院、中国系统工程学会等单位在2017年联合发起。会议的主旨是为系统科学及其相关领域的国内外专家学者提供一个学术交流平台,促进相关学科的交流、发展和融合,促进新方向、新领域的产生。第五届中国系统科学大会将由东南大学主办。
    本次大会将于5月21日下午举办两场会前专题讲座。其中专题讲座2:智能交通前沿论坛将由来自四所高校的行业专家展开精彩报告,就公共自行车系统、自动驾驶、手机大数据、航运运营优化等课题展开深入研讨,敬请关注参与!

第一场


    田立新南京师范大学副校长、教授、博士生导师。主要从事动态大系统建模及控制、能源系统工程等领域研究。先后主持国家自然科学基金12项,完成10项,其中有1项为国家自然科学基金重大项目课题、1项为重点项目课题、4项为重大研究计划项目;主持国家社会科学基金项目2项均完成,其中1项为国家社会科学基金重大项目。在国内外发表学术论文300多篇,被SCI检索240多篇,专著10部。部分工作发表在PNAS, TRCIEEE ITSMResource Policy, Energy EconomicsPhy Rev E等重要杂志上。作为负责人获教育部高等学校优秀科研成果奖一等奖1项、二等奖1获江苏省科技进步一等奖1项、二等奖1获江苏省哲学社会科学奖一等奖2项。
公共自行车系统实时服务的鲁棒性及其预警分析


主讲人:田立新
摘要:本报告着力于分析公共自行车系统的实时服务的鲁棒性,测算对公共自行车系统的实时服务的起预警作用的站点阈值。我们构建了一个比现有的最大联通集更能刻画公共自行车系统的实时服务的新指标,提出了一个刻画正常运营对公共自行车系统的实时服务影响的新鲁棒性策略,并在两种指标下,完成了正常运营及站点失效对公共自行车系统实时服务的鲁棒性分析。为对公共自行车系统的实时服务给出预警,我们依据上述鲁棒性分析,给出了一个计算站点阈值的方法。仿真分析显示[0.19,0.82]是南京市公共自行车系统的站点阈值。该结果改进了现有的结果,将一周流量型窗口下累计有再平衡需求的站点数减少了2.18%,有利于动态再平衡的发展。


第二场

       龙建成,合肥工业大学教授、博士生导师。主要研究方向为城市动态交通分配理论与方法、城市交通拥堵传播建模及分析、城市交通组织优化与管理等。先后主持国家自然科学基金青年科学基金项目、面上项目、优秀青年科学基金项目、国家杰出青年科学基金项目、教育部新世纪优秀人才支持项目、霍英东教育基金会高等学校青年教师基金项目、中国博士后科学基金项目等;在《Operations Research》、《Transportation Science》、《Transportation Research Part B\C\D\E》、《IEEE Transactions on Intelligent Transportation Systems》、《European Journal of Operational Research》、《Networks and Spatial Economics》、《系统工程理论与实践》等国内外期刊上发表论文60余篇。博士学位论文城市道路交通拥堵传播规律及消散控制策略研究2012年全国优秀博士学位论文提名论文。动态交通分配方面的研究成果曾入选了国家自然科学基金委2014年年度报告。现任学术期刊《International Journal of Transportation》和《控制与决策》编委、管理科学与工程学会理事、中国系统工程学会理事、安徽省非线性科学学会常务理事、中国运筹学会智能计算分会常务理事、管理与决策科学专委会常务理事、管理科学与工程学会交通运输管理研究会委员、合肥工业大学学术委员会委员等。  

A time-dependent shared autonomous vehicle system design problem


主讲人:龙建成
摘要:The emergence of the shared autonomous vehicle (SAV) provides new opportunities and challenges for the fashionable car-sharing mode. This study proposes a time-dependent SAV system design problem by jointly optimizing fleet size, parking infrastructure deployment, and daily operation of the system for infrastructure planning in the long run. The dynamic system optimum (DSO) principle in terms of total daily system cost (TDSC) is adopted to formulate the daily operation of the SAV system, i.e., users’ departure time choices and SAVs’ route choices. By incorporating the link transmission model (LTM) as the traffic flow model, the daily operation problem (DOP) of the SAV system is formulated as a linear programming (LP) problem. Further, the time-dependent SAV system design problem is formulated as a mixed integer linear programming (MILP) problem. The LP relaxation of the proposed MILP problem could provide a tight lower bound, and a diving heuristic algorithm is developed to solve the proposed MILP problem. Finally, numerical examples are designed to illustrate the properties of the model and the efficiency of the proposed solution algorithm.

