In the multi-view multi-label (MVML) classification problem, multiple views are simultaneously associated with multiple semantic representations. Multi-view multi-label learning inevitably has the problems of consistency, diversity, and non-alignment among views and the correlation among labels. Most of the existing multi-view multi-label methods for non-aligned views assume that each view has a common or shared label set, but because a single view cannot contain the entire label information, they often learn suboptimal results. Based on this, this paper proposes a non-aligned multi-view multi-label classification method that learns view-specific labels (LVSL), aiming to explicitly mine the information of view-specific labels and low-rank label structures in non-aligned views in a unified model framework. Furthermore, to alleviate insufficient available label information, we thoroughly explored the global and local structural information among labels. Specifically, first, we assume that there is structural consistency between the view and the label space and then construct the view-specific label model in turn. Second, to enrich the original label space information, we mine the consistent information of multiple views and the low-rank correlation information hidden among multiple labels. Finally, the contribution weight of each view is combined with learning the complementary information among the views in the decision-making stage, and extend the model to handle nonlinear data. The results of the proposed method compared with existing state-of-the-art algorithms on several datasets validate its effectiveness.
22 March 2021 in IEEE Transactions on Instrumentation and Measurement
Bearing is one of the most important transmission components and breaks down more frequently than other parts in rotating equipment. The state detection of the bearing has a great significance for their working performance and safety in industrial production. In this article, we propose a very effective fault diagnosis algorithm based on clustering and sparse representation for rolling bearing. To obtain a robust cluster center for the acquired noisy samples, the samples are first clustered by using their frequency spectrums instead of directly in time-domain waveforms. Then, for each class of samples, an adaptive redundant dictionary is trained over residuals between the original frequency spectrums and their component projected on the calculated cluster center. The noise contained in a test sample is reduced by performing sparse coding and representation with the trained dictionary. Finally, the test sample belonging to a specific category is identified by selecting the maximum cosine similarity value between the reconstructed sample and cluster centers. Experimental results show that the proposed algorithm performs well on both simulated signals and real signals and exhibits advantages over other fault diagnosis methods in terms of diagnosis accuracy.
Infrared and visible image fusion can combine the thermal radiation information of infrared images with the detail information of visible images to generate images that are more suitable for human perception and machine processing. In this paper, a novel infrared and visible image fusion method is proposed, which can sufficiently preserve infrared target information by multi-threshold segmentation based on maximum entropy. Meanwhile, a retinex-based brightness correction method is used for visible image enhancement, which can adaptively enhance the brightness and contrast of low-light images. Futhermore, to make the proposed method more robust, the weighting coefficients are determined by optimization using the modified structural similarity as the objective function. The proposed method is compared with seven state-of-the-art methods on publicly available datasets, and the experimental results demonstrate that our method achieves better performances in both quantitative evaluation and visual effects.
Infrared and visible image fusion is a hot research direction in the fields of computer vision and image processing, and it is a common multimodal image fusion. An effective image fusion algorithm via convolutional sparse representation (CSR) and guided filtering is proposed for fusing infrared and visible images in this paper. First, a series of dictionary filters are trained by the CSR strategy, and the smooth image component and detailed image component are obtained by classifying those filters into high-pass filters and low-pass filters. Then two rules are designed to fuse the smooth image component and detailed image component, respectively. For the detailed image component, a weight construction method based on guided filtering is designed to get the weight maps, and the smooth image component is fused by applying the “choose-max” strategy to the corresponding sparse coefficients. Finally, the fused image is obtained by combining the fused smooth image component and detailed image component. Experimental results show that the proposed algorithm achieves good fusion results and exhibits advantages over comparison image fusion methods.
Identification and diagnosis of the incipient fault in electromechanical systems is a challenging task due to its weakness and concealment on magnitude. The one-step signal decomposition method has more or less the problem of losing fault feature information because of over or under decomposition issues. In this paper, a novel diagnosis method is proposed for incipient fault identification via a new algorithm called joint adaptive signal decomposition (JASD). The joint algorithm benefits from the narrow-band signal decomposition superiority of variational mode decomposition (VMD) and the non-stationary signal processing ability of adaptive chirp mode decomposition (ACMD), which greatly enhances the capacity to extract the incipient fault components from vibration signal. Meanwhile, a new index called Integration Kurtosis which covers comprehensive feature of the fault is designed to achieve synchronous parameters optimization of the joint algorithm. In the diagnosis scheme, the parameter-optimized VMD is firstly utilized to reconstruct the original signal by selecting the most relevant modes, and the secondary decomposition of the new signal is conducted by the parameter-optimized ACMD. Then, the feature of the incipient fault can be extracted sufficiently by analyzing the envelope spectrum of the decomposed sub-component modes. Finally, both numerical simulations and real signal experimental results validate the effectiveness and reliability of the proposed JASD fault diagnosis method.
Conducting fault diagnosis to bearing is of great significance to ensure their stable working and reduce economic losses of equipment in industrial manufacturing. However, the existing methods are not accurate enough to detect fault frequency in real operating conditions affected by noise. To detect the fault frequency more accurately, in this paper, a novel fault diagnosis algorithm is proposed by using convolutional sparse representation under the non-local similarity of vibration signal. Firstly, the denoised similar subblocks is collected in non-local region with correlation coefficient to speed up the training process of adaptive filters and reconstruct the original signal more closely. Secondly, to remove noise contained in each component, a denoising algorithm based on adaptive threshold is employed to shrink the coefficients of each component decomposed by convolutional sparse representation. Then, a measure function indicating the activity of fault frequency is designed to select the optimal signal subband which contains the main fault information. Finally, the envelope spectrum is calculated to detect the fault frequency. In order to verify the performance of the proposed algorithm, we conduct a series of experiments on two public datasets and one real collected data, and compare the results with some state-of-the-art fault diagnosis algorithms. Experimental results show that the proposed algorithm can accurately detect the fault frequency of rolling bearings and its harmonics and exhibits advantages in fault frequency detection compared with other fault diagnosis methods.