Bearing fault diagnosis based on wavelet sparse convolutional network and acoustic emission compression signals
6
Citation
27
Reference
10
Related Paper
Citation Trend
Abstract:
<abstract> <p>A bearing is an important and easily damaged component of mechanical equipment. For early fault diagnosis of ball bearings, acoustic emission signals are more sensitive and less affected by mechanical background noise. To cope with the large amount of data brought by the high sampling frequency and high sampling points of acoustic emission signals, a compressed sensing processing framework is introduced to research data compression and feature extraction, and a wavelet sparse convolutional network is proposed for resolved diagnosis and evaluation. The main research objective of this paper is to maximize the compression rate of the signal under the constraint of ensuring the reconstruction error of the acoustic emission signal, which can reduce the data volume of the acoustic emission signal and reduce the pressure of data analysis for subsequent fault diagnosis. At the same time, a wide convolution kernel based on a continuous wavelet is introduced when designing the neural network, and the energy information of different frequency bands of the signal is extracted by the wavelet convolution kernel to characterize the fault characteristics of the equipment. The energy pooling layer is designed to enhance the deep mining ability of compressed features, and the regularized loss function is introduced to improve the diagnostic accuracy and robustness through feature sparseness. The experimental results show that the method can effectively extract the fault characteristics of the bearing acoustic emission signal, improve the analysis efficiency and accurately classify the bearing faults.</p> </abstract>Keywords:
Acoustic Emission
Robustness
Kernel (algebra)
This paper presents a novel scheme for feature extraction for face recognition by fusing local and global discriminant features. The facial changes due to variations of pose, illumination, expression, etc. are often appeared only some regions of the whole face image. Therefore, global features extracted from the whole image fail to cope with these variations. To address these problems, face images are divided into a number of non-overlapping sub-images and then G-2DFLD method is applied to each of these sub-images as well as to the whole image to extract local and global discriminant features, respectively. The G-2DFLD method is found to be superior to other appearance-based methods for feature extraction. All these extracted local and global discriminant features are then fused to get a large feature vector. Its dimensionality is then reduced by the PCA technique to decrease overall complexity of the system. A multi-class SVM is used as a classifier for recognition based on these reduced features. The proposed method was evaluated on two popular face recognition databases, the AT&T (formerly ORL) and the UMIST face databases. The experimental results show that the new method outperforms the global features extracted by the PCA, 2DPCA, PCA+FLD, 2DFLD and G-2DFLD methods in terms of face recognition.
Feature (linguistics)
Cite
Citations (9)
Recently, the capability of deep learning-based approaches, especially deep convolutional neural networks (CNNs), has been investigated for hyperspectral remote sensing feature extraction (FE) and classification. Due to the large number of learnable parameters in convolutional filters, lots of training samples are needed in deep CNNs to avoid the overfitting problem. On the other hand, Gabor filtering can effectively extract spatial information including edges and textures, which may reduce the FE burden of the CNNs. In this letter, in order to make the most of deep CNN and Gabor filtering, a new strategy, which combines Gabor filters with convolutional filters, is proposed for hyperspectral image classification to mitigate the problem of overfitting. The obtained results reveal that the proposed model provides competitive results in terms of classification accuracy, especially when only a limited number of training samples are available.
Overfitting
Contextual image classification
Gabor filter
Cite
Citations (234)
Feature extraction, discriminant analysis, and classification rules are three crucial issues for face recognition. We present hybrid approaches to handle three issues together. For feature extraction, we apply the multiresolution wavelet transform to extract the waveletface. We also perform the linear discriminant analysis on waveletfaces to reinforce discriminant power. During classification, the nearest feature plane (NFP) and nearest feature space (NFS) classifiers are explored for robust decisions in presence of wide facial variations. Their relationships to conventional nearest neighbor and nearest feature line classifiers are demonstrated. In the experiments, the discriminant waveletface incorporated with the NFS classifier achieves the best face recognition performance.
Feature vector
Feature (linguistics)
Cite
Citations (460)
The classification of defects is highly demanded for automated inspection of textile products. In this paper, a new method for textile defect classification is proposed by using discriminative wavelet frames. Multiscale texture properties of textile image are characterized by its wavelet frames representation. For a better description of the latent structure of textile image, wavelet frames adapted to textile are generated rather than using standard ones. Based on discriminative feature extraction (DFE) method, the wavelet frames and the back-end classifier are simultaneously designed with the common objective of minimizing classification errors. The proposed method has been evaluated on the classification of 466 defect samples containing eight classes of textile defects, and 434 nondefect samples. In comparison with standard wavelet frames, the designed discriminative wavelet frames has been shown to largely improve the classification performance, where 95.8% classification accuracy was achieved.
