Spatial modeling of flood probability using geo-environmental variables and machine learning models,case study: Tajan watershed,Iran

The main objective of this study was to produce flood susceptibility maps for Tajan watershed, Sari, Iran using three machine learning (ML) models including Self-Organization Map (SOM), Radial Basis Function Neural Network (RBFNN), and Multi-layers Perceptron (MLP). To reach such a goal, different physical-geographical factors (criteria) were integrated and mapped. 212 flood inventory map was randomly divided into training and testing datasets, where 148 flood locations (70%) were used for training and the remaining 64 locations (30%) were employed for testing. Model validation was performed using several statistical indices and the area under the curve (AUC). The results of the correlation matrix showed, three factors slope (0.277), distance from river (0.263), and altitude (0.223) were the most important factors affecting flood. The accuracy evaluation of the flood susceptibility maps through the AUC method and K-index shows that in the validation phase RBFNN (AUC = 0.90) outperform the MLP (AUC = 0.839) and SOM (AUC = 0.882) models. The highest percentage flood susceptibility of the area in MLP, SOM and RBFNN models is related to moderate (28.7%), very low (40%) and low (37%), respectively. Also, the validation results of the models using the Relative Flood Density (RFD) approach showed that very high class had the highest RFD value.     

焊缝补强方式对大直径贮箱箱底承载性能影响

基于有限元法研究了典型10 m级直径贮箱箱底焊缝在双面对称补强、内表面补强及外表面补强三种情况下的内压承载性能。数值计算采用二维对称平面模型,考虑了筒段和短壳真实边界条件及焊缝对承载能力的影响,构建的考虑材料塑性的非线性数值分析模型准确地获得了贮箱箱底内外表面经向应力。结果表明:顶盖和瓜瓣焊缝区域是箱底的薄弱位置,使用内压下,双面对称补强的加强区内外表面经向应力差较小,结构均未进入塑性,单面补强的加强区内外表面经向应力差远大于双面对称补强,局部进入塑性,且外表面补强的加强区最大和最小经向应力差相对于内表面补强分别增加了9.7%和27.2%,变形不协调；设计内压下,箱底内外表面均有局部进入塑性,材料塑性对内外表面经向应力差有一定的缓解作用,能够显著缓解内外表面应力差造成的附加弯矩；双面对称补强优于内表面补强,内表面补强优于外表面补强,单面补强易产生附加弯矩,不利于箱底的均匀承载和变形协调。该研究结果指导了大直径贮箱箱底结构的优化设计。     

面向林火持续侦察的多无人机分布式控制方法

为解决目前面向林火持续侦察多无人机（UAV）协同控制实用性与自主性不足的问题，基于蔓延速度诱导元胞自动机（SVICA）林火蔓延算法、无人机与传感器建模，构建了较为真实的三维多无人机火场侦察仿真环境与侦察效能指标，提出了一种面向林火持续侦察的多无人机双层分布式控制架构，在行动层基于强化学习训练的人工神经网络（ANN），实现了有风条件下无人机自主火场环绕与地形跟随功能，在策略层设计通过时域均匀分布算法进行各无人机空速的离散自主调节，最终达到多无人机林火持续侦察时域分布的均匀性与即时性目的。通过一系列数值仿真实验，验证了所提出的无人机分布控制策略在无人机损失和补充突发情况下的自适应性。基于无人机数量与侦察效能指标关系的实验与研究，定义了无人机出动阈值并验证了无人机长时间出动回收策略。最终实验结果表明，针对林火持续侦察任务，所提出的多无人机分布式控制方法具备一定的有效性与实用性。     

Improving orbit prediction accuracy through supervised machine learning

Due to the lack of information such as the space environment condition and resident space objects’ (RSOs’) body characteristics, current orbit predictions that are solely grounded on physics-based models may fail to achieve required accuracy for collision avoidance and have led to satellite collisions already. This paper presents a methodology to predict RSOs’ trajectories with higher accuracy than that of the current methods. Inspired by the machine learning (ML) theory through which the models are learned based on large amounts of observed data and the prediction is conducted without explicitly modeling space objects and space environment, the proposed ML approach integrates physics-based orbit prediction algorithms with a learning-based process that focuses on reducing the prediction errors. Using a simulation-based space catalog environment as the test bed, the paper demonstrates three types of generalization capability for the proposed ML approach: (1) the ML model can be used to improve the same RSO’s orbit information that is not available during the learning process but shares the same time interval as the training data; (2) the ML model can be used to improve predictions of the same RSO at future epochs; and (3) the ML model based on a RSO can be applied to other RSOs that share some common features.     

