检索结果-内蒙古大学图书馆

Multiscale Feature-guided Adversarial Examples Quality Assessment via Hierarchical Perception of Human Visual System

引用

IEEE Transactions on Big Data 2024年

作者： Wen, Wenying Huang, Minghui Dong, Li Zhang, Yushu Fang, Yuming Jiangxi University of Finance and Economics School of Computing and Artificial Intelligence Jiangxi Nanchang China Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing Jiangxi Nanchang China Ningbo University Faculty of Electrical Engineering and Computer Science Zhejiang Ningbo China

Deep neural networks (DNNs) reveal significant robustness deficiencies due to their susceptibility to being misled by small and imperceptible adversarial examples, thus it is crucial to improve the robustness of DNNs against such harmful perturbations. The current Lp specification ignores differences in human visual perception when measuring similarity, and most existing image quality assessment (IQA) methods and adversarial example datasets lack subjective scores for evaluation. In this paper, we construct a new database of adversarial examples, called the AED, which contains 35 original images, 1050 adversarial examples, and the corresponding subjective scores of adversarial examples. Then, a novel full-reference IQA model for the quality evaluation of the adversarial examples is proposed by taking into full consideration the hierarchical perception of human visual system (HVS) and the outstanding capabilities of the multi-scale feature extraction network in feature extraction. Specifically, a feature encoding network that uses continuous convolution layers to pre-extract features and expand the receptive field of the image is employed. To simulate the HVS hierarchical perception, the features of different scales are further obtained by designing a multi-scale feature extraction network. The structural similarity scores of the feature maps at different scales are calculated for jointly arriving at the final IQA score of the adversarial examples. Experimental results have demonstrated that our proposed model is closer to the perception of HVS in small imperceptible distortions evaluation of adversarial examples compared with other classical and state-of- the-art models. © 2015 IEEE.

关键词： Adversarial examples HVS hierarchical perception Lp norms multiscale feature

来源：评论

学校读者我要写书评

暂无评论

Paving the Way to 6G: Outage Probability Analysis for FAS-ARIS Systems

arXiv

引用

arXiv 2024年

作者： Zheng, Jianchao Lai, Xiazhi Yao, Junteng Tang, Jie Pan, Yijin Wu, Tuo Yuen, Chau School of Computer Science and Engineering Huizhou University Huizhou516007 China School of Computer Science Guangdong University of Education Guangdong Guangzhou China Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo315211 China School of Electronic and Information Engineering South China University of Technology Guangzhou510640 China School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore National Mobile Communications Research Laboratory Southeast University Nanjing210096 China

In this paper, we pave the way to six-generation (6G) by investigating the outage probability (OP) of fluid antenna system (FAS)-active reconfigurable intelligent surface (ARIS) communication systems. We consider a FAS-ARIS setup consisting of a base station (BS) with a single fixed-position antenna and a receiver equipped with a fluid antenna (FA). Utilizing the block-correlation model, we derive a closed-form expression for the OP. Our analysis, supported by numerical results, confirms the accuracy and effectiveness of the derivation. Furthermore, the results demonstrate that the FAS-ARIS system significantly outperforms other configurations in terms of OP, highlighting its potential to enhance communication performance and reliability in future 6G networks. © 2024, CC BY.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

A Graph-Based Self-Calibration Technique for Cable-Driven Robots with Sagging Cable

A Graph-Based Self-Calibration Technique for Cable-Driven Ro...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： M. R. Dindarloo A. S. Mirjalili S. A. Khalilpour R. Khorrambakht Stephan Weiss H. D. Taghirad Advanced Robotics and Automated Systems (ARAS) Faculty of Electrical Engineering K. N. Toosi University of Technology Tehran Iran Department of Electrical and Computer Engineering Tandon School of Engineering Control/Robotics Research Laboratory New York University Brooklyn NY Department of Smart Systems Technologies University of Klagenfurt Austria

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

The efficient operation of large-scale Cable-Driven Parallel Robots (CDPRs) relies on precise calibration of kinematic parameters and the simplicity of the calibration process. This paper presents a graph-based self-calibration framework that explicitly addresses cable sag effects and facilitates the calibration procedure for large-scale CDPRs by only relying on internal sensors. A unified factor graph is proposed, incorporating a catenary cable model to capture cable sagging. The factor graph iteratively refines kinematic parameters, including anchor point locations and initial cable length, by considering jointly onboard sensor data and the robot’s kineto-static model. The applicability and accuracy of the proposed technique are demonstrated through Finite Element (FE) simulations, on both large and small-scale CDPRs subjected to significant initialization perturbations.