Discriminative model
Contextual image classification
Cite
Citations (9)
Face recognition has been extensively studied by many scholars in the recent decades. Local binary pattern (LBP) is one of the most popular local descriptors and has been widely applied to face recognition. Wavelet transform is also more and more active in the field of pattern recognition. In this paper, a novel feature extraction method is proposed to overcome illumination influence. First, a given face image is processed by the LBP operator, and an LBP image is obtained. Second, wavelet transform is used to extract discriminant feature from the LBP image. The experiment results on LFW, Extended YaleB and CMU-PIE face databases show that the proposed method outperforms several popular face recognition methods, and the preprocessing step plays an important role to extract effective features for classification.
Local Binary Patterns
Feature (linguistics)
Cite
Citations (6)
NMF and FLD based feature extraction with application to Synthetic Aperture Radar target recognition
Feature extraction is a very important step in Synthetic Aperture Radar automatic target recognition (SAR ATR). In this paper, a feature extraction procedure based on the nonnegative matrix factorization (NMF) and Fisher linear discriminant (FLD) analysis is proposed for target recognition in SAR images. Firstly, segmented SAR images are processed by the NMF algorithm, which can extract nonnegative features that contain the local spatial structure information of targets. Then the FLD method is applied to the extracted features, thus the discriminability of the features can be enhanced. Both the spatial locality and separability between classes are enforced by this two-phase feature extracting procedure. Finally, the obtained features are used for automatic target recognition. Compared to several other methods, experimental results show the effectiveness of the proposed method for target feature extraction and recognition in SAR images.
Non-negative Matrix Factorization
Automatic Target Recognition
Feature (linguistics)
Cite
Citations (8)
Pedestrian detection continues to hold a significant role in the concept, analysis and function of computer vision. Deep learning techniques in pedestrian detection have demonstrated powerful results in recent experiments and research. In this paper a powerful deep learning technique of R-CNN is evaluated for Pedestrian detection on two different pedestrian detection datasets. The experiment involves the use of a deep learning feature extraction model along with the R-CNN detector. The deep learning feature extraction used is the Alexnet. Transfer learning is performed on the feature extraction model to adjust the weights of the convolutional neural networks to favour classification on the selected datasets. The R-CNN detector is then trained on the deep learning feature extraction model for pedestrian detection. The results of the experiments as evidently demonstrated, indicate some important truths about the performance of R-CNN detector on varying datasets.
Pedestrian detection
Transfer of learning
Feature (linguistics)
Feature Learning
Cite
Citations (25)
2022 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) (2022)
Convolutional neural network has a very important role in feature extraction, with stronger feature learning and feature expression ability. Therefore, to address the lack of robustness of sparse representation and the changes of environment and age in the face feature classification, at the feature level, this paper studies the convolutional neural network. We proposed a face feature extraction method based on convolutional neural network and then face classification using sparse representation. This method combines convolutional neural network extraction and sparse representation, taking full advantages of convolutional neural network in deep feature extraction and sparse representation in face feature recognition classification. The experimental results show that acquiring features through the convolutional neural network can represent faces linearly, which is more robust, and satisfies the assumption conditions of the face classification method based on sparse representation. The final experimental results show that the proposed face classification method is 9%~20% higher than the traditional feature extraction method.
Robustness
Feature (linguistics)
Representation
Cite
Citations (1)
Abstract Whenever a visual scene is cast onto the retina, much of it will appear degraded due to poor resolution in the periphery; moreover, optical defocus can cause blur in central vision. However, the pervasiveness of blurry or degraded input is typically overlooked in the training of convolutional neural networks (CNNs). We hypothesized that the absence of blurry training inputs may cause CNNs to rely excessively on high spatial frequency information for object recognition, thereby causing systematic deviations from biological vision. We evaluated this hypothesis by comparing standard CNNs with CNNs trained on a combination of clear and blurry images. We show that blur-trained CNNs outperform standard CNNs at predicting neural responses to objects across a variety of viewing conditions. Moreover, blur-trained CNNs acquire increased sensitivity to shape information and greater robustness to multiple forms of visual noise, leading to improved correspondence with human perception. Our results provide novel neurocomputational evidence that blurry visual experiences are very important for conferring robustness to biological visual systems.
Robustness
Cite
Citations (2)
Handwritten character recognition of Devanagari script is an area of research in the field of pattern recognition. Feature extraction is crucially significant step in recognition system. In handwritten optical character recognition, the size of feature vectors is very high. By reducing image size, the dimension of feature vectors can be reduced but this also reduces the pixel information. This paper focus on the improvement in performance of recognition system using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). In proposed system, first raw features are extracted using three different feature extraction methods: chain coding, edge detection using gradient features and direction feature techniques, which are reduced by LDA and characters are classified using SVM classifier.
Devanagari
Feature (linguistics)
Feature vector
Cite
Citations (8)