基于组合方法的人脸识别算法研究

该文试探一种加权融合流形学习的方法进行人脸识别,该算法通过Haar小波和局部线性嵌入（LLE）加权融合的方式来进行人脸识别。首先通过Haar小波变换对人脸图像进行一级分解,得到四个子图;然后利用LLE算法对四个子图降维处理,并加权融合;最后利用支持向量机（SVM）进行分类判决。通过在ORL库中进行实验,结果表明,该文提出的Haar＋LLE识别效率比单独使用主成分分析（PCA）和LLE更高效。     

Trail-following responses of the Argentine ant,Iridomyrmex humilis (Mayr), to a synthetic trail pheromone component and analogs

Behavioral evidence indicates that (Z)-9-hexadecenal (Z9-16ALD) is a trail pheromone component ofIridomyrmex humilis, and that the true trail pheromone may be multicomponent. Trail-following responses ofI. humilis workers to several concentrations of syntheticZ9-16ALD, a constituent of the Pavan's gland, were found to be comparable to responses to gaster extract trails containing ca. 100 times lessZ9-16ALD. Of the five aldehyde analogs tested, only (Z)-7-hexadecenal (Z7-16ALD) elicited significant trail-following. However, following responses to severalZ9-16ALD-Z7-16ALD combinations were lower than responses toZ9-16ALD alone. Trails on filter paper of biologically relevant concentrations ofZ9-16ALD lose activity within 2 hr in the laboratory. The release rate ofZ9-16ALD measured from filter paper trails was 0.25 ± 0.10 pg/cm-sec. This was used to estimate the trail-following threshold for this compound of Argentine ant workers.     

基于小波变换的模糊航迹关联算法

航迹关联是实现分布式多传感器信息融合的关键技术.针对传统的模糊关联算法正确关联率低的问题,基于小波变换对传统的模糊关联算法进行了改进,提出一种新的航迹关联算法.首先,通过小波分析对目标航迹数据序列进行处理,获取新的航迹特征;然后,采用模糊均值聚类法确立隶属度函数、综合相似度和阈值判决准则,完成对已获取的新航迹特征的分类关联.仿真实验表明：与模糊算法相比,该算法的正确关联率提高约0.30.     

一种基于小波系数边信息的鲁棒水印算法

为了实施图像的版权保护,提出了一种基于小波系数幅值关系的盲水印算法。原始图像通过三级小波分解得到小波系数,算法在密钥的控制下,伪随机地选择中频子带中两块共8个系数组成一组。通过小幅度量化来加强每组数据中两块系数幅值的大小关系特征,利用这组系数的特征作为边信息和水印信息生成密钥、嵌入水印。保存密钥,并在密钥的控制下提取水印。实验结果表明,该算法不仅能有效抵抗JPEG压缩、低通滤波、高斯噪声和几何攻击,而且水印图像的PSNR可以保持在50 dB以上。     

基于信道识别的WPM解调性能改善研究

小波包调制的主要优势是其调制结构以及解调策略上的灵活性。该文利用小波包调制多速率传输特性,通过信道识别,采用联合估计的方法,探讨了小波包调制系统在不同信道中的性能改善问题。仿真结果表明该方法明显提高了小波包调制系统在不同信道中的传输性能以及抗干扰能力。     

基于小波分解和最大互信息的图像配准方法研究

研究了基于最大互信息图像配准的理论和实现算法,提出了将小波分解与之相结合的算法,证明了该算法优于基于最大互信息的图像配准。通过实验数据比较可以得出,提出的基于小波分解和最大互信息的图像配准的算法可以有效地提高配准的速度和具有较好的配准效果。     

油气管道堵塞检测及定位技术研究

针对油气输送管道中的堵塞现象,提出利用管道堵塞前后两端压差的剧烈变化,以及利用管道两端压力的模拟值与实际测量值的差异来检测管道的堵塞,提出通过检测管道水力坡降曲线奇异点的方法确定油气管道的堵塞位置的原理和方法,通过采集管道两端运行参数,并建立管道运行的数学模型,对管道实施仿真,获得整条管线的水力坡降曲线,再应用小波变换对管道的水力坡降曲线进行奇异性检测,而管道水力坡降曲线的奇异点将对应管道的堵塞位置.该方法具有所需设备少,操作费用低,操作简单等优点,优于现有管道堵塞位置确定方法.     

基于Morlet小波变换和改进遗传算法的动态识别

如何合理地识别大型复杂结构的动力参数一直是工程领域关心的问题.为此,以Morlet小波变换和采用单亲遗传算子的改进遗传算法为基础,构造一结构动态参数识别模型.并且以C++为平台,通过计算机内部命令调用ANSYS等软件,实现识别模型的程序化.通过模拟算例计算,计算结果与理论值一致.同时,结合一水电站厂房现场振动试验,对该大型结构进行动态参数识别,识别结果与工程经验值基本吻合.     

基于小波域的灰度图像盲水印算法

提出了一种有效的静止图像的自适应盲水印算法。该算法首先对水印图像进行置乱处理,再利用邻居特征平均值法和奇偶判决法将置乱后的水印图像嵌入到DWT变换后的原始图像中,最后对该算法进行了滤波、多种噪声、压缩和灰度转换等抗攻击测试。试验结果表明该算法具有较好的不可见性和抗攻击能力。     

An evaluation of deep thin coal seams and water-beating/resisting layers in the quaternary system using seismic inversion

Non-liner wave equation inversion, wavelet analysis and artificial neural networks were used to obtain stratum parame-ters and the distribution of thin coal seams. The lithology of the water-bearing/resisting layer in the Quaternary system was also predicted. The implementation process included calculating the well log parameters, stratum contrasting the seismic data and the well logs, and extracting, studying and predicting seismic attributes. Seismic inversion parameters, including the layer velocity and wave impedance, were calculated and effectively used for prediction and analysis. Prior knowledge and seismic interpretation were used to remedy a dearth of seismic data during the inversion procedure. This enhanced the stability of the inversion method. Non-linear seismic inversion and artificial neural networks were used to interpret coal seismic lithology and to study the wa-ter-bearing/resisting layer in the Quaternary system. Interpretation of the 1-2 m thin coal seams, and also of the wa-ter-bearing/resisting layer in the Quaternary system, is provided. The upper mining limit can be lifted from 60 m to 45 m. The pre-dictions show that this method can provide reliable data useful for thin coal seam exploitation and for lifting the upper mining limit, which is one of the principles of green mining.