检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Lingzhi Sun Yong He School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China

ISBN: (纸本)9781665426480

Low-grade gliomas (LGG) is the most common primary intracranial tumor, with high incidence rate, high recurrence rate, high mortality rate and low cure rate. Therefore, it is necessary to predict the survival of LGG patients in diagnosis. Considering the complementarity of information, the new proposed algorithm in this study is designed to integrate Magnetic Resonance Image (MRI) data and gene expression data using deep learning method to predict the Disease Specific Survival (DSS) of LGG patients. Firstly, MRI data of 44 patients is screened from TCIA database, and then the corresponding gene expression data of 44 patients is searched from TCGA database. Then, 724 image feature data extracted from MRI data are filtered and extracted by deep learning method, and DSS tags are used to train the model; deep learning method is used to extract 20530 features of gene expression data, and DSS tags are also used for training. As a contrast, the deep learning method is used to integrate the two features to train the model. Experiments are evaluated on MRI data, gene expression data and the integration data of MRI and gene expression data, respectively. The results show that by using the integration of MRI data and gene expression data performs better than using single data in terms of the time-dependent receiver operating characteristic(ROC) and the area under the curve (AUC) of the ROC curve criteria.

关键词： Deep learning Training Databases Magnetic resonance imaging Feature extraction Data models Gene expression

来源：评论

学校读者我要写书评

暂无评论

Solving large-scale MEG/EEG source localization and functional connectivity problems simultaneously using state-space models

arXiv

引用

arXiv 2022年

作者： Sanchez-Bornot, Jose Sotero, Roberto C. Kelso, J.A. Scott Şimşek, Özgür Coyle, Damien Intelligent Systems Research Centre School of Computing Engineering and Intelligent Systems Ulster University Magee campus Derry-Londonderry United Kingdom Department of Radiology Hotchkiss Brain Institute University of Calgary CalgaryAB Canada Human Brain & Behavior Laboratory Center for Complex Systems & Brain Sciences Florida Atlantic University Boca RatonFL United States Bath Institute for the Augmented Human University of Bath BathBA2 7AY United Kingdom

State-space models are widely employed across various research disciplines to study unobserved dynamics. Conventional estimation techniques, such as Kalman filtering and expectation maximisation, offer valuable insights but incur high computational costs in large-scale analyses. Sparse inverse covariance estimators can mitigate these costs, but at the expense of a trade-off between enforced sparsity and increased estimation bias, necessitating careful assessment in low signal-to-noise ratio (SNR) situations. To address these challenges, we propose a three-fold solution: 1) Introducing multiple penalised state-space (MPSS) models that leverage data-driven regularisation;2) Developing novel algorithms derived from backpropagation, gradient descent, and alternating least squares to solve MPSS models;3) Presenting a K-fold cross-validation extension for evaluating regularisation parameters. We validate this MPSS regularisation framework through lower and more complex simulations under varying SNR conditions, including a large-scale synthetic magneto- and electro-encephalography (MEG/EEG) data analysis. In addition, we apply MPSS models to concurrently solve brain source localisation and functional connectivity problems for real event-related MEG/EEG data, encompassing thousands of sources on the cortical surface. The proposed methodology overcomes the limitations of existing approaches, such as constraints to small-scale and region-of-interest analyses. Thus, it may enable a more accurate and detailed exploration of cognitive brain functions. © 2022, CC BY-NC-ND.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Design of Variance-Constrained H∞ State Estimation Algorithm for Delayed Memristive Neural Networks with Attacks: An Adaptive Event-Triggered Approach

Design of Variance-Constrained H∞ State Estimation Algorith...

