Anti-Noise Performance of the FT Continuous Zoom Analysis Method for Discrete Spectrum

As a discrete spectrum correction method, the Fourier transform （FT） continuous zoom analysis method is widely used in vibration signal analysis, but little effort had been made on this method＇s anti-noise performance. It is widely believed that the analysis accuracy of the method can be substantially improved by increasing the zoom multiple, however, with the zoom multiple increases, the frequency estimation accuracy may decline sometimes in practices. Aiming at the problems above, this paper analyzes the sources of frequency estimation error when a harmonic signal mixed with and without noise is processed using the FT continuous zoom analysis. According to the characteristics that the local maximum of the zoom spectrum may be wrongly selected when the signal is corrupted with noise, the number of wrongly selected spectrum lines is deduced under different signal-to-noise ratio and local zoom multiple, and then the maximum frequency estimation error is given accordingly. The validity of the presented analysis is confirmed by simulations results. The frequency estimation accuracy of this method will not improve any more under the influence of noise, and there is a best zoom multiple, when the zoom multiple is larger than the best zoom multiple; the maximum frequency estimation error will fluctuate back and forth. The best zoom multiple curves under different signal-to-noise ratios given provide a theoretical basis for the choice of the appropriate zoom multiples of the FT continuous zoom analysis method in engineering applications.

Damage Diagnosis of Bleacher Based on an Enhanced Convolutional Neural Network with Training Interference

Bleachers play a crucial role in practical engineering applications, and any damage incurred during their operationposes a significant threat to the safety of both life and property. Consequently, it becomes imperative to conductdamage diagnosis and health monitoring of bleachers. The intricate structure of bleachers, the varied types ofpotential damage, and the presence of similar vibration data in adjacent locations make it challenging to achievesatisfactory diagnosis accuracy through traditional time-frequency analysis methods. Furthermore, field environmentalnoise can adversely impact the accuracy of bleacher damage diagnosis. To enhance the accuracy and antinoisecapabilities of bleacher damage diagnosis, this paper proposes improvements to the existing ConvolutionalNeural Network with Training Interference (TICNN). The result is an advanced Convolutional Neural Networkmodel with superior accuracy and robust anti-noise capabilities, referred to as Enhanced TICNN (ETICNN).ETICNN autonomously extracts optimal damage-sensitive features from the original vibration data. To validatethe superiority of the proposed ETICNN, experiments are conducted using the bleacher model from Qatar Universityas the subject. Comparative studies under identical experimental conditions involve TICNN, Deep ConvolutionalNeural Networks with wide first-layer kernels (WDCNN), and One-Dimensional ConvolutionalNeural Network (1DCNN). The experimental findings demonstrate that the ETICNN model achieves the highestaccuracy, approximately 99%, and exhibits robust classification abilities in both Phases I and II of the damagediagnosis experiments. Simultaneously, the ETICNN model demonstrates strong anti-noise capabilities, outperformingTICNN by 3% to 4% and surpassing other models in performance.

Active Source Seismic Identification and Automatic Picking of the P-wave First Arrival Using a Convolutional Neural Network

In seismic data processing,picking of the P-wave first arrivals takes up plenty of time and labor,and its accuracy plays a key role in imaging seismic structures.Based on the convolution neural network(CNN),we propose a new method to pick up the P-wave first arrivals automatically.Emitted from MINI28 vibroseis in the Jingdezhen seismic experiment,the vertical component of seismic waveforms recorded by EPS 32-bit portable seismometers are used for manually picking up the first arrivals(a total of 7242).Based on these arrivals,we establish the training and testing sets,including 25,290 event samples and 710,616 noise samples(length of each sample:2 s).After 3,000 steps of training,we obtain a convergent CNN model,which can automatically classify seismic events and noise samples with high accuracy(>99%).With the trained CNN model,we scan continuous seismic records and take the maximum output(probability of a seismic event)as the P-wave first arrival time.Compared with STA/LTA(short time average/long time average),our method shows higher precision and stronger anti-noise ability,especially with the low SNR seismic data.This CNN method is of great significance for promoting the intellectualization of seismic data processing,improving the resolution of seismic imaging,and promoting the joint inversion of active and passive sources.

