基于变电站多模图像的自动集成配准方法

针对采集的变电站多模图像,提出了一种改进的多模态图像的自动集成配准方法。变电站多模图像的尺寸不同,所以先对其进行小波变换,以变换后得到的两幅概貌图像为待配准图像,以六种配准方法中的每一种作为一个适应度函数。使用遗传算法进行搜索,分别寻找两幅概貌图像的最佳配准位置,再映射回小波变换前的多模图像,最后使用动态可信度进行集成。实验结果证明,该方法能实现不同尺寸的多模态图像的自动配准,速度较快,鲁棒性强,比单一的配准方法准确性高,并且可以不断地修正可信度,具有较强的适应性。     

基于多属性特征胎记的软件盗版检测

针对传统单属性特征在抗攻击性和检测率方面的不足,提出了基于分类多属性特征的软件盗版检测算法。通过对等价语义变换后的软件集合进行静态分析、提取过滤、分割和度量,最后按相似度构造分类器,在低开销下综合判别未知软件版本信息。给出了算法的描述,刻画了算法的实现过程,实验结果表明,该算法在提高判别的鲁棒性、可信度和抗攻击方面具有适用性,与同类方法比较也具有明显优势。     

基于缩放因子的人脸直方图特征距离度量方法

奇异特征区域在人脸直方图匹配过程具有更高的可分辨性。基于此,在人脸直方图特征匹配算法的基础上提出一种基于缩放因子的人脸直方图特征距离度量方法。该方法通过缩小直方图距离较近区域的距离、放大直方图距离较远区域的距离,并在匹配中突出高可分辨性区域,以获得更高的识别精度。实验表明该方法可以显著提高各种局部特征提取方法和直方图距离度量算法在人脸识别中的精度。     

基于高阶累积量的暂态扰动Mahalanobis距离分类

为实现对脉冲暂态和振荡暂态2类暂态电能质量扰动的分类,提出一种基于高阶累积量的暂态电能质量扰动Mahalanobis距离分类法.该方法利用高阶累积量提取暂态扰动的高阶统计特征,选取其2,3,4阶累积量最大值和最小值构成扰动信号的6维特征向量,计算测试样本特征向量与标准模板之间的Mahalanobis距离,以“距离最小”作为分类判据,实现对2类暂态电能质量扰动的分类.仿真结果表明,低阶累积量不能单独用于区分不同类型暂态电能质量扰动;特征向量维数越高,对分类过程越有利.所提方法分类原理简单、准确率高,是暂态电能质量扰动的有效分类方法.     

左右手运动想象脑电模式识别研究

如何提高左右手运动想象脑电信号的分类率是脑机接口研究领域的一个热点话题。基于美国EGI64导脑电采集系统得到3名健康被试的脑电数据,首先,采用独立成分分析（Independent Component Analysis,ICA）对采集的数据进行去噪处理;然后,利用离散小波变换方法对分解C3/C4处的EEG平均功率信号,选用尺度6上逼近系数A6的重构信号作为脑电特征信号;最后,用Fisher线性判别分析法（Fisher Linear Discriminant Analysis,FLDA）、支持向量机方法 （Support Vector Machines,SVM）和极限学习机分类方法 （Extreme Learning Machine,ELM）分别对特征信号进行分类。分类结果表明：极限学习机分类方法得出的平均分类率要高于Fisher方法与SVM方法的平均分类率,可以达到92%,而且运行速度也高于另两种分类算法。     

3D Model Retrieval Method Based on Affinity Propagation Clustering

In order to improve the accuracy and efficiency of 3D model retrieval, the method based on affinity propagation clustering algorithm is proposed. Firstly, projection ray-based method is proposed to improve the feature extraction efficiency of 3D models. Based on the relationship between model and its projection, the intersection in 3D space is transformed into intersection in 2D space, which reduces the number of intersection and improves the efficiency of the extraction algorithm. In feature extraction, multi-layer spheres method is analyzed. The two-layer spheres method makes the feature vector more accurate and improves retrieval precision. Secondly, Semi-supervised Affinity Propagation (S-AP) clustering is utilized because it can be applied to different cluster structures. The S-AP algorithm is adopted to find the center models and then the center model collection is built. During retrieval process, the collection is utilized to classify the query model into corresponding model base and then the most similar model is retrieved in the model base. Finally, 75 sample models from Princeton library are selected to do the experiment and then 36 models are used for retrieval test. The results validate that the proposed method outperforms the original method and the retrieval precision and recall ratios are improved effectively.     

Low temperature J-resistance curve determination of asphalt concrete using wavelet-Radon transform

A single specimen test using the three point single edge notched beam configuration at low temperatures for obtaining hot mix asphalt （HMA） resistance curves is developed.Resistance curves are obtained for mixtures at six temperature levels of＋5,0,-5,-10,-15,and-20 ℃ and three binder contents of 4％,4.5％,and 5％.Crack extension increments during the test are measured by means of an image processing technique using Radon transform and feature extraction.All the specimens exhibit a rising R-curve,indicating ductility and toughening mechanisms in the ductile-quasi brittle fracture of the mixture.It is observed that the reduction of temperature results in a further tendency of the mixture for unstable crack growth and less subcritical crack length.It is also shown that using the binarization process,an automatic index can be developed that can represent the extent of brittleness and extent of the low temperature in which the cracking has occurred.     

西藏多龙矿集区遥感异常提取与成矿预测

以西藏多龙斑岩型铜矿区为例,根据已知矿床,分别利用比值法和主成分分析法对ETM＋和ASTER数据提取铁染与羟基异常信息,分析研究已知矿体遥感异常特征;通过波谱特征拟合的方法,对研究区进行波谱分类。利用两方面的成果来对多龙矿集区作成矿预测,划定远景成矿区,其中一级预测区6个,二级预测区12个。多种异常对比组合,能够发现更好的指示成矿线索的信息。     

状态参数识别在齿轮箱故障诊断中的应用

针对计算机辅助某齿轮箱厂检测线上工人对齿轮箱故障状态类型的诊断,以齿轮箱中齿轮、轴、轴承等主要零件为研究对象,对采集到的齿轮箱振动信号进行细致分析,在敏感特征参数提取上采用聚类分析的方法,有效地消除了冗余参数的干扰,为下一步支持向量机(SVM)模式识提高了参数训练的精确度,建立与检测线工人所定义故障类型相一致的故障状态模式识别模型,从而进一步提高了计算机辅助工人对齿轮箱智能故障诊断的准确性和诊断结论一致性.