Underwater Acoustic Signal Noise Reduction Based on a Fully Convolutional Encoder-Decoder Neural Network

Noise reduction analysis of signals is essential for modern underwater acoustic detection systems.The traditional noise reduction techniques gradually lose efficacy because the target signal is masked by biological and natural noise in the marine environ-ment.The feature extraction method combining time-frequency spectrograms and deep learning can effectively achieve the separation of noise and target signals.A fully convolutional encoder-decoder neural network(FCEDN)is proposed to address the issue of noise reduc-tion in underwater acoustic signals.The time-domain waveform map of underwater acoustic signals is converted into a wavelet low-frequency analysis recording spectrogram during the denoising process to preserve as many underwater acoustic signal characteristics as possible.The FCEDN is built to learn the spectrogram mapping between noise and target signals that can be learned at each time level.The transposed convolution transforms are introduced,which can transform the spectrogram features of the signals into listenable audio files.After evaluating the systems on the ShipsEar Dataset,the proposed method can increase SNR and SI-SNR by 10.02 and 9.5dB,re-spectively.

Automated Classification of Lung Diseases in Computed Tomography Images Using a Wavelet Based Convolutional Neural Network

Recently, convolutional neural networks (CNNs) have been utilized in medical imaging research field and have successfully shown their ability in image classification and detection. In this paper we used a CNN combined with a wavelet transform approach for classifying a dataset of 448 lung CT images into 4 categories, e.g. lung adenocarcinoma, lung squamous cell carcinoma, metastatic lung cancer, and normal. The key difference between the commonly-used CNNs and the presented method is that in this method, we adopt the use of redundant wavelet coefficients at level 1 as inputs to the CNN, instead of using original images. One of the main advantages of the proposed method is that it is not necessary to extract regions of interest from original images. The wavelet coefficients of the entire image are used as inputs to the CNN. We compare the classification performance of the proposed method to that of an existing CNN classifier and a CNN-based support vector machine classifier. The experimental results show that the proposed method outperforms the other two methods and achieve the highest overall accuracy of 91.9%. It demonstrates the potential for use in classification of lung diseases in CT images.

A Novel Lung Cancer Detection Method Using Wavelet Decomposition and Convolutional Neural Network

Computerized tomography (CT) scan is the only screening test recommended by doctors to look for lung cancer. Convolutional neural networks (CNNs) have recently proven their ability to successfully classify medical images. Due to its strong compactness property, the Discrete Wavelet transform (DWT) has been commonly used in image feature extraction applications. This paper presents a novel technique for the classification of Lung cancer in Computerized Tomography (CT) scans using Wavelets to find discriminative features in the CT images and CNN to classify the extracted features. Experimental results prove that the proposed approach outperforms other commonly used methods and gives an overall accuracy of 99.5%.

Deep Spatiotemporal Convolutional-Neural-Network-Based Remaining Useful Life Estimation of Bearings

The remaining useful life(RUL)estimation of bearings is critical for ensuring the reliability of mechanical systems.Owing to the rapid development of deep learning methods,a multitude of data-driven RUL estimation approaches have been proposed recently.However,the following problems remain in existing methods:1)Most network models use raw data or statistical features as input,which renders it difficult to extract complex fault-related information hidden in signals;2)for current observations,the dependence between current states is emphasized,but their complex dependence on previous states is often disregarded;3)the output of neural networks is directly used as the estimated RUL in most studies,resulting in extremely volatile prediction results that lack robustness.Hence,a novel prognostics approach is proposed based on a time-frequency representation(TFR)subsequence,three-dimensional convolutional neural network(3DCNN),and Gaussian process regression(GPR).The approach primarily comprises two aspects:construction of a health indicator(HI)using the TFR-subsequence-3DCNN model,and RUL estimation based on the GPR model.The raw signals of the bearings are converted into TFR-subsequences by continuous wavelet transform and a dislocated overlapping strategy.Subsequently,the 3DCNN is applied to extract the hidden spatiotemporal features from the TFR-subsequences and construct HIs.Finally,the RUL of the bearings is estimated using the GPR model,which can also define the probability distribution of the potential function and prediction confidence.Experiments on the PRONOSTIA platform demonstrate the superiority of the proposed TFR-subsequence-3DCNN-GPR approach.The use of degradation-related spatiotemporal features in signals is proposed herein to achieve a highly accurate bearing RUL prediction with uncertainty quantification.