A Novel Quantum Stegonagraphy Based on Brown States

In this paper,a novel quantum steganography protocol based on Brown entangled states is proposed.The new protocol adopts the CNOT operation to achieve the transmission of secret information by the best use of the characteristics of entangled states.Comparing with the previous quantum steganography algorithms,the new protocol focuses on its anti-noise capability for the phase-flip noise,which proved its good security resisting on quantum noise.Furthermore,the covert communication of secret information in the quantum secure direct communication channel would not affect the normal information transmission process due to the new protocol’s good imperceptibility.If the number of Brown states transmitted in carrier protocol is many enough,the imperceptibility of the secret channel can be further enhanced.In aspect of capacity,the new protocol can further expand its capacity by combining with other quantum steganography protocols.Due to that the proposed protocol does not require the participation of the classic channel when it implements the transmission of secret information,any additional information leakage will not be caused for the new algorithm with good security.The detailed theoretical analysis proves that the new protocol can own good performance on imperceptibility,capacity and security.

Active anti-noise transmitters and receivers

In general, the low-frequency capability of noise reduction of conventional anti-noise transmitters and receivers is not encouraging, but more and more sound energy of the modern high-intensity noise environments concentrates in that frequency range. Active anti-noise transmitters and receivers, which are developed from active ear defenders, supply the devices not only the benefit of advanced low-frequency anti-noise capability, but also a selectivity in sound reduction. The latter virtue ensures a high intelligibility of speech when the low-frequency noise is highly attenuated. On the basis of ref. [1], a thorough discussion on the principles, structures and experimental results of active anti-noise transmitters and receivers are given in this paper.

BACNN: Multi-scale feature fusion-based bilinear attention convolutional neural network for wood NIR classification

Effective development and utilization of wood resources is critical.Wood modification research has become an integral dimension of wood science research,however,the similarities between modified wood and original wood render it challenging for accurate identification and classification using conventional image classification techniques.So,the development of efficient and accurate wood classification techniques is inevitable.This paper presents a one-dimensional,convolutional neural network(i.e.,BACNN)that combines near-infrared spectroscopy and deep learning techniques to classify poplar,tung,and balsa woods,and PVA,nano-silica-sol and PVA-nano silica sol modified woods of poplar.The results show that BACNN achieves an accuracy of 99.3%on the test set,higher than the 52.9%of the BP neural network and 98.7%of Support Vector Machine compared with traditional machine learning methods and deep learning based methods;it is also higher than the 97.6%of LeNet,98.7%of AlexNet and 99.1%of VGGNet-11.Therefore,the classification method proposed offers potential applications in wood classification,especially with homogeneous modified wood,and it also provides a basis for subsequent wood properties studies.

A Modified Fuzzy C-Means Algorithm for Brain MR Image Segmentation and Bias Field Correction

In quantitative brain image analysis, accurate brain tissue segmentation from brain magnetic resonance image （MRI） is a critical step. It is considered to be the most important and difficult issue in the field of medical image processing. The quality of MR images is influenced by partial volume effect, noise, and intensity inhomogeneity, which render the segmentation task extremely challenging. We present a novel fuzzy c-means algorithm （RCLFCM） for segmentation and bias field correction of brain MR images. We employ a new gray-difference coefficient and design a new impact factor to measure the effect of neighbor pixels, so that the robustness of anti-noise can be enhanced. Moreover, we redefine the objective function of FCM （fuzzy c-means） by adding the bias field estimation model to overcome the intensity inhomogeneity in the image and segment the brain MR images simultaneously. We also construct a new spatial function by combining pixel gray value dissimilarity with its membership, and make full use of the space information between pixels to update the membership. Compared with other state-of-the-art approaches by using similarity accuracy on synthetic MR images with different levels of noise and intensity inhomogeneity, the proposed algorithm generates the results with high accuracy and robustness to noise.Jinan.

A multi-scale convolutional neural network for bearing compound fault diagnosis under various noise conditions

Recently,with the urgent demand for data-driven approaches in practical industrial scenarios,the deep learning diagnosis model in noise environments has attracted increasing attention.However,the existing research has two limitations:(1)the complex and changeable environmental noise,which cannot ensure the high-performance diagnosis of the model in different noise domains and(2)the possibility of multiple faults occurring simultaneously,which brings challenges to the model diagnosis.This paper presents a novel anti-noise multi-scale convolutional neural network(AM-CNN)for solving the issue of compound fault diagnosis under different intensity noises.First,we propose a residual pre-processing block according to the principle of noise superposition to process the input information and present the residual loss to construct a new loss function.Additionally,considering the strong coupling of input information,we design a multi-scale convolution block to realize multi-scale feature extraction for enhancing the proposed model’s robustness and effectiveness.Finally,a multi-label classifier is utilized to simultaneously distinguish multiple bearing faults.The proposed AM-CNN is verified under our collected compound fault dataset.On average,AM-CNN improves 39.93%accuracy and 25.84%F1-macro under the no-noise working condition and 45.67%accuracy and 27.72%F1-macro under different intensity noise working conditions compared with the existing methods.Furthermore,the experimental results show that AM-CNN can achieve good cross-domain performance with 100%accuracy and 100%F1-macro.Thus,AM-CNN has the potential to be an accurate and stable fault diagnosis tool.

