基于改进型CGAN的水声信号降噪模型

为降低噪声对水下通信的影响,提出一种基于生成式对抗网络(generative adversarial networks, GAN)和深度卷积神经网络(deep convolutional neural networks, DCNN)的组合降噪处理模型。在数据预处理阶段优化数据分帧策略,最小化接收信号的正交性破坏,通过将含有噪接收信号与不含噪的发射信号的实部、虚部特征分别训练,建立一个同步估计的学习模型进行降噪处理,达到抑制噪声影响的目的。仿真结果表明,在-25 dB～10 dB范围内信噪比变化,所提算法具有更低的通信误码率,湖上实验进一步验证了算法的有效性。     

基于对抗训练方法的水声目标分类研究

为了改善海洋环境改变导致的水声目标分类模型性能下降问题,提高水声目标分类模型的鲁棒性,提出了一种基于对抗训练思想的深度神经网络分类方法。该方法基于博弈论中的对抗思想,通过引入海域环境噪声分类的模块来构造网络的对抗训练框架,实现对网络进行对抗性训练的目的。基于文中实验,采用普通训练框架、对抗训练框架的卷积神经网络,以及支持向量机3种分类模型的性能进行比较,得出采用对抗训练框架的深度学习方法可以缓解海域环境噪声变化带来的模型性能下降,有效提高水声目标分类模型鲁棒性的初步结论。     

水声目标的MFCC特征提取与分类识别

水声目标识别技术在水下信息处理中起着非常重要的作用,从辐射噪声中提取水声目标的有效特征一直都是水声目标识别技术的难点所在。提出了一种利用水声目标辐射噪声的梅尔频率倒谱系数(Mel-Frequency Cepstral Coefficients, MFCC)作为目标特征提取的方法。通过对辐射噪声信号进行梅尔频率滤波得到目标噪声信号的MFCC特征,它模拟了人耳对不同频率的声音具有不同感知能力的听觉非线性效应,因此具有良好的识别效果。通过对实际水声目标的辐射噪声进行测试实验,提取目标噪声信号的MFCC特征向量,并运用K近邻算法对其进行分类识别,实验结果显示MFCC特征提取与分类识别算法对水声目标的识别率达到85%以上。     

生成式对抗网络研究与应用进展

基于零和博弈思想的生成式对抗网络(GAN)可通过无监督学习获得数据的分布,并生成较逼真的数据。基于GAN的基础概念及理论框架,研究各类GAN模型及其在特定领域的应用情况,从数据相似性度量、模型框架、训练方法3个方面进行分析,对GAN改进与扩展的相关研究成果进行总结,并从图像合成、风格迁移等应用领域展开讨论,归纳出GAN的优势与不足,同时对其应用前景进行展望。分析结果表明,GAN的学习能力与可塑性强,改进潜力大,应用范围广,但其发展面临的挑战是训练过程不稳定,且缺乏生成数据质量的客观评价标准。     

面向水声对抗的宽带被动声纳信号仿真平台

水声对抗仿真系统中的声纳仿真台必须具备信号级仿真的能力,才能显示水声对抗的实际效果,针对平台声纳的水声对抗问题研究.为增加真实感和识别有效目标,设计并实现了一个宽带被动声纳信号仿真平台,通过信号产生、常规波束形成、波束功率积分和方位历程显示四个模块解决水声对抗的信号级仿真问题.信号产生模块根据水声对抗器材、水中目标的辐射噪声特征生成声源信号,并通过时延的信号合成,产生被动声纳各路水听器的接收信号;常规波束形成、波束功率积分和方位历程显示模块实现宽带被动声纳的信号处理及输出显示.仿真结果表明,平台实现了水声对抗的信号级仿真,能够支持水声对抗对宽带被动声纳干扰效果的研究,并具有良好的灵活性.     

基于接收端信号的水声网络MAC协议

水声网络的信道具有数据速率低以及传播时延长的特点,如果采用握手机制减少数据冲突,将降低信道利用率和网络的吞吐量。提出了一种基于接收节点发送短信号告知邻居节点其接收状态的水声网络MAC协议,即当接收节点接收数据时,向邻居节点发送短信号通知其当前时刻不要发送数据,解决了隐藏终端和暴露终端的问题,并提高了网络吞吐量;除此之外,使用短信号还能够降低能量损耗。仿真结果表明该协议能够实现上述目的。     

基于生成式对抗网络的结构化数据表生成模型

在机器学习和数据库等领域,高质量数据集的合成一直以来是一个非常重要且充满挑战性的问题.其中,合成的高质量数据集可用来改善模型,尤其是深度学习模型的训练过程.一个健壮的模型训练过程需要大量已标注的数据集,获取这些数据集的一种方法是通过领域专家的手动标注,这种方法不仅代价大还容易出错,因此由模型自动合成高质量数据集的方法更为合理.近年来,由于计算机视觉领域的飞速发展,已经有不少致力于图像数据集合成的研究,但是这些模型不能直接应用在结构化数据表上,并且据调研,对这类数据的相关研究几乎没有.因此,提出了一个针对结构化数据表的生成模型TableGAN,该模型是生成式对抗网络(generative adversarial network, GAN)家族的一种变体,通过对抗训练的方式提高生成模型的性能.针对结构化数据的特征改变了传统GAN模型的内部结构,包括优化函数等,使其能够生成高质量的结构化数据用于改善模型的训练过程.通过在真实数据集上的大量实验表明了此模型的有效性,即在扩大后的数据集上训练模型的效果有明显提升.     

