检索结果-内蒙古大学图书馆

Cascading and Enhanced Residual Networks for Accurate Single-image Super-Resolution

IEEE TRANSACTIONS ON CYBERNETICS 2021年第1期51卷 115-125页

作者： Lan, Rushi Sun, Long Liu, Zhenbing Lu, Huimin Su, Zhixun Pang, Cheng Luo, Xiaonan Guilin Univ Elect Technol Guangxi Key Lab Image & Graph Intelligent Proc Guilin 541004 Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Kyushu Inst Technol Dept Mech & Control Engn Kitakyushu Fukuoka 8048550 Japan Dalian Univ Technol Sch Math Sci Dalian 116024 Peoples R China Guilin Univ Elect Technol Natl Local Joint Engn Res Ctr Satellite Nav & Loc Guilin 541004 Peoples R China

Deep convolutional neural networks (CNNs) have contributed to the significant progress of the single-image super-resolution (SISR) field. However, the majority of existing CNN-based models maintain high performance with massive parameters and exceedingly deeper structures. Moreover, several algorithms essentially have underused the low-level features, thus causing relatively low performance. In this article, we address these problems by exploring two strategies based on novel local wider residual blocks (LWRBs) to effectively extract the image features for SISR. We propose a cascading residual network (CRN) that contains several locally sharing groups (LSGs), in which the cascading mechanism not only promotes the propagation of features and the gradient but also eases the model training. Besides, we present another enhanced residual network (ERN) for image resolution enhancement. ERN employs a dual global pathway structure that incorporates nonlocal operations to catch long-distance spatial features from the the original low-resolution (LR) input. To obtain the feature representation of the input at different scales, we further introduce a multiscale block (MSB) to directly detect low-level features from the LR image. The experimental results on four benchmark datasets have demonstrated that our models outperform most of the advanced methods while still retaining a reasonable number of parameters.

关键词： Feature extraction image reconstruction Spatial resolution Convolutional neural networks Training Graphics Convolutional neural network multiscale learning residual learning single-image super-resolution (SISR)

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Driver Drowsiness Estimation Using an Online Multi-View and Transfer TSK Fuzzy System

引用

IEEE TRANSACTIONS ON intelligent TRANSPORTATION SYSTEMS 2021年第3期22卷 1752-1764页

作者： Jiang, Yizhang Zhang, Yuanpeng Lin, Chuang Wu, Dongrui Lin, Chin-Teng Jiangnan Univ Sch Digital Media Wuxi 214122 Jiangsu Peoples R China Nantong Univ Dept Med Informat Nantong 226001 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen 518000 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Minist Educ Image Proc & Intelligent Control Wuhan 430074 Peoples R China Univ Technol Sydney Fac Engn & Informat Technol Ctr Artificial Intelligence Ultimo NSW 2007 Australia

In the field of intelligent transportation, transfer learning (TL) is often used to recognize EEG-based drowsy driving for a new subject with few subject-specific calibration data. However, most of existing TL-based models are offline, non-transparent, and in which features are only represented from one view (usually only one algorithm is used to extract features). In this paper, we consider an online multi-view regression model with high interpretability. By taking the 1-order TSK fuzzy system as the basic regression component and injecting the nature of the multi-view settings into the existing transfer learning framework and enforcing the consistencies across different views, we propose an online multi-view & transfer TSK fuzzy system for driver drowsiness estimation. In this novel model, features in both the source domain and the target domain are represented from multi-view perspectives such that more pattern information can be utilized during model training. Also, comparing with offline training, the proposed online fuzzy system meets the practical requirements more competently. An experiment on a driving dataset demonstrates that the proposed fuzzy system has smaller drowsiness estimation errors and higher interpretability than introduced benchmarking models.

