Search

Limited-angle CT is a challenging problem in real applications. Incomplete projection data will lead to severe artifacts and distortions in reconstruction images. To tackle this problem, we propose a novel reconstruction framework termed Deep Iterative Optimization-based Residual-learning (DIOR) for limited-angle CT. Instead of directly deploying the regularization term on image space, the DIOR combines iterative optimization and deep learning based on the residual domain, significantly improving the convergence property and generalization ability. Specifically, the asymmetric convolutional modules are adopted to strengthen the feature extraction capacity in smooth regions for deep priors. Besides, in our DIOR method, the information contained in low-frequency and high-frequency components is also evaluated by perceptual loss to improve the performance in tissue preservation. Both simulated and clinical datasets are performed to validate the performance of DIOR. Compared with existing competitive algorithms, quantitative and qualitative results show that the proposed method brings a promising improvement in artifact removal, detail restoration and edge preservation. [ABSTRACT FROM AUTHOR]

Clustering electric load curves is an important part of the load data mining process. In this paper, we propose a clustering algorithm by combining singular value decomposition and KICIC clustering algorithm (SVD-KICIC) for analyzing the characteristics of daily load curves to mitigate some of the traditional clustering algorithm problems, such as only considering intra-class distance and low computational efficiency when dealing with massive load data. Our method identifies effective daily load curve characteristics using the singular value decomposition technique to improve dimensionality reduction, which improves low computational efficiency by reducing the number of dimensions inherent in big data. Additionally, the method performs SVD on the load data to obtain singular values for determination of weight of the KICIC algorithm, which leverages intra-class and inter-class distances of the load data and further improves the computational efficiency of the algorithm. Finally, we perform a series of simulations of actual load curves from a certain city to validate that the algorithm proposed in this paper has a short operation time, high clustering quality, and solid robustness that improves the clustering performance of the load curves. [ABSTRACT FROM AUTHOR]