基于深度学习的声信号分类识别方法

提出了一种基于深度学习的声信号分类识别方法,将声场环境中声源目标的识别等效为声场信号—特定声源的端到端学习过程,建立一种以log-mel能量为声信号特征的预提取方法,以深度残差网络作为特征自动提取及分类的声信号分类识别模型.在两个大型数据集上对模型性能进行了验证,实验结果表明,本文提出的深度残差网络模型在DCASE20...     

基于Radon变换的水声图像矩特征提取与分类

成像声纳采集的水声图像分析是自动水下潜器研究中的一个重要课题,该文提出了一种基于图像边缘Radon变换的水声图像矩特征提取和分类方法。使用一种形态学边缘提取算子和细化算法提取二维图像中目标的轮廓,构造目标轮廓在 Radon变换空间的平移、比例和旋转矩不变量,应用于3类水下物体的分类中,实验仿真结果表明该方法在运算速度上优于Hu’s不变矩和图像目标面Radon投影空间不变矩,具有很好的性能和较高的实用价值。     

Classification of cardiac sound signals using constrained tunable-Q wavelet transform

The features extracted from the cardiac sound signals are commonly used for detection and identification of heart valve disorders. In this paper, we present a new method for classification of cardiac sound signals using constrained tunable-Q wavelet transform (TQWT). The proposed method begins with a constrained TQWT based segmentation of cardiac sound signals into heart beat cycles. The features obtained from heart beat cycles of separately reconstructed heart sounds and murmur can better represent the various types of cardiac sound signals than that from containing both. Therefore, heart sounds and murmur have been separated using constrained TQWT. Then the proposed novel raw feature set has been created by the parameters that have been optimized while constraining the output of TQWT together with that of extracted by using time-domain representation and Fourier–Bessel (FB) expansion of separated heart sounds and murmur. However, the adaptively selected features have been used to obtain the final feature set for subsequent classification of cardiac sound signals using least squares support vector machine (LS-SVM) with various kernel functions. The performance of the proposed method has been validated with publicly available datasets and the results have been compared with the existing short-time Fourier transform (STFT) based method. The proposed method shows higher percentage classification accuracy of 94.01 as compared to 93.53 of STFT based method. In comparison with STFT based method, it is noteworthy that the proposed method uses well defined and lower dimensionality of feature vector that can reduce the computational complexity.     

An underwater acoustic direct sequence spread spectrum communication system using dual spread spectrum code

With the goal of achieving high stability and reliability to support underwater point-to-point communications and code division multiple access (CDMA) based underwater networks, a direct sequence spread spectrum based underwater acoustic communication system using dual spread spectrum code is proposed. To solve the contradictions between the information data rate and the accuracy of Doppler estimation, channel estimation, and frame synchronization, a data frame structure based on dual spread spectrum code is designed. A long spread spectrum code is used as the training sequence, which can be used for data frame detection and synchronization, Doppler estimation, and channel estimation. A short spread spectrum code is used to modulate the effective information data. A delay cross-correlation algorithm is used for Doppler estimation, and a correlation algorithm is used for channel estimation. For underwater networking, each user is assigned a different pair of spread spectrum codes. Simulation results show that the system has a good anti-multipath, anti-interference, and anti-Doppler performance, the bit error rate can be smaller than 10^?6 when the signal-to-noise ratio is larger than ?10 dB, the data rate can be as high as 355 bits/s, and the system can be used in the downlink of CDMA based networks.     

基于广义S变换的声发射信号去噪研究*

为了有效消除声发射信号中的噪声,将广义S变换滤波方法应用于声发射信号去噪,分别采用广义S变换中的充零法、基于带通滤波器设计滤波算子法以及时频滤波法进行滤波比较,针对信号的不同时频特性设计了相应的时频滤波算子.结果表明,基于S变换的三种时频滤波法对声发射信号的去噪均有较好的效果,克服了传统滤波方法滤波因子不能随时间、频率变化而变化的缺陷.其中时频滤波法在高信噪比和低信噪比情况下都能更好地去除噪声,可以满足信号处理的要求.     

