检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Wu, Yingwen Chen, Sizhe Fang, Kun Huang, Xiaolin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University 800 Dongchuan Road Shanghai China Institute of Image Processing and Pattern Recognition The MOE Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University 800 Dongchuan Road Shanghai China

The wide application of deep neural networks (DNNs) demands an increasing amount of attention to their real-world robustness, i.e., whether a DNN resists black-box adversarial attacks, among which score-based query attacks (SQAs) are most threatening since they can effectively hurt a victim network with the only access to model outputs. Defending against SQAs requires a slight but artful variation of outputs due to the service purpose for users, who share the same output information with SQAs. In this paper, we propose a real-world defense by Unifying Gradients (UniG) of different data so that SQAs could only probe a much weaker attack direction that is similar for different samples. Since such universal attack perturbations have been validated as less aggressive than the input-specific perturbations, UniG protects real-world DNNs by indicating attackers a twisted and less informative attack direction. We implement UniG efficiently by a Hadamard product module which is plug-and-play. According to extensive experiments on 5 SQAs, 2 adaptive attacks and 7 defense baselines, UniG significantly improves real-world robustness without hurting clean accuracy on CIFAR10 and imageNet. For instance, UniG maintains a model of 77.80% accuracy under 2500-query Square attack while the state-of-the-art adversarially-trained model only has 67.34% on CIFAR10. Simultaneously, UniG outperforms all compared baselines in terms of clean accuracy and achieves the smallest modification of the model output. The code is released at https://***/snowien/UniG-pytorch. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Implicit Tracking-Based Distributed Constraint-Coupled Optimization

arXiv

引用

arXiv 2022年

作者： Li, Jingwang Su, Housheng The School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China

A class of distributed optimization problem with a globally coupled equality constraint and local constrained sets is studied in this paper. For its special case where local constrained sets are absent, an augmented primal-dual gradient dynamics is proposed and analyzed, but it cannot be implemented distributedly since the violation of the coupled constraint needs to be used. Benefiting from the brand-new comprehending of a classical distributed unconstrained optimization algorithm, the novel implicit tracking approach is proposed to track the violation distributedly, which leads to the birth of the implicit tracking-based distributed augmented primal-dual gradient dynamics (IDEA). A projected variant of IDEA, i.e., Proj-IDEA, is further designed to deal with the general case where local constrained sets exist. With the aid of the Lyapunov stability theory, the convergences of IDEA and Proj-IDEA over undigraphs and digraphs are analyzed respectively. As far as we know, Proj-IDEA is the first constant step-size distributed algorithm which can solve the studied problem without the need of the strict convexity of local cost functions. Besides, if local cost functions are strongly convex and smooth, IDEA can achieve exponential convergence with a weaker condition about the coupled constraint. Finally, numerical experiments are taken to corroborate our theoretical results. © 2022, CC BY.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

NPGA: A Unified Algorithmic Framework for Decentralized Constraint-Coupled Optimization

arXiv

引用

arXiv 2022年

作者： Li, Jingwang Su, Housheng School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China

This work focuses on a class of general decentralized constraint-coupled optimization problems. We propose a novel nested primal-dual gradient algorithm (NPGA), which can achieve linear convergence under the weakest known condition, and its theoretical convergence rate surpasses all known results. More importantly, NPGA serves not only as an algorithm but also as a unified algorithmic framework, encompassing various existing algorithms as special cases. By designing different network matrices, we can derive numerous versions of NPGA and analyze their convergences by leveraging the convergence results of NPGA conveniently, thereby enabling the design of more efficient algorithms. Finally, we conduct numerical experiments to compare the convergence rates of NPGA and existing algorithms, providing empirical evidence for the superior performance of NPGA. Copyright © 2022, The Authors. All rights reserved.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Lithium-ion battery state-of-charge estimation using a real-time moving horizon estimation algorithm

Lithium-ion battery state-of-charge estimation using a real-...

