检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Huang, Haonan Zhou, Guoxu Zheng, Yanghang Qiu, Yuning Wang, Andong Zhao, Qibin School of Automation Guangdong University of Technology Guangzhou China RIKEN AIP Tokyo Japan Key Laboratory of Intelligent Detection and the Internet of Things in Manufacturing Ministry of Education Guangzhou China

Deep Multi-view Clustering (DMVC) stands out as a widely adopted technique aiming at enhanced clustering performance by leveraging diverse data sources. However, the critical issue of vulnerability to adversarial attacks is unexplored due to the lack of well-defined attack objectives. To fill this crucial gap, this paper is the first work to investigate the possibility of adversarial attacks on DMVC models. Specifically, we introduce an adversarial attack with Generative Adversarial Networks (GANs) with the aim to maximally change the complementarity and consistency of multiple views, thus leading to wrong clustering. Building upon this adversarial context, in the realm of defense, we propose a novel Adversarially Robust Deep Multi-View Clustering by leveraging adversarial training. Based on the analysis from an information-theoretic perspective, we design an Attack Mitigator that provides a foundation to guarantee the adversarial robustness of our DMVC models. Experiments conducted on multiview datasets confirmed that our attack framework effectively reduces the clustering performance of the target model. Furthermore, our proposed adversarially robust method is also demonstrated to be an effective defense against such attacks. This work is a pioneer in exploring adversarial threats and advancing both theoretical understanding and practical strategies for robust multiview clustering. Code is available at https://***/libertyhhn/AR-DMVC. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of an Automatic Locking Nut Tightening Control System for a Vision Guided Robot 8

Design of an Automatic Locking Nut Tightening Control System...

引用

8th International Conference on Automation, Control and Robotics Engineering, CACRE 2023

作者： Chang, Kai Lu, Bolin Yin, Jian Tan, Guangchao Chinese Academy of Sciences Key Laboratory on Intelligent Detection Equipment Technology of Liaoning Province Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China

ISBN: (纸本)9798350302776

A set of automatic locking nut tightening control system for a vision guided robot is designed and implemented. Through hand-eye calibration, the coordinate system is unified. By the designed tool plate and tapered tooling, the calibrated reference location for the tightening tool is realized. According to the position and orientation of the reference screw, the vision system detects the offset of the current screw position, and guides the robot to adjust the pose of the tightening tool. By setting up the network topology of the control system, the data interaction of each subsystem is completed, and the automatic workflow is realized. The application of the system can avoid the relative movement between the tool and screw during the tightening process, and improve the tightening quality. © 2023 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised non-negative Tucker decomposition for tensor data representation

引用

Science China(Technological Sciences) 2021年第9期64卷 1881-1892页

作者： QIU YuNing ZHOU GuoXu CHEN XinQi ZHANG DongPing ZHAO XinHai ZHAO QiBin School of Automation Guangdong University of TechnologyGuangzhou 510006China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou 510006China Guangdong Key Laboratory of IoT Information Technology Guangzhou 510006China Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Ministry of EducationGuangzhou 510006China

Non-negative Tucker decomposition(NTD) has been developed as a crucial method for non-negative tensor data ***, NTD is essentially an unsupervised method and cannot take advantage of label information. In this paper, we claim that the low-dimensional representation extracted by NTD can be treated as the predicted soft-clustering coefficient matrix and can therefore be learned jointly with label propagation in a unified framework. The proposed method can extract the physicallymeaningful and parts-based representation of tensor data in their natural form while fully exploring the potential ability of the given labels with a nearest neighbors graph. In addition, an efficient accelerated proximal gradient(APG) algorithm is developed to solve the optimization problem. Finally, the experimental results on five benchmark image data sets for semi-supervised clustering and classification tasks demonstrate the superiority of this method over state-of-the-art methods.

关键词： tensor factorization non-negative Tucker decomposition semi-supervised learning label propagation

来源：评论

学校读者我要写书评

暂无评论

tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs) 41

tnGPS: Discovering Unknown Tensor Network Structure Search A...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zeng, Junhua Li, Chao Sun, Zhun Zhao, Qibin Zhou, Guoxu School of Automation Guangdong University of Technology Guangzhou China Tokyo Japan Tencent Inc. Shenzhen China Key Laboratory of Intelligent Detection and the Internet of Things in Manufacturing Ministry of Education Guangzhou China

Tensor networks are efficient for extremely high-dimensional representation, but their model selection, known as tensor network structure search (TN-SS), is a challenging *** several works have targeted TN-SS, most existing algorithms are manually crafted heuristics with poor performance, suffering from the curse of dimensionality and local *** this work, we jump out of the box, studying how to harness large language models (LLMs) to automatically discover new TN-SS algorithms, replacing the involvement of human *** observing how human experts innovate in research, we model their common workflow and propose an automatic algorithm discovery framework called *** proposed framework is an elaborate prompting pipeline that instruct LLMs to generate new TN-SS algorithms through iterative refinement and *** experimental results demonstrate that the algorithms discovered by tnGPS exhibit superior performance in benchmarks compared to the current state-of-the-art *** code is available at https://***/ChaoLiAtRIKEN/tngps. Copyright 2024 by the author(s)

