University of Electronic Science and Technology of China

About: University of Electronic Science and Technology of China is a education organization based out in Chengdu, China. It is known for research contribution in the topics: Computer science & Antenna (radio). The organization has 50594 authors who have published 58502 publications receiving 711188 citations. The organization is also known as: UESTC.

An empirical study of classification algorithm evaluation for financial risk prediction

Abstract: A wide range of classification methods have been used for the early detection of financial risks in recent years. How to select an adequate classifier (or set of classifiers) for a given dataset is an important task in financial risk prediction. Previous studies indicate that classifiers' performances in financial risk prediction may vary using different performance measures and under different circumstances. The main goal of this paper is to develop a two-step approach to evaluate classification algorithms for financial risk prediction. It constructs a performance score to measure the performance of classification algorithms and introduces three multiple criteria decision making (MCDM) methods (i.e., TOPSIS, PROMETHEE, and VIKOR) to provide a final ranking of classifiers. An empirical study is designed to assess various classification algorithms over seven real-life credit risk and fraud risk datasets from six countries. The results show that linear logistic, Bayesian Network, and ensemble methods are ranked as the top-three classifiers by TOPSIS, PROMETHEE, and VIKOR. In addition, this work discusses the construction of a knowledge-rich financial risk management process to increase the usefulness of classification results in financial risk detection.

Non-locally Enhanced Encoder-Decoder Network for Single Image De-raining

Abstract: Single image rain streaks removal has recently witnessed substantial progress due to the development of deep convolutional neural networks. However, existing deep learning based methods either focus on the entrance and exit of the network by decomposing the input image into high and low frequency information and employing residual learning to reduce the mapping range, or focus on the introduction of cascaded learning scheme to decompose the task of rain streaks removal into multi-stages. These methods treat the convolutional neural network as an encapsulated end-to-end mapping module without deepening into the rationality and superiority of neural network design. In this paper, we delve into an effective end-to-end neural network structure for stronger feature expression and spatial correlation learning. Specifically, we propose a non-locally enhanced encoder-decoder network framework, which consists of a pooling indices embedded encoder-decoder network to efficiently learn increasingly abstract feature representation for more accurate rain streaks modeling while perfectly preserving the image detail. The proposed encoder-decoder framework is composed of a series of non-locally enhanced dense blocks that are designed to not only fully exploit hierarchical features from all the convolutional layers but also well capture the long-distance dependencies and structural information. Extensive experiments on synthetic and real datasets demonstrate that the proposed method can effectively remove rain-streaks on rainy image of various densities while well preserving the image details, which achieves significant improvements over the recent state-of-the-art methods.

Band structure engineering and defect control of Ta3N5 for efficient photoelectrochemical water oxidation

Abstract: Ta3N5 is a promising photoanode material with a theoretical maximum solar conversion efficiency of 15.9% for photoelectrochemical water splitting. However, the highest applied bias photon-to-current efficiency achieved so far is only 2.72%. To bridge the efficiency gap, effective carrier management strategies for Ta3N5 photoanodes should be developed. Here, we propose to use gradient Mg doping for band structure engineering and defect control of Ta3N5. The gradient Mg doping profile in Ta3N5 induces a gradient of the band edge energetics, which greatly enhances the charge separation efficiency. Furthermore, defect-related recombination is significantly suppressed due to the passivation effect of Mg dopants on deep-level defects and, more importantly, the matching of the gradient Mg doping profile with the distribution of defects within Ta3N5. As a result, a photoanode based on the gradient Mg-doped Ta3N5 delivers a low onset potential of 0.4 V versus that of a reversible hydrogen electrode and a high applied bias photon-to-current efficiency of 3.25 ± 0.05%. Despite the efforts to tune their properties, the efficiency of tantalum nitride photoanodes falls short of the theoretical value. Here, a gradient Mg doping strategy is introduced to engineer tantalum nitride’s band structure and control its defects, leading to an applied bias photon-to-current efficiency of 3.25%.

Identifying a set of influential spreaders in complex networks

Abstract: Identifying a set of influential spreaders in complex networks plays a crucial role in effective information spreading. A simple strategy is to choose top-r ranked nodes as spreaders according to influence ranking method such as PageRank, ClusterRank and k-shell decomposition. Besides, some heuristic methods such as hill-climbing, SPIN, degree discount and independent set based are also proposed. However, these approaches suffer from a possibility that some spreaders are so close together that they overlap sphere of influence or time consuming. In this report, we present a simply yet effectively iterative method named VoteRank to identify a set of decentralized spreaders with the best spreading ability. In this approach, all nodes vote in a spreader in each turn, and the voting ability of neighbors of elected spreader will be decreased in subsequent turn. Experimental results on four real networks show that under Susceptible-Infected-Recovered (SIR) and Susceptible-Infected (SI) models, VoteRank outperforms the traditional benchmark methods on both spreading rate and final affected scale. What's more, VoteRank has superior computational efficiency.