强噪声环境下自适应语音端点检测算法

本文在分析基于短时能量的语音端点检测算法局限的基础上,引入短时信噪比SNR估计方法,并设计自适应的判决门限,提出一种自适应语音端点检测算法.通过对平稳高斯白噪声环境下信噪比从-10dB到20dB的带噪语音信号进行的仿真实验表明,所提方法能更为准确地检测到语音的端点.     

基于径向基函数神经网络的混沌干扰信号检测

为提高强混沌背景下谐波信号的检测能力,提高系统的信噪比,提出了一种在混沌背景噪声中提取正弦信号的RBF神经网络方法。依据混沌吸引子固有的几何特性和混沌系统轨迹点在流形中的演化规律,建立混沌系统的RBF神经网络单步预测模型,改进了网络的学习算法,利用RBF神经网络对输入扰动的敏感,预测出误差信号。分析了在低信噪比下的检测性能。通过对Lorenz流和实际舰船辐射噪声信号中的信号检测进行计算机仿真实验,验证了算法的有效性和可行性,并且实验表明信噪比最低达-40dB时,仍能有效检测出信号。     

一种小波特征与深度神经网络结合的信号制式识别算法

针对当前通信信号的制式识别算法在低信噪比情况下识别不准确的问题,提出一种新的小波特征与改进的深度神经网络结合(WL-DNN)的识别算法。该算法将生成的10种{2ASK、4ASK、2PSK、4PSK、2FSK、4FSK、OFDM、16QAM、AM、FM}含有高斯白噪声的通信信号,用小波分解重构算法提取出一类新的小波特征参数。本文测试了含有多层隐含层的改进BP神经网络作为分类器,利用弹性反向传播算法训练神经网络的参数,确定神经网络的最优超参数。仿真结果表明:在信噪比低至0 dB的情况下,单个调制信号最低识别率超过95%,平均识别率超过98%,大幅提高了制式识别在低信噪比下的识别率,由此表明了该算法的有效性和正确性。     

基于循环自相关的跳频信号盲检测算法

针对通信对抗中的跳频信号盲检测问题,提出了一种跳频信号盲检测算法.深入分析了带噪跳频信号和高斯白噪声在二阶循环平稳性上的差异,并考虑到截短效应对循环自相关函数估计的影响,提出利用观测信号的循环自相关函数估计的模值作为检验统计量,利用在接收端构造的高斯白噪声信号的循环自相关函数估计的模值的最大值作为检测阈值的跳频信号的盲检测算法.实验表明,该算法对于高斯白噪声环境中的跳频信号具有良好的检测性能,适于信噪比高于-3dB,非协作通信情况下的跳频信号检测.     

残差密集块的卷积神经网络图像去噪

针对加性高斯白噪声的图像信噪比低, 图像细节丢失问题, 结合现有卷积神经网络算法, 提出了一种基于残差密集块的卷积神经网络图像去噪模型. 该模型通过引入多级残差网络和密集连接, 并对整体网络使用Leaky ReLU激活函数, 去除不同等级强度噪声的同时, 更好保留图像的有效信息, 有效避免特征丢失. 本文提出算法和深度卷积神经网络残差学习(DnCNN)模型对比, 本文提出的模型在Set12和BSD68测试集上峰值信噪比平均提升了约0.12 dB, 结构相似性平均提升了约0.008 6, 通过观察实验效果, 表明该模型能够充分提取图像特征, 保留图像细节, 同时降低网络计算的复杂度.     

结合BEMD与Hilbert曲线的重复嵌入图像水印算法

为解决数字图像水印算法中水印图像与宿主图像在嵌入时尺寸匹配上的局限问题,并提高图像水印算法在抗大尺度剪切、高斯噪声和椒盐噪声等攻击的鲁棒性,提出一种结合二维经验模态分解算法(BEMD)与Hilbert曲线的重复嵌入图像水印算法.首先,利用Arnold变换对水印图像进行置乱处理,以增加水印图像的安全性;其次,利用Hilbert曲线将置乱后的二维水印图像进行数据降维,得到一维水印信号.数据降维不仅有效地解决了嵌入时水印图像与宿主图像在尺寸匹配上的局限,同时也进一步置乱了水印图像,加强了水印图像的安全性.对宿主图像进行BEMD分解得到不同尺度下的内蕴模态函数和余量信息,并检测第1个内蕴模态函数对应图像的极值点作为水印嵌入位置.最后,依据人类视觉系统的纹理掩蔽特性,将一维水印信号按照从左至右、自上而下的顺序依次、重复嵌入到第1个内蕴模态函数对应图像的极值点中,并结合剩余内蕴模态函数及余量信息重建得到嵌入水印后的图像.水印图像的提取为该嵌入过程的逆过程.通过对多组图像进行水印嵌入,得到嵌入水印后图像的峰值信噪比均在40 dB以上;对嵌入水印后图像进行高斯噪声、椒盐噪声、大尺度剪切等攻击实验,得到提取水印图像与原始水印图像的归一化相关系数均在0.96以上.实验结果表明,嵌入水印图像具有良好的不可见性,并对高斯噪声、椒盐噪声,特别是对大尺度剪切具有较强的鲁棒性.     

