Handling Label Noise in Air Traffic Complexity Evaluation Based on Confident Learning and XGBoost

Air traffic complexity is a critical indicator for air traffic operation,and plays an important role in air traffic management(ATM),such as airspace reconfiguration,air traffic flow management and allocation of air traffic controllers(ATCos).Recently,many machine learning techniques have been used to evaluate air traffic complexity by constructing a mapping from complexity related factors to air traffic complexity labels.However,the low quality of complexity labels,which is named as label noise,has often been neglected and caused unsatisfactory performance in air traffic complexity evaluation.This paper aims at label noise in air traffic complexity samples,and proposes a confident learning and XGBoost-based approach to evaluate air traffic complexity under label noise.The confident learning process is applied to filter out noisy samples with various label probability distributions,and XGBoost is used to train a robust and high-performance air traffic complexity evaluation model on the different label noise filtered ratio datasets.Experiments are carried out on a real dataset from the Guangzhou airspace sector in China,and the results prove that the appropriate label noise removal strategy and XGBoost algorithm can effectively mitigate the label noise problem and achieve better performance in air traffic complexity evaluation.

Modeling of 3-D Air Traffic Complexity Based on Route Structure Constraints

It is an important issue to assess traffic situation complexity for air traffic management.There is a lack of systematic review of the existing air traffic complexity assessment methods,and there is no consideration of the role of airspace and traffic coordination mechanism.A new 3-D airspace complexity measurement method is proposed based on route structure constraints to evaluate the air traffic complexity objectively.Firstly,the model of the impact on horizontal and vertical direction for“aircraft pair”is established based on the route guidance.After that,the coupled complexity model for 3-D airspace is given according to the modification on the model in terms of flight standardization.Finally,the global model of the airspace traffic complexity is established.It is proved by the experimental data from the actual operation in airspace that the proposed model can reflect the space coupling situation and complexity of aircraft.At the same time,it can precisely describe the actual operation of civil aviation in China.

Survivability evaluation for networks carrying complex traffic flows

The capability of a system to fulfill its mission promptly in the presence of attacks,failures,or accidents is one of the qualitative definitions of survivability.In this paper,we propose a model for survivability quantification,which is acceptable for networks carrying complex traffic flows.Complex network traffic is considered as general multi-rate,heterogeneous traffic,where the individual bandwidth demands may aggregate in complex,nonlinear ways.Blocking probability is the chosen measure for survivability analysis.We study an arbitrary topology and some other known topologies for the network.Independent and dependent failure scenarios as well as deterministic and random traffic models are investigated.Finally,we provide survivability evaluation results for different network configurations.The results show that by using about 50%of the link capacity in networks with a relatively high number of links,the blocking probability remains near zero in the case of a limited number of failures.

En-route Sector Complexity Control Strategies in Air Traffic Management

Along with the rapid development of air traffic, the contradiction between conventional air traffic management(ATM)and the increasingly complex air traffic situations is more severe,which essentially reduces the operational efficiency of air transport systems. Thus,objectively measuring the air traffic situation complexity becomes a concern in the field of ATM. Most existing studies focus on air traffic complexity assessment,and rarely on the scientific guidance of complex traffic situations. According to the projected time of aircraft arriving at the target sector boundary,we formulated two control strategies to reduce the air traffic complexity. The strategy of entry time optimization was applied to the controllable flights in the adjacent upstream sectors. In contrast,the strategy of flying dynamic speed optimization was applied to the flights in the target sector. During the process of solving complexity control models,we introduced a physical programming method. We transformed the multi-objective optimization problem involving complexity and delay to single-objective optimization problems by designing different preference function. Actual data validated the two complexity control strategies can eliminate the high-complexity situations in reality. The control strategy based on the entry time optimization was more efficient than that based on the speed dynamic optimization. A basic framework for studying air traffic complexity management was preliminarily established. Our findings will help the implementation of a complexity-based ATM.

Measuring air traffic complexity based on small samples

Air traffic complexity is an objective metric for evaluating the operational condition of the airspace. It has several applications, such as airspace design and traffic flow management.Therefore, identifying a reliable method to accurately measure traffic complexity is important. Considering that many factors correlate with traffic complexity in complicated nonlinear ways,researchers have proposed several complexity evaluation methods based on machine learning models which were trained with large samples. However, the high cost of sample collection usually results in limited training set. In this paper, an ensemble learning model is proposed for measuring air traffic complexity within a sector based on small samples. To exploit the classification information within each factor, multiple diverse factor subsets（FSSs） are generated under guidance from factor noise and independence analysis. Then, a base complexity evaluator is built corresponding to each FSS. The final complexity evaluation result is obtained by integrating all results from the base evaluators. Experimental studies using real-world air traffic operation data demonstrate the advantages of our model for small-sample-based traffic complexity evaluation over other stateof-the-art methods.

