基于自注意力机制与图自编码器的路网交通流数据修复模型

针对城市交通流数据修复问题，提出一种基于图卷积网络和多头自注意力机制的自注意 力图自编码器模型。该模型包括基于拓扑图结构和图信号捕获交通流时空关联性的 STGCN (Spatial-temporal Graph Convolutional Networks)网络。在该网络中使用 LSTM(Long Short-Term Memory)网络学习数据中时序规律，通过注意力网络计算道路自注意力及一阶临近道路注意力系 数，用图卷积网络对图信号重组，达到对缺失数据的精确修复。同时，采用多头自注意力网络计 算数据的注意力权值并对数据重组，捕获交通流数据中的二阶及高阶临近道路空间关联性，提取 已知数据与缺失数据的时间关系，以残差链的形式加入到模型中，作为对STGCN功能的补充。 基于真实数据的实验表明，在多种缺失模式和缺失率下，该模型能够学习路网拓扑关系，捕获数 据中的时间规律性和时空关联性，有效地修复缺失数据。     

Optimal development of alternative fuel station networks considering node capacity restrictions

A potential solution to reduce greenhouse gas (GHG) emissions in the transport sector is the use of alternative fuel vehicles (AFV). As global GHG emission standards have been in place for passenger cars for several years, infrastructure modelling for new AFV is an established topic. However, as the regulatory focus shifts towards heavy-duty vehicles (HDV), the market diffusion of AFV-HDV will increase as will planning the relevant AFV infrastructure for HDV. Existing modelling approaches need to be adapted, because the energy demand per individual refill increases significantly for HDV and there are regulatory as well as technical limitations for alternative fuel station (AFS) capacities at the same time. While the current research takes capacity restrictions for single stations into account, capacity limits for locations (i.e. nodes) – the places where refuelling stations are built such as highway entries, exits or intersections – are not yet considered. We extend existing models in this respect and introduce an optimal development for AFS considering (station) location capacity restrictions. The proposed method is applied to a case study of a potential fuel cell heavy-duty vehicle AFS network. We find that the location capacity limit has a major impact on the number of stations required, station utilization and station portfolio variety.     

地铁网络服务韧性评估与最优恢复策略

针对已有基于拓扑效率的地铁网络韧性指标无法反映地铁运营实际的不足，构建考虑线 路流量影响的路网服务效率指标和基于服务效率的路网服务韧性指标，以及基于路网服务效率 的节点重要度指标；提出以路网服务韧性最大化为目标的优化模型，并基于遗传算法求解模型获 得最优恢复策略。算例结果表明：分别以服务效率和拓扑效率作为路网性能指标，获得的失效节 点恢复次序明显不同；蓄意攻击下，最优恢复策略获得的路网服务韧性分别比基于重要度的优先 恢复策略、基于节点度的优先恢复策略和随机恢复策略高16.76%、72.11%和86.21%。上述结果 表明，必须根据地铁运营实际合理选择路网性能指标和恢复策略，否则可能得到次优甚至明显偏 离实际的方案，无法实现预期目标。     

Application of Lagrangian relaxation approach to α-reliable path finding in stochastic networks with correlated link travel times

This study investigates the important problem of determining a reliable path in a stochastic network with correlated link travel times. First, the distribution of path travel time is quantified by using trip records from GPS probe vehicles. Second, the spatial correlation of link travel time is explicitly considered by using a correlation coefficient matrix, which is incorporated into the α-reliable path problem by Cholesky decomposition. Third, the Lagrangian relaxation based framework is used to handle the α-reliable path problem, by which the intractable problem with a non-linear and non-additive structure can be decomposed into several easy-to-solve problems. Finally, the path-finding performance of this approach is tested on a real-world network. The results show that 15 iterations of calculation can yield a small relative gap between upper and lower bounds of the optimal solution and the average running time is about 5 s for most OD settings. The applicability of α-reliable path finding is validated by a case study.     