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

MFDFormer: A Unified Multiscale Frequency Domain MetaFormer Framework for EEG-based Chronic Pain Recognition

引用

IEEE Internet of Things Journal 2025年第11期12卷 16511-16524页

作者： Qiu, Shihan Xie, Kan Yang, Junjie Yang, Qiyu Zhang, Bo Gu, Yuhong Xie, Feng Qiu, Rongjian Xie, Shengli Bai, Wenfang Guangdong University of Technology School of Automation China Guangdong Provincial Key Laboratory of Intelligent Systems and Optimization Integration Guangzhou510006 China Guangdong University of Technology Guangzhou510006 China School of Automation Guangdong University of Technology China 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou510006 China Guangzhou510006 China Guangzhou510080 China

Wearable electroencephalogram (EEG) devices have shown great potential in enabling real-Time monitoring of subtle changes in brain activity, providing new possibilities for the assessment and management of chronic pain. However, recognizing pain-related biomarkers from EEG data remains a complex, multi-Task challenge. Most existing research focuses on single-Task approaches and rarely addresses this issue within a unified framework. In this paper, we propose a novel deep neural network (DNN) model called multiscale frequency domain MetaFormer (MFDFormer), which is designed to simultaneously predict the presence, type, and intensity of chronic pain. The proposed MFDFormer comprises two primary sub-networks: multiscale feature extractor (MFE) and frequency domain MetaFormer (FDFormer) encoder. The MFE extracts diverse EEG features through convolutions with different kernel sizes, while a self-Attention mechanism is integrated into MFE to emphasize the importance of inter-dependency among these features. The FDFormer encoder refines the output MFE features using causal convolutions to capture local patterns and projects them into a higher-dimensional representation domain. Additionally, it incorporates spatial and temporal frequency domain learners in parallel to effectively capture the spatial-Temporal information of EEG data. Based on the publicly available BFCP dataset, the proposed MFDFormer demonstrates superior performance over state-of-The-Art algorithms, achieving accuracies of 97.59%, 96.02%, and 83.48% in pain or non-pain state classification (P/NSC), pain type classification (PTC), and pain intensity classification (PIC) tasks, respectively. This paper proposes a unified, end-To-end DNN-based framework for multi-Task chronic pain recognition, providing a reliable solution with the potential to advance pain diagnosis and management in iot and smart wearable applications. © 2014 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Fast nonnegative tensor ring decomposition based on the modulus method and low-rank approximation

引用

Science China(Technological Sciences) 2021年第9期64卷 1843-1853页

作者： YU YuYuan XIE Kan YU JinShi JIANG Qi XIE ShengLi School of Automation Guangdong University of TechnologyGuangzhou 510006China Guangdong-Hong Kong-Macao Joint Laboratory for Smart Manufacturing Guangzhou 510006China Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Ministry of EducationGuangzhou 510006China Guangdong Key Laboratory of IoT Information Technology Guangdong University of TechnologyGuangzhou 510006China

Nonnegative tensor ring(NTR) decomposition is a powerful tool for capturing the significant features of tensor objects while preserving the multi-linear structure of tensor data. The existing algorithms rely on frequent reshaping and permutation operations in the optimization process and use a shrinking step size or projection techniques to ensure core tensor nonnegativity, which leads to a slow convergence rate, especially for large-scale problems. In this paper, we first propose an NTR algorithm based on the modulus method(NTR-MM), which constrains core tensor nonnegativity by modulus transformation. Second, a low-rank approximation(LRA) is introduced to NTR-MM(named LRA-NTR-MM), which not only reduces the computational complexity of NTR-MM significantly but also suppresses the noise. The simulation results demonstrate that the proposed LRA-NTR-MM algorithm achieves higher computational efficiency than the state-of-the-art algorithms while preserving the effectiveness of feature extraction.