关键词： Brain modeling Electroencephalography Estimation Vehicles Fuzzy systems Feature extraction Accidents Transfer learning multi-view learning TSK fuzzy systems EEG

来源：评论

学校读者我要写书评

暂无评论

GTNet: Generative Transfer Network for Zero-Shot Object Detection 34

GTNet: Generative Transfer Network for Zero-Shot Object Dete...

引用

34th AAAI Conference on Artificial Intelligence / 32nd Innovative Applications of Artificial Intelligence Conference / 10th AAAI Symposium on Educational Advances in Artificial Intelligence

作者： Zhao, Shizhen Gao, Changxin Shao, Yuanjie Li, Lerenhan Yu, Changqian Ji, Zhong Sang, Nang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Minist Educ Image Proc & Intelligent Control Key Lab Wuhan Hubei Peoples R China Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China

ISBN: (纸本)9781577358350

We propose a Generative Transfer Network (GTNet) for zero-shot object detection (ZSD). GTNet consists of an Object Detection Module and a Knowledge Transfer Module. The Object Detection Module can learn large-scale seen domain knowledge. The Knowledge Transfer Module leverages a feature synthesizer to generate unseen class features, which are applied to train a new classification layer for the Object Detection Module. In order to synthesize features for each unseen class with both the intra-class variance and the IoU variance, we design an IoU-Aware Generative Adversarial Network (IoUGAN) as the feature synthesizer, which can be easily integrated into GTNet. Specifically, IoUGAN consists of three unit models: Class Feature Generating Unit (CFU), Foreground Feature Generating Unit (FFU), and Background Feature Generating Unit (BFU). CFU generates unseen features with the intra-class variance conditioned on the class semantic embeddings. FFU and BFU add the IoU variance to the results of CFU, yielding class-specific foreground and background features, respectively. We evaluate our method on three public datasets and the results demonstrate that our method performs favorably against the state-of-the-art ZSD approaches.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

NiuEM: A Nested-iterative Unsupervised Learning Model for Single-particle Cryo-EM image processing

NiuEM: A Nested-iterative Unsupervised Learning Model for Si...

引用

2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020

作者： Hu, Rui Cai, Jiaming Zheng, Wangjie Yang, Yang Shen, Hong-Bin Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai200240 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Jiao Tong University Department of Bioinformatics and Biostatistics Shanghai200240 China

ISBN: (纸本)9781728162157

Cryo-electron microscopy (cryo-EM) has become a mainstream technology for solving spatial structures of biomacromolecules, while the processing of cryo-EM images is a very challenging task. One of the great challenges is the high noise in the images. A common method is to cluster the images with close projecting angles to get mean images, which are used for 3D reconstruction. However, due to the extremely low signal-to-noise-ratio, common clustering methods often fail to obtain high-quality mean images, leading to poorly reconstructed structures. In this study, we present a new unsupervised learning framework, called NiuEM, to discriminate images captured from different angles and yield cluster-mean images. NiuEM first generates pseudo-labels and then exploits both contrastive loss and cross-entropy loss for training convolutional layers to learn feature representations. Moreover, the pseudo-labels are updated iteratively to enhance the reliability of labels. We assess the performance of NiuEM on four data sets via both visualized and quantitative experiments. Especially, two kinds of metrics are adopted to measure the performance, regarding the clustering quality and the resolution of reconstructed 3D models, respectively. The experimental results show that NiuEM achieves very competitive clustering accuracy in the comparison with the state-of-the-art image clustering methods. Moreover, the cluster mean images yielded by NiuEM lead to better initial 3D models compared with the mainstream reconstruction tools. © 2020 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Optimal Fault Detection Observer Design using Excluding Degree

Optimal Fault Detection Observer Design using Excluding Degr...

