一种新的基于混沌的语音、噪声判别方法

语音通信中,区别发音段和非发音段具有一定的意义。其关键在于提取发音段和非发音段的不同特征参数。本文基于混沌信号处理,提出了一种新的语音、噪声判别方法。该方法提取信号在不同相空间重构维下的虚邻点,从而根据信号高维虚邻点平台的不同,判别发音段和非发音段（背景噪声）以及发音段所含噪声的强弱,本文阐述了该方法的原理,讨论了其性能,仿真实验表明,本方法具有较好的结果。     

基于主元分析与支持向量机的方法及其在过程监控诊断中的应用

基于支持向量机（SVM）在处理小样本、高维数及泛化性能强等方面的优势，提出了基于主元分析和支持向量机（PCA—SVM）对过程进行监控的方法。文中先利用主元分析方法进行特征数据提取，得到降维的主元特征向量，去除了高维样本变量相关性。然后分析各状态T^2统计、SPE统计量的变化趋势，对实际生产状况进行监控，最后利用SVM与最近邻法相结合的策略对特征向量进行分类识别。试验结果证实了提出算法的有效性。     

5G超密集网络下的室内压缩重构指纹定位算法

为减少室内定位复杂度并进一步提高定位精度,提出了一种5G超密集网络下的室内压缩重构指纹定位算法.该算法分为离线建库阶段和在线匹配阶段两个阶段.离线建库阶段采用了矩阵填充理论进行指纹库的构建,只需采取少量的指纹点构建具有低秩特性的局部指纹库,并通过非精确增广拉格朗日乘子法(Inexact Augmented Lagrangian Multiplier Method,IALM)算法进行矩阵填充,从而恢复完整的指纹库.在线匹配阶段采用卡方距离代替传统的欧式距离来计算待定位点与参考指纹点的相似度,并用加权K近邻算法估算出待定位点坐标.经过实验仿真分析,所提算法以1.13％的误差节约了40％的工作量,在信噪比为10 dB时定位误差最小为0.2008 m,与传统K近邻指纹匹配算法相比具有更好的定位精度.     

基于统计学习优化SIFT的面部遮挡人脸识别

针对传统的人脸识别算法受面部遮挡的影响导致很难兼顾鲁棒性和保持原始图像核心信息的问题,本文提出了一种基于统计学习优化尺度不变特征变换的面部遮挡人脸识别算法。首先,利用SIFT将所有给定训练图像用一组局部特征描述符表示出来;然后,通过执行统计学习获得正常脸部图像SIFT特征的概率分布函数,利用获得的概率分布函数在新观察到的测试图像中检测异常SIFT特征;最后,计算测试图像与训练图像之间的相似度,并利用K近邻分类器完成人脸识别。在AR人脸数据库上的实验验证了本文算法的有效性及可靠性,实验结果表明,相比其它几种较为先进的人脸识别算法,本文算法取得了更强的识别鲁棒性。     

Supervised learning and frequency domain averaging-based adaptive channel estimation scheme for filterbank multicarrier with offset quadrature amplitude modulation

Filterbank multicarrier with offset quadrature amplitude modulation (FBMC-OQAM) is an attractive alternative to the orthogonal frequency division multiplexing (OFDM) modulation technique. In comparison with OFDM, the FBMC-OQAM signal has better spectral confinement and higher spectral efficiency and tolerance to synchronization errors, primarily due to per-subcarrier filtering using a frequency-time localized prototype filter. However, the filtering process introduces intrinsic interference among the symbols and complicates channel estimation (CE). An efficient way to improve the CE in FBMC-OQAM is using a technique known as windowed frequency domain averaging (FDA); however, it requires a priori knowledge of the window length parameter which is set based on the channel's frequency selectivity (FS). As the channel's FS is not fixed and not a priori known, we propose a k-nearest neighbor-based machine learning algorithm to classify the FS and decide on the FDA's window length. A comparative theoretical analysis of the mean-squared error (MSE) is performed to prove the proposed CE scheme's effectiveness, validated through extensive simulations. The adaptive CE scheme is shown to yield a reduction in CE-MSE and improved bit error rates compared with the popular preamble-based CE schemes for FBMC-OQAM, without a priori knowledge of channel's frequency selectivity.     

