检索结果-内蒙古大学图书馆

image Regularizations Based on the Sparsity of Corner Points

IEEE TRANSACTIONS ON image processing 2019年第1期28卷 72-87页

作者： Liu, Haosen Tan, Shan Huazhong Univ Sci & Technol Sch Automat Minist Educ China Key Lab Image Proc & Intelligent Control Wuhan 430074 Hubei Peoples R China

Many analysis-based regularizations proposed so far employ a common prior information, i. e., edges in an image are sparse. However, in local edge regions and texture regions, this prior may not hold. As a result, the performance of regularizations based on the edge sparsity may be unsatisfactory in such regions for image-related inverse problems. These regularizations tend to smooth out the edges while eliminating the noise. In other words, these regularizations' abilities of preserving edges are limited. In this paper, a new prior that the corner points in a natural image are sparse was proposed to construct regularizations. Intuitively, even in local edge regions and texture regions, the sparsity of corner points may still exist, and hence, the regularizations based on it can achieve better performance than those based on the edge sparsity. As an example, by utilizing the sparsity of corner points, we proposed a new regularization based on Noble's corner measure function. Our experiments demonstrated the excellent performance of the proposed regularization for both image denoising and deblurring problems, especially in local edge regions and texture regions.

关键词： Corner detection image restoration nonlocal method regularization structure tensor

来源：评论

学校读者我要写书评

暂无评论

Causal Invariant Hierarchical Molecular Representation for Out-of-distribution Molecular Property Prediction

Causal Invariant Hierarchical Molecular Representation for O...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xinlong Wen Yifei Guo Shuoying Wei Wenhan Long Lida Zhu Rongbo Zhu Huazhong Agricultural University Wuhan China College of Informatics Huazhong Agricultural University Wuhan China Shenzhen Institute of Nutrition and Health Huazhong Agricultural University Shenzhen China Shenzhen Branch Guangdong Laboratory for Lingnan Modern Agriculture Genome Analysis Laboratory of the Ministry of Agriculture and Agricultural Genomics Institute at Shenzhen Chinese Academy of Agricultural Sciences Shenzhen China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Wuhan China Huazhong University of Science and Technology Wuhan China Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Molecular representation learning is widely used in the field of drug discovery, due to its ability to accurately capture the complex features of compounds in high-dimensional space. However, existing molecular representation learning models are prone to be influenced by spurious parts during distribution shifts (also known as out-of-distribution, or OOD), which results in models mistakenly treating these spurious parts as crucial features of molecules, thereby limiting the generalization capability of the models. To tackle this issue, a novel invariant molecular representation learning model, called Causal Invariant Hierarchical Molecular Representation Graph Neural Networks (CHiMoGNN), is proposed for OOD molecular property prediction. In CHiMoGNN, a Feature Enhancement (FE) module is designed to leverage the multi-level molecular parts to enhance the expression of invariant features, thereby enhancing the model’s capability to capture key molecular information. In addition, a Cartesian Product based Environmental Impact (EI) module is adopted to generate counterfactual samples with environmental diversity. Consequently, these samples are utilized to train a classifier that maintains consistent performance across various environments. Extensive experiments on seven real-world datasets demonstrate that CHiMoGNN outperforms 9 state-of-the-art models, achieving a 5.73% increase in average ROC-AUC, and the results also show that CHiMoGNN can effectively maintain generalization in various distribution shifts. Code and datasets are available at https://***/Chertuion/CHiMoGNN.

关键词： Representation learning Limiting Codes Predictive models Feature extraction Iron Graph neural networks Drug discovery Data mining Compounds

来源：评论

学校读者我要写书评

暂无评论

A New control System Based on An Improved PID Neural Network controller for Landslide System control

A New Control System Based on An Improved PID Neural Network...

引用

第三十九届中国控制会议

作者： Ying Zhang Shu Sun Cheng Lian Xiaoping Wang the School of Artificial Intelligence and Automation the Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology the School of Artificial Intelligence and Automation the Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology the School of Automation Wuhan University of Technology IEEE

In this paper, a new control system based on the improved PID neural network controller（PIDNNC） is designed to control the landslide displacement. In the control system,the fuzzy comprehensive judgement model of landslide system is established to judge whether the system needs to be controlled and give the expected displacement. To solve the problem of random initialization in PIDNNC, This paper proposed an improved PIDNNC based on fuzzy PID controller（F-PIDNNC）.The fuzzy PID controller is used to obtain the proportional,integral and differential coefficients kp, ki and kd. Then the obtained parameters are taken as the initial weights of *** effectiveness of the proposed control system is simulated on Baishuihe and Shiliushubao landslides. The results show that the proposed control system based on F-PIDNNC is much accurate and faster than the traditional one-dimensional fuzzy PID controller and PIDNNC.