Air Traffic Operation Complexity Analysis Based on Metrics System

In order to quantitatively analyze air traffic operation complexity,multidimensional metrics were selected based on the operational characteristics of traffic flow.The kernel principal component analysis method was utilized to reduce the dimensionality of metrics,therefore to extract crucial information in the metrics.The hierarchical clustering method was used to analyze the complexity of different airspace.Fourteen sectors of Guangzhou Area Control Center were taken as samples.The operation complexity of traffic situation in each sector was calculated based on real flight radar data.Clustering analysis verified the feasibility and rationality of the method,and provided a reference for airspace operation and management.

Traffic Control Under Complex Weather Conditions in Suining Airport

Complex weather conditions is meaning thunderstorm freezing turbulence wind-shear low visibility weather affect the flight safety.When confronted with complex weather conditions,the controllers should know the weather condition and trend weather,and notify the aircraft under your control zone.The controllers provide the required services to the pilots,help the pilots to avoid the complex weather.In this paper,through different complex weathers under different control command,get the different methods of control.

地铁线网性能分析及最小化韧性损失恢复策略

为更好地分析地铁线网性能,优化其在扰动状态下的恢复策略,采用基于复杂网络的地铁线网性能分析方法,并提出最小化韧性损失恢复策略.鉴于地铁线网复杂网络特征,采用Space L拓扑方法处理地铁线网,并运用复杂网络理论计算线网内各站点的基本参数,包括线网的度、平均路径和线网效率等.其次根据韧性理论以线网效率作为性能指标求解各站点韧性损失,采用遗传算法求解站点恢复序列.最后,以福州市为例,分析其地铁线网的复杂网络特征并进行扰动仿真,比较在多站点失效情况下的最小化韧性损失恢复策略与随机恢复策略的恢复效果.研究结果表明:在多个地铁站点受到扰动失效,采用最小化韧性损失恢复策略能够令地铁线网性能在恢复期间仍处于较优水平,恢复效果明显优于具有不确定性的随机恢复策略.

面向智能视频监控的空中交通管制员图像分割

为解决复杂场景下空中交通管制员检测与分割精度低、鲁棒性差的问题,提出一种基于掩码区域卷积神经网络(Mask Region-based Convolutional Neural Networks, Mask R-CNN)的管制员图像分割模型ATC Mask R-CNN(ATC Mask Region-based Convolutional Neural Networks)。首先,构建管制员监控图像数据集(ATC Monitor Image Dataset, AMID)并用于模型训练、测试;其次,在主干网络中引入瓶颈注意力模块(Bottleneck Attention Module, BAM)以增强管制员特征提取,采取改进的柔性非极大值抑制算法(Soft Non-maximum Suppression, Soft-NMS)替代NMS算法进行候选框选取,提高对遮挡目标的检测分割;最后,基于AMID进行管制员图像分割试验。结果显示:ATC Mask R-CNN的精确率、召回率和平均精度分别为96.49%、95.62%和88.84%,表明了该方法的有效性。与Mask R-CNN相比,ATC Mask R-CNN有效降低了复杂场景的不利影响,更适用于管制员工作场景,可以为管制大厅安全管理自动化应用提供技术支撑。

考虑出行阻抗的城市群综合客运网络可达性

为阐明城市群综合客运交通网络的多层空间结构并丰富网络的功能属性,以耦合这一全新视角提出考虑城市交通换乘的城市群综合客运网络模型,并从出行费用与出行时间出发分析节点与网络的可达性。首先,基于复杂网络理论Space-P建模方法,将城市群中的客运站点抽象为网络中的节点并进行编号,以票价与出行时间标定边权,分别构建公路客运子网、铁路客运子网。其次,划设城市群中的各城市中心城区为独立的交通小区,将有城市公共交通、步行等换乘方式连接的节点间添加耦合边,构建耦合子网。再次,将两类客运子网通过耦合子网组合叠加为综合网络,改进传统网络效率指标,构建加权的阻抗效率指标评估节点与网络的阻抗可达性。最后,以成渝城市群为实例研究,构建成渝城市群综合客运网络并分析公路、铁路、综合网络的阻抗可达性。结果表明:多个节点的耦合使得这些节点的阻抗可达性较好,因此在研究城市群综合客运交通网络时,城市交通换乘是不可忽略的因素;综合网络的阻抗可达性相较于公路子网、铁路子网分别提升了83.4%,28.5%,公路与铁路客运子网的耦合提高了城市群客运交通网络的阻抗可达性;推进站点间、多种运输方式间的耦合协调,继而构建更加便捷顺畅的城市群综合客运交通网络,是降低旅客的出行成本的重要途径。

