With the rapid development of mechanical equipment,mechanical health monitoring field has entered the era of big data.Deep learning has made a great achievement in the processing of large data of image and speech due ...With the rapid development of mechanical equipment,mechanical health monitoring field has entered the era of big data.Deep learning has made a great achievement in the processing of large data of image and speech due to the powerful modeling capabilities,this also brings influence to the mechanical fault diagnosis field.Therefore,according to the characteristics of motor vibration signals(nonstationary and difficult to deal with)and mechanical‘big data’,combined with deep learning,a motor fault diagnosis method based on stacked de-noising auto-encoder is proposed.The frequency domain signals obtained by the Fourier transform are used as input to the network.This method can extract features adaptively and unsupervised,and get rid of the dependence of traditional machine learning methods on human extraction features.A supervised fine tuning of the model is then carried out by backpropagation.The Asynchronous motor in Drivetrain Dynamics Simulator system was taken as the research object,the effectiveness of the proposed method was verified by a large number of data,and research on visualization of network output,the results shown that the SDAE method is more efficient and more intelligent.展开更多
Healthcare systems nowadays depend on IoT sensors for sending data over the internet as a common practice.Encryption ofmedical images is very important to secure patient information.Encrypting these images consumes a ...Healthcare systems nowadays depend on IoT sensors for sending data over the internet as a common practice.Encryption ofmedical images is very important to secure patient information.Encrypting these images consumes a lot of time onedge computing;therefore,theuse of anauto-encoder for compressionbefore encodingwill solve such a problem.In this paper,we use an auto-encoder to compress amedical image before encryption,and an encryption output(vector)is sent out over the network.On the other hand,a decoder was used to reproduce the original image back after the vector was received and decrypted.Two convolutional neural networks were conducted to evaluate our proposed approach:The first one is the auto-encoder,which is utilized to compress and encrypt the images,and the other assesses the classification accuracy of the image after decryption and decoding.Different hyperparameters of the encoder were tested,followed by the classification of the image to verify that no critical information was lost,to test the encryption and encoding resolution.In this approach,sixteen hyperparameter permutations are utilized,but this research discusses three main cases in detail.The first case shows that the combination of Mean Square Logarithmic Error(MSLE),ADAgrad,two layers for the auto-encoder,and ReLU had the best auto-encoder results with a Mean Absolute Error(MAE)=0.221 after 50 epochs and 75%classification with the best result for the classification algorithm.The second case shows the reflection of auto-encoder results on the classification results which is a combination ofMean Square Error(MSE),RMSprop,three layers for the auto-encoder,and ReLU,which had the best classification accuracy of 65%,the auto-encoder gives MAE=0.31 after 50 epochs.The third case is the worst,which is the combination of the hinge,RMSprop,three layers for the auto-encoder,and ReLU,providing accuracy of 20%and MAE=0.485.展开更多
Intelligent diagnosis approaches with shallow architectural models play an essential role in healthcare.Deep Learning(DL)models with unsupervised learning concepts have been proposed because high-quality feature extra...Intelligent diagnosis approaches with shallow architectural models play an essential role in healthcare.Deep Learning(DL)models with unsupervised learning concepts have been proposed because high-quality feature extraction and adequate labelled details significantly influence shallow models.On the other hand,skin lesionbased segregation and disintegration procedures play an essential role in earlier skin cancer detection.However,artefacts,an unclear boundary,poor contrast,and different lesion sizes make detection difficult.To address the issues in skin lesion diagnosis,this study creates the UDLS-DDOA model,an intelligent Unsupervised Deep Learning-based Stacked Auto-encoder(UDLS)optimized by Dynamic Differential Annealed Optimization(DDOA).Pre-processing,segregation,feature removal or separation,and disintegration are part of the proposed skin lesion diagnosis model.Pre-processing of skin lesion images occurs at the initial level for noise removal in the image using the Top hat filter and painting methodology.Following that,a Fuzzy C-Means(FCM)segregation procedure is performed using a Quasi-Oppositional Elephant Herd Optimization(QOEHO)algorithm.Besides,a novel feature extraction technique using the UDLS technique is applied where the parameter tuning takes place using DDOA.In the end,the disintegration procedure would be accomplished using a SoftMax(SM)classifier.The UDLS-DDOA model is tested against the International Skin Imaging Collaboration(ISIC)dataset,and the experimental results are examined using various computational attributes.The simulation results demonstrated that the UDLS-DDOA model outperformed the compared methods significantly.展开更多
Brain magnetic resonance images(MRI)are used to diagnose the different diseases of the brain,such as swelling and tumor detection.The quality of the brain MR images is degraded by different noises,usually salt&pep...Brain magnetic resonance images(MRI)are used to diagnose the different diseases of the brain,such as swelling and tumor detection.The quality of the brain MR images is degraded by different noises,usually salt&pepper and Gaussian noises,which are added to the MR images during the acquisition process.In the presence of these noises,medical experts are facing problems in diagnosing diseases from noisy brain MR images.Therefore,we have proposed a de-noising method by mixing concatenation,and residual deep learning techniques called the MCR de-noising method.Our proposed MCR method is to eliminate salt&pepper and gaussian noises as much as possible from the brain MRI images.The MCR method has been trained and tested on the noise quantity levels 2%to 20%for both salt&pepper and gaussian noise.The experiments have been done on publically available brain MRI image datasets,which can easily be accessible in the experiments and result section.The Structure Similarity Index Measure(SSIM)and Peak Signal-to-Noise Ratio(PSNR)calculate the similarity score between the denoised images by the proposed MCR method and the original clean images.Also,the Mean Squared Error(MSE)measures the error or difference between generated denoised and the original images.The proposed MCR denoising method has a 0.9763 SSIM score,84.3182 PSNR,and 0.0004 MSE for salt&pepper noise;similarly,0.7402 SSIM score,72.7601 PSNR,and 0.0041 MSE for Gaussian noise at the highest level of 20%noise.In the end,we have compared the MCR method with the state-of-the-art de-noising filters such as median and wiener de-noising filters.展开更多
