检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Meng, Lubin Jiang, Xue Huang, Jian Li, Wei Luo, Hanbin Wu, Dongrui The Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Wuhan430074 China The School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan China

A brain-computer interface (BCI) establishes a direct communication pathway between the brain and an external device. Electroencephalogram (EEG) is the most popular input signal in BCIs, due to its convenience and low cost. Most research on EEG-based BCIs focuses on the accurate decoding of EEG signals;however, EEG signals also contain rich private information, e.g., user identity, emotion, and so on, which should be protected. This paper first exposes a serious privacy problem in EEG-based BCIs, i.e., the user identity in EEG data can be easily learned so that different sessions of EEG data from the same user can be associated together to more reliably mine private information. To address this issue, we further propose two approaches to convert the original EEG data into identity-unlearnable EEG data, i.e., removing the user identity information while maintaining the good performance on the primary BCI task. Experiments on seven EEG datasets from five different BCI paradigms showed that on average the generated identity-unlearnable EEG data can reduce the user identification accuracy from 70.01% to at most 21.36%, greatly facilitating user privacy protection in EEG-based BCIs. © 2024, CC BY.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Fpga-Only Mvt Digitizer for Neutron Logging Apparatus

SSRN

引用

SSRN 2022年

作者： Zhao, Siyuan Wang, Zhen Li, Muyao Zhang, Pu Cheng, Jingjing China -Belt and Road Joint Laboratory On Measurement and Control Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Well-Tech R&D Institutes China Oilfield Service Limited Beijing101149 China

The multi-voltage threshold (MVT) digitization method has been widely used in energy spectrum measurement, thanks to its property of direct sampling fast pulse signals and cost efficiency. Many field-deployable applications require high reading accuracy, even outside of normal temperature ranges, this is difficult and impractical, and may involve the need for additional temperature sensors and their circuitry. In our approach, we used an on-site temperature compensation method, it solves the problem of the internal delay line time drifting (IDLTD), temperature compensation is performed using only the temperature characteristics of the FPGA's internal delay lines to detect temperature changes. In hardware software co-design FPGAs are being used in order to accelerate existing solutions so they meet real-time constraints. The algorithm validation and board architecture are described. A full metrological characterization of the module is reported and temperature tests results are discussed. © 2022, The Authors. All rights reserved.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Bearing remaining useful life prediction using spatial-temporal multiscale graph convolutional neural network

引用

measurement Science and technology 2023年第8期34卷 085009-085009页

作者： Yang, Xiaoyu Li, Xinye Zheng, Ying Zhang, Yong Wong, David Shan-Hill The Belt and Road Joint Laboratory on Measurement and Control Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Information Science and Engineering Wuhan University of Science and Technology Wuhan430081 China Department of Chemical Engineering National Tsing-Hua University Hsin-Chu Taiwan

Remaining useful life (RUL) prediction of bearings is important to guarantee their reliability and formulate a maintenance strategy. Recently, deep graph neural networks (GNNs) have been applied to predict the RUL of bearings. However, they usuallylack dynamic features, use manual stage identification, and experience the over-smoothing problem, which will have a negative effect on the prediction accuracy. This paper proposes a new framework for bearing RUL prediction based on spatial-temporal multi-scale graph convolutional neural network (STMSGCN), which can improve the accuracy of prediction by solving the above-mentioned problems. Specifically, different to the most-used static feature of bearings, a dynamic feature that can capture the time-varying change of vibration energy is proposed. A sliding window alarm method is proposed to detect the fault occurrence time (FOT), which can offer an accurate healthy stage rather than human-defined methods. Then, the STMSGCN is proposed to predict the RUL of bearings, which solves the over-smoothing problem of the deep GNN model. The PRONOSTIA platform is adopted to verify the proposed method. The results verify that the sliding window alarm method can detect the FOT faster for slowly degrading bearings, and the proposed STMSGCN structure gives higher prediction accuracy compared to the existing methods. © 2023 IOP Publishing Ltd

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Adversarial Filtering Based Evasion and Backdoor Attacks to EEG-Based Brain-Computer Interfaces

arXiv

引用

arXiv 2024年

作者： Meng, Lubin Jiang, Xue Chen, Xiaoqing Liu, Wenzhong Luo, Hanbin Wu, Dongrui Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan430074 China

