化学铣切槽液中Na2S的分析

本文采用“碘量法”测定化铣液中的硫化钠，分析结果的准确度和精密度完全能够满足生产要求。     

A new parallel lattice reduction algorithm for BKZ reduced bases

In order to implement the original BKZ algorithm in parallel,we describe it in terms of parallelism and give its parallel implementation scheme.Then we analyze the efficiency of algorithm’s parallel implementation and show that the speedup factor of BKZ algorithm in parallel is extremely low.Therefore we present a new parallel lattice reduction algorithm suitable for multiprocessor computer architecture.The new algorithm can obtain a BKZ reduced basis and the parallel speedup is effective.Also with the practical results,although the computational complexity increases compared with the original BKZ algorithm,we still indicate that the new algorithm performs well in parallel and the time cost in parallel is less.At the same time,we show that the length of the shortest vector is smaller.     

FAGNet:基于MAFPN和GVR的遥感图像多尺度目标检测算法

针对大场景遥感图像内容复杂,并且具有目标种类较多、尺度不一、方向多变等特点,导致遥感图像中目标多类多尺度多方向的问题,提出一种基于多尺度注意力特征金字塔网络(MAFPN)以及滑动顶点回归(GVR)机制的遥感图像目标检测方法.首先利用骨干网络提取多层特征作为MAFPN的输入,MAFPN结合特征融合和注意力机制,在融合多个尺度的特征映射的基础上使用通道域注意力和空间域注意力机制来抑制噪声,增强有效特征复用,提高网络对目标多尺度特征的自适应性;将MAFPN输出的融合特征图输入区域建议网络(RPN)生成感兴趣区域,然后将其送入分类/回归网络;在分类/回归网络中使用GVR机制在预测水平框的基础上增加4个顶点偏移比例参数和旋转因子,将水平框转换为旋转框,以减少边框中冗余区域,使预测得到的旋转边框更贴合目标.在DOTA公开数据集上与多种基于卷积神经网络的经典检测算法进行对比的实验结果表明,该方法的平均检测精度得到显著提高,能够更加准确地检测多个尺度以及多个方向的目标,实现了多尺度目标的鲁棒性检测.     

基于Android的IETM平板阅读器设计

针对传统IETM阅读器不方便携带和操作使用的问题,提出了一种IETM平板阅读器设计.该设计从平板电脑硬件和IETM阅读软件两个方面进行了设计,选择并定制了基于ARM架构和安卓操作系统的初级加固型平板电脑,具有一定抗防摔特性;提出基于安卓操作系统的IETM阅读软件轻量化技术架构和业务架构,并对S1000D 4.0数据包、文档、音视频、动画、三维模型等数据的解析、展示关键技术进行设计与实现.该设计为传统IETM阅读器向便携式和小型化IETM平板阅读进化提供了一种解决思路,为丰富IETM阅读器的产品形态奠定了基础.     

基于特征变换的图像检索对抗防御

对抗攻击在图像分类中较早被研究,目的是产生可以误导神经网络预测的不可察觉的扰动.最近,图像检索中的对抗攻击也被广泛探索,研究结果表明最先进的基于深度神经网络的图像检索模型同样容易受到干扰,从而将不相关的图像返回.文中首次尝试研究无需训练的图像检索模型的对抗防御方法,根据图像基本特征因素对输入图像进行变换,以在预测阶段消除对抗攻击的影响.所提方法探索了4种图像特征变换方案,即调整大小、填充、总方差最小化和图像拼接,这些都是在查询图像被送入检索模型之前对其执行的.文中提出的防御方法具有以下优点:1)不需要微调和增量训练过程;2)仅需极少的额外计算;3)多个方案可以灵活集成.大量实验的结果表明,提出的变换策略在防御现有的针对主流图像检索模型的对抗攻击方面是非常有效的.     

Adaptive Backstepping Sliding Mode Control of Tractor-trailer System with Input Delay Based on RBF Neural Network

In this paper, an adaptive sliding mode neural network(NN) control method is investigated for input delay tractor-trailer system with two degrees of freedom. An uncertain camera-object kinematic tracking error model of a tractor car with n trailers with input delay is proposed. Radial basis function neural networks(RBFNNs) are applied to approximate the unknown functions in the error model. A sliding mode surface with variable structure control is designed by using backstepping method. Then, an adaptive NN sliding mode control method is thus obtained by combining Lyapunov-Krasovskii functionals. The controller realizes the global asymptotic trajectories tracking of the kinematics system. The stability of the closed-loop system is strictly proved by the Lyapunov theory. Matlab simulation results demonstrate the feasibility of the proposed method.

     

Research on Action Strategies and Simulations of DRL and MCTS-based Intelligent Round Game

International Journal of Control, Automation and Systems - The reinforcement learning problem of complex action control in multiplayer online battlefield games has brought considerable interest in...     

Research and Practice of Hybrid Teaching for Software Testing based on Interactive Learning

To address the problems of insufficient number of personalized exercises and cases and teachers' lack of grasp of students' weak knowledge points in the current software testing online courses, we study the strategy of establishing and updating intelligent exercise sets and case libraries and analyze the answers and dig out the weak points of knowledge through group intelligence reasoning and interactive machine learning methods. This will help teachers to make uniform and targeted explanations, reduce manual judgment, and achieve intelligent teaching quality reform, and implement the educational concepts of "keeping up with the times" and "teaching according to students' abilities".     

基于对比机制和算法因子的蜂群优化算法

人工蜂群算法是一种简单、高效的智能算法.同时,蜂群算法也存在很多问题,例如:收敛速度不是太快、容易发生局部最优的问题等.一种改进的蜂群算法得以提出,其思想是:引入一种对比机制,和算法因子来改进算法,加强算法全局搜索能力,采用四个基本测试函数对所提出方法进行测试.结果表明,优化后的算法较原算法提高了收敛精度,有效解决了会发生局部最优的问题.     

Fast method for SAR echo simulation of a three-dimensional ground scene

Due to huge calculation of SAR echo simulation of a three-dimensional (3D) ground scene, a fast simulation method is proposed. First, the data of a 3D ground scene are fractionally interpolated based on the Fractional Brownian Motion (FBM) model. Second, the data interpolated are divided into lots of small facets whose precision meets the simulation requirement, the backscattering coefficients of the small facets are calculated. Third, the shaded area is judged by the comparison method of overlook angles. Three parallel levels are analyzed and the kernel function is designed. Finally, the computing method of reduction adding and external thread are also utilized under the framework of GPU in order to get high efficiency. With the methods mentioned above, the imaging result of experimental DEM data verifies the validity and superiority of the proposed method.