关键词： Meters Accuracy Perturbation methods Kinematics Robot sensing systems End effectors Software Calibration Sensors Finite element analysis

来源：评论

学校读者我要写书评

暂无评论

Moisture stable and ultrahigh-rate Ni/Mn-based sodium-ion battery cathodes via K^(+)decoration

引用

Nano Research 2023年第5期16卷 6890-6902页

作者： Tao Yuan Yuanyuan Sun Siqing Li Haiying Che Qinfeng Zheng Yongjian Ni Yixiao Zhang Jie Zou Xiaoxian Zang Shi-Hao Wei Yuepeng Pang Shuixin Xia Shiyou Zheng Liwei Chen Zi-Feng Ma School of Materials and Chemistry University of Shanghai for Science and TechnologyShanghai 200093China Zhejiang Natrium Energy Co. Ltd.Shaoxing 312000China In-situ Center for Physical Sciences Shanghai Electrochemical Energy Device Research CenterFrontiers Science Center for Transformative MoleculesSchool of Chemistry and Chemical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Faculty of Electrical Engineering and Computer Science Ningbo UniversityNingbo 315000China Key Laboratory of Solar Energy Utilization&Energy Saving Technology of Zhejiang Province Zhejiang Energy R&D Institute Co.Ltd.Hangzhou 311121China

As one of the most promising cathodes for sodium-ion batteries(SIBs),the layered transition metal oxides have attracted great attentions due to their high specific capacities and facile ***,their applications are still hindered by the problems of poor moisture stability and sluggish Na^(+)diffusion caused by intrinsic structural Jahn–Teller ***,we demonstrate a new approach to settle the above issues through introducing K^(+)into the structures of Ni/Mn-based *** physicochemical characterizations reveal that K^(+)induces atomic surface reorganization to form the birnessite-type K_(2)Mn_(4)O_(8).Combining with the phosphate,the mixed coating layer protects the cathodes from moisture and hinders metal dissolution into the electrolyte ***,K^(+)substitution at Na site in the bulk structure can not only widen the lattice-spacing for favoring Na^(+)diffusion,but also work as the rivet to restrain the grain crack upon *** as achieved K^(+)-decorated P2-Na_(0.67)Mn_(0.75)Ni_(0.2)5O_(2)(NKMNO@KM/KP)cathodes are tested in both coin cell and pouch cell configurations using Na metal or hard carbon(HC)as ***,the NKMNO@KM/KP||Na half-cell demonstrates a high rate performance of 50 C and outstanding cycling performance of 90.1%capacity retention after 100 cycles at 5 ***,the NKMNO@KM/KP||HC fullcell performed a promising energy density of 213.9 Wh·kg^(−1).This performance significantly outperforms most reported state-ofthe-art ***,by adopting this strategy on O3-NaMn_(0.5)Ni_(0.5)O_(2),we further proved the universality of this method on layered cathodes for SIBs.

关键词： sodium-ion battery cathode layered oxide material K^(+)decoration

来源：评论

学校读者我要写书评

暂无评论

Blood Pressure Estimation through Photoplethysmography and Machine Learning Models

Blood Pressure Estimation through Photoplethysmography and M...

引用

International Conference on Control, Instrumentation, and Automation

作者： Hanieh Mohammadi Bahram Tarvirdizadeh Khalil Alipour Mohammad Ghamari Department of Mechatronics Engineering Advanced Service Robots (ASR) Laboratory Faculty of New Sciences and Technologies University of Tehran Tehran Iran Department of Electrical and Computer Engineering Kettering University Flint Michigan USA

Blood pressure (BP) is a crucial health element, the fluctuations of which may have profound implications for an individual's well-being. Traditional methods of measuring BP, such as cuff-based and invasive devices, are not only uncomfortable but also unable to provide continuous monitoring. In response to this need, we propose a cuffless, continuous, and noninvasive BP measurement system utilizing photoplethysmograph (PPG) signals and machine learning (ML) models. PPG, an optical volumetric measurement technique, can identify alterations in blood volume within the tissue's vascular network. In this study, PPG signals obtained from diverse individuals underwent preprocessing and feature extraction. Subsequently, a feature selection technique was employed to identify suitable features. These selected features were then employed to train and evaluate ML models. Ultimately, we identified optimal regression models for independent estimation of diastolic blood pressure (DBP) and systolic blood pressure (SBP). Our findings indicate that the random forest (RF) model, in combination with the SelectFromModel feature selection method, outperformed other models. This model yielded significant outcomes, achieving a root mean square error (RMSE) of 6.61 for DBP and 10.06 for SBP, highlighting its superior performance in BP estimation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of BLE V.5 and BLE V.4 Communication Protocols for Multi-Agent Rescue Robots under Rayleigh Fading Channel

A Comparative Analysis of BLE V.5 and BLE V.4 Communication ...