To address the difficulties in fusing multi-mode sensor data for complex industrial machinery, an adaptive deep coupling convolutional auto-encoder (ADCCAE) fusion method was proposed. First, the multi-mode features e...To address the difficulties in fusing multi-mode sensor data for complex industrial machinery, an adaptive deep coupling convolutional auto-encoder (ADCCAE) fusion method was proposed. First, the multi-mode features extracted synchronously by the CCAE were stacked and fed to the multi-channel convolution layers for fusion. Then, the fused data was passed to all connection layers for compression and fed to the Softmax module for classification. Finally, the coupling loss function coefficients and the network parameters were optimized through an adaptive approach using the gray wolf optimization (GWO) algorithm. Experimental comparisons showed that the proposed ADCCAE fusion model was superior to existing models for multi-mode data fusion.展开更多
In the present study of peak particle velocity(PPV)and frequency,an improved algorithm(principal empirical mode decomposition,PEMD)based on principal component analysis(PCA)and empirical mode decomposition(EMD)is prop...In the present study of peak particle velocity(PPV)and frequency,an improved algorithm(principal empirical mode decomposition,PEMD)based on principal component analysis(PCA)and empirical mode decomposition(EMD)is proposed,with the goal of addressing poor filtering de-noising effects caused by the occurrences of modal aliasing phenomena in EMD blasting vibration signal decomposition processes.Test results showed that frequency of intrinsic mode function(IMF)components decomposed by PEMD gradually decreases and that the main frequency is unique,which eliminates the phenomenon of modal aliasing.In the simulation experiment,the signal-to-noise(SNR)and root mean square errors(RMSE)ratio of the signal de-noised by PEMD are the largest when compared to EMD and ensemble empirical mode decomposition(EEMD).The main frequency of the de-noising signal through PEMD is 75 Hz,which is closest to the frequency of the noiseless simulation signal.In geotechnical engineering blasting experiments,compared to EMD and EEMD,the signal de-noised by PEMD has the lowest level of distortion,and the frequency band is distributed in a range of 0-64 Hz,which is closest to the frequency band of the blasting vibration signal.In addition,the proportion of noise energy was the lowest,at 1.8%.展开更多
Phase-frequency characte ristics of approximate sinusoidal geomagnetic signals can be used fo r projectile roll positioning and other high-precision trajectory correction applications.The sinusoidal geomagnetic signal...Phase-frequency characte ristics of approximate sinusoidal geomagnetic signals can be used fo r projectile roll positioning and other high-precision trajectory correction applications.The sinusoidal geomagnetic signal deforms in the exposed and magnetically contaminated environment.In order to preciously recognize the roll information and effectively separate the noise component from the original geomagnetic sequence,based on the error source analysis,we propose a moving horizon based wavelet de-noising method for the dual-observed geomagnetic signal filtering where the captured rough roll frequency value provides reasonable wavelet decomposition and reconstruction level selection basis for sampled sequence;a moving horizon window guarantees real-time performance and non-cumulative calculation amount.The complete geomagnetic data in full ballistic range and three intercepted paragraphs are used for performance assessment.The positioning performance of the moving horizon wavelet de-noising method is compared with the band-pass filter.The results show that both noise reduction techniques improve the positioning accuracy while the wavelet de-noising method is always better than the band-pass filter.These results suggest that the proposed moving horizon based wavelet de-noising method of the dual-observed geomagnetic signal is more applicable for various launch conditions with better positioning performance.展开更多
Based on wavelet transform theory,a method for signal de-noising and singularity detection and elimination is proposed,which can reduce the noises and express local singularity.Each singularity can also be detected an...Based on wavelet transform theory,a method for signal de-noising and singularity detection and elimination is proposed,which can reduce the noises and express local singularity.Each singularity can also be detected and located through the local modulus maxima of wavelet transform.Simulation experiments are conducted with MATLAB software.The experimental results demonstrate that the method proposed in this paper is effective and feasible.展开更多
A novel synthetic aperture radar(SAR)image de-noising method based on the local pixel grouping(LPG)principal component analysis(PCA)and guided filter is proposed.This method contains two steps.In the first step,we pro...A novel synthetic aperture radar(SAR)image de-noising method based on the local pixel grouping(LPG)principal component analysis(PCA)and guided filter is proposed.This method contains two steps.In the first step,we process the noisy image by coarse filters,which can suppress the speckle effectively.The original SAR image is transformed into the additive noise model by logarithmic transform with deviation correction.Then,we use the pixel and its nearest neighbors as a vector to select training samples from the local window by LPG based on the block similar matching.The LPG method ensures that only the similar sample patches are used in the local statistical calculation of PCA transform estimation,so that the local features of the image can be well preserved after coefficients shrinkage in the PCA domain.In the second step,we do the guided filtering which can effectively eliminate small artifacts left over from the coarse filtering.Experimental results of simulated and real SAR images show that the proposed method outstrips the state-of-the-art image de-noising methods in the peak signalto-noise ratio(PSNR),the structural similarity(SSIM)index and the equivalent number of looks(ENLs),and is of perceived image quality.展开更多
