基于DFT的频率敏感双分支Transformer多变量长时间序列预测方法

在进行多变量长时间序列预测时,仅利用时域分析通常无法充分捕捉长时间序列依赖,而这会导致信息利用率不足、预测精度不够高。因此,结合频域时域分析,提出一种基于离散傅里叶变换(DFT)的频率敏感双分支多变量长时间序列预测(FSDformer)方法。首先,通过DFT实现时间和频率的相互转换,从而将复杂的时间序列数据分解为结构简单的低频趋势项、中频季节项和高频余项3个分量;其次,采用双分支结构,针对中高频分量预测,应用Encoder-Decoder结构,设计了周期性增强注意力机制;针对低频趋势分量预测,采用多层感知机(MLP)结构;最后将中高频分量与低频分量预测结果相加,得到多变量长时间序列的最终预测结果。在2个数据集上把FSDformer与其他5个经典算法进行了对比分析,在Electricity数据集上,当历史序列长度为96,预测序列长度为336时,相较于Autoformer等对比算法,FSDformer的平均绝对误差(MAE)下降了11.5%~29.1%,均方误差(MSE)下降了20.9%~43.7%,达到了最优预测精度。实验结果表明,FSDformer能有效捕捉长时间序列的相关依赖,在提升预测精度和计算效率的同时,增强了模型预测的稳定性。

A Deepfake Detection Algorithm Based on Fourier Transform of Biological Signal

Deepfake-generated fake faces,commonly utilized in identity-related activities such as political propaganda,celebrity impersonations,evidence forgery,and familiar fraud,pose new societal threats.Although current deepfake generators strive for high realism in visual effects,they do not replicate biometric signals indicative of cardiac activity.Addressing this gap,many researchers have developed detection methods focusing on biometric characteristics.These methods utilize classification networks to analyze both temporal and spectral domain features of the remote photoplethysmography(rPPG)signal,resulting in high detection accuracy.However,in the spectral analysis,existing approaches often only consider the power spectral density and neglect the amplitude spectrum—both crucial for assessing cardiac activity.We introduce a novel method that extracts rPPG signals from multiple regions of interest through remote photoplethysmography and processes them using Fast Fourier Transform(FFT).The resultant time-frequency domain signal samples are organized into matrices to create Matrix Visualization Heatmaps(MVHM),which are then utilized to train an image classification network.Additionally,we explored various combinations of time-frequency domain representations of rPPG signals and the impact of attention mechanisms.Our experimental results show that our algorithm achieves a remarkable detection accuracy of 99.22%in identifying fake videos,significantly outperforming mainstream algorithms and demonstrating the effectiveness of Fourier Transform and attention mechanisms in detecting fake faces.

A Physical Security Technology Based upon Doubly Multiple Parameters Weighted Fractional Fourier Transform

Enhancing the security of the wireless communication is necessary to guarantee the reliable of the data transmission, due to the broadcast nature of wireless channels. In this paper, we provide a novel technology referred to as doubly multiple parameters weighted fractional Fourier transform(DMWFRFT), which can strengthen the physical layer security of wireless communication. This paper introduces the concept of DM-WFRFT based on multiple parameters WFRFT(MP-WFRFT), and then presents its four properties. Based on these properties, the parameters decryption probability is analyzed in terms of the number of parameters. The number of parameters for DM-WFRFT is more than that of the MP-WFRFT,which indicates that the proposed scheme can further strengthen the the physical layer security. Lastly, some numerical simulations are carried out to illustrate that the efficiency of proposed DM-WFRFT is related to preventing eavesdropping, and the effect of parameters variety on the system performance is associated with the bit error ratio(BER).

An improved non-uniform fast Fourier transform method for radio imaging of coronal mass ejections

Radioheliographs can obtain solar images at high temporal and spatial resolution,with a high dynamic range.These are among the most important instruments for studying solar radio bursts,understanding solar eruption events,and conducting space weather forecasting.This study aims to explore the effective use of radioheliographs for solar observations,specifically for imaging coronal mass ejections(CME),to track their evolution and provide space weather warnings.We have developed an imaging simulation program based on the principle of aperture synthesis imaging,covering the entire data processing flow from antenna configuration to dirty map generation.For grid processing,we propose an improved non-uniform fast Fourier transform(NUFFT)method to provide superior image quality.Using simulated imaging of radio coronal mass ejections,we provide practical recommendations for the performance of radioheliographs.This study provides important support for the validation and calibration of radioheliograph data processing,and is expected to profoundly enhance our understanding of solar activities.