基于复杂网络的成渝地区双城经济圈区域铁路网络时空演化研究

基于复杂网络理论,借助Space L空间方法,构建区域铁路网络拓扑结构模型,研究2000—2030年成渝地区双城经济圈区域铁路网络时空演化。将成渝区域铁路网络的演化划分为初步发展、快速发展、高等化完善化3个发展阶段,分析铁路网络整体结构特征与节点特征的演化,结果表明,成渝地区双城经济圈区域铁路网络空间格局分布存在差异性,成渝地区双城经济圈内部已演变形成以成都、重庆双核心为引领,以遂宁、南充、合川等城市为次核心的非均衡区域铁路网络;随着铁路站点与线路的增加,成渝地区双城经济圈区域铁路网络逐渐呈现小世界特性,核心-边缘的分异特征较为明显;第二阶段的网络化水平提升幅度高于第一阶段的网络化水平提升幅度,且区域边缘节点城市的中心性指标提升较大。

空管数据复杂事件处理技术研究

为智能化处理空中交通数据所蕴含的复杂态势,依据空管领域特性,在复杂事件处理技术的基础上设计实现一个空管复杂事件处理系统,进行数据处理与Web可视化;参考民航业规章及专业知识,制定飞机安全间隔预警、飞机高度变化异常、飞机遭遇恶劣天气三类空管复杂事件模式。在真实数据下模拟应用场景以检测上述模式,结果表明系统可在毫秒级处理延迟下检测到空管复杂事件,能为空管工作提供智能化技术支持。

旅游交通综合体影响因素及动力机制研究

旅游交通综合体属于交通运输与旅游业融合发展进程中的新生事物。为有效推进旅游交通综合体健康、可持续发展,针对目前其概念内涵不清晰、影响因素不明确、发展路径不明朗、建设发展偏盲目等问题,基于节点布局规律,借助交通运输学、旅游学、经济学、系统学等相关理论,提出旅游交通综合体的定义、内涵、主要组成要素及构成原理。借鉴旅游目的地生命周期理论,提出了旅游交通综合体“孕育阶段—快速成长阶段—逐步成熟阶段—稳定阶段—衰退(或重生)阶段”的演进发展过程。遵循“研究基础—理论体系—影响因素—阶段分析—动力机制”的总体思路,从文献分析、实证探索、自身功能特征分析3方面入手,通过专家问卷调查确定旅游交通综合体的2个1级影响因素、12个2级影响因素和37个3级影响因素。依据主成分分析法,遴选确定7个核心影响因素。利用动力机制中“内生动力、外生动力”等相关概念和作用原理,对旅游交通综合体的影响机理和动力机制进行分析。在此基础上,深入剖析5个发展阶段的核心影响因素和辅助影响因素,进而得出旅游交通综合体不同阶段发展演进的影响机理及推动其发展演进的核心动力因素。

全域旅游背景下离岛“乡村活力节点”——洞头区鹿西码头交通综合体策划研究

全域旅游是推动乡村振兴的重要途径。鹿西乡是温州市洞头区唯一的离岛乡镇,全岛建设空间有限,项目资源稀缺,规划建设的鹿西码头不应仅是功能单一的交通码头,而应在海岛乡村整体发展和洞头区全域旅游建设中扮演更重要的角色。因此如何把握机会,补足乡村发展迫切需求的功能要素,打造一个“乡村活力节点”,是进行本次策划研究的核心理念。针对鹿西乡面临的交通与旅游、游客与岛民、发展与保护三对主要矛盾,研究团队提出了“综合交通换乘、功能用途混合、地域文化融入、场所记忆延续”四大策划理念,并进一步规划了交通集散、社区服务、旅游集散、特色餐饮、观光游览、文化展览、综合商业七大业态板块,将鹿西码头打造成一个交通综合体,从而激发海岛乡村活力,并进一步带动洞头北部全域旅游发展,实现局部发展与整体发展的融合。这也将为今后其他海岛乡村发展和小规模码头综合体建设提供可资借鉴的经验。

基于街区演替对出行拥堵影响的城市更新启示——以江苏淮安为例

城市街区演替的多维现象是各种城市问题持续劣化的微观成因,探明其中影响是实施城市更新行动的重要依据。针对江苏省淮安市107处城市街区,利用时空多源数据,采用逻辑降维、关联分析、地理加权回归等方法,构建可表征空间规模、交通设施、日常出行、社会经济及公共交通等演替现象的多维复合要素体系,揭示城市街区演替对交通出行拥堵的时空影响机理。影响机理表明空间规模与日常出行演替具有显著一致的正向影响,公共交通演替具有显著一致的负向影响,交通设施与社会经济的演替则不具显著影响。依循时空影响机理,结合可预见变化、官方指导意见和近期实践经验,情景模拟了全局性交通出行改善下各类街区更新的空间增容阙值,作为城市更新启示。