As a relatively new method of processing non-stationary signal with high time-frequency resolution, S transform can be used to analyze the time-frequency characteristics of seismic signals. It has the following charac...As a relatively new method of processing non-stationary signal with high time-frequency resolution, S transform can be used to analyze the time-frequency characteristics of seismic signals. It has the following characteristics: its time-frequency resolution corresponding to the signal frequency, reversible inverse transform, basic wavelet that does not have to meet the permit conditions. We combined the threshold method, proposed the S-transform threshold filtering on the basis of S transform timefrequency filtering, and processed airgun seismic records from temporary stations in "Yangtze Program"(the Anhui experiment). Compared with the results of the bandpass filtering, the S transform threshold filtering can improve the signal to noise ratio(SNR) of seismic waves and provide effective help for first arrival pickup and accurate travel time. The first arrival wave seismic phase can be traced farther continuously, and the Pm seismic phase in the subsequent zone is also highlighted.展开更多
This paper introduces a new method to separate PD1 from other disturbing signals present on the high voltage genera-tors and motors. The method is based on combination of a pattern classifier, the Discrete Wavelet Tra...This paper introduces a new method to separate PD1 from other disturbing signals present on the high voltage genera-tors and motors. The method is based on combination of a pattern classifier, the Discrete Wavelet Transform (DWT), to de-noise PD and Time-Of-Arrival method to separate PD sources. Furthermore, it will be shown that it can recognize PD sources including rotating machine’s internal and external discharge pulses (e.g. on the bus bar).展开更多
Rolling bearings are important central components in rotating machines, whose fault diagnosis is crucial in condition-based maintenance to reduce the complexity of different kinds of faults. To classify various rollin...Rolling bearings are important central components in rotating machines, whose fault diagnosis is crucial in condition-based maintenance to reduce the complexity of different kinds of faults. To classify various rolling bearing faults, a prognostic algorithm consisting of four phases was proposed. Since stacked denoising auto-encoder can be filtered, noise of large numbers of mechanical vibration signals was used for deep learning structure to extract the characteristics of the noise. Unsupervised pre-training method, which can greatly simplify the traditional manual extraction approach, was utilized to process the depth of the data automatically. Furthermore, the aggregation layer of stacked denoising auto-encoder(SDA) was proposed to get rid of gradient disappearance in deeper layers of network, mix superficial nodes’ expression with deeper layers, and avoid the insufficient express ability in deeper layers. Principal component analysis(PCA) was adopted to extract different features for classification. According to the experimental data of this method and from the comparison results, the proposed method of rolling bearing fault classification reached 97.02% of correct rate, suggesting a better performance than other algorithms.展开更多
With the development of science and technology,the status of the water environment has received more and more attention.In this paper,we propose a deep learning model,named a Joint Auto-Encoder network,to solve the pr...With the development of science and technology,the status of the water environment has received more and more attention.In this paper,we propose a deep learning model,named a Joint Auto-Encoder network,to solve the problem of outlier detection in water supply data.The Joint Auto-Encoder network first expands the size of training data and extracts the useful features from the input data,and then reconstructs the input data effectively into an output.The outliers are detected based on the network’s reconstruction errors,with a larger reconstruction error indicating a higher rate to be an outlier.For water supply data,there are mainly two types of outliers:outliers with large values and those with values closed to zero.We set two separate thresholds,and,for the reconstruction errors to detect the two types of outliers respectively.The data samples with reconstruction errors exceeding the thresholds are voted to be outliers.The two thresholds can be calculated by the classification confusion matrix and the receiver operating characteristic(ROC)curve.We have also performed comparisons between the Joint Auto-Encoder and the vanilla Auto-Encoder in this paper on both the synthesis data set and the MNIST data set.As a result,our model has proved to outperform the vanilla Auto-Encoder and some other outlier detection approaches with the recall rate of 98.94 percent in water supply data.展开更多
Wavelet forced de-noising algorithm is suitable for denoising of unsteady drilling fluid pulse signal, including baseline drift rectification and two-stage de-noising processing of frame synchronization signal and ins...Wavelet forced de-noising algorithm is suitable for denoising of unsteady drilling fluid pulse signal, including baseline drift rectification and two-stage de-noising processing of frame synchronization signal and instruction signal. Two-stage de-noising processing can reduce the impact of baseline drift and determine automatic peak detection threshold range for signal recognition by distinguishing different features of frame synchronization pulse and instruction pulse. Rising and falling edge relative protruding threshold is defined for peak detection in signal recognition, which can make full use of the degree of the signal peak change and detect peaks flexibly with rising and falling edge relative protruding threshold combination. A synchronous decoding method was designed to reduce position uncertainty of the frame synchronization pulse and eliminate the accumulative error of time base drift, which determines the first instruction pulse position according to position of the frame synchronization pulse and decodes subsequent instruction pulse by taking current instruction pulse as new bit synchronization pulse. Special tool software was developed to tune algorithm parameters, which has a decoding success rate of about 95% for the universal coded signals. For the special coded signals with check byte, decoding success rate using the automatic threshold adjustment algorithm is as high as 99%.展开更多