Wavelet Multiview-Based Hybrid Deep Learning Model for Forecasting El Niño-Southern Oscillation Cycles

The El Niño-Southern Oscillation (ENSO) is a significant climate phenomenon with far-reaching impacts on global weather patterns, ecosystems, and economies. This study aims to enhance ENSO forecasting with the Extended Reconstruction Sea Surface Temperature v5 (ERSSTv5) climate model. The M-band discrete wavelet transforms (DWT) are utilized to capture multi-scale temporal and spatial features effectively. Long-short term memory (LSTM) autoencoders are also used to capture significant spatial and temporal patterns in sea surface temperature (SST) anomaly data. Deep learning techniques such as the convolutional neural networks (CNN) are used with non-image and image time series data. We also employ parallel computing in a various support vector regression (SVR) approximators to enhance accuracy. Preliminary results indicate that this hybrid model effectively identifies key precursors and patterns associated with El Niño events, surpassing traditional forecasting methods. Results of the hybrid model produce a correlation of 0.93 in 4-month lagged forecasting of the Oceanic Niño Index (ONI)—indicative of high success rate of the model. Future work will focus on evaluating the model’s performance using additional reanalysis datasets and other methods of deep learning to further refine its robustness and applicability. We propose wavelet-based deep learning models which have potential to shine a light on achieving United Nations’ 2030 Agenda for Sustainable Development’s goal 13: “Climate Action”, as an innovation with potential in improving time series image forecasting in all fields.

Channel attention based wavelet cascaded network for image super-resolution

Convolutional neural networks(CNNs) have shown great potential for image super-resolution(SR).However,most existing CNNs only reconstruct images in the spatial domain,resulting in insufficient high-frequency details of reconstructed images.To address this issue,a channel attention based wavelet cascaded network for image super-resolution(CWSR) is proposed.Specifically,a second-order channel attention(SOCA) mechanism is incorporated into the network,and the covariance matrix normalization is utilized to explore interdependencies between channel-wise features.Then,to boost the quality of residual features,the non-local module is adopted to further improve the global information integration ability of the network.Finally,taking the image loss in the spatial and wavelet domains into account,a dual-constrained loss function is proposed to optimize the network.Experimental results illustrate that CWSR outperforms several state-of-the-art methods in terms of both visual quality and quantitative metrics.

Crack Segmentation Based on Fusing Multi-Scale Wavelet and Spatial-Channel Attention

Accurate and reliable crack segmentation is a challenge and meaningful task.In this article,aiming at the characteristics of cracks on the concrete images,the intensity frequency information of source images which is obtained by Discrete Wavelet Transform(DWT)is fed into deep learning-based networks to enhance the ability of network on crack segmentation.To well integrate frequency information into network an effective and novel DWTA module based on the DWT and scSE attention mechanism is proposed.The semantic information of cracks is enhanced and the irrelevant information is suppressed by DWTA module.And the gap between frequency information and convolution information from network is balanced by DWTA module which can well fuse wavelet information into image segmentation network.The Unet-DWTA is proposed to preserved the information of crack boundary and thin crack in intermediate feature maps by adding DWTA module in the encoderdecoder structures.In decoder,diverse level feature maps are fused to capture the information of crack boundary and the abstract semantic information which is beneficial to crack pixel classification.The proposed method is verified on three classic datasets including CrackDataset,CrackForest,and DeepCrack datasets.Compared with the other crack methods,the proposed Unet-DWTA shows better performance based on the evaluation of the subjective analysis and objective metrics about image semantic segmentation.