引用

2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes, SAFEPROCESS 2021

作者： Yan, Jiayu Li, Song Wan, Yiming Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan China 29th Research Institute of China Electronics Technology Group Corporation Chengdu China

ISBN: (纸本)9781665401159

For battery management systems, it is significant to reliably estimate state-of-charge (SOC) from limited measurements in real time. Based on a nonlinear SOC-dependent equivalent circuit model, we propose a real-time moving horizon estimation (MHE) algorithm for SOC estimation. For efficient computation, the sequential quadratic programming strategy is applied, and each quadratic programming (QP) iteration is solved via the structure-exploiting forward and backward recursions. To account for the limited computation time allowed within each sampling interval, the proposed algorithm does not fully solve the receding horizon optimization problem over each sliding window, but performs fixed number of QP iterations. The simulation results show that compared to the existing fully solved MHE applied to SOC estimation, the proposed real-time MHE algorithm significantly saves computation time at the cost of a slight loss of estimation performance. © 2021 IEEE.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Energy Management Strategies for PEMFC-Lithium Battery Hybrid Power Systems Based on Pt Degradation

Energy Management Strategies for PEMFC-Lithium Battery Hybri...

引用

Chinese control Conference (CCC)

作者： Ziang Guo Beijia Li Linghong Zeng Jun Fu Chuang Sheng Xi Li School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry Huazhong University of Science and Technology Wuhan Hubei China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen China

Proton Exchange Membrane Fuel Cells(PEMFCs) are prone to decreased lifespan due to the degradation of the plat-inum(Pt) catalyst during operation. In this study, we have established a one-dimensional model to investigate the effects of different voltage conditions on Pt degradation. High potential is found to be the most significant factor affecting the degradation. Prolonged exposure to high potentials will significantly reduce the PEMFC's lifespan, and frequent voltage changes will exac-erbate the problem. To mitigate this issue, we have designed three energy management strategies with different limitations and simulated their performance in the operating scenario of a fuel-cell hybrid electric vehicle(FCHEV). The results demonstrate that strategies restricting high potential occurrences and voltage variations can effectively alleviate Pt degradation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GraphCFC: A Directed Graph Based Cross-Modal Feature Complementation Approach for Multimodal Conversational Emotion Recognition

arXiv

引用

arXiv 2022年

作者： Li, Jiang Wang, Xiaoping Lv, Guoqing Zeng, Zhigang The School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China

Emotion Recognition in Conversation (ERC) plays a significant part in Human-Computer Interaction (HCI) systems since it can provide empathetic services. Multimodal ERC can mitigate the drawbacks of uni-modal approaches. Recently, Graph Neural Networks (GNNs) have been widely used in a variety of fields due to their superior performance in relation modeling. In multimodal ERC, GNNs are capable of extracting both long-distance contextual information and inter-modal interactive information. Unfortunately, since existing methods such as MMGCN directly fuse multiple modalities, redundant information may be generated and diverse information may be lost. In this work, we present a directed Graph based Cross-modal Feature Complementation (GraphCFC) module that can efficiently model contextual and interactive information. GraphCFC alleviates the problem of heterogeneity gap in multimodal fusion by utilizing multiple subspace extractors and Pair-wise Cross-modal Complementary (PairCC) strategy. We extract various types of edges from the constructed graph for encoding, thus enabling GNNs to extract crucial contextual and interactive information more accurately when performing message passing. Furthermore, we design a GNN structure called GAT-MLP, which can provide a new unified network framework for multimodal learning. The experimental results on two benchmark datasets show that our GraphCFC outperforms the state-of-the-art (SOTA) approaches. Copyright © 2022, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

GNet: 3D Object Detection from Point Cloud with Geometry-Aware Network

GNet: 3D Object Detection from Point Cloud with Geometry-Awa...

引用

IEEE International Conference on Cyborg and Bionic Systems (CBS)

作者： Hao Ruan Bingrong Xu Junbin Gao Lianguang Liu Junting Lv Yin Sheng Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan China School of Automation Wuhan University of Technology Wuhan China

3D object detection based on point clouds in real-world applications has been a challenging task because the raw point cloud may be sparse or occluded. It may be caused by bad weather or limited sensor resolution, leading to decreasing detection performance. To this end, a novel highperformance Geometry-aware Network (GNet) is proposed and used to accurately detect 3D objects from sparse point clouds. Different from previous work that only regresses the offset of 3D bounding boxes numerically between ground truth (GT) and prediction, GNet considers the geometric information of 3D bounding boxes and combines the two effectively to achieve a better regression performance. In particular, Point Nets blocks learned voxel-wise features and the proposals are generated by the 3D voxel convolution neural network (voxel CNN). By utilizing the prior knowledge and the geometric properties of the 3D bounding boxes, the proposed novel OS-loss can improve detection performance and accelerate speed of inference. Furthermore, GNet takes advantage of prior geometry properties rather than only regressing the offset numerically. These speed up the convergence of the regression network. Finally, our proposed GNet was evaluated on the KITTI dataset for 3D objects and Bird’s Eye View (BEV) detection aspects. The results demonstrate that GNet can improve object detection performance for sparse point clouds.

