Institution
Sichuan University
Education•Chengdu, China•
About: Sichuan University is a education organization based out in Chengdu, China. It is known for research contribution in the topics: Catalysis & Population. The organization has 107623 authors who have published 102844 publications receiving 1612131 citations. The organization is also known as: Sìchuān Dàxué.
Topics: Catalysis, Population, Medicine, Cancer, Chemistry
Papers published on a yearly basis
Papers
More filters
••
TL;DR: The definition and basic properties of the different types of fuzzy sets that have appeared up to now in the literature are reviewed and the relationships between them are analyzed.
Abstract: In this paper, we review the definition and basic properties of the different types of fuzzy sets that have appeared up to now in the literature. We also analyze the relationships between them and enumerate some of the applications in which they have been used.
386 citations
•
TL;DR: Zhang et al. as discussed by the authors proposed an image super-resolution feedback network (SRFBN) to refine low-level representations with high-level information, which uses hidden states in an RNN with constraints to achieve such feedback manner.
Abstract: Recent advances in image super-resolution (SR) explored the power of deep learning to achieve a better reconstruction performance. However, the feedback mechanism, which commonly exists in human visual system, has not been fully exploited in existing deep learning based image SR methods. In this paper, we propose an image super-resolution feedback network (SRFBN) to refine low-level representations with high-level information. Specifically, we use hidden states in an RNN with constraints to achieve such feedback manner. A feedback block is designed to handle the feedback connections and to generate powerful high-level representations. The proposed SRFBN comes with a strong early reconstruction ability and can create the final high-resolution image step by step. In addition, we introduce a curriculum learning strategy to make the network well suitable for more complicated tasks, where the low-resolution images are corrupted by multiple types of degradation. Extensive experimental results demonstrate the superiority of the proposed SRFBN in comparison with the state-of-the-art methods. Code is avaliable at this https URL.
386 citations
••
TL;DR: This article proposes an automatic CNN architecture design method by using genetic algorithms, to effectively address the image classification tasks and shows the very comparable classification accuracy to the best one from manually designed and automatic + manually tuning CNNs, while consuming fewer computational resources.
Abstract: Convolutional neural networks (CNNs) have gained remarkable success on many image classification tasks in recent years. However, the performance of CNNs highly relies upon their architectures. For the most state-of-the-art CNNs, their architectures are often manually designed with expertise in both CNNs and the investigated problems. Therefore, it is difficult for users, who have no extended expertise in CNNs, to design optimal CNN architectures for their own image classification problems of interest. In this article, we propose an automatic CNN architecture design method by using genetic algorithms, to effectively address the image classification tasks. The most merit of the proposed algorithm remains in its “automatic” characteristic that users do not need domain knowledge of CNNs when using the proposed algorithm, while they can still obtain a promising CNN architecture for the given images. The proposed algorithm is validated on widely used benchmark image classification datasets, compared to the state-of-the-art peer competitors covering eight manually designed CNNs, seven automatic + manually tuning, and five automatic CNN architecture design algorithms. The experimental results indicate the proposed algorithm outperforms the existing automatic CNN architecture design algorithms in terms of classification accuracy, parameter numbers, and consumed computational resources. The proposed algorithm also shows the very comparable classification accuracy to the best one from manually designed and automatic + manually tuning CNNs, while consuming fewer computational resources.
385 citations
••
TL;DR: In this article, a discrete fractional logistic map is proposed in the left Caputo discrete delta sense, which holds discrete memory, and the bifurcation diagrams are given and the chaotic behaviors are numerically illustrated.
Abstract: A discrete fractional logistic map is proposed in the left Caputo discrete delta’s sense. The new model holds discrete memory. The bifurcation diagrams are given and the chaotic behaviors are numerically illustrated.
385 citations
••
TL;DR: The results demonstrate that the NiCo2S4@PPy-50 core-shell heterostructure nanotube array is promising as electrode material for supercapacitors in energy storage.
Abstract: In this paper, a hierarchical NiCo2S4@polypyrrole core–shell heterostructure nanotube array on Ni foam (NiCo2S4@PPy/NF) was successfully developed as a bind-free electrode for supercapacitors. NiCo2S4@PPy-50/NF obtained under 50 s PPy electrodeposition shows a low charge-transfer resistance (0.31 Ω) and a high area specific capacitance of 9.781 F/cm2 at a current density of 5 mA/cm2, which is two times higher than that of pristine NiCo2S4/NF (4.255 F/cm2). Furthermore, an asymmetric supercapacitor was assembled using NiCo2S4@PPy-50/NF as positive electrode and activated carbon (AC) as negative electrode. The resulting NiCo2S4@PPy-50/NF//AC device exhibits a high energy density of 34.62 Wh/kg at a power density of 120.19 W/kg with good cycling performance (80.64% of the initial capacitance retention at 50 mA/cm2 over 2500 cycles). The superior electrochemical performance can be attributed to the combined contribution of both component and unique core–shell heterostructure. The results demonstrate that the ...
383 citations
Authors
Showing all 108474 results
Name | H-index | Papers | Citations |
---|---|---|---|
Jie Zhang | 178 | 4857 | 221720 |
Robin M. Murray | 171 | 1539 | 116362 |
Xiang Zhang | 154 | 1733 | 117576 |
Rui Zhang | 151 | 2625 | 107917 |
Xiaoyuan Chen | 149 | 994 | 89870 |
Yi Yang | 143 | 2456 | 92268 |
Xinliang Feng | 134 | 721 | 73033 |
Chuan He | 130 | 584 | 66438 |
Lei Zhang | 130 | 2312 | 86950 |
Jian Zhou | 128 | 3007 | 91402 |
Shaobin Wang | 126 | 872 | 52463 |
Yi Xie | 126 | 745 | 62970 |
Pak C. Sham | 124 | 866 | 100601 |
Wei Chen | 122 | 1946 | 89460 |
Bo Wang | 119 | 2905 | 84863 |