关键词： PID neural network Fuzzy PID controller Landslide control Stability evaluation

来源：评论

学校读者我要写书评

暂无评论

Deep neural learning techniques with long short-term memory for gesture recognition

引用

NEURAL COMPUTING & APPLICATIONS 2020年第20期32卷 16073-16089页

作者： Jain, Deepak Kumar Mahanti, Aniket Shamsolmoali, Pourya Manikandan, Ramachandran Chongqing Univ Posts & Telecommun Key Lab Intelligent Air Ground Cooperat Control U Coll Automat Chongqing Peoples R China Univ Auckland Auckland New Zealand Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai Peoples R China SASTRA Deemed Univ Sch Comp Thanjavur India

Gesture recognition is a kind of biometric which has assumed great significance in the field of computer vision for communicating information through human activities. To recognize the various gestures and achieve efficient classification, an efficient computational machine learning technique is required. The Shift Invariant Convolutional Deep Structured Neural Learning with Long Short-Term Memory (SICDSNL-LSTM) and Bivariate Fully Recurrent Deep Neural Network with Long Short-Term Memory (BFRDNN-LSTM) have been introduced for classifying human activities with efficient accuracy and minimal time complexity. The SICDSNL-LSTM technique collects gesture data (a kind of biometric) from the dataset and gives it to the input layers of Shift Invariant Convolutional Deep Structured Neural Learning. The SICDSNL-LSTM technique uses two hidden layers for performing regression and classification. In the regression process, dice similarity is used for measuring the relationship between data and output classes. In the second process, the input data are classified into dissimilar classes for each time step using LSTM unit with soft-step activation function. The soft-step activation function uses 'forget gate' for removing the less significant data from the cell state. This is also used to make a decision to display the output at a particular time step and to remove other class results. Then, LSTM output is given to the output layers, and convolutional deep neural learning is performed to classify the gesture. Based on the classification results, human activity and gesture are recognized with high accuracy. The BFRDNN-LSTM technique also performs regression in the first hidden layers using bivariate correlation to find relationship between data and classes. The LSTM unit in BFRDNN-LSTM technique uses Gaussian activation function in the second hidden layers for categorizing incoming data into various classes at each time step. In this proposed BFRDNN-LSTM method, fully recurrent dee

关键词： Gesture recognition Shift invariant Convolutional deep structured Neural learning Long short-term memory Bivariate fully recurrent deep neural network

来源：评论

学校读者我要写书评

暂无评论

Positive edge consensus of networked systems with input saturation

引用

ISA TRANSACTIONS 2020年 96卷 210-217页

作者： Wu, Han Su, Housheng Huazhong Univ Sci & Technol Educ Minist China Sch Artificial Intelligence & Automat Image Proc & Intelligent Control Key Lab Luoyu Rd 1037 Wuhan 430074 Peoples R China Wuhan Univ Sci & Technol Sch Informat Sci & Engn 947 Heping Ave Wuhan 430081 Hubei Peoples R China

This paper studies the edge consensus problems of undirected networked systems with positivity constraint and input saturation. Based on a given nodal network, the definition of edge network is introduced, and the edge dynamics is described by positive systems subject to input saturation. With the connections between the edge network and the nodal network, the lower and upper bounds of the nonzero eigenvalues of the edge Laplacian matrix are presented. Rigorous convergence analysis is carried out. Based on the special properties of positive systems, sufficient conditions of positive edge consensus with input saturation are given without using global topology information, that is, the topology information in the given results only relates to the edge and vertex number of the nodal network. Furthermore, the nonnegative edge consensus problem with uncertain parameters is also studied based on the properties of Metzler matrix. Different from many consensus problems with input saturation which achieve semi-global consensus, the results in this paper are global consensus. The feedback matrix can be computed by solving linear matrix inequality. Some illustrative numerical and practical simulation examples are finally introduced to verify the proposed methods in this paper. (C) 2019 ISA. Published by Elsevier Ltd. All rights reserved.

关键词： Edge consensus Positivity constraint Input saturation Uncertain parameters Global consensus

来源：评论

学校读者我要写书评

暂无评论

A Single-Cell Clustering Algorithm Based on Structure Perturbation Non-Negative Matrix Factorization

A Single-Cell Clustering Algorithm Based on Structure Pertur...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Hanjing Jiang Meineng Wang Luping Zhang Yu-An Huang Yangyuan Li Yabing Huang Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology China University of Mining and Technology Xuzhou China School of Mathematics and Computer Science Yichun University Yichun China School of Information Engineering East China University of Technology Nanchang China School of Computer Science Northwestern Polytechnical University Xi’an China Department of Pathology Renmin Hospital of Wuhan University Wuhan China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The advent of single-cell RNA sequencing (scRNA-seq) has facilitated the acquisition of high-resolution data regarding cell heterogeneity across various tissues. A fundamental and critical step in the analysis of scRNA-seq data is cell type identification. An appropriate graph construction strategy can reflect the topological structure between cells and allows for detailed exploration of the relationships between cells and genes. Given the sparsity of scRNA-seq data and the pronounced noise generated by shallow sequencing, choosing an appropriate graph construction strategy has become a significant challenge. In this paper, we propose a single-cell clustering method, named Sc-PNNMF, based on structural perturbation of nonnegative matrix factorization. Sc-PNNMF employs a structural perturbation algorithm to optimize the gene expression matrix. The optimized matrix guides the matrix factorization process, effectively overcoming the impact of data sparsity and significant noise in gene expression data on the graph construction strategy. We compared the clustering abilities of Sc-PNNMF with five other methods on ten real datasets.