Efficient Authentication System Using Wavelet Embeddings of Otoacoustic Emission Signals

Biometrics,which has become integrated with our daily lives,could fall prey to falsification attacks,leading to security concerns.In our paper,we use Transient Evoked Otoacoustic Emissions(TEOAE)that are generated by the human cochlea in response to an external sound stimulus,as a biometric modality.TEOAE are robust to falsification attacks,as the uniqueness of an individual’s inner ear cannot be impersonated.In this study,we use both the raw 1D TEOAE signals,as well as the 2D time-frequency representation of the signal using Continuous Wavelet Transform(CWT).We use 1D and 2D Convolutional Neural Networks(CNN)for the former and latter,respectively,to derive the feature maps.The corresponding lower-dimensional feature maps are obtained using principal component analysis,which is then used as features to build classifiers using machine learning techniques for the task of person identification.T-SNE plots of these feature maps show that they discriminate well among the subjects.Among the various architectures explored,we achieve a best-performing accuracy of 98.95%and 100%using the feature maps of the 1D-CNN and 2D-CNN,respectively,with the latter performance being an improvement over all the earlier works.This performance makes the TEOAE based person identification systems deployable in real-world situations,along with the added advantage of robustness to falsification attacks.

基于Wavelet-CNN的电磁炮过靶信号识别方法

电磁炮测试中,炮口产生强烈的火光信号以及振动等噪声,会严重干扰电枢特征信号的识别处理;为了提升对电枢信号的自动识别率,提出了一种基于小波变换和卷积神经网络(CNN)相结合的电枢信号识别方法;利用小波变换对过靶信号进行小波阈值去噪,进而重构信号,然后利用CNN提取信号的深层次特征,通过CNN的全连接层输出信号的分类结果;当输入信号为电枢信号时,对其作最大值检测获取电枢信号的特征点;实验结果表明,所提方法对比传统小波阈值滤波法在特征点自动拾取准确率上提升了5.88%;该算法对电磁炮电枢过靶信号的滤波、识别具有一定的参考意义。

A Wavelet-Based Deep Learning Framework for Predicting Peak Intensity of Hurricanes in the Atlantic Ocean

Every year, hurricanes pose a serious threat to coastal communities, and forecasting their maximum intensities has been a crucial task for scientists. Computational methods have been used to forecast the intensities of hurricanes across varying time horizons. However, as climate change has increased the volatility of the intensities of recent hurricanes, newer and adaptable methods must be devised. In this study, a framework is proposed to estimate the maximum intensity of tropical cyclones (TCs) in the Atlantic Ocean using a multi-input convolutional neural network (CNN). From the Atlantic hurricane seasons of 2000 through 2021, over 100 TCs that reached hurricane-level wind speeds are used. Novel algorithms are used to collect and preprocess both satellite image data and non-image data for these TCs. Namely, Discrete Wavelet Transforms (DWTs) are used to decompose individual bands of satellite image data, eliminating noise and extracting hidden frequency details before training. Validation tests indicate that this framework can estimate the maximum wind speed of TCs with a root mean square error of 15 knots. This framework provides preliminary predictions that can supplement current computational methods that would otherwise not be able to account for climate change. Future work can be done by forecasting with time constraints, and to provide estimations for more metrics such as pressure and precipitation.

基于改进卷积神经网络和射频指纹的无人机检测与识别

针对无人机(UAV)在图像识别时易受环境干扰,而传统信号识别难以准确提取特征且实时性较差的问题,提出一种基于改进卷积神经网络(CNN)和射频(RF)指纹的无人机检测识别方法。首先,使用通用软件无线电外设(USRP)捕获环境中的无线电信号,经过多分辨率分析获取偏差值,检测是否为无人机射频信号;其次,将检测到的无人机射频信号经过小波变换和主成分分析(PCA)处理,获得射频信号频谱,作为神经网络的输入;最后,构建轻量级残差神经网络(LRCNN),输入射频频谱进行网络训练,进行无人机的分类识别。实验结果表明,所提方法可以有效检测并识别无人机信号,平均识别精度可达84%;在信噪比(SNR)大于20 dB时,LRCNN的识别精度达到了88%,相较于支持向量机(SVM)、原始OracleCNN分别提高31和7个百分点,在识别精度和鲁棒性方面比这两种方法均有所提升。