噪声ICA模型去偏技术研究

偏差去除算法通常假设高斯噪声条件下对普通ICA算法进行修正来消除噪声带来的影响。但是存在高斯噪声条件时,普通ICA算法对解混矩阵仍然可以辨识。故引入基于QR分解的RLS自适应噪声抵消算法和Fast-ICA算法相结合,只需对观测信号进行去噪处理,不需要对解混矩阵修正。并分别在同一噪声和相关噪声条件下做了仿真实验,与LMS-ICA算法进行了比较。仿真实验证明,该方法比后者效果显著。提出了用最小二乘算法计算分离信号的输出信噪比,作为评价算法的性能指标。     

一种基于支持向量机的数字调制识别方法

信号调制方式的自动识别是控制多模式软件无线电接收机解调单元对信号进行正确解调的基础,因此近年来得到了越来越多的研究者的关注.本文提出了一种基于支持向量机的数字调制识别方法.与传统的神经网络方法相比,该方法具有更好的泛化推广能力.计算机仿真表明,当噪声采用高斯白噪声,并且信噪比大于15 dB时,正确识别率高于97%.     

非高斯噪声环境下基于RLS的稀疏信道估计算法

现有的信道估计算法大多是基于高斯噪声模型假设。然而在实际无线通信环境中,常常出现脉冲噪声使得噪声不再满足高斯模型,而是满足一种广义高斯分布(GGD)噪声模型。采用传统的自适应信道估计算法(如递归最小二乘(RLS)算法)无法抑制这种非高斯噪声的干扰。对此提出一种可抑制非高斯噪声干扰的RLS信道估计算法。该算法通过在标准RLS算法中引入两种稀疏约束函数(L1-范数和L0-范数)来有效地挖掘稀疏结构信息。通过蒙特卡罗仿真,验证了提出的信道估计算法的估计性能比标准RLS算法更好。     

对称α稳定分布噪声下的软解映射算法

对称α稳定(SαS)分布噪声是一种非高斯噪声,相对于高斯噪声具有明显的脉冲特性,因此高斯噪声下的软解映射算法不适用于SαS分布噪声中。为解决该问题,根据高斯噪声下软解映射算法的对数似然比和信号幅度呈线性的特点,提出一种SαS分布噪声下基于欧式距离的软解映射算法,只需在高斯噪声下的软解映射算法和译码算法之间加入预处理算法,限制比特软信息的幅度,并将幅度过高的软信息置零。仿真结果显示,该算法实现简单、运算量低,所需信噪比在α=1.84的SαS分布噪声下比Huber算法低0.3 dB,在α=1.3的SαS分布噪声下低2 dB~5 dB。     

基于小波-EEMD-Adaline网络的容栅传感器信号去噪方法

针对容栅传感器检测的转动轴扭振信号掺杂的环境噪声干扰和自身的电磁噪声干扰使得信噪比低、微弱信号难提取的问题,提出了一种基于小波-EEMD-Adaline自适应线性神经网络去噪方法.该方法对信号进行小波、EEMD、Adaline网络消噪处理,采用三级去噪、噪声过滤、对消来逼近原始信号.用典型加噪超声信号、Doppler信号、Block信号对该方法进行有效性验证,与EEMD、基于小波分解的EEMD去噪效果相比较.实验结果表明,后两种方法信号去噪的SNR提升小(均不到20),而本文方法SNR(RMSE)提升(减小)明显,对于9 dB的Doppler信号SNR提升达90,RMSE从1.038 5降至0.009 5.对容栅电路实测大噪声微弱信号去噪,结果表明,该方法去噪性能更优,去噪后信号光滑性好,波动稳定性强.     

Recurrent neural network approach to quantum signal: coherent state restoration for continuous-variable quantum key distribution

In continuous-variable quantum key distribution (CV-QKD), weak signal carrying information transmits from Alice to Bob; during this process it is easily influenced by unknown noise which reduces signal-to-noise ratio, and strongly impacts reliability and stability of the communication. Recurrent quantum neural network (RQNN) is an artificial neural network model which can perform stochastic filtering without any prior knowledge of the signal and noise. In this paper, a modified RQNN algorithm with expectation maximization algorithm is proposed to process the signal in CV-QKD, which follows the basic rule of quantum mechanics. After RQNN, noise power decreases about 15 dBm, coherent signal recognition rate of RQNN is 96%, quantum bit error rate (QBER) drops to 4%, which is 6.9% lower than original QBER, and channel capacity is notably enlarged.     