Unbalanced classification method using least squares support vector machine with sparse strategy for steel surface defects with label noise

Least squares support vector machine (LS-SVM) plays an important role in steel surface defects classification because of its high speed. However, the defect samples obtained from the real production line may be noise. LS-SVM suffers from the poor classification performance in the classification stage when there are noise samples. Thus, in the classification stage, it is necessary to design an effective algorithm to process the defects dataset obtained from the real production line. To this end, an adaptive weight function was employed to reduce the adverse effect of noise samples. Moreover, although LSSVM offers fast speed, it still suffers from a high computational complexity if the number of training samples is large. The time for steel surface defects classification should be as short as possible. Therefore, a sparse strategy was adopted to prune the training samples. Finally, since the steel surface defects classification belongs to unbalanced data classification, LSSVM algorithm is not applicable. Hence, the unbalanced data information was introduced to improve the classification performance. Comprehensively considering above-mentioned factors, an improved LS-SVM classification model was proposed, termed as ILS-SVM. Experimental results show that the new algorithm has the advantages of high speed and great anti-noise ability.

Multi-class classification method for steel surface defects with feature noise

Defect classification is the key task of a steel surface defect detection system.The current defect classification algorithms have not taken the feature noise into consideration.In order to reduce the adverse impact of feature noise,an anti-noise multi-class classification method was proposed for steel surface defects.On the one hand,a novel anti-noise support vector hyper-spheres(ASVHs)classifier was formulated.For N types of defects,the ASVHs classifier built N hyper-spheres.These hyper-spheres were insensitive to feature and label noise.On the other hand,in order to reduce the costs of online time and storage space,the defect samples were pruned by support vector data description with parameter iteration adjustment strategy.In the end,the ASVHs classifier was built with sparse defect samples set and auxiliary information.Experimental results show that the novel multi-class classification method has high efficiency and accuracy for corrupted defect samples in steel surface.

Deep learning methods for noisy sperm image classification from convolutional neural network to visual transformer:a comprehensive comparative study

Background With the gradual increase of infertility in the world,among which male sperm problems are the main factor for infertility,more and more couples are using computer-assisted sperm analysis(CASA)to assist in the analysis and treatment of infertility.Meanwhile,the rapid development of deep learning(DL)has led to strong results in image classification tasks.However,the classification of sperm images has not been well studied in current deep learning methods,and the sperm images are often affected by noise in practical CASA applications.The purpose of this article is to investigate the anti-noise robustness of deep learning classification methods applied on sperm images.Methods The SVIA dataset is a publicly available large-scale sperm dataset containing three subsets.In this work,we used subset-C,which provides more than 125,000 independent images of sperms and impurities,including 121,401 sperm images and 4,479 impurity images.To investigate the anti-noise robustness of deep learning classification methods applied on sperm images,we conducted a comprehensive comparative study of sperm images using many convolutional neural network(CNN)and visual transformer(VT)deep learning methods to find the deep learning model with the most stable anti-noise robustness.Results This study proved that VT had strong robustness for the classification of tiny object(sperm and impurity)image datasets under some types of conventional noise and some adversarial attacks.In particular,under the influence of Poisson noise,accuracy changed from 91.45%to 91.08%,impurity precison changed from 92.7%to 91.3%,impurity recall changed from 88.8%to 89.5%,and impurity F1-score changed 90.7%to 90.4%.Meanwhile,sperm precision changed from 90.9%to 90.5%,sperm recall changed from 92.5%to 93.8%,and sperm F1-score changed from 92.1%to 90.4%.Conclusion Sperm image classification may be strongly affected by noise in current deep learning methods;the robustness with regard to noise of VT methods based on global information is greater than that of CNN methods based on local information,indicating that the robustness with regard to noise is reflected mainly in global information.