Roles of transforming growth factor-βsignaling in liver disease

In this editorial we expand the discussion on the article by Zhang et al published in the recent issue of the World Journal of Hepatology.We focus on the diagnostic and therapeutic targets identified on the basis of the current understanding of the molecular mechanisms of liver disease.Transforming growth factor-β(TGF-β)belongs to a structurally related cytokine super family.The family members display different time-and tissue-specific expression patterns associated with autoimmunity,inflammation,fibrosis,and tumorigenesis;and,they participate in the pathogenesis of many diseases.TGF-βand its related signaling pathways have been shown to participate in the progression of liver diseases,such as injury,inflammation,fibrosis,cirrhosis,and cancer.The often studied TGF-β/Smad signaling pathway has been shown to promote or inhibit liver fibrosis under different circumstances.Similarly,the early immature TGF-βmolecule functions as a tumor suppressor,inducing apoptosis;but,its interaction with the mitogenic molecule epidermal growth factor alters this effect,activating anti-apoptotic signals that promote liver cancer development.Overall,TGF-βsignaling displays contradictory effects in different liver disease stages.Therefore,the use of TGF-βand related signaling pathway molecules for diagnosis and treatment of liver diseases remains a challenge and needs further study.In this editorial,we aim to review the evidence for the use of TGF-βsignaling pathway molecules as diagnostic or therapeutic targets for different liver disease stages.

基于Transformer和卷积神经网络的齿轮故障诊断方法

针对部分齿轮的运行环境复杂,导致采集的样本数据不够的问题,提出了一种基于Transformer和卷积神经网络(CNN)的迁移学习齿轮故障诊断方法。首先,采用高斯滤波对原始振动信号进行了预处理,使信号变得平滑,降低了噪声信号的干扰;再将信号处理成带有位置信息的补丁序列以作为Transformer的输入,并增强了Transformer特征提取的能力,提高了诊断精度;然后,将信号输入到CNN继续提取特征信息,在模型中添加了一个残差块以防止网络退化;接着,划分了实验室采集的齿轮数据集和东南大学齿轮箱数据集的源域和目标域,采用了源域数据预训练模型,选择了每种类型的齿轮各100个样本为目标域;最后,以不同数据集为源域共进行了4组10次重复实验,测试了模型的准确率。研究结果表明:以不同数据集为源域的4组10次迁移实验的齿轮故障诊断准确率较高,均在90%以上,最高准确率可达100%;与其他不含Transformer的卷积神经网络、多尺度卷积神经网络和二维卷积神经网络相比,Transformer-CNN的齿轮故障诊断平均准确率更高,其平均准确率可达到99.64%。因此,基于Transformer-CNN的迁移学习方法能在小样本下诊断齿轮的故障。

基于混合信号多域特征和Transformer的干扰识别

针对无线通信信道易受到蓄意射频信号干扰问题,提出了一种从混合信号中识别干扰类型的方法。通过改进经典Transformer结构,形成新型网络模型Multidomain-former,以提取多域特征和识别信号干扰类型。首先,通过特定的序列划分机制对输入频谱进行预处理,并通过线性嵌入和位置编码保留原始顺序特征;其次,设计了逆傅氏变换和傅氏变换结合的编码模块,使Multidomain-former能同时提取频域和时域特征。使用通用仪器和收发天线搭建了无线收发信道,在不同干信比条件下对混合信号频谱进行采集,得到训练集和测试集。干扰对比实验通过所提Multidomain-former网络模型完成,并将经典的Transformer结构和其他常见的深度学习模型与所提网络模型进行了对比。对比实验结果表明,在干信比小于10 dB时,所提模型性能相较于经典Transformer在识别正确率方面有2%~3%的提升;在干信比等于-5 dB时,所提模型以最少参数量和次低计算复杂度获得了比另外5种基准网络高3.0%~9.3%的识别率。

基于CNN-Swin Transformer Network的LPI雷达信号识别

针对在低信噪比(SNR)条件下,低截获概率雷达信号调制方式识别准确率低的问题,提出一种基于Transformer和卷积神经网络(CNN)的雷达信号识别方法。首先,引入Swin Transformer模型并在模型前端设计CNN特征提取层构建了CNN+Swin Transformer网络(CSTN),然后利用时频分析获取雷达信号的时频特征,对图像进行预处理后输入CSTN模型进行训练,由网络的底部到顶部不断提取图像更丰富的语义信息,最后通过Softmax分类器对六类不同调制方式信号进行分类识别。仿真实验表明:在SNR为-18 dB时,该方法对六类典型雷达信号的平均识别率达到了94.26%,证明了所提方法的可行性。