货车轨迹数据在公路货运系统中应用研究综述

随着轨迹数据可获取性及精度的持续提高，货车轨迹数据被广泛应用于公路货运系统的 规划与管理中，同时，人工智能和大数据分析技术的快速发展也为公路货运系统研究带来新的机 遇与挑战。本文全面梳理并总结了公路货运轨迹数据应用领域的相关研究，从基于轨迹数据的 货运出行信息辨识、货运系统关键特征预测、货运轨迹数据进一步应用3个方面回顾现有文献的 研究目标、主要内容和研究方法。通过文献分析发现：货运出行信息辨识研究聚焦于货运停留 点、车辆和货物、活动出行模式等热点主题，但现有辨识方法多移植于旅客出行研究，需要更多地 考虑货运出行的独特特征。在货运系统关键特征预测方面，研究者主要针对货运行程时间、空间 位置、出行需求等主题展开研究，并证明了基于轨迹数据预测货运特征的可行性，但预测时空范 围较为局限，需要根据具体的货运任务、货车司机特征和货运政策进行深入研究。此外，轨迹数 据也被应用于货运出行路径选择行为、货运停车休息行为、行驶安全、货运排放和能耗分析、货运 政策评估等研究。最后，在总结现有研究不足的基础上，本文认为未来研究应重点将货运轨迹数 据与其他多源数据相结合，从3个关键技术进行突破：一是针对货运实践个体，重点探索高效货车 驾驶员的出行特征和出行模式，并在货运系统中进行推广应用；二是针对交通运输新技术和新形 势，重点开发和优化自动驾驶技术和重大应急事件影响下的货运组织模式与策略；三是针对货运 供需关系及匹配机制，重点研究货运全流程供需状态辨识与预测，并结合深度学习等方法训练和 开发智能供需匹配模型，从而优化货运系统调度，助力社会散乱运力资源整合，提高货运系统的 综合效率。     

Reconfigurable Communication Processor： A New Approach for Network Processor

As the traditional RISC ASIC/ASSP approach for network processor design can not meet the today‘s requirements, this paper described an alternate approach, Reconfigurable Processing Architecture, to boost the performance to ASIC level while reserve the programmability of the traditional RISC based system. This paper covers both the hardware architecture and the software development environment architecture.     

WGS-84至工程坐标系的转换参数获取

随着直接由GPS相对定位获取高精度的工程坐标成为可能 ,由GPS测定WGS 84坐标系的坐标 (或坐标增量 )至用户定义的工程坐标系坐标 (或坐标增量 )所需的转换参数的获取方法以及精度日益为人们所重视 .提出了研究这一问题的必要性 .在给出不同条件下坐标转换参数的获取技术的基础上 ,对转换参数的精度的影响因素进行了分析 ,对转换网的要求提出了定性的观点     

Effect of interference on transmission for newly deployed wireless sensor networks

The co-channel interference （collisions） seriously affect the transmission for the newly deployed wireless sensor networks since there is no structure at that phase. In this paper, the interference of the whole network is analyzed based on the SNIR model. The new concept of critical transmitting range is proposed, based on which the transmission theorem is obtained and proved. The results provide the theoretical ground to set up the primary structure of newly deployed networks.     

Additive—Multiplicative Fuzzy Neural Network and Its Performance

Introduction　　Kosko[1] hasprovedthatanadditivefuzzysystemcanapproximateanycontinuousfunctiononacompactdomaintoarbitraryaccuracy .AspointedbyWang[2 ] ,amultiplicativefuzzysystem ,whichisconstructedbyusingGaussianmembershipfunctionandcentroiddefuzzificati…     

无线Mesh网络的跨层设计理论与关键技术

由于无线M esh网络(WMN)在拓扑、传输和业务上的特性,传统的用于有线网络的分层协议设计方法已不能保证其服务质量(QoS).探索基于物理层、MAC层、路由等协议层的WMN跨层设计方法的目标是在无线资源利用率和多媒体业务的QoS需求两方面达到较好的折衷.WMN各个协议层在设计过程中的有关协议和算法要求附加统一的跨层管理器,监测各层的分组传输性能或需求,动态控制或调节相关算法.通过实现较高协议层的多媒体业务QoS需求与较低协议层的网络状态信息在各协议层之间的共享,可以达到对协议层控制算法的优化.在合理地选择跨层设计目标的基础上,多个协议层需要联合设计与优化.从物理层、MAC层、路由协议层和TCP层等层面介绍了WMN跨层设计的一般原则和方法.归纳了目前WMN跨层设计中亟待深入研究的一些理论和关键技术,包括自适应速率与节能机制、基于QoS需求的跨层MAC协议设计和路由协议设计等.