第三场

      肖峰,工学博士,教授,博士生导师。毕业于清华大学,获得土木工程学士学位和交通工程硕士学位,并于香港科技大学获得交通工程博士学位,曾任美国加州大学戴维斯分校博士后,英国Maunsell咨询公司香港总部交通规划师。现任西南财经大学大数据研究院副院长,教授、博士生导师、国家杰出青年基金、国家自然科学基金优秀青年基金获得者,教育部长江学者青年学者,四川省百人计划特聘专家。研究方向主要包括人工智能算法与数据挖掘、复杂交通系统建模优化、金融风控与智能投顾、区块链等。先后主持和参与了NSFC-RGC香港-内地联合基金, NSFC-广东大数据科学中心项目,国家重点研发计划等10余项重要国家和省部级课题。在管理科学与工程、交通科技及数据挖掘领域著名国际期刊和会议如Transportation ScienceTransportation Research Part ABCD, IEEE TKDEISTTT等发表论文40余篇。     
Estimating Traffic Flow States with Smart Phone Sensor Data


主讲人:肖峰
摘要:This study proposes a framework to classify traffic flow states. The framework is capable of processing massive, high-density, and noise-contaminated data sets generated from smartphone sensors. The statistical features of vehicle acceleration, angular acceleration, and GPS speed data, recorded by smartphone software, are analyzed, and then used as input for traffic flow state classification. Data collected by a five-day experiment is used to train and test the proposed model. A total of 747,856 sets of data are generated and used for both traffic flow state classification and sensitivity analysis of input variables. After applying various algorithms to the proposed framework, the study found that acceleration and angular acceleration data can increase the accuracy of traffic flow classification significantly. When the hyper-parameters of the Deep Belief Network model are optimized by the Differential Evolution Grey Wolf Optimizer algorithm, the classification accuracy is further improved. The results have demonstrated the effectiveness of using smartphone sensor data to estimate the traffic flow states and shown that our proposed model outperforms some traditional machine learning methods in traffic flow state classification accuracy.

第四场

       王亚东,南京理工大学经济管理学院教授。致力于多模式交通系统管理与优化研究,综合运用混合整数规划、随机优化、鲁棒优化等优化理论与方法,解决航运运营中的关键科学问题。承担多项省部级以上科研课题,相关研究成果已在Transportation ScienceTransportation Research Part B等交通与运筹管理知名期刊发表学术论文二十余篇。 

Optimal deployment and scheduling for heterogeneous vessels in a global linear container shipping route



主讲人:王亚东
摘要:Previous studies on liner container shipping operations usually assume identical container ships deployed in the same shipping route. However, in real operations, this assumption does not always hold considering the distinct capacities, ages, fuel efficiencies, cost structures, etc. of these ships. These distinctions significantly influence the number of containers transported, the bunker fuel consumption, and the operating cost of a shipping route. In this regard, this paper considers the joint ship deployment, sequencing, and scheduling problem for a fleet of heterogeneous vessels in a shipping route. A mixed integer programming model is developed to select the optimal ships from a set of candidate ships together with their sequences, schedules, and sailing speeds in the shipping route to minimize the total cost. A tailored solution algorithm is subsequently developed to calculate the global optimal solution. Numerical experiments demonstrate that this algorithm significantly outperforms the classical branch-and-cut algorithm in solving the model. In addition, by applying our model in a real-case shipping route, we find that the model is able to reduce the total cost by 5% compared with that considering homogeneous vessels.

主持人介绍


    顾子渊东南大学交通学院副研究员,主要研究方向包括交通网络建模,宏观基本图理论与应用,拥挤收费,交通仿真及优化等。迄今为止在Transportation Research Part A\B\C等期刊发表学术论文二十余篇。