Design and implementation of code acquisition using sparse Fourier transform

Code acquisition is the kernel operation for signal synchronization in the spread-spectrum receiver.To reduce the computational complexity and latency of code acquisition,this paper proposes an efficient scheme employing sparse Fourier transform(SFT)and the relevant hardware architecture for field programmable gate array(FPGA)and application-specific integrated circuit(ASIC)implementation.Efforts are made at both the algorithmic level and the implementation level to enable merged searching of code phase and Doppler frequency without incurring massive hardware expenditure.Compared with the existing code acquisition approaches,it is shown from theoretical analysis and experimental results that the proposed design can shorten processing latency and reduce hardware complexity without degrading the acquisition probability.

Performance of Continuous Wavelet Transform over Fourier Transform in Features Resolutions

This study presents a comparative analysis of two image enhancement techniques, Continuous Wavelet Transform (CWT) and Fast Fourier Transform (FFT), in the context of improving the clarity of high-quality 3D seismic data obtained from the Tano Basin in West Africa, Ghana. The research focuses on a comparative analysis of image clarity in seismic attribute analysis to facilitate the identification of reservoir features within the subsurface structures. The findings of the study indicate that CWT has a significant advantage over FFT in terms of image quality and identifying subsurface structures. The results demonstrate the superior performance of CWT in providing a better representation, making it more effective for seismic attribute analysis. The study highlights the importance of choosing the appropriate image enhancement technique based on the specific application needs and the broader context of the study. While CWT provides high-quality images and superior performance in identifying subsurface structures, the selection between these methods should be made judiciously, taking into account the objectives of the study and the characteristics of the signals being analyzed. The research provides valuable insights into the decision-making process for selecting image enhancement techniques in seismic data analysis, helping researchers and practitioners make informed choices that cater to the unique requirements of their studies. Ultimately, this study contributes to the advancement of the field of subsurface imaging and geological feature identification.

Enhanced Fourier Transform Using Wavelet Packet Decomposition

Many domains, including communication, signal processing, and image processing, use the Fourier Transform as a mathematical tool for signal analysis. Although it can analyze signals with steady and transitory properties, it has limits. The Wavelet Packet Decomposition (WPD) is a novel technique that we suggest in this study as a way to improve the Fourier Transform and get beyond these drawbacks. In this experiment, we specifically considered the utilization of Daubechies level 4 for the wavelet transformation. The choice of Daubechies level 4 was motivated by several reasons. Daubechies wavelets are known for their compact support, orthogonality, and good time-frequency localization. By choosing Daubechies level 4, we aimed to strike a balance between preserving important transient information and avoiding excessive noise or oversmoothing in the transformed signal. Then we compared the outcomes of our suggested approach to the conventional Fourier Transform using a non-stationary signal. The findings demonstrated that the suggested method offered a more accurate representation of non-stationary and transient signals in the frequency domain. Our method precisely showed a 12% reduction in MSE and a 3% rise in PSNR for the standard Fourier transform, as well as a 35% decrease in MSE and an 8% increase in PSNR for voice signals when compared to the traditional wavelet packet decomposition method.

基于时频图与视觉Transformer的滚动轴承智能故障诊断方法

基于循环神经网络的故障诊断方法在计算过程中难以保存间隔时间过长的信息且无法并行计算,在大型数据建模方面存在不足,为提高轴承故障诊断工作的效率及准确性,提出了一种基于短时傅里叶变换时频图与视觉Transformer(ViT)的轴承故障诊断方法:通过短时傅里叶变换将原始振动信号转换为二维时频图像,再将时频图作为特征图输入ViT网络中进行训练,详细分析网络参数对故障诊断性能和计算复杂度的影响,构建最优模型结构,最终实现轴承的故障诊断。采用凯斯西储大学和江南大学轴承数据对模型进行验证,结果表明该模型可以有效结合短时傅里叶变换在处理时变信号方面的优势和ViT网络强大的图像分类能力,具有更高的诊断精度和更好的泛化性、通用性。

The Similarity Transformation of Regularizing Functionals and Simularity Property of Their Fourier Transformations

Let and denote respectively the functionswhere λ≥1, The author discusses the similarity transformation of the regularizing functionals of these functions and the similar property of their Fourier transformation.

基于WFRFT的噪声式隐蔽传输方案研究

隐蔽无线通信旨在实现通信双方信息的隐藏传输,以保证信息的安全性。提出一种基于加权分数傅里叶变换的混沌扩频噪声式信号隐蔽通信方法,该方法利用改进后的Logistic映射产生的两个不同的混沌序列对隐蔽信号进行符号扩频,再对其进行加权分数傅里叶变换生成噪声式隐蔽信号。发送方将隐蔽信号与公开信号叠加到一起一同传输,同步等问题交由公开信号解决,而经过处理的隐蔽信号具有低能量和类高斯特性,能够很好地与背景噪声混淆在一起,具有较强的隐蔽性和抗截获能力。仿真结果表明,所提出的方法具有较好的隐蔽性能,仿真误码率与理论推导一致,并且功率比取值在0.007~0.01之间时,可以使隐蔽信号和公开信号都能达到较好的误码率。

