Hyperspectral unmixing is a critical step to process hyperspectral images (HSIs). Nonnegative matrix factorization (NMF) has drawn extensive attention in remotely sensed hyperspectral unmixing since it does not require prior knowledge about the pure spectral constituents (endmembers) in the scene. However, this approach is normally implemented as a single-layer procedure, which does not allow for a refinement of the obtained endmember abundances. In addition, HSIs suffer from the interference of sparse noise (besides Gaussian noise), which brings challenges when pursuing efficient hyperspectral unmixing. To address these issues, we propose a new self-supervised robust deep matrix factorization (SSRDMF) model for hyperspectral unmixing, which consists of two parts: encoder and decoder . In the encoder , a multilayer nonlinear structure is designed to directly map the observed HSI data to the corresponding abundances. The abundances are then decoded by the decoder , in which the connected weights are treated as the extracted endmembers. By modeling the sparse noise explicitly, the proposed method can reduce the effect caused by both Gaussian and sparse noise. Furthermore, a self-supervised constraint is included for exploring the spectral information, which is beneficial to further improve unmixing performance. To validate our method, we have conducted extensive experiments on both synthetic and real datasets. Our experiments reveal that our newly developed SSRDMF achieves superior unmixing performance compared to other state-of-the-art methods.

The bracing wire is one of the most important components of catenary support devices (CSCs) in the high-speed railway, which is used to connect the messenger wire base and bracing wire hook for stabilizing the contact line receiving current. However, it is prone to a loose defect due to the frequent impact of the pantograph. Therefore, in this article, an automatic defect detection method for catenary bracing wires using computer vision technologies is proposed. First, the catenary images are enhanced through a deep convolutional neural network (CNN) called image-adaptive 3-D LUTs (3-D lookup tables) to make the image more clear and easier to identify. Next, the bracing wire is localized by an angle-based CNN called dynamic anchor learning (DAL), which introduces the angle parameter into the object detection network to make the bracing wire more accurate to localization and easier to follow up failure analysis. Last, bracing wires are detected by the Hough transformation (HT), and based on the peak distribution of HT, a looseness defect criterion of bracing wires is proposed according to the curvature change. Experimental results prove that the proposed method can effectively enhance the catenary images, and the bracing wires are precisely localized, and all the defects of bracing wire components under different conditions accurately.

Parkinson’s disease (PD) is a neurodegenerative disease of the brain associated with motor symptoms. With the maturation of machine learning (ML), especially deep learning, ML has been used to assist in the diagnosis of PD. In this paper, we explore graph neural networks (GNNs) to implement PD prediction using MRI data. However, most existing GNN models suffer from the efficiency of graph construction on MRI data and the problem of overfitting on small data. This paper proposes a novel multi-layer GNN model that incorporates a fast graph construction method and a sparsity-based pooling layer with an attention mechanism. In addition, graph structure sparsity is plugged into the graph pooling layer as prior knowledge to mitigate overfitting in model training. Experimental results on real-world datasets demonstrate the effectiveness of the proposed model and its superiority over baseline methods.