检索结果-内蒙古大学图书馆

An Image Denoising Method Based on Deep Residual GAN

Journal of Physics: Conference Series 2020年第3期1550卷

作者： Ziyuan Wang Lidan Wang Shukai Duan Yunfei Li Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing 400715 China Schoolof Electronic and information engineering Southwest University Chongqing400715 China College of Artificiall Intelligence Southwest University Chongqing 400715 China Braininspired Computing & Intelligent Control of Chongqing Key Lab Chongqing 400715 China National & Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing 400715 China Chongqing Brain Science Collaborative Innovation Center Chongqing 400715 China

As people come into contact with image data more often, high quality and clear images attract more attention. Many methods have been proposed to deal with image noise problem including deep learning (DL). However most of them is lack of capability when customers want more perceptual details of the image without information loss. In this paper, a deep residual network based on generative adversarial (GAN) network was proposed to complete the image denoising mission. Firstly, a generative-adversarial network structure based on residual blocks was designed. Secondly, a refined loss function was given to train the GAN network. The well designed loss function can help the generated image to be very close to the clear counterpart (ground truth) while enhancing more details in colours and brightness. Finally, extensive experiments show that our network is not only convincing for images denoising, but also effective for other image process tasks, such as image defogging, medical CT denoising etc., presenting impressive and competitive effects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recommendation in heterogeneous information network via dual similarity regularization

引用

International Journal of Data science and Analytics 2017年第1期3卷 35-48页

作者： Zheng, Jing Liu, Jian Shi, Chuan Zhuang, Fuzhen Li, Jingzhi Wu, Bin Beijing Key Lab of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Southern University of Science and Technology Shenzhen China

Recommender system has caught much attention from multiple disciplines, and many techniques are proposed to build it. Recently, social recommendation becomes a hot research direction. The social recommendation methods tend to leverage social relations among users obtained from social network to alleviate data sparsity and cold-start problems in recommender systems. It employs simple similarity information of users as social regularization on users. Unfortunately, the widely used social regularization suffers from several aspects: (1) The similarity information of users only stems from social relations of related users;(2) it only has constraint on users without considering the impact of items for recommendation;(3) it may not work well for dissimilar users. To overcome the shortcomings of social regularization, we design a novel dual similarity regularization to impose the constraint on users and items with high and low similarities simultaneously. With the dual similarity regularization, we further propose an optimization function to integrate the similarity information of users and items under different semantic meta-paths, and a gradient descend solution is derived to optimize the objective function. Experiments with different meta-paths validate the superiority of integrating much available information, and the experiments conducted on three real data sets validate the effectiveness of the proposed solution. © 2016, Springer International Publishing Switzerland.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Self-Evolutionary Neuron Model for Fast-Response Spiking Neural Networks

TechRxiv

引用

TechRxiv 2019年

作者： Zhang, Anguo Han, Ying Hu, Jing Niu, Yuzhen Gao, Yueming Chen, Zhizhang Zhao, Kai College of Physics and Information Engineering Fuzhou University Fujian350108 China The Key Laboratory of Medical Instrumentation Pharmaceutical Technology of Fujian Province Fuzhou350116 China Research Institute of Ruijie Ruijie Networks Co. Ltd Fujian350002 China School of Public Health Xiamen University Xiamen361102 China College of Information and Intelligent Transportation Fujian Chuanzheng Communications College Fuzhou350007 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Mathematics and Computer Science Fuzhou University The Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fujian350108 China College of Physics and information Engineering Fuzhou University the Key Laboratory of Medical Instrumentation Pharmaceutical Technology of Fujian Province Fujian350108 China College of Physics and Information Engineering Fuzhou University 350108 China Faculty of Science and Technology University of Macau 999078 China

We propose two simple and effective spiking neuron models to improve the response time of the conventional spiking neural network. The proposed neuron models adaptively tune the presynaptic input current depending on the input received from its presynapses and subsequent neuron firing events. We analyze and derive the firing activity homeostatic convergence of the proposed models. We experimentally verify and compare the models on MNIST handwritten digits and FashionMNIST classification tasks. We show that the proposed neuron models significantly increase the response speed to the input signal. Experiment codes are available at https://***/anvien/Evol-SNN. © 2019, CC0.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Fog computing: Concept, Applications and Future