引用

IEEE Conference on Decision and control

作者： Feng Xu Yiming Wan Ye Wang Division of Information Science and Technology Shenzhen International Graduate School Tsinghua University Shenzhen P.R. China School of Artificial Intelligence and Automation Huazhong University of Science and Technology and Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan P.R. China Department of Electrical and Electronic Engineering The University of Melbourne Parkville VIC Australia

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

This paper proposes a novel optimal gain design method for robust fault detection using set-valued observers. First, a new fault detection performance specification is proposed for set-valued observers based on a new notion named the excluding degree of the origin from a zonotope. Second, a fractional programming problem is formulated to describe fault detection optimality of set-valued observers. Third, optimal fault detection gains are obtained by solving the fractional programming problem. Finally, numerical examples are used to illustrate the effectiveness of the proposed method.

关键词： Fault detection Design methodology Observers Programming Computational complexity Optimization Numerical stability

来源：评论

学校读者我要写书评

暂无评论

An image Encryption Method Based on Logistic Chaotic Mapping and DNA Coding 11

An Image Encryption Method Based on Logistic Chaotic Mapping...

引用

SPIE 11th International Symposium on Multispectral image processing and Pattern Recognition (MIPPR) - Remote Sensing image processing, Geographic Information Systems, and Other Applications

作者： Lin, Jiayu Zhao, Kangnan Cai, Xin Li, Danning Wang, Zuxi Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Minist Educ Key Lab Image Informat Proc & Intelligent Control Wuhan 430074 Peoples R China Natl Key Lab Multispectral Informat Proc Technol Wuhan 430074 Peoples R China

ISBN: (纸本)9781510636422

This paper proposes a new image encryption algorithm, which is based on Logistic chaotic mapping and DNA coding. A variable parameter logistic mapping coupled chaotic system is proposed to generate pseudo-random sequences with good pseudo-random properties. Before encrypting plain-text images, the distinct features of some special images are eliminated by superposing them with a pseudo-random image. Combining with DNA encoding operation, an encrypting algorithm of cross-operation of diffusion and peunutation is designed. The simulation results show that the proposed algorithm has large key space, high sensitivity to key and plain-text, and good robustness to resist exhaustive attack, statistic attack, differential attack, etc. It shows that the proposed method has good encryption effect and security.

关键词： Chaos DNA code Pseudo random number image encryption

来源：评论

学校读者我要写书评

暂无评论

Adaptive consensus of two-time-scale multi-agent systems

引用

INTERNATIONAL JOURNAL OF control 2021年第4期94卷 943-951页

作者： Wei, Li-Mei Yang, Wu Wang, Yan-Wu Guangxi Univ XingJian Coll Sci & Liberal Arts Nanning Guangxi Peoples R China Huazhong Univ Sci & Technol Sch Automat Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Minist Educ Key Lab Image Proc & Intelligent Control Wuhan Hubei Peoples R China Huazhong Univ Sci & Technol Sch Elect & Elect Engn Wuhan Hubei Peoples R China China Three Gorges Univ Hubei Prov Collaborat Innovat Ctr New Energy Micr Yichang Peoples R China

This paper studies the distributed consensus problem of a new class of multi-agent systems, where each agent is represented by the two-time-scale system. Two fully distributed, epsilon-dependent adaptive consensus protocols are designed, namely, the relative states based adaptive protocol and the relative outputs based adaptive protocol. By using the merit of the proposed epsilon-Lyapunov function, some sufficient consensus criteria in terms of well-conditioned linear matrix inequalities are derived. The upper bound of epsilon is also determined. A numerical example for the drying section of a paper converting machine with nine rolls verifies the effectiveness of the proposed results.