引用

RSI/ISM International Conference on Robotics and Mechatronics (ICROM)

作者： Armin Javadi Rayeheh Niroomanesh Mohammad Ghamari Khalil Alipour Bahram Tarvirdizadeh Department of Mechatronics Engineering Faculty of New Sciences and Technologies Advanced Service Robots (ASR) Laboratory University of Tehran Tehran Iran Department of Electrical and Computer Engineering Kettering University Flint Michigan USA

This article presents a thorough evaluation of the applicability of Bluetooth Low Energy (BLE) version 5 as a communication protocol for multi-agent systems in search and rescue missions. The study extensively investigates the energy efficiency and reliability aspects of BLE v.5.3 to facilitate effective communication among multiple robots in such scenarios. A key focus of the research is the simulation of the advertising mode of BLE in the challenging presence of the Rayleigh fading channel, which is inevitable in the search and rescue environment. Furthermore, a comprehensive analysis is conducted by comparing BLE v.5.3 with the previous version, BLE v.4, with specific emphasis on energy efficiency and throughput metrics. Additionally, the study delves into the investigation of packet collision phenomena within the advertising mode of BLE v.5.3, shedding light on energy consumption, throughput performance, and the probability of packet collision. The findings of this study provide valuable insights for the design and implementation of communication systems within comparable scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design Method for Series-Fed Omnidirectional Filtenna Based on Full-Metal 3-D Printing

Design Method for Series-Fed Omnidirectional Filtenna Based ...

引用

Cross Strait Quad-Regional Radio Science and Wireless Technology Conference (CSRWTC)

作者： Shu-Qing Zhang Shu-Ting Wu Sai-Wai Wong Yejun He Zhonghe Zhang Xuzhou Yu State Key Laboratory of Radio Frequency Heterogeneous Integration Shenzhen Key Laboratory of Antennas and Propagation Guangdong Engineering Research Center of Base Station Antennas and Propagation College of Electronics and Information Engineering Shenzhen University China The Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macau SAR China

ISBN: (数字)9798331507794

ISBN: (纸本)9798331507800

This paper proposed a design approach for a series-fed omnidirectional antenna based on 3D full-metal printing. A major issue when designing series-fed antennas is the radiation pattern lobing caused by the unique feeding mechanism. In this paper, necessary adjustments are made based on the phase relationships between the currents and electric fields of each radiating element, resulting in improved radiation characteristics for the series-fed antenna. To validate this idea, the paper designs a rod-shaped full-metal omnidirectional antenna, achieving a wide operating bandwidth and high gain. Additionally, a filtering antenna with omnidirectional radiation is designed, which achieves a high level of out-of-band suppression as well as good omnidirectional radiation performance.

关键词： Wireless communication Phased arrays Filtering Design methodology Omnidirectional antennas Bandwidth Three-dimensional printing Antenna feeds Electric fields Antenna radiation patterns

来源：评论

学校读者我要写书评

暂无评论

Predicting Vascular Age using PPG Signals and Machine Learning Algorithms: A Non-Invasive Approach for Early Cardiovascular Risk Detection

Predicting Vascular Age using PPG Signals and Machine Learni...

引用

RSI/ISM International Conference on Robotics and Mechatronics (ICROM)

作者： Kiana Pilevar Abrisham Khalil Alipour Bahram Tarvirdizadeh Mohammad Ghaman Department of Mechatronics Engineering Faculty of New Sciences and Technologies Advanced Service Robots (ASR) Laboratory University of Tehran Tehran Iran Department of Electrical and Computer Engineering Kettering University Flint Michigan USA