关键词： Sequential analysis Perturbation methods Clustering methods RNA Noise Clustering algorithms Sparse matrices Gene expression Unsupervised learning Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Odor source localization algorithms on mobile robots: A review and future outlook

引用

ROBOTICS AND AUTONOMOUS SYSTEMS 2019年 112卷 123-136页

作者： Chen, Xin-Xing Huang, Jian Huazhong Univ Sci & Technol Key Lab Minist Educ Image Proc & Intelligent Control Sch Automat Wuhan Hubei Peoples R China

When applied in some harsh environments (e.g. in poisonous atmosphere or underwater), odor source localization robots are able to perform better than animals without being hurt. During the past three decades, robotic odor source localization has become a popular research field with various algorithms being proposed. These algorithms can be roughly divided into four categories: gradient-based algorithms, bio-inspired algorithms, multi-robot algorithms and probabilistic and map-based algorithms. In this paper, we present a literature review of these four categories and discuss their pros and cons. We also discuss the current trends and some future challenges according to some research papers published in recent years. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Odor source localization Chemical plume tracking Mobile robot

来源：评论

学校读者我要写书评

暂无评论

Distributed Frequency controller for MT-HVDC Systems Via Adaptive Dynamic Programming 32

Distributed Frequency Controller for MT-HVDC Systems Via Ada...

引用

32nd Chinese control And Decision Conference (CCDC)

作者： Hu, Zhongjie Liu, Zhi-Wei Hu, Xiong Chi, Ming Huazhong Univ Sci & Technol Coll Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Minist Educ Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

ISBN: (纸本)9781728158556

The exact mathematical models of multi-terminal high-voltage direct current (MT-HVDC) systems are hard to be obtained in the practical application of HVDC technology. To overcome this challenge, a model-free distributed frequency controller for MT-HVDC systems is proposed based on Adaptive dynamic programming (ADP) in this paper. Specifically, for each AC area, only the local and neighboring sampling data of frequency is required without the MT-HVDC system model. Besides, the proposed controller is distributed which effectively balances the communication burden among the AC areas. Moreover, the proposed controller makes the connected AC areas share their power reserves via HVDC grids to compensate load disturbances so that the necessary power reserves can be downsized. Some simulations carried out on a five-terminal HVDC system evaluate the performance of the proposed controller.

关键词： MT-HVDC system distributed frequency controller adaptive dynamic programming (ADP) neural network reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Serial Access Scheme Design on Memristor-CMOS Hybrid Memory

引用

IEEE ACCESS 2020年 8卷 35031-35037页

作者： Guo, Yanwen Wang, Xiaoping Hong, Qinghui Zhang, Yang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Hunan Peoples R China Shenzhen Univ Sch Comp Sci & Software Engn Comp Vis Inst Shenzhen Key Lab Spatial Smart Sensing & Serv Shenzhen 518060 Peoples R China

A new serial access scheme for memristor-CMOS hybrid memory cell is proposed, which addresses the limitations of sneak-path current, crosstalk and cell-cell interference. The serial access circuit consists of only one multiplexer and one I/O circuit, implementing memory addressing for memristor memory crossbar array. Memristor is used to store the bit information, and CMOS is used to isolate, control, decode and interoperate the logic. The proposed design is verified with PSPICE simulation utilizing a modified memristor model. Compared with conventional circuitry in parallel access scheme, the dedicated designed serial I/O circuitry for memristor-CMOS hybrid memory is simpler and area saving. The new serial access scheme, juxtaposed with conventional parallel access scheme, can get better performance in some area critical and ultra high frequency memory applications.

关键词： Memristors Microprocessors Transistors Logic gates Arrays Threshold voltage Memristor serial access parallel access CMOS nonvolatile memory

来源：评论

学校读者我要写书评

暂无评论

On the Vulnerability of CNN Classifiers in EEG-Based BCIs

引用

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2019年第5期27卷 814-825页

作者： Zhang, Xiao Wu, Dongrui Huazhong Univ Sci & Technol Minist Educ Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Hubei Peoples R China

Deep learning has been successfully used in numerous applications because of its outstanding performance and the ability to avoid manual feature engineering. One such application is electroencephalogram (EEG)-based brain-computer interface (BCI), where multiple convolutional neural network (CNN) models have been proposed for EEG classification. However, it has been found that deep learning models can be easily fooled with adversarial examples, which are normal examples with small deliberate perturbations. This paper proposes an unsupervised fast gradient sign method (UFGSM) to attack three popular CNN classifiers in BCIs, and demonstrates its effectiveness. We also verify the transferability of adversarial examples in BCIs, which means we can perform attacks even without knowing the architecture and parameters of the target models, or the datasets they were trained on. To the best of our knowledge, this is the first study on the vulnerability of CNN classifiers in EEG-based BCIs, and hopefully will trigger more attention on the security of BCI systems.

关键词： Electroencephalogram brain-computer interfaces convolutional neural networks adversarial examples

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：