引用

IEEE International Conference on Cloud computing and Intelligence systems (CCIS)

作者： Yan Gao Jun Hu Hui Yu Chaoqing Jia Department of Mathematics Harbin University of Science and Technology Harbin China School of Automation Harbin University of Science and Technology Harbin China Heilongjiang Provincial Key Laboratory of Optimization Control and Intelligent Analysis for Complex Systems Harbin University of Science and Technology Harbin China

ISBN: (纸本)9781665456579

This paper studies the algorithm design of variance-constrained $H_{\infty}$ state estimation problem for delayed memristive neural networks with adaptive event-triggered mechanism. The denial-of-service attacks are modeled by a series of random variables obeying the Bernoulli distribution with known probability. In addition, the adaptive event-triggered mechanism is introduced into the sensor-to-estimator to avoid unnecessary resource consumption. Our purpose is to construct a finite-horizon state estimation algorithm, and sufficient condition is obtained for the estimation error system satisfying the $H_{\infty}$ performance requirement and the error variance boundedness. Finally, a numerical example is used to illustrate the feasibility of the presented $H_{\infty}$ state estimation algorithm.

关键词： Sufficient conditions Adaptation models Wireless sensor networks Adaptive systems Neural networks Machine learning Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Interval Robust Optimization Method of Vpp Bidding Strategy in Spot Market Under Multiple Uncertainties

SSRN

引用

SSRN 2024年

作者： Ma, Ying Li, Zhen Liu, Ruyi Liu, Bin Yu, Samson S. Liao, Xiaozhong Shi, Peng School of Automation Key Laboratory for Intelligent Control & Decision on Complex Systems Beijing Institute of Technology Beijing100081 China School of Mathematics and Statistics University of Sydney NSW2006 Australia Beijing102249 China School of Engineering Deakin University VIC3216 Australia School of Electrical and Electronic Engineering Univerty of Adelaide SA5005 Australia Research and Innovation Center Obuda University Budapest1034 Hungary

Virtual power plant (VPP) participating in the spot market can improve the flexibility of new-type power systems with the increasing penetration of renewable energy. However, multiple uncertainties on the market side, load side and generation side affect the bidding plans and operation efficiency of a VPP. In this paper, a two-stage interval robust optimization model is established to optimize the bidding plans of a VPP including gas turbine, energy storage, photovoltaic (PV) and electric vehicles (EVs). Interval numbers generated by the data-driven model are used to describe the uncertainty and correlation of electricity price in the spot market. Uncertainty sets are employed to describe the uncertainties in the number of EVs and PV power generation. The objective of the model is to jointly optimize the cost of VPP participating in the spot market considering arbitrage opportunity. The objective function containing interval numbers is transformed into a solvable form based on a ranking method considering pessimistic decisions. To solve this model, an improved column-and-constraint generation (C&CG) algorithm is developed based on the combination method of genetic algorithm (GA) and solver Gurobi. The results show that the interval numbers of electricity price generated by the data-driven model proposed in this paper can reduce the cost fluctuation of VPP by 3.2%. The two-stage interval robust model proposed in this paper can reduce the cost by 1.4% compared with the single-stage robust method, and lessen the cost by 35.2% compared with the robust method that does not consider arbitrage opportunities in day-ahead and real-time markets. The improved C&CG algorithm presents superior performance in convergence and accuracy. Compared to the stochastic optimization method that generates n scenarios, the computational time of the model with the interval optimization method introduced in this paper can be reduced to 1∕n. Results from case studies illustrate the effectivene

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

TEVA: Training-Efficient and Verifiable Aggregation for Federated Learning for Consumer Electronics in Industry 5.0

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Xia, Yuanjun Liu, Yining Chen, Jingxue Liang, Yangfan Khan, Fazlullah Alturki, Ryan Wang, Xiaopei Guilin University of Electronic Technology Guangxi Key Laboratory of Trusted Software School of Computer and Information Security Guilin541004 China Wenzhou University of Technology School of Data Science and Artificial Intelligence Wenzhou325027 China University of Technology School of Mathematical and Physical Sciences SydneyNSW2007 Australia Jiaxing University Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems The Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province The Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing314001 China University of Nottingham Ningbo China School of Computer Science Faculty of Science and Engineering Zhejiang Ningbo315104 China Umm AI-Qura University Makkah Department of Software Engineering College of Computing Saudi Arabia Riverside Department of Computer Science and Engineering University of California CA92521 United States