基于CNN-Transformer网络融合模型的动态肌肉疲劳状态识别研究

为了解决现有的肌肉疲劳状态分类较少以及识别准确率不高的问题,提出一种基于表面肌电信号的CNN-Transformer肌肉疲劳识别模型,实现了动态肌肉疲劳的准确分类.该模型将传统的卷积神经网络与Transformer编码器模块相结合,相比单一卷积神经网络模型有更好的全局信息捕捉能力,对运动性肌肉疲劳识别具有更好的分类精度.首先,对15名健康受试者进行肘关节屈伸运动疲劳实验并基于疲劳程度划分了四种状态;其次,将获取的表面肌电信号数据进行预处理,并提取近似熵和排列熵两个非线性特征作为机器学习的特征输入;最后,利用原始表面肌电信号数据构建CNN-Transformer识别模型,与卷积神经网络、Transformer、随机森林模型进行比较.结果表明,在识别肌肉疲劳状态准确率方面CNN-Transformer模型比卷积神经网络、Transformer和随机森林模型分别高出2.89%、5.48%、7.24%,可见该模型具有良好的分类效果.

Variational Mode Decomposition-Informed Empirical Wavelet Transform for Electric Vibrator Noise Analysis

Electric vibrators find wide applications in reliability testing, waveform generation, and vibration simulation, making their noise characteristics a topic of significant interest. While Variational Mode Decomposition (VMD) and Empirical Wavelet Transform (EWT) offer valuable support for studying signal components, they also present certain limitations. This article integrates the strengths of both methods and proposes an enhanced approach that integrates VMD into the frequency band division principle of EWT. Initially, the method decomposes the signal using VMD, determining the mode count based on residuals, and subsequently employs EWT decomposition based on this information. This addresses mode aliasing issues in the original method while capitalizing on VMD’s adaptability. Feasibility was confirmed through simulation signals and ultimately applied to noise signals from vibrators. Experimental results demonstrate that the improved method not only resolves EWT frequency band division challenges but also effectively decomposes signal components compared to the VMD method.

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.

RESEARCH OF WAVELET TRANSFORM INSTRUMENT SYSTEM FOR SIGNAL ANALYSIS

After brief describing the Principle of wavelet transform (WT) of signals, a new signals analysis system based on wavelet transform is introduced. The design and development of the instryment of wavelet transform are described. A number of practical uses of this system demonstrate that wavelet transform system is specially functional in identifying and processing impulse, singular and non-smooth signals, so that it should be evaluated the most advanced signal analyzing system.

Total flavone of Abelmoschus manihot suppresses epithelial-mesenchymal transition via interfering transforming growth factor-β1 signaling in Crohn's disease intestinal fibrosis

AIM To explore the role and mechanism of total flavone of Abelmoschus manihot(TFA) on epithelial-mesenchymal transition(EMT) progress of Crohn's disease(CD) intestinal fibrosis.METHODS First,CCK-8 assay was performed to assess TFA on the viability of intestinal epithelial(IEC-6) cells and select the optimal concentrations of TFA for our further studies.Then cell morphology,wound healing and transwell assays were performed to examine the effect of TFA on morphology,migration and invasion of IEC-6 cells treated with TGF-β1.In addition,immunofluorescence,real-time PCR analysis(q RT-PCR) and western blotting assays were carried out to detect the impact of TFA on EMT progress.Moreover,western blotting assay was performed to evaluate the function of TFA on the Smad and MAPK signaling pathways.Further,the role of co-treatment of TFA and si-Smad or MAPK inhibitors has been examined by q RTPCR,western blotting,morphology,wound healing andtranswell assays.RESULTS In this study,TFA promoted transforming growth factor-β1(TGF-β1)-induced(IEC-6) morphological change,migration and invasion,and increased the expression of epithelial markers and reduced the levels of mesenchymal markers,along with the inactivation of Smad and MAPK signaling pathways.Moreover,we revealed that si-Smad and MAPK inhibitors effectively attenuated TGF-β1-induced EMT in IEC-6 cells.Importantly,co-treatment of TFA and si-Smad or MAPK inhibitors had better inhibitory effects on TGF-β1-induced EMT in IEC-6 cells than either one of them.CONCLUSION These findings could provide new insight into the molecular mechanisms of TFA on TGF-β1-induced EMT in IEC-6 cells and TFA is expected to advance as a new therapy to treat CD intestinal fibrosis.

