BP网络模型对人脸朝向的识别

研究BP神经网络模型,通过计算机模拟人脑建立神经元网络,使用一部分人脸朝向信息作为训练的实例集,训练稳健后,可以推广应用判断其他人脸的朝向信息,以实现计算机自动识别人脸朝向。先对图片进行归一化等预处理,再应用主成分分析提取特征信息,每幅提取出的特征信息都是8个数据的列向量,构建一个8个输入、17个隐含、3个输出的三层BP网络模型。将训练实例集的特征向量代入训练,调整参数后保证其性能和收敛速度。最后通过大量实验验证,计算机识别的误判率仅为6.7%,模型可靠。     

一种基于相关函数法铁磁谐振波形研究

对铁磁谐振波形进行了系统的分类分级,提出了一种基于Matlab的相关函数方法,并且利用大量数据进行对比,已经得到了效果验证,经过桂林市电力电容器责任有限公司认证,具有良好的实际效果。     

结构正则化多视图非负矩阵分解

现存非负矩阵分解（non-negative matrix factorization,NMF）研究多考虑单一视图分解数据,忽略了数据信息的全面性。此外,NMF限制其获取数据的内在几何结构。针对以上问题,提出一个结构正则化多视图非负矩阵分解算法（structure regularized multi-view nonnegative matrix factorization,SRMNMF）。首先,通过主成分分析来对数据进行全局结构的判别式学习;其次,利用流形学习来捕获数据的局部结构;然后,通过利用多视图数据的多样性和差异性来学习表征。模型提升了算法聚类的整体性能,更加有效地挖掘数据的结构信息。此外,采用高效的交替迭代算法优化目标函数得到最优的因子矩阵。在六个数据集上与现存的代表性方法比较,所提出的SRMNMF的准确率、NMI和Purity分别最大提高4.4%、6.1%和4.05%。     

基于功能磁共振成像的人脑效应连接网络识别方法综述

人脑效应连接网络刻画了脑区间神经活动的因果效应. 对不同人群的脑效应连接网络进行研究不仅能为神经精神疾病病理机制的理解提供新视角, 而且能为疾病的早期诊断和治疗评价提供新的脑网络影像学标记, 具有十分重要的理论意义和应用价值. 利用计算方法从功能磁共振成像(Functional magnetic resonance imaging, fMRI)数据中识别脑效应连接网络是目前人脑连接组学中一项重要的研究课题. 本文首先概括了从fMRI数据中进行脑效应连接网络识别的主要流程, 说明了其中的主要步骤和方法; 然后, 给出了一种脑效应连接网络识别方法的分类体系, 并对其中一些代表性的识别算法进行了阐述; 最后, 通过对该领域挑战性问题的分析, 预测了脑效应连接网络识别未来的研究方向, 以期对相关研究提供一定的参考.     

Weighted principal component extraction with genetic algorithms

Pattern recognition techniques have been widely used in a variety of scientific disciplines including computer vision, artificial intelligence, biology, and so forth. Although many methods present satisfactory performances, they still have several weak points, thus leaving a lot of space for further improvements. In this paper, we propose two performance-driven subspace learning methods by extending the principal component analysis (PCA) and the kernel PCA (KPCA). Both methods adopt a common structure where genetic algorithms are employed to pursue optimal subspaces. Because the proposed feature extractors aim at achieving high classification accuracy, enhanced generalization ability can be expected. Extensive experiments are designed to evaluate the effectiveness of the proposed algorithms in real-world problems including object recognition and a number of machine learning tasks. Comparative studies with other state-of-the-art techniques show that the methods in this paper are capable of enhancing generalization ability for pattern recognition systems.     

基于神经网络的聚类方法研究

针对常用聚类方法不能有效处理噪声数据的问题,本文结合神经网络具有自适应性的特点,提出基于神经网络的聚类(NN_Cluster)模型,并设计了基于自适应共振理论的神经网络聚类模型(ARTNN_Cluster)和基于自组织特征映射的神经网络聚类模型(SOMNN_Cluster)。标准数据集上的实验结果表明,与传统的K_means聚类方法相比,本文提出的基于神经网络的聚类模型有效地克服了传统方法的噪声问题,得到了较好的聚类效果。     

小波变换和特征加权融合的人脸识别

在人脸识别领域,提取人脸特征和降低维数是人脸识别的关键。传统的基于小波变换的人脸识别算法仅在小波分解的低频分量上提取用于分类的图像特征,造成了高频分量中部分对识别有利信息的丢失。为了更有效地提取人脸图像特征,提出一种基于小波变换和特征加权融合的人脸识别算法。首先通过小波变换对人脸图像进行降维处理,然后对4个小波子图分别运用主成分分析法(PCA)提取特征,并把这4部分特征加权融合,最后利用支持向量机(SVM)进行分类识别。在ORL人脸库上进行实验验证,识别准确率可达到97.5%,实验结果表明该算法能够有效提高人脸识别能力,与传统识别算法相比具有较高的识别准确率和识别速度。     

地铁车辆永磁同步电机振动噪声测试及特性分析

为获得某地铁车辆永磁同步电机的噪声特性,开展了永磁同步电机的电磁力波理论分析和振动噪声测试,从A计权声压级、1/3倍频程和色谱图等指标分析不同测试工况与转速下的噪声特性。研究结果表明：永磁同步电机噪声主要由电磁振动产生,加速过程的主要频谱成分是48阶、56阶和104阶等阶次成分以及以开关频率及其倍频为中心的调制成分,减速过程无开关频率作用,其余阶次成分一致;电机在316 Hz、440 Hz和910 Hz等频率处存在局部模态,在电机阶次激励作用下易引发共振。振动噪声测试及特性分析可为永磁同步电机的应用提供指导。     

Sex-Related Differences in Regional Blood–Brain Barrier Integrity in Non-Demented Elderly Subjects

The role of the blood–brain barrier (BBB) breakdown has been recognized as being important in Alzheimer’s disease pathogenesis. We aimed to evaluate whether regional BBB integrity differed according to sex and whether differences in BBB integrity changed as a consequence of aging or cognitive decline, using dynamic contrast-enhanced (DCE)-magnetic resonance imaging (MRI). In total, 75 participants with normal cognition (NC) or mild cognitive impairment (MCI) underwent cognitive assessments and MRI examination including DCE-MRI. Regional K_trans was calculated in cortical regions and the Patlak permeability model was used to calculate BBB permeability (K_trans, min⁻¹). Females had a lower median K_trans in the cingulate and occipital cortices. In the “older old” group, sex differences in K_trans were only observed in the occipital cortex. In the MCI group, sex differences in K_trans were only observed in the occipital cortex. Age was the only predictor of cognitive assessment scores in the male MCI group; however, educational years and K_trans in the occipital cortex could predict cognitive scores in the female MCI group. Our study revealed that females may have better BBB integrity in cingulate and occipital cortices. We also found that sex-related differences in BBB integrity are attenuated with aging or cognitive decline.