Based on the statistical characteristics analysis of random noise power and autocorrelation function, this paper proposes a de-noising method for track state detection signal by using Empirical Mode Decomposition (EMD...Based on the statistical characteristics analysis of random noise power and autocorrelation function, this paper proposes a de-noising method for track state detection signal by using Empirical Mode Decomposition (EMD). This method is used to noise reduction refactoring for the first Intrinsic Mode Function (IMF) component in accordance with the “random sort-accumulation-average-refactoring' order. Signal autocorrelation function characteristics are used to determine the cut-off point of the dominant mode. This method was applied to test signals and the actual inertial unit signals;the experimental results show that the method can effectively remove the noise and better meet the precision requirement.展开更多
Since the effectiveness of extracting fault features is not high under traditional bearing fault diagnosis method, a bearing fault diagnosis method based on Deep Auto-encoder Network (DAEN) optimized by Cloud Adaptive...Since the effectiveness of extracting fault features is not high under traditional bearing fault diagnosis method, a bearing fault diagnosis method based on Deep Auto-encoder Network (DAEN) optimized by Cloud Adaptive Particle Swarm Optimization (CAPSO) was proposed. On the basis of analyzing CAPSO and DAEN, the CAPSO-DAEN fault diagnosis model is built. The model uses the randomness and stability of CAPSO algorithm to optimize the connection weight of DAEN, to reduce the constraints on the weights and extract fault features adaptively. Finally, efficient and accurate fault diagnosis can be implemented with the Softmax classifier. The results of test show that the proposed method has higher diagnostic accuracy and more stable diagnosis results than those based on the DAEN, Support Vector Machine (SVM) and the Back Propagation algorithm (BP) under appropriate parameters.展开更多
In the track irregularity detection, the acceleration signals of the inertial measurement unit (IMU) output which with low frequency components and noise, this paper studied a de-noising algorithm. Based on the criter...In the track irregularity detection, the acceleration signals of the inertial measurement unit (IMU) output which with low frequency components and noise, this paper studied a de-noising algorithm. Based on the criterion of consecutive mean square error, a de-noising method for IMU acceleration signals based on empirical mode decomposition (EMD) was proposed. This method can divide the intrinsic mode functions (IMFs) derived from EMD into signal dominant modes and noise dominant modes, then the modes reflecting the important structures of a signal were combined together to form partially reconstructed de-noised signal. Simulations were conducted for simulated signals and a real IMU acceleration signals using this method. Experimental results indicate that this method can efficiently and adaptively remove noise, and this method can better meet the precision requirement.展开更多
The quality of the low frequency electromagnetic data is affected by the spike and the trend noises.Failure in removal of the spikes and the trends reduces the credibility of data explanation.Based on the analyses of ...The quality of the low frequency electromagnetic data is affected by the spike and the trend noises.Failure in removal of the spikes and the trends reduces the credibility of data explanation.Based on the analyses of the causes and characteristics of these noises,this paper presents the results of a preset statistics stacking method(PSSM)and a piecewise linear fitting method(PLFM)in de-noising the spikes and trends,respectively.The magnitudes of the spikes are either higher or lower than the normal values,which leads to distortion of the useful signal.Comparisons have been performed in removing of the spikes among the average,the statistics and the PSSM methods,and the results indicate that only the PSSM can remove the spikes successfully.On the other hand,the spectrums of the linear and nonlinear trends mainly lie in the low frequency band and can change the calculated resistivity significantly.No influence of the trends is observed when the frequency is higher than a certain threshold value.The PLSM can remove effectively both the linear and nonlinear trends with errors around 1% in the power spectrum.The proposed methods present an effective way for de-noising the spike and the trend noises in the low frequency electromagnetic data,and establish a research basis for de-noising the low frequency noises.展开更多
In this paper, a different method for de-noising of ECG signals using wavelets is presented. In this strategy, we will try to design the best wavelet for de-nosing. Genetic algorithm tests wide range of quadrature fil...In this paper, a different method for de-noising of ECG signals using wavelets is presented. In this strategy, we will try to design the best wavelet for de-nosing. Genetic algorithm tests wide range of quadrature filter banks and the best of them will be chosen that minimize the Signal-to-Noise Ratio (SNR). Furthermore, the wavelet function and scaling function related to these filters are reported as the best wavelet for de-noising. Simulation results for de-noising of a noisy ECG signal show that using obtained wavelet by proposed method improves the SNR of about 2.5 dB.展开更多
The influenza virus changes its antigenicity frequently due to rapid mutations, leading to immune escape and failure of vaccination. Rapid determination of the influenza antigenicity could help identify the antigenic ...The influenza virus changes its antigenicity frequently due to rapid mutations, leading to immune escape and failure of vaccination. Rapid determination of the influenza antigenicity could help identify the antigenic variants in time. Here, we built a stacked auto-encoder (SAE) model for predicting the antigenic variant of human influenza A(H3N2) viruses based on the hemagglutinin (HA) protein sequences. The model achieved an accuracy of 0.95 in five-fold cross-validations, better than the logistic regression model did. Further analysis of the model shows that most of the active nodes in the hidden layer reflected the combined contribution of multiple residues to antigenic variation. Besides, some features (residues on HA protein) in the input layer were observed to take part in multiple active nodes, such as residue 189, 145 and 156, which were also reported to mostly determine the antigenic variation of influenza A(H3N2) viruses. Overall,this work is not only useful for rapidly identifying antigenic variants in influenza prevention, but also an interesting attempt in inferring the mechanisms of biological process through analysis of SAE model, which may give some insights into interpretation of the deep learning展开更多
基金This research is supported financially by Natural Science Foundation of China(Grant No.51505234,51405241,51575283).