基于Transformer的智能轴承声-振融合故障诊断

针对单一信源(振动或声音)轴承故障诊断方法所蕴含信息不全面的问题,开展了具有多源传感器集成的智能轴承的声-振融合故障诊断研究,引入Transformer架构作为声-振融合诊断模型的基本模式以加强信号的时序特征提取能力,利用交叉自注意力机制使声音信号与振动信号在特征提取过程中交互与融合,从而实现端到端的智能轴承故障诊断。搭建智能轴承试验台采集声音与振动数据进行验证的结果表明,基于Transformer的智能轴承声-振融合故障诊断方法相对于单独使用声音、振动的方法以及基线Transformer方法,诊断性能均有提升。

Combining Radon-ambiguity transform with second-order difference to improve detection probability of LFM signals in low SNR

The Radon-ambiguity transform （RAT）, although efficient for detecting the linear frequency modulated signals （LFMs）, is troubled by the energy accumulation of noise in low signal-to-noise ratio （SNR）. A secondorder difference （SOD） method is proposed to treat with this problem. In the SOD method, the optimal search step and difference step are derived from the LFM rate resolution formula. The sharpness of the peaks of RAT is measured by curvature, and the sharpness, but not the magnitude of the peaks, is used to detect the LFMs. The SOD method removes the noise energy accumulation and reserves the drastically changing components integrally; thus, it improves the detection probability of LFMs in low SNR. The expected performance of the new method is verified by 100 Monte Carlo simulations.

RECURSIVE FILTERING RADON-AMBIGUITY TRANSFORM ALGORITHM FOR DETECTING MULTI-LFM SIGNALS

In multi-LFM signal condition, Radon-Ambiguity Transform (RAT) of the strongLFM component has strong suppression effect on that of the weak LFM component. A methodnamed as Recursive Filtering RAT (RFRAT) Mgorithm is proposed for solving this problem. Byfully using of the Maximum Likelihood (ML) estimation value of the frequency modulation rategot by RAT. RFRAT can detect the noisy multi-LFM signals out step by step. The merit of thisnew method is validated by an illustrative example in low Signal-to-Noise-Ratio (SNR) condition.

A Real-Valued 2D DOA Estimation Algorithm of Noncircular Signal via Euler Transformation and Rotational Invariance Property

The problem of two-dimensional(2 D)direction of arrival(DOA)estimation for double parallel uniform linear arrays is investigated in this paper.A real-valued DOA estimation algorithm of noncircular(NC)signal is proposed,which combines the Euler transformation and rotational invariance(RI)property between subarrays.In this work,the effective array aperture is doubled by exploiting the noncircularity of signals.The complex arithmetic is converted to real arithmetic via Euler transformation.The main contribution of this work is not only extending the NC-Euler-ESPRIT algorithm from uniform linear array to double parallel uniform linear arrays,but also constructing a new 2 Drotational invariance property between subarrays,which is more complex than that in NCEuler-ESPRIT algorithm.The proposed 2 DNC-Euler-RI algorithm has much lower computational complexity than2 DNC-ESPRIT algorithm.The proposed algorithm has better angle estimation performance than 2 DESPRIT algorithm and 2 D NC-PM algorithm for double parallel uniform linear arrays,and is very close to that of 2 D NC-ESPRIT algorithm.The elevation angles and azimuth angles can be obtained with automatically pairing.The proposed algorithm can estimate up to 2(M-1)sources,which is two times that of 2 D ESPRIT algorithm.Cramer-Rao bound(CRB)of noncircular signal is derived for the proposed algorithm.Computational complexity comparison is also analyzed.Finally,simulation results are presented to illustrate the effectiveness and usefulness of the proposed algorithm.

Wigner-Hough transform based on slice's entropy and its application to multi-LFM signal detection

To enhance the capacity of the radar-reconnaissance interception receiver recognizing linear frequency modulated (LFM) at a low signal-noise ratio, this paper presents WignerHough transform (WHT) of the LFM signal and its corresponding characteristics, derives the probability density functions of the LFM signal and Gaussian white noise within WHT based on entropy (WHTE), dimension under different assumptions and puts forward a WHT algorithm based on entropy of slice to improve the capacity of detecting the LFM signal. Entropy of the WHT domain slice is adopted to assess the information size of polar radius or angle slice, which is converted into the weight factor to weight every slice. Double-deck weight is used to weaken the influences of noise and disturbance terms and WHTE treatment and signal detection procedure are also summarized. The rationality of the algorithm is demonstrated through theoretical analysis and formula derivation, the efficiency of the algorithm is verified by simulation comparison between WHT, fractional Fourier transform and periodic WHT, and it is highlighted that the WHTE algorithm has better detection accuracy and range of application against strong noise background.

