高职计算机文化分专业分层次教学的实践与思考

指出了高职计算机文化课程教学面临的诸多问题,这些问题的存在严重制约了课程教学效果的提高.为此,在深入企业调研和对教学对象调查的基础上,结合各专业类别特点及其对计算机基本操作技能的不同需求,选取不同专业的班级作为研究对象,采用“横向分专业,纵向分层次”的教学方法进行了实践教学.实践结果表明,分专业分层次教学方法能有效解决高职“计算机文化”课程教学中存在的主要问题.     

采用虚拟监测点的供水管网水力模型优化校核

供水管网水力模型参数优化校核过程中,由于监测点个数少于待校核参数的数量,校核后的模型参数存在"异参同效"的问题,也可能导致部分优化后的参数取值脱离其物理意义.而在建成区的管网中增设大量监测点难度较大,为解决管网水力模型应用中的这个实际问题,提出根据实际监测点数据预测非监测节点的压力,并将被预测的节点作为虚拟监测点的方法,以增加模型校核问题中的边界条件.应用案例分析结果表明,提出的基于灵敏度分析法改进的GRNN-PSO混合方法在保证校核精度的同时还提高了校核效率,为供水管网水力模型优化校核的应用提供了新思路.     

A method of credit evaluation modeling based on block-wise missing data

Missing data is a common problem in credit evaluation practice and can obstruct the development and application of an evaluation model. Block-wise missing data is a particularly troublesome issue. Based on multi-task feature selection approach, this paper proposes a method called MMPFS to build a model for credit evaluation that primarily includes two steps: (1) dividing the dataset into several nonoverlapping subsets based on missing patterns, and (2) integrating the multi-task feature selection approach using logistic regression to perform joint feature learning on all subsets. The proposed method has the following advantages: (1) missing data do not need to be managed in advance, (2) available data can be fully used for model learning, (3) information loss or bias caused by general missing data processing methods can be avoided, and (4) overfitting risk caused by redundant features can be reduced. The implementation framework and algorithm principle of the proposed method are described, and three credit datasets from UCI are investigated to compare the proposed method with other commonly used missing data treatments. The results show that MMPFS can produce a better credit evaluation model than data preprocessing methods, such as sample deletion and data imputation.

     

基于D-FNN的混沌铁磁谐振系统非线性补偿控制方法

针对电网混沌铁磁谐振系统产生的混沌现象,提出基于动态模糊神经网络的混沌铁磁谐振系统非线性补偿控制方法。该方法采用动态模糊神经网络来逼近系统的非线性部分,消除了过电压的混沌现象,将系统稳定到目标位置,实现了对系统的非线性补偿控制。Matlab仿真结果表明,基于动态模糊神经网络的非线性补偿控制方法控制结果正确,响应快速。     

逆向工程点云数据采集系统设计及应用

针对目前四轴激光测量机的不足,设计了一种五轴逆向工程点云数据采集系统;在四轴的基础上增加了激光测头的旋转轴,采用基于PCI总线的运动控制系统及USB总线的数据采集系统,并植入了图像采集系统,通过二次开发技术利用Windows的应用程序编程接口函数对扫描范围进行自动识别;软件系统使用了采集路径规划及测量数据优化处理算法;在原始数据测量及曲面反求建模两个方面进行了实例应用,零件大斜度面和垂直于工作台的表面均能覆盖测量,并且所有点云数据是一次测量完成,实验结果验证了本系统的可行性与稳定性。     

基于五层十五级遥感数据结构的并行算法研究

针对当前环境与监测预报小卫星宽覆盖和海量数据显示与处理不足的现状,设计五层十五级遥感数据组织结构,并依据此结构设计一种新的并行计算算法,得到并行计算的最大近优估算值,优化环境与监测预报小卫星海量数据的遥感产品生产能力,提高环境监测预报效率。     

图像处理中模糊算法问题的分析

图像处理是计算机常用技术之一,模糊算法的运用有助于提高图像处理的效果。传统图像处理存在诸多弊端,影响了用户获取信息的便捷性。本文分析了图像处理的基本操作内容,并阐述了模糊算法在图像处理流程中的运用,以进一步提升原始图像处理的效果。     

Magnetic properties and microstructural characteristics of bulk Nd–Al–Fe–Co glassy alloys

Bulk Nd–Al–Fe–Co glassy alloys with diameter up to 5 mm were investigated by magnetic measurements, magnetic force microscopy (MFM) and high resolution electron microscopy (HREM) at room temperature. The results from the measurement of vibrating sample magnetometer show that these samples with compositions Nd₆₅Al₁₀Fe_25-xCo_x (x=0–10 at.%) and Nd₆₀Al₁₀Fe₂₀Co₁₀ display hard magnetic properties with H_C of 300 kAm⁻¹, M_S of 10 Am² kg⁻¹, and M_r of 7 Am² kg⁻¹. The MFM measurements of the Nd₆₀Al₁₀Fe₂₀Co₁₀ bulk metallic glass (BMG) reveal the existence of magnetic domains with a period of about 0.36 μm, and the ordered clusters with the averaged size of about 5 nm was observed by the HREM on the sample. The domain structure or cluster is believed to be associated with the appearance of hard-magnetic properties in this alloy system. The existence of the large-size domains demonstrates that magnetic moment of a great deal of ordered atomic clusters in the BMG has been aligned by exchange-coupling.     

Adsorption characteristics of hexadecyl ammonium with different numbers of carbon chains in montmorillonite and the structure of the prepared composites

Journal of Porous Materials - The dynamics and thermodynamics of adsorption of hexadecyl ammonium with different numbers of carbon chains in montmorillonite (Mt) with different layer charge density...     

Multi-Scale Dilated Convolutional Neural Network for Hyperspectral Image Classification

基于多尺度空洞卷积神经网络的高光谱图像分类

郑姗姗¹,刘文¹,单锐¹,赵静一²,江国乾³,张智⁴

（1. 燕山大学理学院,河北 秦皇岛 066004;2. 燕山大学机械工程学院,河北 秦皇岛 066004;3. 燕山大学电气工程学院,河北 秦皇岛 066004;4. 北京航天研究所,北京 100094）

创新点说明：

1）将图像分割方法——空洞卷积用于卷积神经网络进行高光谱图像分类,提取更加广泛、抽象的图像特征。

2）构建基于多尺度空洞卷积神经网络的高光谱图像分类方法。搭建多尺度聚合结构,在每个通道中使用快捷连接和空洞卷积结构,有效提取图像特征,避免信息丢失。

研究目的：

针对图像信息丢失问题,得到高精度的高光谱图像分类方法。

研究方法：

在Indian Pines和Pavia University数据集上,与4个已有的高光谱图像分类方法进行对比实验,比较OA, AA和Kappa值。

研究结果：

多尺度空洞卷积神经网络在Indian Pines和Pavia University数据集上OA值分别达到了99.58%,99.92%。AA值分别达到了99.57%,99.90%。Kappa分别达到了99.52%,99.89%。

结论：

1）在卷积神经网络中引入空洞卷积,可以有效避免图像信息丢失。

2）多尺度空洞卷积神经网络能提取更佳的判别性特征,实现高分类性能。

关键词：多尺度聚合;空洞卷积;高光谱图像分类;快捷连接