基于融合能量代价函数的水声信号识别算法

提出了融合能量代价函数的概念及基于代价函数的小波包能量法,并将其应用于水声信号的识别。新算法以融合能量代价函数为标准,在整个小波库中构造最优小波包基,从小波包基上提取信号最有价值的特征值。由于从分类最佳的角度选择特征,所以与固定尺度小波包能量法相比,算法对分类特征模糊的信号有较好的识别效果。     

Classification of mental tasks using stockwell transform

In recent years, various physiological signal based rehabilitation systems have been developed for the physically disabled in which electroencephalographic (EEG) signal is one among them. The efficiency of such a system depends upon the signal processing and classification algorithms. In order to develop an EEG based rehabilitation or assistive system, it is necessary to develop an effective EEG signal processing algorithm. This paper proposes Stockwell transform (ST) based analysis of EEG dynamics during different mental tasks. EEG signals from Keirn and Aunon database were used in this study. Three classifiers were employed such as k-means nearest neighborhood (kNN), linear discriminant analysis (LDA) and support vector machine (SVM) to test the strength of the proposed features. Ten-fold cross validation method was used to demonstrate the consistency of the classification results. Using the proposed method, an average accuracy ranging between 84.72% and 98.95% was achieved for multi-class problems (five mental tasks).     

基于FPGA的水声信号高速采集存储系统设计

介绍了一种基于FPGA的水声信号数据采集与存储系统的设计与实现,给出了系统的总体方案,并对各部分硬件和软件的设计进行了详细描述。系统以FPGA作为数据的控制处理核心,以存储容量达2 GB的大容量NAND型Flash作为存储介质。该系统主要由数据采集模块、数据存储模块和RS-232串行通信模块组成,具有稳定可靠、体积小、功耗低、存储容量大等特点,实验证明该系统满足设计要求。     

Classification of normal and epileptic seizure EEG signals using wavelet transform,phase-space reconstruction,and Euclidean distance

This paper proposes new combined methods to classify normal and epileptic seizure EEG signals using wavelet transform (WT), phase-space reconstruction (PSR), and Euclidean distance (ED) based on a neural network with weighted fuzzy membership functions (NEWFM). WT, PSR, ED, and statistical methods that include frequency distributions and variation, were implemented to extract 24 initial features to use as inputs. Of the 24 initial features, 4 minimum features with the highest accuracy were selected using a non-overlap area distribution measurement method supported by the NEWFM. These 4 minimum features were used as inputs for the NEWFM and this resulted in performance sensitivity, specificity, and accuracy of 96.33%, 100%, and 98.17%, respectively. In addition, the area under Receiver Operating Characteristic (ROC) curve was used to measure the performances of NEWFM both without and with feature selections.     

Automatic segmentation of acoustic musical signals using hiddenMarkov models

In this paper, we address an important step toward our goal of automatic musical accompaniment-the segmentation problem. Given a score to a piece of monophonic music and a sampled recording of a performance of that score, we attempt to segment the data into a sequence of contiguous regions corresponding to the notes and rests in the score. Within the framework of a hidden Markov model, we model our prior knowledge, perform unsupervised learning of the data model parameters, and compute the segmentation that globally minimizes the posterior expected number of segmentation errors. We also show how to produce “online” estimates of score position. We present examples of our experimental results, and readers are encouraged to access actual sound data we have made available from these experiments     

Classification of acoustic events using SVM-based clustering schemes

Acoustic events produced in controlled environments may carry information useful for perceptually aware interfaces. In this paper we focus on the problem of classifying 16 types of meeting-room acoustic events. First of all, we have defined the events and gathered a sound database. Then, several classifiers based on support vector machines (SVM) are developed using confusion matrix based clustering schemes to deal with the multi-class problem. Also, several sets of acoustic features are defined and used in the classification tests. In the experiments, the developed SVM-based classifiers are compared with an already reported binary tree scheme and with their correlative Gaussian mixture model (GMM) classifiers. The best results are obtained with a tree SVM-based classifier that may use a different feature set at each node. With it, a 31.5% relative average error reduction is obtained with respect to the best result from a conventional binary tree scheme.     

Classification of audio signals using AANN and GMM

Today, digital audio applications are part of our everyday lives. Audio classification can provide powerful tools for content management. If an audio clip automatically can be classified it can be stored in an organised database, which can improve the management of audio dramatically. In this paper, we propose effective algorithms to automatically classify audio clips into one of six classes: music, news, sports, advertisement, cartoon and movie. For these categories a number of acoustic features that include linear predictive coefficients, linear predictive cepstral coefficients and mel-frequency cepstral coefficients are extracted to characterize the audio content. The autoassociative neural network model (AANN) is used to capture the distribution of the acoustic feature vectors. The AANN model captures the distribution of the acoustic features of a class, and the backpropagation learning algorithm is used to adjust the weights of the network to minimize the mean square error for each feature vector. The proposed method also compares the performance of AANN with a Gaussian mixture model (GMM) wherein the feature vectors from each class were used to train the GMM models for those classes. During testing, the likelihood of a test sample belonging to each model is computed and the sample is assigned to the class whose model produces the highest likelihood.