Fog Computing: Concept, Applications and Future

引用

International Conference on Cloud computing, Big Data and Blockchain (ICCBB)

作者： Xianghan Zheng Wei Wu Chunming Rong Tao Zhang Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Department of Computer Science and Electronic Engineering University of Stavanger Stavanger Norway College of Mathematics and Computer Science Fuzhou University Fuzhou China

ISBN: (纸本)9781728112787

Recently, both academia and industry have initiated research projects directed on fog computing. Fog computing is not composed of a powerful server, but by the relatively weak and scattered computers, processing appliances, factories, cars, street lamps and other equipment data. In this paper, we survey fog computing recently both in the academic and industrial research. We introduce it and consider case study that include In-vehicle Network, NextGen Manufacturing, Wireless sensor network, and technical challenges. Our survey is based on recent research publications..

关键词： cloud computing Cloud computing street light industrial research research project OTHER EQUIPMENT

来源：评论

学校读者我要写书评

暂无评论

POSTER: STAR (Space-Time Adaptive and Reductive) Algorithms for Real-World Space-Time Optimality

引用

ACM SIGPLAN Notices 2017年第8期52卷 455-456页

作者： Tang, Yuan You, Ronghui School of Computer Science School of Software Fudan University Shanghai Key Lab. of Intelligent Information Processing State Key Lab. of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China

It's important to hit a space-time balance for a real-world algorithm to achieve high performance on modern shared-memory multi-core or many-core systems. However, a large class of dynamic programs with more than $O(1)$ dependency achieve optimality either in space or time, but not both. In the literature, the problem is known as the fundamental space-time tradeoff. By exploiting properly on the runtime system, we show that our STAR (Space-Time Adaptive and Reductive) technique can help these dynamic programs to achieve sublinear parallel time bounds while still maintaining work-, space-, and cache-optimality in a processor- and cache-oblivious fashion. © 2017 ACM.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Brain EEG time series selection: A novel graph-based approach for classification

arXiv

引用

arXiv 2018年

作者： Dai, Chenglong Wu, Jia Pi, Dechang Cui, Lin Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China Department of Computing Macquarie University NSW2109 Australia Intelligent Information Processing Laboratory Suzhou University Suzhou234000 China

Brain Electroencephalography (EEG) classification is widely applied to analyze cerebral diseases in recent years. Unfortunately, invalid/noisy EEGs degrade the diagnosis performance and most previously developed methods ignore the necessity of EEG selection for classification. To this end, this paper proposes a novel maximum weight clique-based EEG selection approach, named mwcEEGs, to map EEG selection to searching maximum similarity-weighted cliques from an improved Fréchet distance-weighted undirected EEG graph simultaneously considering edge weights and vertex weights. Our mwcEEGs improves the classification performance by selecting intra-clique pairwise similar and inter-clique discriminative EEGs with similarity threshold δ. Experimental results demonstrate the algorithm effectiveness compared with the state-of-the-art time series selection algorithms on real-world EEG datasets. Copyright © 2018, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Nonlinearity in the dark: Broadband terahertz generation with extremely high efficiency

arXiv

引用

arXiv 2019年

作者： Fang, Ming Shen, Nian-Hai Sha, Wei E.I. Huang, Zhixiang Koschny, Thomas Soukoulis, Costas M. Ames Laboratory U.S. DOE and Department of Physics and Astronomy Iowa State University AmesIA50011 United States Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230039 China Key Laboratory of Micro-nano Electronic Devices and Smart Systems of Zhejiang Province College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China FORTH Heraklion Crete71110 Greece

Plasmonic metamaterials and metasurfaces offer new opportunities in developing high performance terahertz emitters/detectors beyond the limitations of conventional nonlinear materials. However, simple meta-atoms for second-order nonlinear applications encounter fundamental trade-offs in the necessary symmetry-breaking and local-field enhancement due to radiation damping that is inherent to the operating resonant mode and cannot be controlled separately. Here we present a novel concept that eliminates this restriction obstructing the improvement of terahertz generation efficiency in nonlinear metasurfaces based on metallic nano-resonators. This is achieved by combing a resonant dark-state metasurface, which locally drives nonlinear SRRs in the near field, with a specific spatial symmetry that enables destructive interference of the radiating linear moments of the SRRs, and perfect absorption via simultaneous electric and magnetic critical coupling of the pump radiation to the dark mode. Our proposal allows eliminating linear radiation damping, while maintaining constructive interference and effective radiation of the nonlinear components. We numerically demonstrate a giant second-order nonlinear susceptibility ∼ 10−11 m/V, one order improvement compared to previously reported split-ring-resonator metasurface, and correspondingly, two orders of magnitude enhanced terahertz energy extraction should be expected with our configuration under the same conditions. Our study offers a paradigm of high efficiency tunable nonlinear meta-devices and paves the way to revolutionary terahertz technologies and optoelectronic nanocircuitry. Copyright © 2019, The Authors. All rights reserved.