文摘With the rapid development of mechanical equipment,mechanical health monitoring field has entered the era of big data.Deep learning has made a great achievement in the processing of large data of image and speech due to the powerful modeling capabilities,this also brings influence to the mechanical fault diagnosis field.Therefore,according to the characteristics of motor vibration signals(nonstationary and difficult to deal with)and mechanical‘big data’,combined with deep learning,a motor fault diagnosis method based on stacked de-noising auto-encoder is proposed.The frequency domain signals obtained by the Fourier transform are used as input to the network.This method can extract features adaptively and unsupervised,and get rid of the dependence of traditional machine learning methods on human extraction features.A supervised fine tuning of the model is then carried out by backpropagation.The Asynchronous motor in Drivetrain Dynamics Simulator system was taken as the research object,the effectiveness of the proposed method was verified by a large number of data,and research on visualization of network output,the results shown that the SDAE method is more efficient and more intelligent.
基金funding was provided by the Institute for Research and Consulting Studies at King Khalid University through Corona Research(Fast Track)[Grant No.3-103S-2020].
文摘Healthcare systems nowadays depend on IoT sensors for sending data over the internet as a common practice.Encryption ofmedical images is very important to secure patient information.Encrypting these images consumes a lot of time onedge computing;therefore,theuse of anauto-encoder for compressionbefore encodingwill solve such a problem.In this paper,we use an auto-encoder to compress amedical image before encryption,and an encryption output(vector)is sent out over the network.On the other hand,a decoder was used to reproduce the original image back after the vector was received and decrypted.Two convolutional neural networks were conducted to evaluate our proposed approach:The first one is the auto-encoder,which is utilized to compress and encrypt the images,and the other assesses the classification accuracy of the image after decryption and decoding.Different hyperparameters of the encoder were tested,followed by the classification of the image to verify that no critical information was lost,to test the encryption and encoding resolution.In this approach,sixteen hyperparameter permutations are utilized,but this research discusses three main cases in detail.The first case shows that the combination of Mean Square Logarithmic Error(MSLE),ADAgrad,two layers for the auto-encoder,and ReLU had the best auto-encoder results with a Mean Absolute Error(MAE)=0.221 after 50 epochs and 75%classification with the best result for the classification algorithm.The second case shows the reflection of auto-encoder results on the classification results which is a combination ofMean Square Error(MSE),RMSprop,three layers for the auto-encoder,and ReLU,which had the best classification accuracy of 65%,the auto-encoder gives MAE=0.31 after 50 epochs.The third case is the worst,which is the combination of the hinge,RMSprop,three layers for the auto-encoder,and ReLU,providing accuracy of 20%and MAE=0.485.
基金deputyship for Research&Innovation,Ministry of Education in Saudi Arabia,for funding this research work through Project Number (IFP-2020-133).
文摘Intelligent diagnosis approaches with shallow architectural models play an essential role in healthcare.Deep Learning(DL)models with unsupervised learning concepts have been proposed because high-quality feature extraction and adequate labelled details significantly influence shallow models.On the other hand,skin lesionbased segregation and disintegration procedures play an essential role in earlier skin cancer detection.However,artefacts,an unclear boundary,poor contrast,and different lesion sizes make detection difficult.To address the issues in skin lesion diagnosis,this study creates the UDLS-DDOA model,an intelligent Unsupervised Deep Learning-based Stacked Auto-encoder(UDLS)optimized by Dynamic Differential Annealed Optimization(DDOA).Pre-processing,segregation,feature removal or separation,and disintegration are part of the proposed skin lesion diagnosis model.Pre-processing of skin lesion images occurs at the initial level for noise removal in the image using the Top hat filter and painting methodology.Following that,a Fuzzy C-Means(FCM)segregation procedure is performed using a Quasi-Oppositional Elephant Herd Optimization(QOEHO)algorithm.Besides,a novel feature extraction technique using the UDLS technique is applied where the parameter tuning takes place using DDOA.In the end,the disintegration procedure would be accomplished using a SoftMax(SM)classifier.The UDLS-DDOA model is tested against the International Skin Imaging Collaboration(ISIC)dataset,and the experimental results are examined using various computational attributes.The simulation results demonstrated that the UDLS-DDOA model outperformed the compared methods significantly.