Weak Seismic Signal Extraction Based on the Curvelet Transform

Seismic signal denoising is a key step in seismic data processing.Airgun signals are easy to be interfered with by noise when it travels a long distance due to the weak energy of active source signal of the airgun.Aiming to solve this problem,and considering that the conventional Curvelet transform threshold processing method does not use the seismic spectrum information,we independently process the Curvelet scale layer corresponding to valid data based on the characteristics of the Curvelet transform of multi-scale,multi-direction and capable of expressing the sparse seismic signals in order to fully excavate the information features.Combined with the Curvelet adaptive threshold denoising the algorithm,we apply the Curvelet transform to denoising seismic signals while retaining the weak information in the signal as much as possible.The simulation experiments show that the improved threshold denoising method based on Curvelet transform is superior to the frequency domain filtering,wavelet denoising and traditional Curvelet denoising method in detailed information extraction and signal denoising of low SNR signals.The calculation accuracy of the relative wave velocity variation of underground medium is improved.

Feature Extraction of Symmetrical Triangular LFMCW Signal Using Wigner-Hough Transform

Feature extraction of symmetrical triangular linear frequency modulation continuous wave （LFM- CW） signal is studied. Combined with its peculiar charaeteristics, a novel algorithm based on Wigner-Hough transform （WHT） is presented for the deteetion and parameter estimation of this type of waveform. The initial frequency and chirp rate of each segment of this wave are estimated, and the peak-value searching steps in the parameter spaee is given. Compared with Wigner-Ville distribution （WVD）, Pseudo-Wigner-Ville distri- bution （PWD） and Smoothed-Peseudo-Wigner-Ville distribution （SPWD）, WHT has proven itself to be the best method for feature extraetion of symmetrical triangular LFMCW signal. In the end, Monte-Carlo simulations under different SNRs are earried out, with validating results on this method.

Investigation on the automatic parameters extraction of pulse signals based on wavelet transform

This paper analyses a key problem in the quantification of pulse diagnosis. Due to the subjectivity and fuzziness of pulse diagnosis,quantitative methods are needed. To extract the parameters of pulse signals,the prerequisite is to detect the corners of pulse signals correctly. Up to now,the pulse parameters are mostly acquired by marking the pulse corners manually,which is an obstacle to modernize pulse diagnosis. Therefore,a new automatic parameters extraction approach for pulse signals using wavelet transform is presented. The results testified that the method we proposed is feasible and effective and can detect corners of pulse signals accurately,which can be expected to facilitate the modernization of pulse diagnosis.

Radar Emitter Signal Recognition Using Wavelet Packet Transform and Support Vector Machines

This paper presents a novel method for radar emitter signal recognition. First, wavelet packet transform （WPT） is introduced to extract features from radar emitter signals. Then, rough set theory is used to select the optimal feature subset with good discriminability from original feature set, and support vector machines （SVMs） are employed to design classifiers. A large number of experimental results show that the proposed method achieves very high recognition rates for 9 radar emitter signals in a wide range of signal-to-noise rates, and proves a feasible and valid method.

FEATURE EXTRACTION OF VIBRATION SIGNALS BASED ON WAVELET PACKET TRANSFORM

A method is proposed for the analysis of vibration signals from components ofrotating machines, based on the wavelet packet transformation (WPT) and the underlying physicalconcepts of modulation mechanism. The method provides a finer analysis and better time-frequencylocalization capabilities than any other analysis methods. Both details and approximations are splitinto finer components and result in better-localized frequency ranges corresponding to each node ofa wavelet packet tree. For the punpose of feature extraction, a hard threshold is given and theenergy of the coefficients above the threshold is used, as a criterion for the selection of the bestvector. The feature extraction of a vibration signal is accomplished by computing thereconstruction signal and its spectrum. When applied to a rolling bear vibration signal featureextraction, the proposed method can lead to be very effective.

Short-time Lv transform and its application for non-linear FM signal detection

A new time-frequency transform, known as short-time Lv transform （STLVT）, is proposed by applying the inverse Lv distribution to process consecutive segments of long data sequence. Compared with other time-frequency representations, the STLVT is able to achieve better energy concentration in the time-frequency domain for signals containing multiple linear and/or non-linear frequency modulated components. The merits of the STLVT are demonstrated in terms of the effects of window length and overlap length between adjacent segments on signal energy concentration in the time-frequency domain, and the required computational complexity. An application on the spectrum sensing for cognitive ratio （CR） by using a joint use of the STLVT and Hough transform （HT） is proposed and simulated.