空间机器人深度学习识别捕获部位的应用探讨

针对空间机器人对捕获部位识别方法的普适性、实时性和准确性等要求,提出了采用深度学习方法对空间机器人捕获目标的特征部位进行识别。通过比较分析方法、数据驱动方法等传统识别方法和深度学习方法的优缺点,发现深度学习方法对于解决空间机器人捕获部位识别问题具有显著优势。进一步分析了应用深度学习方法解决捕获部位识别问题的几个关键技术问题,为后续空间机器人在轨捕获目标的研究与实践提供了新的思路。     

高职生英语学习动机调查分析

调查广州民航职业技术学院学生的英语学习动机,结果表明：（1）高职生对英语学习的重要性有较充分的认识,但对提高跨国文化交流能力的必要性和重要性认识不足;（2）学习动机与学习成绩、学习动机三阶段间的相关分析以及成功学习者与非成功学习者在学习动机的差异性T检验结果都表明对学习成绩影响起决定作用的是持续阶段因素。     

神经网络集成的分布式入侵检测方法

分布式入侵检测系统需具有分布式检测功能及部件增量更新能力.文中提出了一种基于神经网络集成的分布式入侵检测方法,采用单个Agent检测与多个Agent协同检测的两级集成算法实现分布式入侵检测;在发现新的入侵时,Agent上的神经网络集成采用基于资源分配网的增量学习算法进行更新.实验结果表明,该算法能有效检测各种攻击,并且具有对未知攻击的增量学习能力.     

基于BP神经网络的复合材料性能预测

针对复合材料性能表征十分复杂、困难的情况,利用人工神经网络的BP算法,建立了复合材料性能预测模型。模型由3层神经元组成,分别为输入层、隐含层和输出层。以碳/陶瓷复合材料性能与成分的关系为研究对象,选取了38组实验数据作为学习样本,模型总误差为0.18,用建立的网络预测未知,并给出预报曲线。和试验值相比较表明,所建立的网络能反映碳/陶瓷复合材料组分与其材料性能之间的关系,为实验设计提供了新的思路,节省了时间和劳力。     

基于Kriging模型的冰风洞试验冰形参数化方法

为增强冰形使用的可靠性,基于Kriging模型,提出了冰形曲线参数化的方法.以多组冰风洞试验冰形为对象,分析了方法的可操作性及其关键参数对结果的影响规律.同时,结合等效砂粒高度的概念,阐述了参数化冰形实际应用中的有效建议.研究表明:方法是可行的,它在保证了原冰形几何特征的基础上,有效光滑了小尺度的尖角和凹陷,优化了原冰...     

一种深度学习分割遥感影像道路的损失函数

传统的根据光谱特征或形态学算法来分割道路,存在精度低、阈值难确定等缺点,而深度学习中已有的方法并未考虑道路的特性,只是利用通用方法来分割道路.针对上述不足,提出了一种针对道路特有形态的深度学习损失函数——形态损失函数.首先使用连通性算法将预测结果划分为若干个相互分离的连通区域,分别计算这些区域的面积与外接圆面积的比值,...     

基于MADDPG的多无人机协同任务决策

针对多无人机任务决策方法研究中传统优化算法难以在短时间内得到期望结果的问题,基于深度强化学习提出一种无人机多智能体深度确定性策略梯度(MADDPG)算法,通过允许无人机在学习时使用全局信息,在应用决策的时候只使用局部信息的方法,从网络结构、状态空间、动作空间和奖励函数设计了 MADDPG算法的模型结构.最后通过仿真实验...     

Improved specular point prediction precision using gradient descent algorithm

Global Navigation Satellite Systems Reflectometry (GNSS-R) utilizes GNSS signals reflected off the Earth surface for remote sensing applications. Due to weak power of reflected signals, GNSS-R receiver needs to track reflected signals by open loop. The first step is to calculate the position of specular point. The specular point position error of the existing algorithm—Quasi-Spherical Earth (QSE) Approach—is about 3 km which may cause troubles in data post-processing. In this paper, gradient descent algorithm is applied to calculate position of specular point and the calculation is based on World Geodetic System 1984 (WGS 84) ellipsoid in geodetic coordinate. The benefit of this coordinate is that it is easy to investigate the effect of real surface’s altitude. Learning rate—the key parameter of the algorithm—is adaptively adjusted according to initial error, latitude and gradient descent rate. With self-adaptive learning rate strategy, the algorithm converges fast. Through simulation and test on Global Navigation Satellite System Occultation Sounder II (GNOS II), the performances of the algorithm are validated. The specular point position error of the proposed algorithm is about 10 m. The speed of the proposed algorithm is competitive compared with the existing algorithm. The test on GNOS II shows that the proposed algorithm has good real-time performance.     

Fuzzy energy-based dual contours model for automated coronal hole detection in SDO/AIA solar disk images

The presence of coronal holes in solar disk plays an important role in influencing the space weather and generation of the solar wind. As such there lies a requirement in proper study and prediction of coronal holes occurs in the solar disk. This, in turn, arises the necessity of detection of coronal holes present in the solar disk. In this work, a Hough transformed inspired fuzzy-energy simulated dual contours-based segmentation technique has been proposed for the detection and extraction of holes in solar disk. In the proposed method Hough transform has been induced to initialize the contour for the contour-based method of segmentation. In the algorithm, two contours (active and static) have been initiated and made to evolve based on the energy function by incorporating the gray-scale intensity. Here in the work one contour is made to deform its shape while the other contour is kept static for the coronal holes detection purpose. The experiment has been carried out on few benchmark datasets and the corresponding outcomes have been compared with the results of other existing algorithms. The comparison results highlight the performance of the proposed technique in detection of coronal holes in solar disk.