关键词： nonnegative tensor ring decomposition modulus method low-rank approximation

来源：评论

学校读者我要写书评

暂无评论

Learning the continuous-time optimal decision law from discrete-time rewards

引用

National Science Open 2024年第5期3卷 130-147页

作者： Ci Chen Lihua Xie Kan Xie Frank Leroy Lewis Yilu Liu Shengli Xie School of Automation Guangdong University of TechnologyGuangdong Key Laboratory of IoT Information TechnologyGuangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou 510006China UTA Research Institute the University of Texas at ArlingtonFort Worth 76118USA Department of Electrical Engineering and Computer Science University of TennesseeKnoxville 37996USA Oak Ridge National Laboratory Oak Ridge 37830USA Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou 510006China

The concept of reward is fundamental in reinforcement learning with a wide range of applications in natural and social *** an interpretable reward for decision-making that largely shapes the system's behavior has always been a challenge in reinforcement *** this work,we explore a discrete-time reward for reinforcement learning in continuous time and action spaces that represent many phenomena captured by applying physical *** find that the discrete-time reward leads to the extraction of the unique continuous-time decision law and improved computational efficiency by dropping the integrator operator that appears in classical results with integral *** apply this finding to solve output-feedback design problems in power *** results reveal that our approach removes an intermediate stage of identifying dynamical *** work suggests that the discrete-time reward is efficient in search of the desired decision law,which provides a computational tool to understand and modify the behavior of large-scale engineering systems using the optimal learned decision.

关键词： continuous-time state and action decision law learning discrete-time reward dynamical systems reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Control of Drilling Rig Power Head Speed 8th

Adaptive Control of Drilling Rig Power Head Speed

引用

8th International Conference on Advances in Construction Machinery and Vehicle Engineering, ICACMVE 2023

作者： Xu, Xinxin Cai, Wanzhi National Engineering Research Center for Highway Maintenance Equipment Chang’an University Xi’an710064 China Henan Key Laboratory of High. Grade Highway Detection and Maintenance Technology Xinxiang453003 China Key Laboratory of Intelligent Manufacturing of Construction Machinery Anhui230009 China

ISBN: (纸本)9789819718757

In the drilling process, the adjustment of drill pipe rotational speed is essential to accommodate the variations encountered in different geological strata. However, the existing low automation level in drilling rigs and heavy operator reliance often result in suboptimal speed regulation, leading to low drilling efficiency. An adaptive control approach for power head speed based on a fuzzy clustering algorithm was proposed, which utilizes the fuzzy clustering algorithm (FCM) to cluster drilling parameters, including drilling pressure, rotational speed, and drilling speed, to identify of distinct strata. Furthermore, the rotational speeds of the clustering centers of different strata were used as the input rotational speeds of its control system, the simulation results show that the speed control can be realized by controlling the opening of the valve port, and the fuzzy PID control is used to realize the adaptive control of the speed and the tracking of the speed curve. © The Author(s) 2024.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Learning-based Prescribed Rate Design for Output Regulation of Discrete-time Systems

Learning-based Prescribed Rate Design for Output Regulation ...

引用

第35届中国控制与决策会议

作者： Chengye Zhang Ci Chen Shengli Xie School of Automation Guangdong University of Technology Guangdong Key Laboratory of IoT Information Technology School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Ministry of Education

This paper presents data-driven output regulation designs for unknown discrete-time systems with the prescribed convergence *** integrating the convergence rate specified by the designer,the tracking problem is composed of learning two components:a feedback control gain and solutions to output regulator *** RL algorithm can learn the feedback control gain from system measurements from a specified auxiliary system without knowing its full *** output regulator equations associated with the convergence rate are solved as a feedforward control gain by leveraging the system data rather than the dynamic *** proposed designs assure that the tracking error asymptotically converges to zero at the prescribed convergence *** simulation results show the effectiveness of the proposed methods.

关键词： Reinforcement learning prescribed convergence rate model-free tracking design discrete-time systems

来源：评论

学校读者我要写书评

暂无评论

Approximately orthogonal nonnegative Tucker decomposition for flexible multiway clustering

引用

Science China(Technological Sciences) 2021年第9期64卷 1872-1880页

作者： QIU YiChun SUN WeiJun ZHANG Yu GU XiaoBo ZHOU GuoXu School of Automation Guangdong University of TechnologyGuangzhou 510006China Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Ministry of EducationGuangzhou 510006China Department of Bioengineering Lehigh UniversityBethlehemPA 18015USA Guangdong-Hong Kong-Macao Joint Laboratory for Smart Manufacturing Guangzhou 510006China Guangdong Key Laboratory of IoT Information Technology Guangzhou 510006China

High-order tensor data are prevalent in real-world applications, and multiway clustering is one of the most important techniques for exploratory data mining and compression of multiway data. However, existing multiway clustering is based on the K-means procedure and is incapable of addressing the issue of crossed membership degrees. To overcome this limitation, we propose a flexible multiway clustering model called approximately orthogonal nonnegative Tucker decomposition(AONTD). The new model provides extra flexibility to handle crossed memberships while fully exploiting the multilinear property of tensor *** accelerated proximal gradient method and the low-rank compression tricks are adopted to optimize the cost function. The experimental results on both synthetic data and real-world cases illustrate that the proposed AONTD model outperforms the benchmark clustering methods by significantly improving the interpretability and robustness.

关键词： multiway data analysis nonnegative Tucker decomposition flexible clustering accelerated proximal gradient

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：