Federated learning (FL) has been widely used for privacy-preserving model updates in Industry 5.0, facilitated by 6G networks. Despite FL's privacy-preserving advantages, it remains vulnerable to attacks where adversaries can infer private data from local models or manipulate the central server (CS) to deliver falsified global models. Current privacy-preserving approaches, primarily based on the FedAvg algorithm, fail to optimize training efficiency for non-independent and identically distributed (non-IID) data. This article proposes training-efficient and verifiable aggregation (TEVA) for FL to resolve these issues. This scheme combines threshold Paillier homomorphic encryption (TPHE), verifiable aggregation, and an optimized double momentum update mechanism (OdMum). TEVA not only leverages TPHE to protect the privacy of local models but also ensures the integrity of the global model through a verifiable aggregation mechanism. Additionally, TEVA integrates the OdMum algorithm to effectively address the challenges posed by non-IID data, promoting rapid model convergence and significantly enhancing overall training efficiency. Security analysis indicates that TEVA meets the requirements for privacy protection. Extensive experimental results demonstrate that TEVA can accelerate model convergence while incurring lower computational and communication overheads. © 1975-2011 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Coordinate Attention Based 3D-CNN Using Ghost Multi-Scale for Diagnosing Alzheimer’s Disease

Coordinate Attention Based 3D-CNN Using Ghost Multi-Scale fo...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiaolu Lin Pinya Lu Jie Pan Hongqin Yang Xuemei Ding Fujian Provincial Engineering Research Center for Public Service Big Data Mining and Application Fujian Provincial University Engineering Research Center for Big Data Analysis and Application Fujian Normal University Fuzhou China Xiamen Jingyi Zhikang Technology Co. Ltd Xiamen China Fujian Provincial Key Laboratory for Photonics Technology Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education Fujian Normal University Fuzhou China School of Computing Engineering and Intelligent Systems Ulster University Derry-Londonderry NI UK

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Alzheimer's disease (AD) is a neurodegenerative disease and mild cognitive impairment (MCI) is the early stage of AD. Previous studies have predominantly focused on binary classification using 3 dimensional - convolutional neural network (3D-CNN) for AD diagnosis, with limited progress in multi-classification. Moreover, the current 3D-CNNs often adopt a single-scale architecture with massive parameters growth. Additionally, obtaining precise location information of brain imaging data is crucial for improving the classification accuracy with 3D-CNN. Hence, we propose a multi-scale 3D-CNN based on coordinate attention mechanism to marvelously capture and integrate 3D features with fewer parameters, improving the accuracy of AD diagnosis. A total of 447 cognitively normal (CN), 512 MCI, and 358 AD sMRI images from the Alzheimer's Disease Neuroimaging Initiative datasets are used for multi-class classification task, yielding a classification accuracy of 92.8%. The model merely involves 2.41 M parameters and achieves the best classification results with the least number of parameters when compared to other representative CNN architectures including ResNet 18, ResNet 34, ConvNeXt tiny, and VGG 11. Through the ablation experiment, the addition of attention mechanism and the multi-scale classification enhances the classification performance by 4.5% and 1.5%, respectively. Furthermore, our model outperforms the other six existing studies in terms of accuracy for classifying AD vs. MCI vs. CN. Overall, this study underscores the efficacy of our approach for AD diagnosis, showcasing its utility in diagnosing AD patients and providing novel insights for diagnosing other neurological disorder diseases.