基于FrFT和RVM的变压器局部放电模式识别

快速准确识别局部放电类型对于保证变压器安全稳定运行具有重要意义。针对局部放电信号模式识别中面临的最优特征参数提取和分类器设计难题,提出一种基于分数阶傅里叶变换(fractional Fourier transform,FrFT)和相关向量机(relevance vector machine,RVM)的局部放电模式识别方法。首先将FrFT引入局部放电信号分析领域,利用FrFT将局部放电信号转换至分数域并对其进行多尺度分析,在扩充信息提取维度的同时,提取可反映不同局部放电信号波形差异的14维特征构成特征向量;然后将特征向量作为输入,建立RVM模型进行最优特征选择和分类判决函数的联合优化,从而实现对不同局部放电信号的分类识别。建立电晕放电、沿面放电和气隙放电试验模型并采集局部放电超声信号开展试验,结果表明所提方法对于每种局部放电信号均能获得较高的识别精度,平均正确识别率相对于常规支持向量机(support vector machine,SVM)分类方法提升超过2.7%。

基于STFT图像和迁移学习的次同步振荡源定位方法

直驱风机与电网交互引发次同步振荡,严重威胁电网的安全稳定运行。为快速定位诱发机组,提出了一种基于短时傅里叶变换(STFT)图像和迁移学习的次同步振荡源定位方法。首先,采用压缩感知技术将出口数据转化为观测信号,再对观测信号进行STFT得到具备振荡特征的映射图,构建映射图与振荡源机组之间的联系;然后,采用对抗式迁移学习架构,结合电力系统,实现对目标域无标签振荡数据的快速泛化;最后,与传统迁移学习方法进行比较,结果表明所提方法在定位准确率和效率方面表现更优,且具备较强的抗噪能力。

基于面积加权GWT-GFT的水声目标识别

由于海洋环境的复杂性,水声目标的识别具有很大的挑战性。为解决这类复杂环境下特征提取的问题,提出了一种基于面积加权的图小波变换-图傅里叶变换(GWT-GFT)的分析方法。在完成数据预处理后,为了能够凸显顶点之间的关系,提出了一种新的基于顶点三角形面积的加权方法来构建图信号;构建好的图信号通过GWT分解为多尺度图分量;然后,利用GFT将这些分量从图域变换到特征值谱域进行分析;在此基础上,提取各分量特征值谱的特征;最后,利用基于高斯核函数的支持向量机(SVM)对获取的特征向量进行分类。基于水声信号ShipsEar数据库,采用5折交叉验证方法进行验证。与现有的其它方法相比,所提的模型以36个特征在376656个样本上取得了97.22%的准确率,证明了该分析方法的有效性和鲁棒性。

基于FrFT-FH架构LPD通信波形设计与性能分析

针对Chirp基调制信号在分数阶傅里叶变换域特征明显,信号周期易被检测等问题,提出一种能够实现多域隐蔽的低检测概率(low probability of detection,LPD)波形构造方法。该方法采用分数阶傅里叶变换跳频(fractional Fourier transform-frequency hopping,FrFT-FH)架构,在不改变Chirp信号扩频增益的前提下,通过时宽分割和重组(time width division and reorganization,TDR),降低信号在分数阶傅里叶变换域和周期域的能量聚敛特性。仿真结果表明,相较于现有LPD波形只能实现单一特征域隐蔽的问题,所提波形在不影响系统通信性能的前提下,面对频域检测、分数阶傅里叶变换域检测、周期域检测多种检测手段,在10 dB信噪比条件下的信号检测概率均低于0.2,满足系统在不同特征域下的LPD需求。

Quantum entangled fractional Fourier transform based on the IWOP technique

In our previous papers,the classical fractional Fourier transform theory was incorporated into the quantum theoretical system using the theoretical method of quantum optics,and the calculation produced quantum mechanical operators corresponding to the generation of fractional Fourier transform.The core function of the coordinate-momentum exchange operators in the addition law of fractional Fourier transform was analyzed too.In this paper,the bivariate operator Hermite polynomial theory and the technique of integration within an ordered product of operators(IWOP)are used to establish the entanglement fractional Fourier transform theory to the extent of quantum.A new function generating formula and an operator for generating quantum entangled fractional Fourier transform are obtained using the fractional Fourier transform relationship in a pair of conjugated entangled state representations.

