scispace - formally typeset
Search or ask a question
Institution

Nanjing University of Information Science and Technology

EducationNanjing, China
About: Nanjing University of Information Science and Technology is a education organization based out in Nanjing, China. It is known for research contribution in the topics: Precipitation & Aerosol. The organization has 14129 authors who have published 17985 publications receiving 267578 citations. The organization is also known as: Nan Xin Da.


Papers
More filters
Journal ArticleDOI
TL;DR: Wang et al. as discussed by the authors proposed a sequence-based recurrent neural network (RNN) for hyperspectral image classification, which makes use of a newly proposed activation function, parametric rectified tanh (PRetanh), instead of the popular tanh or rectified linear unit.
Abstract: In recent years, vector-based machine learning algorithms, such as random forests, support vector machines, and 1-D convolutional neural networks, have shown promising results in hyperspectral image classification. Such methodologies, nevertheless, can lead to information loss in representing hyperspectral pixels, which intrinsically have a sequence-based data structure. A recurrent neural network (RNN), an important branch of the deep learning family, is mainly designed to handle sequential data. Can sequence-based RNN be an effective method of hyperspectral image classification? In this paper, we propose a novel RNN model that can effectively analyze hyperspectral pixels as sequential data and then determine information categories via network reasoning. As far as we know, this is the first time that an RNN framework has been proposed for hyperspectral image classification. Specifically, our RNN makes use of a newly proposed activation function, parametric rectified tanh (PRetanh), for hyperspectral sequential data analysis instead of the popular tanh or rectified linear unit. The proposed activation function makes it possible to use fairly high learning rates without the risk of divergence during the training procedure. Moreover, a modified gated recurrent unit, which uses PRetanh for hidden representation, is adopted to construct the recurrent layer in our network to efficiently process hyperspectral data and reduce the total number of parameters. Experimental results on three airborne hyperspectral images suggest competitive performance in the proposed mode. In addition, the proposed network architecture opens a new window for future research, showcasing the huge potential of deep recurrent networks for hyperspectral data analysis.

560 citations

Journal ArticleDOI
TL;DR: In this article, model projections of tropical cyclone activity response to anthropogenic warming in climate models are assessed and observations, theory, and models, with increasing robustness, indicate that tropical cyclones respond well to global warming.
Abstract: Model projections of tropical cyclone (TC) activity response to anthropogenic warming in climate models are assessed. Observations, theory, and models, with increasing robustness, indicate ...

536 citations

Journal ArticleDOI
01 Sep 2019-Nature
TL;DR: It is shown that a statistical forecast model employing a deep-learning approach produces skilful ENSO forecasts for lead times of up to one and a half years, overcoming a weakness of dynamical forecast models.
Abstract: Variations in the El Nino/Southern Oscillation (ENSO) are associated with a wide array of regional climate extremes and ecosystem impacts1. Robust, long-lead forecasts would therefore be valuable for managing policy responses. But despite decades of effort, forecasting ENSO events at lead times of more than one year remains problematic2. Here we show that a statistical forecast model employing a deep-learning approach produces skilful ENSO forecasts for lead times of up to one and a half years. To circumvent the limited amount of observation data, we use transfer learning to train a convolutional neural network (CNN) first on historical simulations3 and subsequently on reanalysis from 1871 to 1973. During the validation period from 1984 to 2017, the all-season correlation skill of the Nino3.4 index of the CNN model is much higher than those of current state-of-the-art dynamical forecast systems. The CNN model is also better at predicting the detailed zonal distribution of sea surface temperatures, overcoming a weakness of dynamical forecast models. A heat map analysis indicates that the CNN model predicts ENSO events using physically reasonable precursors. The CNN model is thus a powerful tool for both the prediction of ENSO events and for the analysis of their associated complex mechanisms.

531 citations

Journal ArticleDOI
TL;DR: A simple yet effective and efficient tracking algorithm with an appearance model based on features extracted from a multiscale image feature space with dataindependent basis that performs favorably against state-of-the-art methods on challenging sequences in terms of efficiency, accuracy and robustness.
Abstract: It is a challenging task to develop effective and efficient appearance models for robust object tracking due to factors such as pose variation, illumination change, occlusion, and motion blur. Existing online tracking algorithms often update models with samples from observations in recent frames. Despite much success has been demonstrated, numerous issues remain to be addressed. First, while these adaptive appearance models are data-dependent, there does not exist sufficient amount of data for online algorithms to learn at the outset. Second, online tracking algorithms often encounter the drift problems. As a result of self-taught learning, misaligned samples are likely to be added and degrade the appearance models. In this paper, we propose a simple yet effective and efficient tracking algorithm with an appearance model based on features extracted from a multiscale image feature space with data-independent basis. The proposed appearance model employs non-adaptive random projections that preserve the structure of the image feature space of objects. A very sparse measurement matrix is constructed to efficiently extract the features for the appearance model. We compress sample images of the foreground target and the background using the same sparse measurement matrix. The tracking task is formulated as a binary classification via a naive Bayes classifier with online update in the compressed domain. A coarse-to-fine search strategy is adopted to further reduce the computational complexity in the detection procedure. The proposed compressive tracking algorithm runs in real-time and performs favorably against state-of-the-art methods on challenging sequences in terms of efficiency, accuracy and robustness.

520 citations

Journal ArticleDOI
TL;DR: In this article, a novel bifunctional electrode consisting of two monolayer thick manganese dioxide (δ-MnO2) nanosheet arrays on a nickel foam, using a novel in-situ method was developed.
Abstract: Recently, defect engineering has been used to intruduce half-metallicity into selected semiconductors, thereby significantly enhancing their electrical conductivity and catalytic/electrocatalytic performance. Taking inspiration from this, we developed a novel bifunctional electrode consisting of two monolayer thick manganese dioxide (δ-MnO2) nanosheet arrays on a nickel foam, using a novel in-situ method. The bifunctional electrode exposes numerous active sites for electrocatalytic rections and displays excellent electrical conductivity, resulting in strong performance for both HER and OER. Based on detailed structure analysis and density functional theory (DFT) calculations, the remarkably OER and HER activity of the bifunctional electrode can be attributed to the ultrathin δ-MnO2 nanosheets containing abundant oxygen vacancies lead to the formation od Mn3+ active sites, which give rise to half-metallicity properties and strong H2O adsorption. This synthetic strategy introduced here represents a new method for the development of non-precious metal Mn-based electrocatalysts for eddicient energy conversion.

509 citations


Authors

Showing all 14448 results

NameH-indexPapersCitations
Ashok Kumar1515654164086
Lei Zhang135224099365
Bin Wang126222674364
Shuicheng Yan12381066192
Zeshui Xu11375248543
Xiaoming Li113193272445
Qiang Yang112111771540
Yan Zhang107241057758
Fei Wang107182453587
Yongfa Zhu10535533765
James C. McWilliams10453547577
Zhi-Hua Zhou10262652850
Tao Li102248360947
Lei Liu98204151163
Jian Feng Ma9730532310
Network Information
Related Institutions (5)
Chinese Academy of Sciences
634.8K papers, 14.8M citations

90% related

University of Science and Technology of China
101K papers, 2.4M citations

88% related

City University of Hong Kong
60.1K papers, 1.7M citations

88% related

Harbin Institute of Technology
109.2K papers, 1.6M citations

88% related

Nanjing University
105.5K papers, 2.2M citations

87% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
2023173
2022552
20213,000
20202,492
20192,221
20181,822