基于连续小波卷积神经网络的轴承智能故障诊断方法

传统故障诊断方法存在特征提取有限和故障检测不准确的问题,为此提出新的轴承智能故障诊断方法.构建连续小波卷积层取代卷积神经网络(CNN)中的初始卷积层,用于提取轴承数据的初级特征;使用增强ACON激活函数处理提取的振动信号;设计新的计算空间,提高CNN的整体自适应性.在凯斯西储大学轴承数据集上开展滚动轴承故障诊断方法对比实验.结果表明,与传统基于CNN、快速傅里叶变换-CNN、长短时记忆CNN故障诊断方法相比,所提方法的故障诊断精度分别提高了7.45、4.46和1.53个百分点,CNN的收敛速度更快.在不同工况的泛化任务中,所提方法的平均准确率为99.64%,准确性和泛化能力良好.

小波包和1D CNN结合的刀具磨损状态识别

为监测机床切削加工过程中刀具的非线性磨损变化,提出了一种基于小波包分解和一维卷积神经网络(1D CNN)的刀具磨损状态识别方法。采集机床主轴振动数据作为监测信号,采用经信噪比定量分析后的小波包进行预处理,然后选取小波包分解后各频带的能量特征作为1D CNN的输入,实现了对刀具磨损状态的有效识别。实验表明,该模型能够实现刀具磨损状态的准确预测,相比于BP网络、能量频谱图-Alexnet和Lstm网络模型,刀具磨损状态识别率最优,平均准确率达到98.262%。

基于空频特征融合的双流晶圆缺陷分类网络

晶圆缺陷模式分类在晶圆制造过程中扮演着至关重要的角色,准确识别晶圆缺陷能够确定缺陷产生的根本原因,进而定位生产流程中的问题。然而,现有深度学习晶圆缺陷分类方法仅从空间域或者频率域出发进行网络设计,未能实现空频信息的相互补充与融合,限制了晶圆缺陷分类准确性的进一步提高。针对这一问题,提出了一种基于空间域和频率域特征融合的双流晶圆缺陷分类网络—SFWD-Net。该网络利用提出的多尺度特征提取卷积模块和多视角注意力模块构成空间流分支提取晶圆图的空间信息,利用离散小波变换构成频率流分支提取晶圆图的频率信息,空频信息融合后再进行缺陷分类。在大规模半导体晶圆图数据集WM-811K的实验证明,SFWD-Net由于同时从空间域和频率域出发进行网络设计,其分类准确度达到99.2992%,优于其他5种先进方法,能够显著提高晶圆缺陷分类的精度。

基于可分离卷积与小波变换融合的道路裂缝检测

针对目前对细小裂缝检测能力不强、分割精度低等问题,提出了一种改进的U-Net模型来检测路面裂缝,提高检测能力和分割精度。中文设计了新的模块MSDWBlock(Multi-Scale Depthwise Separable Convolutional Block),应用在编码器和解码器部分,通过深度可分离卷积增强模型的能力,扩大模型感受野,在跳跃连接部分引入了C2G注意力机制模块,提升模型对裂缝特征的感知能力;并引入了ASPP(Atrous Spatial Pyramid Pooling)和DWT(Discrete Wavelet Transformation)。ASPP通过在多个尺度上进行操作,有助于捕捉到裂缝的特征,而DWT能够减少卷积池化过程中的裂缝空间信息损失,保留裂缝边缘信息。这种结构设计使得网络更专注于裂缝的特征,从而提升了裂缝检测的准确性。通过实验证明所提模型显示出优于U-Net,Segnet,U2net等先进模型的精确性。在CFD数据集上mIoU,F1分别达到78.51%,0.868。这些成果表明,所提方法能有效提升道路裂缝检测的性能。