基于压缩近邻的查重元数据去冗算法设计

随着重复数据删除次数的增加,系统中用于存储指纹索引的清单文件等元数据信息会不断累积,导致不可忽视的存储资源开销。因此,如何在不影响重复数据删除率的基础上,对重复数据删除过程中产生的元数据信息进行压缩,从而减小查重索引,是进一步提高重复数据删除效率和存储资源利用率的重要因素。针对查重元数据中存在大量冗余数据,提出了一种基于压缩近邻的查重元数据去冗算法Dedup2。该算法先利用聚类算法将查重元数据分为若干类,然后利用压缩近邻算法消除查重元数据中相似度较高的数据以获得查重子集,并在该查重子集上利用文件相似性对数据对象进行重复数据删除操作。实验结果表明,Dedup2可以在保持近似的重复数据删除比的基础上,将查重索引大小压缩50%以上。     

Research on LBS privacy preservation based on pseudorandom permutation in road network

A method of privacy preservation based on pseudorandom permutation was put forward for the issues of location privacy and query content privacy.Firstly,the distribution information of points of interest (PoI) based on the vertexes in the road network was organized,each single road vertex was taken as the foundational processing object.Based on the pseudorandom permutation,a permutation scheme of the point-of-interest records at the LBS server's end was put forward,a 32-bit random seed was adopted to generate a permuted table in the scheme,and the point-of-interest records were encrypted and permuted according to the table.These processed records were stored in the LBS database.Then a trusted intermediate server,replacing of the user,issued a query request with a record number instead of the query content to the LBS server.The LBS server could not determine which kind of PoI the user was interested in or which road section the user was locating on,and therefore the scheme achieved private information retrieval.Finally,the efficiency in the metrics of query accuracy,communication overhead and processing time was also analyzed.By the performance analysis and extensive experiments,the proposed scheme is proved to be location untraceable and query content uncorrelation.     

Low-latency neighbor discovery algorithm based on multi-beacon message in mobile low-duty-cycle sensor network

Neighbor discovery enables nodes in the networks to discover each other through simple information interaction,which was suitable for the new mobile low duty cycle sensor network (MLDC-WSN).However,because the nodes in MLDC-WSN can move randomly and sleep,the network topology was changed frequently,which results in that some nodes need a lot of energy and time to find their neighbors.How to realize fast neighbor discovery for all nodes in the network was a difficult problem in current research.To solve this problem,a new low-latency neighbor discovery algorithm based on multi-beacon messages was proposed.In this algorithm,the nodes were discovered by sending a short beacon message through their neighbor nodes,and by adjusting the time and frequency of beacon message sent,a lower neighbor discovery delay was obtained.Eventually,through quantitative analysis and simulation experiments,it is found that compared with existing algorithms,this algorithm can find all neighbor nodes in MLDC-WSN with less energy consumption,lower latency and greater probability.     

基于最近相关性分类器的单样本掌纹识别

为了解决单样本掌纹识别的困难,研究了基于最近相关性分类器(NCC)的单样本掌纹识别方法。首先对掌纹图像进行分块,划分为若干个子图像;然后运用统计特征、傅里叶变换、离散余弦变换(DCT)和Gabor变换4种方法对子图像进行特征提取,将所有子图像的特征向量组合在一起形成该图像的特征向量;最后应用NCC进行分类识别。运用PolyU掌纹图像库,对本文算法进行测试。实验结果表明:与最近邻分类器(NNC)和支持向量机(SVM)相比,在不同大小的子图像上,运用不同的特征提取算法,NCC均提高了识别率;分类时间在0.3～0.7s之间,满足实时系统的需求。     

无线通信系统异构网络的自动邻区关联方法

主要提出一种宏小区与毫微微小区混合组网的异构无线通信网络,从而设计了一种用于异构无线通信网络中的基站间自动邻区关联的方法,并阐述了具体实施步骤。该方法支持异构网络中的基站自组织功能,基站能够在自动邻区关联的过程中正确地获得邻区基站的ID,从而成功构造邻区关系且无需人工配置,克服了已有方法存在的缺陷。同时,该方法无需修改空口信令,也不会增加空口信令开销。