关键词： Consensus multi-agent systems two-time-scale feature fully distributed protocol adaptive control strategy

来源：评论

学校读者我要写书评

暂无评论

Memristive LSTM Network for Sentiment Analysis

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2021年第3期51卷 1794-1804页

作者： Wen, Shiping Wei, Huaqiang Yang, Yin Guo, Zhenyuan Zeng, Zhigang Huang, Tingwen Chen, Yiran Huazhong Univ Sci & Technol Sch Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Minist China Key Lab Image Proc & Intelligent Control Educ Wuhan 430074 Peoples R China Hamad Bin Khalifa Univ Coll Sci Engn & Technol Doha Qatar Hunan Univ Coll Math & Econometr Changsha 410082 Peoples R China Texas A&M Univ Qatar Sci Program Doha Qatar Duke Univ Dept Elect & Comp Engn Durham NC 27708 USA

This paper presents a complete solution for the hardware design of a memristor-based long short-term memory (MLSTM) network. Throughout the design process, we fully consider the external and internal structures of the long short-term memory (LSTM), both of which are efficiently implemented by memristor crossbars. In the specific design of the internal structure, the parameter sharing mechanism is used between the LSTM cells to minimize the hardware design scale. In particular, we designed a circuit that requires only one memristor crossbar for each unit in the LSTM cell. The activation function, including sigmoid and tanh (hyperbolic tangent function), involved in each unit is approximated by a piecewise function, which is designed with the corresponding hardware. To verify the effectiveness of the system we designed, we test it on IMDB and SemEval datasets. Considering the huge impact of the dimensions of the input data on the scale of the hardware design, we use word2vector instead of one-hot encoding for the input data encoding. With the parameter sharing mechanism, the transformed vectors are input in different periods, so only 65 memristive crossbars are needed in the entire system to complete the sentiment analysis of the input text. The experimental results verify the effectiveness of our proposed MLSTM system.

关键词： Hardware Memristors Neural networks Sentiment analysis Task analysis Training image coding Deep learning long short-term memory (LSTM) memristor sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Adversarial semantic data augmentation for human pose estimation

arXiv

引用

arXiv 2020年

作者： Bin, Yanrui Cao, Xuan Chen, Xinya Ge, Yanhao Tai, Ying Wang, Chengjie Li, Jilin Huang, Feiyue Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Tencent Youtu Lab China

Human pose estimation is the task of localizing body keypoints from still images. The state-of-the-art methods suffer from insufficient examples of challenging cases such as symmetric appearance, heavy occlusion and nearby person. To enlarge the amounts of challenging cases, previous methods augmented images by cropping and pasting image patches with weak semantics, which leads to unrealistic appearance and limited diversity. We instead propose Semantic Data Augmentation (SDA), a method that augments images by pasting segmented body parts with various semantic granularity. Furthermore, we propose Adversarial Semantic Data Augmentation (ASDA), which exploits a generative network to dynamiclly predict tailored pasting configuration. Given off-the-shelf pose estimation network as discriminator, the generator seeks the most confusing transformation to increase the loss of the discriminator while the discriminator takes the generated sample as input and learns from it. The whole pipeline is optimized in an adversarial manner. State-of-the-art results are achieved on challenging benchmarks. The code has been publicly available at https://***/Binyr/ASDA. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Towards Environmentally Adaptive Odor Source Localization: Fuzzy Lévy Taxis Algorithm and Its Validation in Dynamic Odor Plumes

Towards Environmentally Adaptive Odor Source Localization: F...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Xinxing Chen Jian Huang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728164793

ISBN: (纸本)9781728164809

In this paper, we propose a bio-inspired Fuzzy Lévy Taxis algorithm to solve the robotic odor source localization problem in dynamic odor plumes. According to the proposed algorithm, the robot is programmed to move for a length with a turning angle at each step until reaching the odor source. The movement length and the turning angle follow two specific probability distribution, of which the parameters are adaptive through a fuzzy logic system. The proposed algorithm was compared with the Adaptive Lévy Taxis algorithm in simulated pseudo-Gaussian plumes. Our proposed algorithm shows a higher success rate and efficiency. The algorithm has also been systematically evaluated in simulated filament-based odor plumes under various environmental conditions. The results revealed that the performance of the proposed algorithm is consistently good in various environmental conditions in terms of success rate, number of steps and distance overhead to find the odor source.

关键词： Public transportation Heuristic algorithms Turning Robot sensing systems Adaptation models Fuzzy systems

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：