关键词： Neuroimaging Accuracy Attention mechanisms Three-dimensional displays Resonance Convolutional neural networks Alzheimer's disease

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Interval Robust Optimization Method of Vpp Bidding Strategy in Spot Market Under Multiple Uncertainties

SSRN

引用

SSRN 2024年

Virtual power plant (VPP) participating in the spot market can improve the flexibility of new-type power systems with the increasing penetration of renewable energy. However, multiple uncertainties on the market side, load side and generation side affect the bidding plans and operation efficiency of a VPP. In this paper, a two-stage interval robust optimization model is established to optimize the bidding plans of a VPP including gas turbine, energy storage, photovoltaic (PV) and electric vehicles (EVs). Interval numbers generated by the data-driven model are used to describe the uncertainty and correlation of electricity price in the spot market. Uncertainty sets are employed to describe the uncertainties in the number of EVs and PV power generation. The objective of the model is to jointly optimize the cost of VPP participating in the spot market considering arbitrage opportunity. The objective function containing interval numbers is transformed into a solvable form based on a ranking method considering pessimistic decisions. To solve this model, an improved column-and-constraint generation (C&CG) algorithm is developed based on the combination method of genetic algorithm (GA) and solver Gurobi. The results show that the interval numbers of electricity price generated by the data-driven model proposed in this paper can reduce the cost fluctuation of VPP by 3.2%. The two-stage interval robust model proposed in this paper can reduce the cost of VPP by 1.4% compared with the conventional single-stage robust method, and lessen the cost by 35.2% compared with the robust method that does not consider arbitrage opportunities in day-ahead and real-time markets. The improved C&CG algorithm presents superior performance in convergence and accuracy. Compared to the stochastic optimization method that generates n scenarios, the computational time of the model with the interval optimization method introduced in this paper can be reduced to 1∕n. Results from case studies illust

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

A Multi-feature Extraction-based Image Identification Method for Rock Debris in The Drilling Process

A Multi-feature Extraction-based Image Identification Method...

引用

Chinese Automation Congress (CAC)

作者： Pengju Xu Chao Gan Luzhao Wang Weihua Cao School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China No.3 Exploration Institute of Geology and Mineral Resources of Shandong Province Yantai China

In this paper, a multi-feature extraction-based image identification method for rock debris in the drilling process is proposed, involving three main parts (trainable feature extractor, strong feature extraction, and classification). In trainable feature extractor, abstract features are obtained by extracting the full connection layer of Convolutional Neural Network (CNN). In strong feature extraction, the method uses Gray-Level Co-occurrence Matrix (GLCM) and Color Coherence Vector (CCV) to get the strong feature. In classification, the extracted abstract features and strong features are concatenated and fed into the Support Vector Machine (SVM). Comparison results with two well-known methods indicated the effectiveness of the proposed method.

关键词： Support vector machines Drilling Measurement Image color analysis Neural networks Feature extraction Rocks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

arXiv

引用

arXiv 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China University of Kent CanterburyCT2 7NP United Kingdom Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Intelligent Transportation Systems Lab Innopolis University Innopolis Russia School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi’an710071 China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Consensus in multi-agent systems with multiple disturbances and time delay via proportional-integral control

Consensus in multi-agent systems with multiple disturbances ...

引用

第40届中国控制会议

作者： Fenglan Sun Yunhao Shen Key Laboratory of Intelligent Analysis and Decision on Complex Systems School of ScienceChongqing University of Posts and Telecommunications Key Laboratory of Intelligent Air-Ground Cooperative Control for Universities in Chongqing College of AutomationChongqing University of Posts and Telecommunications Potsdam Institute for Climate Impact Research

This paper studies the consensus in multi-agent systems with multiple disturbances and time delay over fixed and switching topology via proportional-integral control. The controller that includes proportional and integral actions is *** adopting matrix theory, algebraic graph theory and Lyapunov stability theory, sufficient conditions for consensus are obtained. Several numerical simulations are given to verify the effectiveness of the algorithms.

关键词： consensus multiple disturbances switching topology proportional-integral control

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：