关键词： Point cloud compression Location awareness Geometry Three-dimensional displays Neural networks Object detection Proposals

来源：评论

学校读者我要写书评

暂无评论

Multimodal Representations Learning Based on Mutual Information Maximization and Minimization and Identity Embedding for Multimodal Sentiment Analysis

arXiv

引用

arXiv 2022年

作者： Zheng, Jiahao Zhang, Sen Wang, Xiaoping Zeng, Zhigang School of Artificial Intelligence and Automation The Key Laboratory of Image Processing Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China

Multimodal sentiment analysis (MSA) is a fundamental complex research problem due to the heterogeneity gap between different modalities and the ambiguity of human emotional expression. Although there have been many successful attempts to construct multimodal representations for MSA, there are still two challenges to be addressed: 1) A more robust multimodal representation needs to be constructed to bridge the heterogeneity gap and cope with the complex multimodal interactions, and 2) the contextual dynamics must be modeled effectively throughout the information flow. In this work, we propose a multimodal representation model based on Mutual information Maximization and Minimization and Identity Embedding (MMMIE). We combine mutual information maximization between modal pairs, and mutual information minimization between input data and corresponding features to mine the modal-invariant and task-related information. Furthermore, Identity Embedding is proposed to prompt the downstream network to perceive the contextual information. Experimental results on two public datasets demonstrate the effectiveness of the proposed model. Copyright © 2022, The Authors. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Cooperative Target-Surrounding control of Unmanned Surface Vessels Based on MADDPG

Cooperative Target-Surrounding Control of Unmanned Surface V...

引用

Annual Conference of Industrial Electronics Society

作者： Taoman Li Fei Zhu Zihan Gan Zexing Zhou Xiaotao Wang Renzhi Lu Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China China Ship Scientific Research Center Wuxi China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan China

This article proposes a multi-agent deep reinforce-ment learning algorithm to control a fleet of unmanned surface vessels (USVs) that encircle and capture sea targets. First, a simulation environment for USVs is established based on a dynamic model; two-dimensional control variables are used to control movements in three directions. Second, the multi-agent deep deterministic policy gradient (MADDPG) algorithm is employed to achieve intelligent control of the USVs, using a reward function based on certain prior knowledge. Finally, centralized training and decentralized execution are used to complete the offline learning of multiple agents, and continuous action decisions are made based on the observations of the USV sensors. Simulations demonstrate that the method can capture stationary moving sea targets with any number of multi-agents under disturbances, and exhibits strong robustness and practicality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Thermoelectric Tracking control of Solid Oxide Fuel Cell System Using Adaptive Dynamic Programming

Thermoelectric Tracking Control of Solid Oxide Fuel Cell Sys...

引用

第34届中国控制与决策会议

作者： Xiao-long Wu Hongli Liu Hong Zhang Jinting Fu Bin Xie Han Hu Xi Li School of information engineering Nanchang University School of Artificial and Automation Key Laboratory of Education Ministry for Image Processing and Intelligent ControlHuazhong University of Science & Technology

An adaptive optimal control strategy for solid oxide fuel cell power generation systems(SOFCs) is proposed in this paper.A new estimator is proposed in a simple form to solve the modeling uncertainty,and express the control of SOFCs as an optimal control ***,a new system thermoelectric parameter tracking control strategy is *** strategy uses data-driven to build the recursive neural network model of the system thermoelectric *** order to ensure convergence,an adaptive law based on parameter estimation error is proposed to update the weights of neural networks *** simulation results show that the data-driven model can effectively identify the power generation process of solid oxide fuel cell *** the same time,the control method can realize the optimal tracking control of power,voltage,stack temperature and afterburner temperature with limited input.

关键词： Solid oxide fuel cell adaptive optimal control adaptive dynamic programming system thermoelectric performance

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：