检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Liang, Daojun Zhang, Haixia Wang, Jing Yuan, Dongfeng Zhang, Minggao School of Information Science and Engineering Shandong University China School of Control Science and Engineering Shandong University China Ocean College Jiangsu University of Science and Technology China School of Qilu Transportation Shandong University China Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration China

In this paper, we find that existing online forecasting methods have the following issues: 1) They do not consider the update frequency of streaming data and directly use labels (future signals) to update the model, leading to information leakage. 2) Eliminating information leakage can exacerbate concept drift and online parameter updates can damage prediction accuracy. 3) Leaving out a validation set cuts off the model’s continued learning. 4) Existing GPU devices cannot support online learning of large-scale streaming data. To address the above issues, we propose a novel online learning framework, Act-Now, to improve the online prediction on large-scale streaming data. Firstly, we introduce a Random Subgraph Sampling (RSS) algorithm designed to enable efficient model training. Then, we design a Fast Stream Buffer (FSB) and a Slow Stream Buffer (SSB) to update the model online. FSB updates the model immediately with the consistent pseudo- and partial labels to avoid information leakage. SSB updates the model in parallel using complete labels from earlier times. Further, to address concept drift, we propose a Label Decomposition model (Lade) with statistical and normalization flows. Lade forecasts both the statistical variations and the normalized future values of the data, integrating them through a combiner to produce the final predictions. Finally, we propose to perform online updates on the validation set to ensure the consistency of model learning on streaming data. Extensive experiments demonstrate that the proposed Act-Now framework performs well on large-scale streaming data, with an average 28.4% and 19.5% performance improvement, respectively. Experiments can be reproduced via https://***/Anoise/Act-Now. © 2024, CC BY.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Acceleration of Formation control Based on Hessian Matrix of Artificial Potential Field

Acceleration of Formation Control Based on Hessian Matrix of...

引用

Chinese control Conference (CCC)

作者： Haoran Han Zhilong Xi Maolong Lv Jian Cheng School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu P. R. China Air Traffic Control and Navigation College Air Force Engineering University Xian P. R. China

The formation control of multi-agent system has become a hotspot in recent years. One of the most commonly used methods is to use artificial potential field (APF) to generate the attractive and repulsive force to organize the agents into a low-energy and stable formation. In this paper, we regard the APF as the difference in the desired position, and introduce the derivative of the gradient of the APF with respect to time, which is simplified as the Hessian matrix of the APF, into the formation control from the perspective of trajectory tracking. The energy-based Lyapunov function is selected to prove the stability and collision avoidance ability of the proposed control law. Moreover, we show that the maneuverability of the multi-agent system is enormously improved with the additional Hessian matrix term.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Breather dynamics in an optomechanical array with staggered coupling

引用

Physical Review A 2025年第3期111卷 033502-033502页

作者： Yuan Zhao Yiheng Hou Yu Wang Zhuo Fan Wei Peng Qin Zhou Siliu Xu Shihua Chen Key Laboratory of Optoelectronic Sensing and Intelligent Control Hubei University of Science and Technology Xianning 437100 China School of Biomedical Engineering and Imaging Xianning Medical College Hubei University of Science and Technology Xianning 437100 China School of Electronic and Information Engineering Hubei University of Science and Technology Xianning 437100 China Research Center of Nonlinear Science School of Mathematics and Physical Sciences Wuhan Textile University Wuhan 430200 China School of Physics and Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing 211189 China

We present an approach toward generating highly controllable breathers, using an array of staggered optomechanical cavities that feature alternating coupling strengths. Four different types of breather states as well as stable two-soliton states are demonstrated to form in such an optomechanical array, thanks to the interplay between the photon-hopping induced tunneling effect and the photon-phonon coupling in the optomechanical cell. It is seen that both their photonic and phononic wave components manifest quasi-periodic oscillatory patterns and coherent localization. We unveil that such breather dynamics can be well controlled by adjusting the coupling strength, the cavity field decay, and the number of array cells. As a result, we observe an unusual odd-even lattice effect in that stable breathers are only available when the cell number is even. We anticipate that these findings from the staggered optomechanical configuration may expand the realm of cavity optomechanics, yielding promising applications such as on-chip manipulation of light propagation.

关键词： Solitons

来源：评论

学校读者我要写书评

暂无评论

The Preparation Method, Resistive Switching Mechanism and Application Prospects of Memristor

The Preparation Method, Resistive Switching Mechanism and Ap...

引用

2023 7th International Conference on Electrical, Mechanical and Computer engineering (ICEMCE)

作者： Jiao Li Ximei Zhao Tengfei Lei Lin Chai Shi Wang Yuna Yu Collaborative Innovation Center of Memristive and Computing Application Qilu Institute of Technology Jinan China School of Intelligent Manufacturing and Control Engineering Qilu Institute of Technology Jinan China Collaborative Innovation Center of Memristive and Computing Application Oilu Institute of Technology Jinan China College of Computer and Communication Engineering Qilu Institute of Technology Jinan China