我国高校无形资产经营管理分析

高等学校的无形资产经营管理是市场经济条件下各个高校需要解决的一个难题和重点。分析我国高校无形资产经营管理的现状及其问题,并给出相关政策建设。对加快相关的法规建设,规范高校无形资产经营管理具有现实意义。     

复合材料钻削刀具状态集成学习分类技术

刀具状态监测关系到工件加工质量,因此实时掌握刀具的磨损状态具有重要的意义。针对单一模式识别分类器的局限性,提出了基于异态集成学习模型的刀具状态监测系统。在该系统中,根据集成学习基分类器选择原则,选取了支持向量机(SVM)、隐马尔科夫模型(HMM)以及径向基神经网络(RBF)这3个单分类器作为基分类器。为了验证监测系统的有效性,进行了复合材料钻削实验,提取了加工过程中的钻削力信号、振动信号的时域特征并利用局部保持法(LPP)进行了特征选择。通过与单分类器和集成学习分类效果的对比,表明了集成学习模型相比于单一基分类器具有更高的分类精度和更好的稳定性。     

Learning Routes from Visualizations for Indoor Wayfinding: Presentation Modes and Individual Differences

Abstract

Participants (N = 78) studied a visualization of a route through a complex building and walked that route in the real building without further assistance. Erroneous turns on the route as well as indicators of uncertainty such as hesitations were assessed. Three types of route visualizations were compared: (1) an allocentric, map-based visualization with the route indicated in floor maps, (2) an ordered sequence of pictures of decision points shown from the egocentric perspective, and (3) an animation showing a virtual walk of the route from the egocentric perspective. In addition to the experimental variation, gender differences, differences in visual-spatial abilities and differences in self-reported wayfinding strategies were considered as predictor variables. Wayfinding performance did not differ between allocentric (map) and egocentric (decision point pictures and animation) visualizations. However, wayfinding performance was better with animated than with static egocentric visualizations. Individual differences in the ability to encode visual-spatial information from the visualization played a critical role for route learning. Self-reported sense of direction related to egocentric wayfinding strategies also predicted wayfinding performance. Gender differences were attributable to differences in visual-spatial abilities and egocentric wayfinding strategies. Interactions between visualizations and individual differences were not found. It is concluded that animations of virtual walks are suitable to convey route information in complex buildings. Successful acquisition of route knowledge from maps is possible but might depend on the comprehensibility of the structure of the building.     

中国共产党人学习观研究述评

学习在多学科的共同探索和推进下,已成为当下的一个前沿和热门课题。由此,探究当前中国共产党人学习观研究中已取得的主要理论成果、薄弱环节、有待进一步创新之处,对于进一步深化对中国共产党人学习观的科学研究,构筑一个完整的中国共产党人学习观的科学体系具有重要意义。     

一种基于迁移学习的遥测数据异常检测方法

为解决卫星遥测数据异常检测面临的数据不平衡且缺乏有标签样本的问题，提出一种基于一维卷积神经网络(1dCNN)迁移学习的异常检测方法。首先利用源域卫星的遥测数据对1dCNN进行预训练，使得模型的卷积层具有卫星状态特征的提取能力；然后将训练好的模型迁移到缺乏标签数据的目标域卫星中；利用目标域有标签样本对预训练模型进行微调，从而实现了对目标域测试集样本的异常检测。为了使1dCNN能够适应遥测数据样本的不平衡性，引入了代价敏感训练策略，建立动态损失函数，从而提升代价敏感一维卷积神经网络(cs 1dCNN)对于异常样本的识别能力。以某两个卫星的电源分系统遥测数据进行了验证，实验结果表明该异常检测迁移方法具有较好的有效性和鲁棒性。     

飞行员导航专家系统

论述一个飞行员导航专家系统方案。此系统包括二次通道：飞行员助理（ＰＡ）通道和飞行员助理学习（ＰＡＬ）通道。ＰＡ通道完成导航计算、形势判断和决策，通道还将显示出当前形势及给飞行员提出的建议。ＰＡＬ通道完成知识库（ＫＢ）的更新，包括：对飞行员完成的操作作出评价、综合归纳知识和规则以及知识库的修正更新。对系统所涉及的一些原则方法和算法进行了研究。