文摘Brain magnetic resonance images(MRI)are used to diagnose the different diseases of the brain,such as swelling and tumor detection.The quality of the brain MR images is degraded by different noises,usually salt&pepper and Gaussian noises,which are added to the MR images during the acquisition process.In the presence of these noises,medical experts are facing problems in diagnosing diseases from noisy brain MR images.Therefore,we have proposed a de-noising method by mixing concatenation,and residual deep learning techniques called the MCR de-noising method.Our proposed MCR method is to eliminate salt&pepper and gaussian noises as much as possible from the brain MRI images.The MCR method has been trained and tested on the noise quantity levels 2%to 20%for both salt&pepper and gaussian noise.The experiments have been done on publically available brain MRI image datasets,which can easily be accessible in the experiments and result section.The Structure Similarity Index Measure(SSIM)and Peak Signal-to-Noise Ratio(PSNR)calculate the similarity score between the denoised images by the proposed MCR method and the original clean images.Also,the Mean Squared Error(MSE)measures the error or difference between generated denoised and the original images.The proposed MCR denoising method has a 0.9763 SSIM score,84.3182 PSNR,and 0.0004 MSE for salt&pepper noise;similarly,0.7402 SSIM score,72.7601 PSNR,and 0.0041 MSE for Gaussian noise at the highest level of 20%noise.In the end,we have compared the MCR method with the state-of-the-art de-noising filters such as median and wiener de-noising filters.
文摘To address the difficulties in fusing multi-mode sensor data for complex industrial machinery, an adaptive deep coupling convolutional auto-encoder (ADCCAE) fusion method was proposed. First, the multi-mode features extracted synchronously by the CCAE were stacked and fed to the multi-channel convolution layers for fusion. Then, the fused data was passed to all connection layers for compression and fed to the Softmax module for classification. Finally, the coupling loss function coefficients and the network parameters were optimized through an adaptive approach using the gray wolf optimization (GWO) algorithm. Experimental comparisons showed that the proposed ADCCAE fusion model was superior to existing models for multi-mode data fusion.
基金National Natural Science Foundation of China under Grant Nos.52064015 and 51404111Jiangxi Provincial Natural Science Foundation under Grant No.20192BAB206017+1 种基金Scientific Research Project of Jiangxi Provincial Education Department under Grant No.GJJ160643the Program of Qingjiang Excellent Young Talents,Jiangxi University of Science and Technology under Grant No.JXUSTQJYX2016007。
文摘In the present study of peak particle velocity(PPV)and frequency,an improved algorithm(principal empirical mode decomposition,PEMD)based on principal component analysis(PCA)and empirical mode decomposition(EMD)is proposed,with the goal of addressing poor filtering de-noising effects caused by the occurrences of modal aliasing phenomena in EMD blasting vibration signal decomposition processes.Test results showed that frequency of intrinsic mode function(IMF)components decomposed by PEMD gradually decreases and that the main frequency is unique,which eliminates the phenomenon of modal aliasing.In the simulation experiment,the signal-to-noise(SNR)and root mean square errors(RMSE)ratio of the signal de-noised by PEMD are the largest when compared to EMD and ensemble empirical mode decomposition(EEMD).The main frequency of the de-noising signal through PEMD is 75 Hz,which is closest to the frequency of the noiseless simulation signal.In geotechnical engineering blasting experiments,compared to EMD and EEMD,the signal de-noised by PEMD has the lowest level of distortion,and the frequency band is distributed in a range of 0-64 Hz,which is closest to the frequency band of the blasting vibration signal.In addition,the proportion of noise energy was the lowest,at 1.8%.
基金funded by National Natural Science Foundation of China(61201391)。
文摘Phase-frequency characte ristics of approximate sinusoidal geomagnetic signals can be used fo r projectile roll positioning and other high-precision trajectory correction applications.The sinusoidal geomagnetic signal deforms in the exposed and magnetically contaminated environment.In order to preciously recognize the roll information and effectively separate the noise component from the original geomagnetic sequence,based on the error source analysis,we propose a moving horizon based wavelet de-noising method for the dual-observed geomagnetic signal filtering where the captured rough roll frequency value provides reasonable wavelet decomposition and reconstruction level selection basis for sampled sequence;a moving horizon window guarantees real-time performance and non-cumulative calculation amount.The complete geomagnetic data in full ballistic range and three intercepted paragraphs are used for performance assessment.The positioning performance of the moving horizon wavelet de-noising method is compared with the band-pass filter.The results show that both noise reduction techniques improve the positioning accuracy while the wavelet de-noising method is always better than the band-pass filter.These results suggest that the proposed moving horizon based wavelet de-noising method of the dual-observed geomagnetic signal is more applicable for various launch conditions with better positioning performance.
文摘Based on wavelet transform theory,a method for signal de-noising and singularity detection and elimination is proposed,which can reduce the noises and express local singularity.Each singularity can also be detected and located through the local modulus maxima of wavelet transform.Simulation experiments are conducted with MATLAB software.The experimental results demonstrate that the method proposed in this paper is effective and feasible.
