Learning aircraft operational factors to improve aircraft climb prediction: A large scale multi-airport study

Ground-based aircraft trajectory prediction is a major concern in air traffic control and management. A safe and efficient prediction is a prerequisite to the implementation of new automated tools.In current operations, trajectory prediction is computed using a physical model. It models the forces acting on the aircraft to predict the successive points of the future trajectory. Using such a model requires knowledge of the aircraft state (mass) and aircraft intent (thrust law, speed intent). Most of this information is not available to ground-based systems.This paper focuses on the climb phase. We improve the trajectory prediction accuracy by predicting some of the unknown point-mass model parameters. These unknown parameters are the mass and the speed intent. This study relies on ADS-B data coming from The OpenSky Network. It contains the climbing segments of the year 2017 detected by this sensor network. The 11 most frequent aircraft types are studied. The obtained data set contains millions of climbing segments from all over the world. The climbing segments are not filtered according to their altitude. Predictive models returning the missing parameters are learned from this data set, using a Machine Learning method. The trained models are tested on the two last months of the year and compared with a baseline method (BADA used with the mean parameters computed on the first ten months). Compared with this baseline, the Machine Learning approach reduce the RMSE on the altitude by 48% on average on a 10 min horizon prediction. The RMSE on the speed is reduced by 25% on average. The trajectory prediction is also improved for small climbing segments. Using only information available before the considered aircraft take-off, the Machine Learning method can predict the unknown parameters, reducing the RMSE on the altitude by 25% on average.The data set and the Machine Learning code are publicly available.     

客运专线与既有线合理分工原则与优化模型

客运专线与平行既有线的合理分工及使用,对方便各类旅客出行和增加铁路运营效益有着直接的影响.本文综合分析了影响客运专线与既有线分工的社会因素和经济因素;基于福利经济学原理,论证了客运专线与既有线的合理分工应是一种帕累托的改进过程,合理方案应是实现帕累托最优状态.藉此,提出了兼顾效率与公平的合理分工基本原则.依据分工原则,运用定量优化理论建立了铁路运输收益和旅客收益最大化优化数学模型,并从优选思想与启发算法相结合的角度,提出相应的求解方法.     

Empirical Estimation of Term Structure of Interbank Rates in China

Nelson-Siegel model （ NS model） and 2 extended NS models were compared by using daily interbank government bond data Based on the grouping of bonds according to the residual term to maturity, the empirical research proceeded with in-sample and outof-sample tests. The results show that the 3 models are almost equivalent in estimating interbank term structure of interest rates. Within the term to maturities between 0 and 7 years, the gap of the absolute errors of the 3 models between in-sample and out-of-sample is smRller than 0.2 Yuan, and the absolute values of the in-sample and out-of-sample errors are smaller than 0. 1 Yuan, so the estimation is credible. Within the term to maturities between 7 and 20 years, the gap of the absolute errors of the 3 models between in-sample and out-of-sample is larger than 0.4 Yuan, and the absolute values of the in-sample and out-of-sample errors are larger than 1.0 Yuan, so the estimation is incredible.     

我国集装箱班轮运输市场垄断程度研究

从市场集中度指数、市场力量和垄断行为3个方面考察我国国际集装箱班轮运输市场的垄断程度，显然高于将全球作为“一个”市场的程度。从市场集中度指数可以认为我国班轮运输市场已经达到中型寡头垄断程度。我国远洋班轮航线的勒纳指数高于0．6，甚至接近于1，说明班轮公司市场力量之强大。而我国现行的法律法规中没有为班轮运输市场的买方预设运价谈判和利益诉求机制，则使运输需求快速增长的中国外贸企业明显处于弱势地位。     

Blog在现代教学中的应用研究

随着“校校通”工程的深入实施网络应用于教学的功能得到了更深更广的认识和开发。博客(Blog)在网络时代的飞速发展,冲击着传统教育。本文分析了博客对传统教学的影响和在现代教学中的应用。     

智能Agent在网络虚拟学习社区教学活动中的应用

随着计算机技术的发展,人工智能技术逐步开始了实用化的进程。近些年来,最为热门的人工智能应用就是“智能Agent”。随着教育信息化进程的推进,智能Agent在网络化学习中发挥着其独特的作用。本文首先介绍了智能代理(IntelligentAgent)的知识,然后探讨其在网络虚拟学习社区教学活动中的具体应用。     

一种新型的船舶横摇运动实时预报方法

本文在阐述强化学习的基本原理，方法的基础上，提出了一种强化学习的TD算法与BP算法相结合的BPTD方法，并将基用于对角回归神经网络的在线训练，最后以在船舶横摇运动时预报技术上的应用为例，说明这种算法有很强的实时多步预报能力。     

基于PointNet++的船体分段合拢面智能识别方法

船体分段合拢面的精度检测是分段总组合拢过程中的重要环节。在船体分段合拢面的精度检测方面,三维扫描仪相对全站仪有着巨大优势。然而,三维扫描仪在扫描过程中会记录很多与合拢面无关的点,因此本文对三维扫描仪扫描出的点云数据,进行合拢面的智能识别。通过采用深度学习理论对PointNet++点云网络进行适合本文的改进,使用CAD模型导出的点云数据构建有标注的船体分段点云数据集,进而使用Adam优化算法对网络进行优化训练。最终网络模型对分段合拢面的识别在验证集上获得精确率73%,召回率90%的效果。     

行动学习理论在高职应用写作教材编写中的应用

行动学习是一种透过行动实践学习理论并与实践相结合的学习方法。文章分析了高职应用写作教材编写中应着重解决的矛盾，阐述了基于行动学习的高职应用写作教材的编写思路。     

地铁工程全生命周期造价的确定与控制

通过对地铁工程项目全生命周期造价管理现状的分析，在项目组织集成的基础上，通过地铁工程项目利益相关者的诉求分析，合理确定项目的全生命周期工程造价，并以此作为控制地铁工程项目全生命周期造价的基础。