Dual Image Cryptosystem Using Henon Map and Discrete Fourier Transform

This paper introduces an efficient image cryptography system.The pro-posed image cryptography system is based on employing the two-dimensional(2D)chaotic henon map(CHM)in the Discrete Fourier Transform(DFT).The proposed DFT-based CHM image cryptography has two procedures which are the encryption and decryption procedures.In the proposed DFT-based CHM image cryptography,the confusion is employed using the CHM while the diffu-sion is realized using the DFT.So,the proposed DFT-based CHM image crypto-graphy achieves both confusion and diffusion characteristics.The encryption procedure starts by applying the DFT on the image then the DFT transformed image is scrambled using the CHM and the inverse DFT is applied to get the final-ly encrypted image.The decryption procedure follows the inverse procedure of encryption.The proposed DFT-based CHM image cryptography system is exam-ined using a set of security tests like statistical tests,entropy tests,differential tests,and sensitivity tests.The obtained results confirm and ensure the superiority of the proposed DFT-based CHM image cryptography system.These outcomes encourage the employment of the proposed DFT-based CHM image cryptography system in real-time image and video applications.

基于STFT-ECA-ResNet18网络模型的滚动轴承变负载故障诊断

针对传统方法处理变负载轴承故障诊断时存在的自适应能力弱,模型泛化性差的问题,提出了一种改进的基于深度残差网络的故障诊断方法。首先,将采集到的一维时间序列信号进行短时傅里叶变换得到二维时频数据,再利用二维卷积神经网络从变换后的数据中提取特征。然后,通过高效通道注意力机制获取通道全局信息并对其权值进行调整,以增强改进网络模型的泛化能力,使其在变负载工况下分类效果得到提高。最后,通过仿真对所提方法进行了验证,结果表明相比传统方法诊断效果改进明显。

Fourier and wavelet transformations application to fault detection of induction motor with stator current

Fault detection of an induction motor was carried out using the information of the stator current. After synchronizing the actual data, Fourier and wavelet transformations were adopted in order to obtain the sideband or detail value characteristics under healthy and various faulty operating conditions. The most reliable phase current among the three phase currents was selected using an approach that employs the fuzzy entropy measure. Data were trained with a neural network system, and the fault detection algorithm was verified using the unknown data. Results of the proposed approach based on Fourier and wavelet transformations indicate that the faults can be properly classified into six categories. The training error is 5.3×10-7, and the average test error is 0.103.

Retrieval algorithm of quantitative analysis of passive Fourier transform infrared (FTRD) remote sensing measurements of chemical gas cloud from measuring the transmissivity by passive remote Fourier transform infrared

Passive Fourier transform infrared （FTIR） remote sensing measurement of chemical gas cloud is a vital technology. It takes an important part in many fields for the detection of released gases. The principle of concentration measurement is based on the Beer-Lambert law. Unlike the active measurement, for the passive remote sensing, in most cases, the difference between the temperature of the gas cloud and the brightness temperature of the background is usually a few kelvins. The gas cloud emission is almost equal to the background emission, thereby the emission of the gas cloud cannot be ignored. The concentration retrieval algorithm is quite different from the active measurement. In this paper, the concentration retrieval algorithm for the passive FTIR remote measurement of gas cloud is presented in detail, which involves radiative transfer model, radiometric calibration, absorption coefficient calculation, et al. The background spectrum has a broad feature, which is a slowly varying function of frequency. In this paper, the background spectrum is fitted with a polynomial by using the Levenberg-Marquardt method which is a kind of nonlinear least squares fitting algorithm. No background spectra are required. Thus, this method allows mobile, real-time and fast measurements of gas clouds.

The application of Fourier transform mid-infrared(FTIR) spectroscopy to identify variation in cell wall composition of Setaria italica ecotypes

Cell wall composition in monocotyledonous grasses has been identified as a key area of research for developing better feedstocks for forage and biofuel production.Setaria viridis and its close domesticated relative Setaria italica have been chosen as suitable monocotyledonous models for plants possessing the C4 pathway of photosynthesis including sorghum,maize,sugarcane,switchgrass and Miscanthus×giganteus.Accurate partial least squares regression（PLSR）models to predict S.italica stem composition have been generated,based upon Fourier transform mid-infrared（FTIR）spectra and calibrated with wet chemistry determinations of ground S.italica stem material measured using a modified version of the US National Renewable Energy Laboratory（NREL）acid hydrolysis protocol.The models facilitated a high-throughput screening analysis for glucan,xylan,Klason lignin and acid soluble lignin（ASL）in a collection of 183 natural S.italica variants and clustered them into classes,some possessing unique chemotypes.The predictive models provide a highly efficient screening tool for large scale breeding programs aimed at identifying lines or mutants possessing unique cell wall chemotypes.Genes encoding key catalytic enzymes of the lignin biosynthesis pathway exhibit a high level of conservation with matching expression profiles,measured by RT-q PCR,among accessions of S.italica,which closely mirror profiles observed in the different developmental regions of an elongating internode of S.viridis by RNASeq.