A brain-computer interface (BCI) enables direct communication between the brain and an external device. Electroencephalogram (EEG) is a common input signal for BCIs, due to its convenience and low cost. Most research on EEG-based BCIs focuses on the accurate decoding of EEG signals, while ignoring their security. Recent studies have shown that machine learning models in BCIs are vulnerable to adversarial attacks. This paper proposes adversarial filtering based evasion and backdoor attacks to EEG-based BCIs, which are very easy to implement. Experiments on three datasets from different BCI paradigms demonstrated the effectiveness of our proposed attack approaches. To our knowledge, this is the first study on adversarial filtering for EEG-based BCIs, raising a new security concern and calling for more attention on the security of BCIs. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis of Quadrotor UAV Propeller with Local-Global Attention-Based Graph Neural Networks

Fault Diagnosis of Quadrotor UAV Propeller with Local-Global...

引用

Data Driven control and Learning Systems (DDCLS)

作者： Zhiwei Wang Shaojun Liang Ye Sun Yi Yang Yanwei Wang Ying Zheng Belt and Road Joint Laboratory on Measurement and Control Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Ordnance Sergeant Army Engineering University Wuhan China School of Mechanical & Electrical Engineering Wuhan Institute of Technology Wuhan

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

With the wide application of Quadrotor Unmanned Aerial Vehicles (QUAV) in military and civilian fields, its flight reliability problem has become a hot research topic. The propellers, which are the important components relating to the performance of QUAV, play a central role in safe flight. Traditional data-driven fault diagnosis methods of QUAV are based on Euclidean distance, which cannot effectively capture the interrelationship of multiple variables. In this paper, we treat the fault diagnosis of QUAV propeller as a node classification problem in non-Euclidean infinite dimensional space by introducing the method of Local-Global Attention-based Graph Neural Network (LGA-GNN). First, the graph topology is constructed using the KNN method based on the real flight log of the QUAV. Then, the local and global attention strategies are integrated to form a graph-based collaborative feature extraction model. Finally, a unified end-to-end fault diagnosis framework tailored for QUAV is proposed. In the experiment section, real flight data of QUAV with different propeller fault conditions are collected, and the effectiveness and superiority of the proposed method are verified by comparing with other methods based on real data.

关键词： Fault diagnosis Learning systems Propellers Network topology Nearest neighbor methods Autonomous aerial vehicles Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation Integrated with Feature-Enhanced Convolutional Neural Network for Imbalanced Fault Diagnosis in Rolling Bearings

Data Augmentation Integrated with Feature-Enhanced Convoluti...

引用

Data Driven control and Learning Systems (DDCLS)

作者： Li Wang Qilin Qu Yanwei Wang David Shan-Hill Wong Ying Zheng China -Belt and Road Joint Laboratory On Measurement and Control Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Mechanical & Electrical Engineering Wuhan Institute of Technology Wuhan Department of Chemical Engineering National Tsing-Hua University Hsinchu Taiwan

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

Imbalance in fault samples is a key problem with most rolling bearing datasets in real industrial processes, limiting the performance of fault detection. In addition, existing fault diagnosis methods for rolling bearings do not adopt a modular division between the initial layer and the classification layer. This lack of modularization inhibits the full activation of the network's feature extraction capabilities and impedes subsequent model improvements. In this paper, a novel fault diagnosis method based on data augmentation integrated with a feature-enhanced convolutional neural network (DA-FECNN) is proposed. First, Variational Autoencoder-Generative Adversarial Network (VAE-GAN) is utilized to expand the number of fault samples and improve the diversity of few-shot. Second, a uniform feature-enhanced structure is designed with a feature extraction module, a multi-scale classification module, and a reconstruction module. The network's ability on feature extraction is improved by focusing on high quality features. Thereby, accurate fault classification is realized simultaneously. Experiments on real world data show the effectiveness of the proposed method on fault diagnosis task.