基金supported by the National Natural Science Foundation of China(6200220861572063+1 种基金61603225)the Natural Science Foundation of Shandong Province(ZR2016FQ04)。
文摘A novel synthetic aperture radar(SAR)image de-noising method based on the local pixel grouping(LPG)principal component analysis(PCA)and guided filter is proposed.This method contains two steps.In the first step,we process the noisy image by coarse filters,which can suppress the speckle effectively.The original SAR image is transformed into the additive noise model by logarithmic transform with deviation correction.Then,we use the pixel and its nearest neighbors as a vector to select training samples from the local window by LPG based on the block similar matching.The LPG method ensures that only the similar sample patches are used in the local statistical calculation of PCA transform estimation,so that the local features of the image can be well preserved after coefficients shrinkage in the PCA domain.In the second step,we do the guided filtering which can effectively eliminate small artifacts left over from the coarse filtering.Experimental results of simulated and real SAR images show that the proposed method outstrips the state-of-the-art image de-noising methods in the peak signalto-noise ratio(PSNR),the structural similarity(SSIM)index and the equivalent number of looks(ENLs),and is of perceived image quality.
基金funded by the National Natural Science Foundation Item (41674068)Seismic Youth Funding of GEC (YFGEC2016001)
文摘As a relatively new method of processing non-stationary signal with high time-frequency resolution, S transform can be used to analyze the time-frequency characteristics of seismic signals. It has the following characteristics: its time-frequency resolution corresponding to the signal frequency, reversible inverse transform, basic wavelet that does not have to meet the permit conditions. We combined the threshold method, proposed the S-transform threshold filtering on the basis of S transform timefrequency filtering, and processed airgun seismic records from temporary stations in "Yangtze Program"(the Anhui experiment). Compared with the results of the bandpass filtering, the S transform threshold filtering can improve the signal to noise ratio(SNR) of seismic waves and provide effective help for first arrival pickup and accurate travel time. The first arrival wave seismic phase can be traced farther continuously, and the Pm seismic phase in the subsequent zone is also highlighted.
文摘This paper introduces a new method to separate PD1 from other disturbing signals present on the high voltage genera-tors and motors. The method is based on combination of a pattern classifier, the Discrete Wavelet Transform (DWT), to de-noise PD and Time-Of-Arrival method to separate PD sources. Furthermore, it will be shown that it can recognize PD sources including rotating machine’s internal and external discharge pulses (e.g. on the bus bar).
基金Sponsored by the National Natural Science Foundation of China(Grant No.51704138)
文摘Rolling bearings are important central components in rotating machines, whose fault diagnosis is crucial in condition-based maintenance to reduce the complexity of different kinds of faults. To classify various rolling bearing faults, a prognostic algorithm consisting of four phases was proposed. Since stacked denoising auto-encoder can be filtered, noise of large numbers of mechanical vibration signals was used for deep learning structure to extract the characteristics of the noise. Unsupervised pre-training method, which can greatly simplify the traditional manual extraction approach, was utilized to process the depth of the data automatically. Furthermore, the aggregation layer of stacked denoising auto-encoder(SDA) was proposed to get rid of gradient disappearance in deeper layers of network, mix superficial nodes’ expression with deeper layers, and avoid the insufficient express ability in deeper layers. Principal component analysis(PCA) was adopted to extract different features for classification. According to the experimental data of this method and from the comparison results, the proposed method of rolling bearing fault classification reached 97.02% of correct rate, suggesting a better performance than other algorithms.
基金The work described in this paper was supported by the National Natural Science Foundation of China(NSFC)under Grant No.U1501253 and Grant No.U1713217.
文摘With the development of science and technology,the status of the water environment has received more and more attention.In this paper,we propose a deep learning model,named a Joint Auto-Encoder network,to solve the problem of outlier detection in water supply data.The Joint Auto-Encoder network first expands the size of training data and extracts the useful features from the input data,and then reconstructs the input data effectively into an output.The outliers are detected based on the network’s reconstruction errors,with a larger reconstruction error indicating a higher rate to be an outlier.For water supply data,there are mainly two types of outliers:outliers with large values and those with values closed to zero.We set two separate thresholds,and,for the reconstruction errors to detect the two types of outliers respectively.The data samples with reconstruction errors exceeding the thresholds are voted to be outliers.The two thresholds can be calculated by the classification confusion matrix and the receiver operating characteristic(ROC)curve.We have also performed comparisons between the Joint Auto-Encoder and the vanilla Auto-Encoder in this paper on both the synthesis data set and the MNIST data set.As a result,our model has proved to outperform the vanilla Auto-Encoder and some other outlier detection approaches with the recall rate of 98.94 percent in water supply data.