复杂道路环境下大流量路口多车牌自动识别

复杂道路口车流量大,车牌采集图像存在遮挡,倾斜等现象,导致车牌检测准确率低、泛化性差。为解决上述问题,提出一种基于改进Yolov3车辆识别与Mask R-CNN车牌检测相融合的算法,通过两步分别检测车辆与车牌,最终构建出YOL3-RCNN多车牌识别模型。模型首先基于上采样算法将图像的大、中、小特征有机融合;然后采用形态聚类算法,自适应计算IOU阈值,提高车辆检出率与准确率;接着对检测出的车辆进行裁剪,SOFTNMS优化与仿射变换,解决车牌遮挡,倾斜与背景复杂的难题;最后基于ResNet50网络识别车牌字符与数字,并利用RPN进行回归校验。多组基线算法的仿真结果显示,在UA-DETRAC车辆检测数据集上,与传统车牌检测算法相比,YOL3-RCNN算法的准确率与召回率分别提高了7.7%与9.6%,且具有较高的车牌检测速率。综上所述,所构建的YOL3-RCNN多车牌识别模型具有较高的检测准确性、时效性与普适性。

基于复杂网络的空中交通流量短期预测

为合理预测空中交通流量,结合复杂网络链路预测进行研究。首先,将时间序列转化为可视图得到拓扑特征量,然后结合基于局部信息、路径和随机游走的算法,比较在三亚不同扇区内的预测精度,发现RWR0.85算法预测精度最高。由于链路预测只能预测可能存在的连边,不能预测节点,因此引入D⁃S证据理论预测流量值,预测精度最高可达99.85%。结果表明,复杂网络链路预测结合D⁃S证据理论进行空中交通流量的预测是可行有效的,为进一步深入研究奠定了基础。

终端区交通复杂性评估及演变分析

终端区内飞行密集、环境多变,已成为国家空域系统运行能力提升的重要瓶颈。精准量化终端区内交通复杂性并把握其演化规律是实现空中交通精细化管理的基础,对于提升终端区运行能力有重要意义。终端区空中交通复杂性描述了某一时间点或时间段内空中交通流特征的复杂程度。基于动态密度思想,针对终端区运行特征,构建了多维度的空中交通复杂性评价指标,并运用熵权法确定指标权重,反映评估指标的无序化程度,评定信息量的大小。构建复杂度计算模型,从客观上利用多指标反映航空器实时复杂性演变。采用多智能体仿真建模工具NetLogo搭建了终端区仿真环境,以广州终端区的实际进场数据搭建了基础场景,模拟了终端区交通复杂性的宏观演化过程。通过调节进场移交点交通流需求比例、设计不同天气情景,分析了不同场景下交通复杂性演化特征。结果表明,该评估体系使用较少的指标和计算时间,能够较为准确、客观地评估时间片内的复杂性,符合实际情况。NetLogo建模工具能够仿真终端区交通流,直观地观察交通流运行行为。当进场移交点交通流流量分布更为均匀时,复杂性较低。终端区受恶劣天气影响时,其受影响程度取决于恶劣天气覆盖航段的航班流量分布情况、影响的范围以及受影响航段到跑道距离。部分交通流存在迟滞现象,反映了复杂性的蔓延时空特征。该复杂性评估方法能够有效评估航段、航线、终端区复杂性及演变规律,为开展终端区精细化空中交通管理提供参考。

基于复杂网络的高速公路交通事故风险动态演化模型

为有效挖掘高速公路交通事故规律信息,基于复杂网络理论提出高速公路交通事故致因网络构建方法.从风险结构与风险模式两方面定义风险传播机制,通过高速公路交通事故致因网络与风险传播机制的有机结合,建立了高速公路交通事故风险演化模型.以高速公路重特大交通事故为例,对201份高速公路重特大交通事故调查报告进行风险分析.结果表明,基于复杂网络的风险演化模型适用于高速公路的交通事故风险分析;通过高速公路交通事故风险演化模型可对各致因的风险传播特性进行解析与归类,从而制定出针对不同情形致因的控制策略,为高速公路交通事故风险演化研究提供新思路.

复杂交汇水域船舶航路网提取方法研究

文中提出了一种适用于复杂交汇水域船舶航路网的提取方法.采用轨迹聚类算法获取水域主要船舶交通流,通过水域栅格化将各船舶交通流转化为栅格图像,运用图像细化的原理从不同交通流中提取对应船舶航路,以距离阈值为标准识别航路之间的交汇点,最终形成水域船舶航路网.结果表明:该方法不仅可有效提取水域内主要船舶航路以及航路交汇点,还可同时获取交汇点密集区域.