关键词： Terahertz waves

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis Model Based on Structure Attention Mechanism

Advances in Intelligent Systems and Computing

引用

Advances in intelligent Systems and computing 2018年 650卷 17-27页

作者： Lin, Kai Lin, Dazhen Cao, Donglin Cognitive Science Department Xiamen University Xiamen China Fujian Key Laboratory of Brain-Inspired Computing Technique and Applications Xiamen University Xiamen China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

ISBN: (纸本)9783319669380

Since the long short-term memory (LSTM) network is a sequential structure, it is difficult to effectively represent the structural level information of the context. Sentiment analysis based on the original LSTM causes a problem of structural level information loss, and its capacity to capture the context information is finite. To address this problem, we proposed a novel structure-attention-based LSTM as a hierarchical structure model. It may capture relevant information in the context as much as possible. We propose HM (ht matrix) to storage the structural information of the context. Furthermore, we introduce the attention mechanism to realize vector selection. Compared with the original LSTM and normal attention-based sentiment classification methods, our model obtains a higher classification precision. It is proved that the structure-attention-based method proposed in this study has an advantage in capturing the potential semantic structure. © 2018, Springer International Publishing AG.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Traffic Condition Analysis Based on Users Emotion Tendency of Microblog

Advances in Intelligent Systems and Computing

引用

Advances in intelligent Systems and computing 2018年 650卷 299-311页

作者： Wang, Shuru Cao, Donglin Lin, Dazhen Chao, Fei Cognitive Science Department Xiamen University Xiamen China Fujian Key Laboratory of Brain-Inspired Computing Technique and Applications Xiamen University Xiamen China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

ISBN: (纸本)9783319669380

Analysis of traffic condition is of great significance to urban planning and public administration. However, traditional traffic condition analysis approaches mainly rely on sensors, which are high-cost and limit their coverage. To solve these problems, we propose a semi-supervised learning method which uses the social network data instead and analyzes the traffic condition based on user’s emotion tendency. First we train the Gated Recurrent Unit (GRU) model to estimate the sentiment of microblog with traffic information, then using the emotional tendency to predict whether traffic jams happen or not. In order to reduce the data annotated by manpower, we propose a new idea to employ the Conditional Generative Adversarial Networks (CGAN) to generate samples which are as a supplement to the training set of GRU. Finally compared with the GRU model trained by solely the manual annotation data, our method improves the classification accuracy by 4.07%. We also use our model to predict the time and roads of traffic jams in 4 Chinese cities which is proved to be effective. © 2018, Springer International Publishing AG.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Parallel Multi-Label Propagation Based on Influence Model and Its Application to Overlapping Community Discovery

Parallel Multi-Label Propagation Based on Influence Model an...

引用

作者： Qiu, Qirong Guo, Wenzhong Chen, Yuzhong Guo, Kun Li, Rongrong School of Economics and Management Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350116 China College of Mathematics and Computer Science Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350116 China

Finding communities in networks is one of the challenging issues in complex network research. We have to deal with very large networks that contain billions of vertices, which makes community discovery a computationally intensive work. Moreover, communities usually overlap each other, which greatly increases the difficulty of identifying the boundaries of communities. In this paper, we propose a parallel multi-label propagation algorithm (PMLPA) that enhances traditional multi-label propagation algorithm (MLPA) in two ways. First, the critical steps of MLPA are parallelized based on the MapReduce model to get higher scalability. Second, new label updating strategy is used to automatically determine the most valuable labels of each vertex. Furthermore, we study the improvement of PMLPA through considering the influence of vertices and labels on label updating. In this way, the importance of each label can be described with higher precision. Experiments on artificial and real networks prove that the proposed algorithms can achieve both high discovering accuracy and high scalability. © 2017 World Scientific Publishing Company.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：