Direct estimation of noisy sinusoids using abductive networks

Spectral estimation techniques have been used for many years. In many cases, their complexity warrants investigating machine-learning alternatives where intensive computations are required only during training, with actual estimation simplified and speeded up. This allows using simple portable apparatus for fast and automated estimation in real time. We propose using abductive network machine learning for estimating both the amplitude and frequency of a single sine wave in the presence of additive Gaussian noise. Models synthesized by training on 1000 representative simulated sinusoids were evaluated on 500 new cases. With no phase variations and a signal to noise ratio of 7 dB, average absolute percentage errors for the sinusoid amplitude and period are 8.4% and 3.6%, respectively. Effects of the range of frequency variations and the noise level on the complexity and accuracy of the models were investigated. Amplitude and period estimates show signs of bias at a signal to noise ratio of 3 dB. Error variances track the Cramer-Rao bounds at high noise levels, with no thresholding observed down to 0 dB. The method is compared with a neural network model and with conventional discrete Fourier transform (DFT) based techniques and a Prony's based approach. The new approach is particularly useful when only a small portion of the sinusoid cycle is measured.     

Comparative study of adaptive techniques for denoising CN Tower lightning current derivative signals

The lightning current derivative data recorded at the CN Tower during the past 18 years contain different kinds of noise and needs to be denoised for accurately determining the lightning current waveform parameters. It is usually a challenging task to denoise transient signals having large bandwidth without altering their waveshapes or shrinking their amplitudes. This paper deals with denoising the CN Tower lightning current derivative signals using several adaptive techniques. A new adaptive denoising approach (Divide-and-Conquer) has been successfully used to denoise a vast variety of CN Tower lightning current derivative waveshapes. The supremacy of the new technique over the existing ones is outlined for a signal with a poor signal-to-noise ratio (SNR). While keeping the signal amplitude unchanged and preserving its waveshape, the new denoising technique improved its SNR from ?22.93 dB to 71.41 dB.     

小波阈值神经网络在信号去噪及预测中的应用

提出了一种小波阈值神经网络模型(wavelet threshold neural network,WTNN),对合作式接收到的雷达信号进行去噪和预测.这种网络模型把小波最优阂值去噪器加到神经网络中,对带噪信号具有小波最优阈值去噪和预测的功能.对小波系数作单层重构,可简化训练算法,使编程得到精简.其次,通过对训练算法进行分析,得出了最优阈值及权值的调整公式.最后通过对线性调频信号去噪及前向一步预测的实验结果可以看出,当网络输入分别为带有高斯白噪卢、高斯带限噪声、瑞利噪声的线性调频信号时WTNN得到的结果均优于利用Donoho阈值进行去噪后再预测的结果.     

低信噪比条件下正弦信号幅度盲估计

研究了电子侦察信号处理中正弦信号幅度盲估计问题。提出了一种基于相关累加及线性回归的正弦信号幅度盲估计算法。先对接收到的信号进行频率估计,建立参考信号,将接收信号与参考信号相关后变换到基带并作累加,后将相关累加曲线进行最小二乘线性回归,以回归得到的直线斜率值作为信号幅度的估计值。仿真结果表明,当信噪比大于[-3 dB]时,方法的估计均方根误差小于1.1倍克拉美罗限,可在低信噪比条件下,实现正弦信号幅度的盲估计。     

Detrended fluctuation thresholding for empirical mode decomposition based denoising

Signal decompositions such as wavelet and Gabor transforms have successfully been applied in denoising problems. Empirical mode decomposition (EMD) is a recently proposed method to analyze non-linear and non-stationary time series and may be used for noise elimination. Similar to other decomposition based denoising approaches, EMD based denoising requires a reliable threshold to determine which oscillations called intrinsic mode functions (IMFs) are noise components or noise free signal components. Here, we propose a metric based on detrended fluctuation analysis (DFA) to define a robust threshold. The scaling exponent of DFA is an indicator of statistical self-affinity. In our study, it is used to determine a threshold region to eliminate the noisy IMFs. The proposed DFA threshold and denoising by DFA–EMD are tested on different synthetic and real signals at various signal to noise ratios (SNR). The results are promising especially at 0 dB when signal is corrupted by white Gaussian noise (WGN). The proposed method outperforms soft and hard wavelet threshold method.     

基于小波熵自适应阈值的语音信号去噪新方法

针对语音信号去噪问题, 提出小波熵自适应阈值去噪法。首先利用小波变换分解带噪语音信号, 计算小波分解后信号子带区间的小波熵, 然后将小波熵和自适应阈值相结合确定各层高频系数的阈值门限, 采用折中指数阈值函数对各层高频系数进行去噪处理, 重构降噪后的语音信号, 最后对比小波熵自适应阈值、极大极小阈值、固定阈值和无偏风险阈值去噪方法的性能。实验结果表明, 当输入信噪比为5 dB时, 小波熵自适应阈值去噪法的输出信噪比是最大的, 且其输入输出信噪比曲线高于其他三种阈值去噪法的输入输出信噪比曲线, 从而证实该算法具有更好的去噪性能。