关键词： Fault diagnosis Learning systems Accuracy Limiting Rolling bearings Feature extraction Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Temperature measurement based on electron spin resonance of magnetic nanoparticles

arXiv

引用

arXiv 2021年

作者： Wang, Shuai Zhong, Jing Liu, Wenzhong School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Ministry of Education Wuhan430074 China School of Instrumentation and Optoelectronic Engineering Beihang University Beijing100191 China

Magnetic nanoparticles (MNPs) have excellent magnetic-temperature characteristic. However, current temperature measurement based on MNPs is interfered by concentration. Utilizing the electron spin resonance (ESR), we propose a highly sensitive temperature measurement method without concentration coupling. The anisotropic field is affected by temperature, thus affecting the g-value. The influence of the MNP concentration, size, and the data analysis method on temperature estimation are studied. The optimal temperature sensitivity is achieved with 15-nm MNPs while Gaussian smoothing method allows an optimal accuracy at Fe concentration of 5 mg/ml with a standard deviation of 0.07 K. Copyright © 2021, The Authors. All rights reserved.

关键词： Magnetic moments

来源：评论

学校读者我要写书评

暂无评论

Trajectory Planning for Minimizing Floating Pedestal Disturbance of Spatial Dual-Arm Robots

Trajectory Planning for Minimizing Floating Pedestal Disturb...

引用

第43届中国控制会议

作者： Hui Zhang Xiaozhong Zuo Wei Zhang Sheng Gao College of Electrical and Control Engineering Shenyang Jianzhu University State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of Sciences China-Portugal Belt and Road Joint Laboratory on Space & Sea Technology Advanced Research

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This paper addresses the trajectory planning problem of a spatial dual-arm robot and proposes a method to minimize the floating pedestal perturbation using a nonlinear planning *** joint angle of the dual-arm robot is the optimization variable,and the positioning accuracy of the end-effector and the pedestal disturbance are the optimization objective and constraints,respectively.A constrained multi-objective optimization problem is formulated,and the kinematic model of the robot is established by parameterizing the joint trajectory.A penalty factor and a collision detection mechanism are applied to ensure the safety of the planning process.A nonlinear planning method is used to solve the optimization problem and obtain the optimal joint trajectory of the dual-arm *** results demonstrate that the proposed method effectively reduces the base disturbance while ensuring the positioning accuracy of the end-effector.

关键词： trajectory planning space dual-arm robot multi-objective optimization fmincon

来源：评论

学校读者我要写书评

暂无评论

A Power Split Strategy for a Vehicular Hybrid Energy Storage System Using Adaptive Neuro Fuzzy Inference System

A Power Split Strategy for a Vehicular Hybrid Energy Storage...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Jiao Li Lijun Zhang Longzhi Yang Bo Wang School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Wuhan China Department of Computer Science and Digital Technologies Faculty of Engineering and Environment Northumbria University Newcastle upon Tyne U.K

This paper presents a real-time power split strategy for a battery-supercapacitor hybrid energy storage system. The objective of the proposed strategy is to alleviate battery degradation through effective supercapacitor utilization. The proposed strategy employs an adaptive neural fuzzy inference system, which is capable of learning a power split strategy from offline optimization results and distributing power in real-time. The performance of the strategy proposed and a low pass filtering technique is compared through simulations. The results demonstrate that the proposed method can effectively reduce battery capacity loss and perform well under unknown driving cycles in real time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Highly sensitive detection of magneto-optical markers based on magneto-optical gate effect

arXiv

引用

arXiv 2023年

作者： Cui, Xinchao Lu, Chong Liu, Chunping Liu, Wenzhong School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Tongji Medical College Huazhong University of Science and Technology Wuhan430022 China The China-Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518063 China

In this paper, a new concept of magnetic nanoparticles as magneto-optical markers is proposed, and a "magneto-optical gate" effect is explored. High-sensitivity detection of magnetic nanoparticles (MNPs) was developed based on this principle. Under irradiation from monochromatic light with a wavelength much larger than the size of a given MNP, Rayleigh scattering occurs on the MNP surface. The MNPs anisotropic and orientate themselves into chains, meaning that the Rayleigh scattering now decreases under magnetic field excitation. After applying an AC magnetic field of frequency f, the transmitted light passing through the MNPs reagent generates an AC signal with a frequency of 2f. Moreover, the 2f signal disappears after removal of the magnetic field. This creates a "magneto-optical gate" effect. The instantaneous and highly sensitive detection of magneto-optical markers with a concentration of 0.2 µg/mL and an effective optical path length of 10 µm is realized based on this "magneto-optical gate" effect. Copyright © 2023, The Authors. All rights reserved.

关键词： Rayleigh scattering

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：