Cardiovascular diseases (CVDs) pose a significant global health challenge, necessitating effective strategies for early risk assessment and intervention. Arterial stiffness, a critical parameter within the cardiovascular system, is considered a primary risk factor for CVD development. This parameter undergoes natural age-related structural and functional changes in arterial walls, resulting in increased arterial stiffness and reduced elasticity. These changes contribute to vascular aging and alter pulse wave velocity. Photoplethysmography (PPG) offers a non-invasive means to assess these alterations. Our research leverages PPG in combination with machine learning to develop a portable, non-invasive method for predicting vascular age. We identify and select 21 features from the fiducial points of the digital artery PPG signals obtained from simulated pulse waves across a diverse sample of healthy adults aged 25 to 75 years, its first derivative, and its second derivative waveforms. We assess the performance of machine learning algorithms, including Decision Tree, k-Nearest Neighbors (KNN), and Support Vector Machine (SVM). Among these algorithms, SVM outperformed the others, achieving an accuracy, precision, recall, and F1 score of 99%. This high accuracy underscores the potential of SVM in predicting vascular age. Accurate vascular age prediction within the healthy population has the potential to establish age-specific benchmarks, aiding in the detection of outliers indicative of accelerated cardiovascular aging or underlying cardiovascular diseases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vascular Age Prediction with PPG-Based LSTM Model

Vascular Age Prediction with PPG-Based LSTM Model

引用

International Conference on Control, Instrumentation, and Automation

作者： Kiana Pilevar Abrisham Khalil Alipour Bahram Tarvirdizadeh Mohammad Ghamari Department of Mechatronics Engineering Advanced Service Robots (ASR) Laboratory Faculty of New Sciences and Technologies University of Tehran Tehran Iran Department of Electrical and Computer Engineering Kettering University Flint Michigan USA

Vascular aging encompasses structural and functional changes in blood vessels associated with aging, including increased stiffness, reduced elasticity, and atherosclerosis development. These changes contribute to cardiovascular diseases (CVDs), a global health challenge necessitating precise assessment methods. Evaluating vascular age involves comparing blood vessel health to chronological age, offering insights into arterial stiffness for potential cardiovascular disease prevention. In this study, we introduce an approach using Long Short-Term Memory (LSTM) models for vascular age prediction. Leveraging simulated Photoplethysmogram (PPG) waveforms from the radial artery and a diverse sample of healthy adults aged 25 to 75, our method offers a non-invasive, cost-effective means of health evaluation. Following 5-fold cross-validation, the LSTM-based model demonstrated significant performance, with an average test accuracy, precision, recall, and F1 Score of approximately 97%. This innovative approach, with its non-invasive nature, minimal power consumption, and user-friendly interface, showcases the potential of PPG technology's integration into various devices, such as fitness trackers, smartphones, and tablets, ensuring its widespread accessibility and applicability in real-world health assessments. Accurate vascular age prediction aids in identifying cardiovascular aging deviations and underlying disorders, advancing assessment methods and contributing to proactive cardiovascular health management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive position tracking control of the lower limb exoskeleton robot with an uncertain dynamic model 18

Adaptive position tracking control of the lower limb exoskel...

引用

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Yuan, Ting Zhang, Chi Yi, Feng Lv, Pingping Li, Shupei Zhang, Meitong Ningbo University Ningbo Instituteof Materials Technology and Engineering Chinese Academy of Sciences Faculty of Electrical Engineering and Computer Science Ningbo315201 China Chinese Academy of Sciences Zhejiang Key Laboratory of Robotics and Intelligent Manufacturing Equipment Technology Ningbo Institute of Materials Technology and Engineering Ningbo315201 China University of Chinese Academy of Sciences Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences College of Materials Science and Opto-Electronic Technology Ningbo315201 China Hebei University of Science and Technology Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences School of Electrical Engineering Ningbo315201 China

ISBN: (纸本)9798350312201

In this paper, an adaptive position control method combining proportional-derivative (PD) control, RBF neural network-based sliding mode (SM) control, and feedforward (FF) control, i.e., PD-FF-SM control, is proposed to deal with the dynamic uncertainties, disturbances, and slow response in lower limb exoskeleton robot system. The Lagrange method is utilized to establish dynamic models that ignore the uncertainties and disturbances in the swing phase and supporting phase. Then, the PD feedback controller is designed with a sliding surface function, to keep the system stable. The FF controller is adopted to improve the response by using dynamic models. And the RBF neural network-based SM controller is designed to compensate for the uncertainties and disturbances. The system's stability is verified by Lyapunov's theorem. The simulation results show that the proposed control method can effectively reduce the error of position tracking and response time with inaccurate dynamic modeling. © 2023 IEEE.

关键词： Sliding mode 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：