基于多频特征学习的恶意代码变种分类

针对恶意代码变种分类方法没有充分对原始输入进行分析的问题,提出一种更加高效的基于深度学习的办法,使用卷积神经网络对多频信息进行学习。对恶意代码转化而成的图像进行研究,利用小波变换进行多频和多层次的分析,抓住低频和高频特征;针对多频信息输入,设计一种多频特征学习模块,充分挖掘其中有用信息。实验结果表明,该方法在Malimg数据集上,相比其它两种恶意代码分类办法,分别取得了1.5%和0.8%的效果提升。

基于声振融合的二次EWT-CNN刀具磨损监测

为了实现加工过程中对刀具磨损状态的监测,提出一种基于协同过滤融合的方法。首先,对工作刀具振动信号和声音信号进行特征相关性分析后进行数据层融合;然后,将得到的声振融合信号进行二次经验小波变换(EWT)后去噪重构;最后,将重构信号进行信号增强并送入CNN实现特征提取及刀具故障识别。通过对不同故障类型的麻花钻头进行故障识别实验,在声音、振动以及声振融合信号和不同信号去噪重构方法的对比下,该方法对不同故障类型的钻头作出了98.96%的高识别率。验证了所提方法在刀具故障识别方面的优越性。

联合多连接特征编解码与小波池化的轻量级语义分割

语义分割是当前场景理解领域的基础技术之一。现存的语义分割网络通常结构复杂、参数量大、图像特征信息损失过多和计算效率低。针对以上问题,基于编-解码器框架和离散小波变换,设计了一个联合多连接特征编解码与小波池化的轻量级语义分割网络MLWP-Net(Multi-Link Wavelet-Pooled Network),在编码阶段利用多连接策略并结合深度可分离卷积、空洞卷积和通道压缩设计了轻量级特征提取瓶颈结构,并设计了低频混合小波池化操作替代传统的下采样操作,有效降低编码过程造成的信息丢失;在解码阶段,设计了多分支并行空洞卷积解码器以融合多级特征并行实现图像分辨率的恢复。实验结果表明,MLWP-Net仅以0.74 MB的参数量在数据集Cityscapes和CamVid上分别达到74.1%和68.2%mIoU的分割精度,验证了该算法的有效性。

基于GADF-CWT-GCNN的滚动轴承故障诊断方法研究

针对滚动轴承故障诊断在小样本环境下引起的模型泛化能力差、诊断精度低的问题,提出一种基于格拉姆角分场(GADF)和连续小波变化(continuous wavelet transform,CWT)与并行二维组归一化卷积神经网络(parallel convolutional neural network,P2D-GCNN)的滚动轴承故障诊断方法。对采集的数据进行预处理,采用格拉姆角场和连续小波变换将一维振动信号转换成二维图像作为模型输入,再选用数据增强技术扩充样本子图,满足网络输入要求,并将其导入搭建的组归一化卷积神经网络中进行诊断检测。结果表明:文中数据处理方法与搭建模型在小样本环境下泛化能力远高于SVM和1D-CNN等其他网络模型。为进一步验证模型在小样本数据下的识别能力,取数据集的70%,40%和20%样本量进行多次实验,所对应的训练准确率及测试准确率分为99.38%,99.02%,99.47%,98.29%,99.05%,97.08%。结果证明,文中模型在小样本环境下对轴承故障诊断具有很高的准确率。

基于模式识别的舰船机械电子设备故障自动监测

舰船机械电子设备故障数据量较为庞大,且模式复杂多样,为满足其复杂性的要求,提出基于模式识别的舰船机械电子设备故障自动监测方法,采集舰船机械电子设备运行中的温度、压力、振动等数据作为故障监测的原始数据,计算数据间的相似系数和欧氏距离,结合K均值算法实现数据聚类处理。通过小波包算法对聚类后的数据进行特征提取,将其输入到卷积神经网络中,通过对监测模型进行训练,最终实现对舰船机械电子设备故障自动监测。通过实验分析,该方法与相关人员进行监测的故障情况高度一致,在不同故障类型监测的时间均能够保持在5 ms以内,具有较高的监测效率和监测精准度。