基金Supported by the China National Science and Technology Major Project(2016ZX05020005-001)
文摘Wavelet forced de-noising algorithm is suitable for denoising of unsteady drilling fluid pulse signal, including baseline drift rectification and two-stage de-noising processing of frame synchronization signal and instruction signal. Two-stage de-noising processing can reduce the impact of baseline drift and determine automatic peak detection threshold range for signal recognition by distinguishing different features of frame synchronization pulse and instruction pulse. Rising and falling edge relative protruding threshold is defined for peak detection in signal recognition, which can make full use of the degree of the signal peak change and detect peaks flexibly with rising and falling edge relative protruding threshold combination. A synchronous decoding method was designed to reduce position uncertainty of the frame synchronization pulse and eliminate the accumulative error of time base drift, which determines the first instruction pulse position according to position of the frame synchronization pulse and decodes subsequent instruction pulse by taking current instruction pulse as new bit synchronization pulse. Special tool software was developed to tune algorithm parameters, which has a decoding success rate of about 95% for the universal coded signals. For the special coded signals with check byte, decoding success rate using the automatic threshold adjustment algorithm is as high as 99%.
文摘Based on the statistical characteristics analysis of random noise power and autocorrelation function, this paper proposes a de-noising method for track state detection signal by using Empirical Mode Decomposition (EMD). This method is used to noise reduction refactoring for the first Intrinsic Mode Function (IMF) component in accordance with the “random sort-accumulation-average-refactoring' order. Signal autocorrelation function characteristics are used to determine the cut-off point of the dominant mode. This method was applied to test signals and the actual inertial unit signals;the experimental results show that the method can effectively remove the noise and better meet the precision requirement.
文摘Since the effectiveness of extracting fault features is not high under traditional bearing fault diagnosis method, a bearing fault diagnosis method based on Deep Auto-encoder Network (DAEN) optimized by Cloud Adaptive Particle Swarm Optimization (CAPSO) was proposed. On the basis of analyzing CAPSO and DAEN, the CAPSO-DAEN fault diagnosis model is built. The model uses the randomness and stability of CAPSO algorithm to optimize the connection weight of DAEN, to reduce the constraints on the weights and extract fault features adaptively. Finally, efficient and accurate fault diagnosis can be implemented with the Softmax classifier. The results of test show that the proposed method has higher diagnostic accuracy and more stable diagnosis results than those based on the DAEN, Support Vector Machine (SVM) and the Back Propagation algorithm (BP) under appropriate parameters.
文摘In the track irregularity detection, the acceleration signals of the inertial measurement unit (IMU) output which with low frequency components and noise, this paper studied a de-noising algorithm. Based on the criterion of consecutive mean square error, a de-noising method for IMU acceleration signals based on empirical mode decomposition (EMD) was proposed. This method can divide the intrinsic mode functions (IMFs) derived from EMD into signal dominant modes and noise dominant modes, then the modes reflecting the important structures of a signal were combined together to form partially reconstructed de-noised signal. Simulations were conducted for simulated signals and a real IMU acceleration signals using this method. Experimental results indicate that this method can efficiently and adaptively remove noise, and this method can better meet the precision requirement.
文摘The quality of the low frequency electromagnetic data is affected by the spike and the trend noises.Failure in removal of the spikes and the trends reduces the credibility of data explanation.Based on the analyses of the causes and characteristics of these noises,this paper presents the results of a preset statistics stacking method(PSSM)and a piecewise linear fitting method(PLFM)in de-noising the spikes and trends,respectively.The magnitudes of the spikes are either higher or lower than the normal values,which leads to distortion of the useful signal.Comparisons have been performed in removing of the spikes among the average,the statistics and the PSSM methods,and the results indicate that only the PSSM can remove the spikes successfully.On the other hand,the spectrums of the linear and nonlinear trends mainly lie in the low frequency band and can change the calculated resistivity significantly.No influence of the trends is observed when the frequency is higher than a certain threshold value.The PLSM can remove effectively both the linear and nonlinear trends with errors around 1% in the power spectrum.The proposed methods present an effective way for de-noising the spike and the trend noises in the low frequency electromagnetic data,and establish a research basis for de-noising the low frequency noises.
文摘In this paper, a different method for de-noising of ECG signals using wavelets is presented. In this strategy, we will try to design the best wavelet for de-nosing. Genetic algorithm tests wide range of quadrature filter banks and the best of them will be chosen that minimize the Signal-to-Noise Ratio (SNR). Furthermore, the wavelet function and scaling function related to these filters are reported as the best wavelet for de-noising. Simulation results for de-noising of a noisy ECG signal show that using obtained wavelet by proposed method improves the SNR of about 2.5 dB.
文摘The influenza virus changes its antigenicity frequently due to rapid mutations, leading to immune escape and failure of vaccination. Rapid determination of the influenza antigenicity could help identify the antigenic variants in time. Here, we built a stacked auto-encoder (SAE) model for predicting the antigenic variant of human influenza A(H3N2) viruses based on the hemagglutinin (HA) protein sequences. The model achieved an accuracy of 0.95 in five-fold cross-validations, better than the logistic regression model did. Further analysis of the model shows that most of the active nodes in the hidden layer reflected the combined contribution of multiple residues to antigenic variation. Besides, some features (residues on HA protein) in the input layer were observed to take part in multiple active nodes, such as residue 189, 145 and 156, which were also reported to mostly determine the antigenic variation of influenza A(H3N2) viruses. Overall,this work is not only useful for rapidly identifying antigenic variants in influenza prevention, but also an interesting attempt in inferring the mechanisms of biological process through analysis of SAE model, which may give some insights into interpretation of the deep learning