Memristors have also become one of the most promising research hotspots for solving data storage and computing problems faced in the big data era. As an emerging electronic device, memristor has potentially important applications in information storage and processing. This paper constructs a rod-shaped TiO 2 −x nanoscale memristor with FTO/TiO 2 −x/Cu structure, whose reliability is based on the memory behavior and its conversion mechanism. Research progress including materials, preparation methods, resistive switching mechanism and application prospects are described. First, the constituent materials of memristor are introduced, focusing on metal oxides and organic materials such as titanium oxide (TiO 2 ). The choice of these materials is critical to memristor performance and applications. Secondly, the advantages and limitations of the preparation methods are discussed. Then the resistance switching mechanism of memristor was studied in depth, focusing on the generation principle and adjustment mechanism of memristor effect. These include important concepts such as charge migration, Schottky barrier formation and oxygen vacancy drift, which help to understand the electrical properties of memristors. In addition, we explore the prospects of memristors in practical applications. Finally, past and current work in this field is summarized, and the prospects and challenges of memristorrelated research are prospected.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on properties and composition of ancient glass based on PCA and gradient lifting tree model

Study on properties and composition of ancient glass based o...

引用

作者： Hengtian Zhao Junjia Du Yayue Xu Yujie Li Yingai Jin State Key Laboratory of Automotive Simulation and Control Jilin University College of Automotive Engineering Jilin University College of Computer Science and Technology Jilin University College of Journalism & Communication Jilin University

In order to help archaeologists better study ancient glass, uncover the mystery of the early Silk Road, and also better protect these cultural *** this paper, the properties and composition of ancient glass are *** types of glass samples were analyzed by PCA principal component analysis and weighted summation, and the type characteristic equation was *** calculating the candidate points iteratively in MATLAB, the optimal critical eigenvalue was set to 5, and the type judgment model was *** to get the type of the characteristic equation, the selection is related components as high potassium and the composition of class division, choose negative correlation components as lead, barium and the composition of class division, through the PCA principal component analysis of two types of glass data are reduced to 3d in the class we USES Kmeans clustering algorithm for two types of glass, For the sensitivity analysis of subclass partitioning, we used SOBOL global sensitivity analysis method, and obtained that principal component 1 would have the greatest impact on the model output.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Underwater Electric Dipole Source Localization Based on Hybrid Particle Swarm Optimization-Gravitational Search Algorithm

Underwater Electric Dipole Source Localization Based on Hybr...

引用

IEEE/OES China Ocean Acoustics (COA)

作者： Jiahui Liu Wentie Yang Zuoshuai Wang Jiong Chen Yidong Xu College of Information and Communication Engineering Harbin Engineering University Harbin China Hubei Key Laboratory of Marine Electromagnetic Detection and Control Wuhan Second Ship Design and Research Institute Wuhan China SiEngine Technology Co. Ltd. Wuhan China Yantai Research Institute of Harbin Engineering University Yantai China

ISBN: (数字)9798350340297

ISBN: (纸本)9798350340303

The localization process of the underwater electric dipole source involves solving the global optimal solution of a nonlinear function, which necessitates a multidimensional search and remarkable computational resources. Challenges including slow solution speed and the risk of missing the global optimal solution also exist. To address these challenges, in this study, a global search and localization method based on normalized electric field amplitude, which simultaneously matches and solves the target source position and dipole moment, is proposed. Moreover, the particle swarm optimization (PSO) algorithm is integrated with the gravitational search (GSA) algorithm to propose the improved time-varying inertia-weighted PSO and GSA hybrid optimization algorithm (TVIW-PSO-GSA), enabling rapid optimization and solution of underwater electric dipole source localization. The proposed algorithm exhibits strong convergence capabilities while ensuring local search accuracy. The simulation results reveal that the proposed algorithm achieves faster convergence speed and more accurate estimation performance when compared with traditional optimization algorithms.

关键词： Location awareness Accuracy Simulation Oceans Estimation Search problems Electric fields Particle swarm optimization Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Enhancing Ethereum Fraud Detection via Generative and Contrastive Self-supervision

arXiv

引用

arXiv 2024年

作者： Jin, Chengxiang Zhou, Jiajun Xie, Chenxuan Yu, Shanqing Xuan, Qi Yang, Xiaoniu Institute of Cyberspace Security College of Information Engineering Zhejiang University of Technology Hangzhou310023 China Binjiang Institute of Artificial Intelligence ZJUT Hangzhou310056 China Institute of Cyberspace Security College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China Institute of Cyberspace Security Zhejiang University of Technology Hangzhou310023 China Science and Technology on Communication Information Security Control Laboratory Jiaxing314033 China

he rampant fraudulent activities on Ethereum hinder the healthy development of the blockchain ecosystem, necessitating the reinforcement of regulations. However, multiple imbalances involving account interaction frequencies and interaction types in the Ethereum transaction environment pose significant challenges to data mining-based fraud detection research. To address this, we first propose the concept of meta-interactions to refine interaction behaviors in Ethereum, and based on this, we present a dual self-supervision enhanced Ethereum fraud detection framework, named Meta-IFD. This framework initially introduces a generative self-supervision mechanism to augment the interaction features of accounts, followed by a contrastive self-supervision mechanism to differentiate various behavior patterns, and ultimately characterizes the behavioral representations of accounts and mines potential fraud risks through multi-view interaction feature learning. Extensive experiments on real Ethereum datasets demonstrate the effectiveness and superiority of our framework in detecting common Ethereum fraud behaviors such as Ponzi schemes and phishing scams. Additionally, the generative module can effectively alleviate the interaction distribution imbalance in Ethereum data, while the contrastive module significantly enhances the framework’s ability to distinguish different behavior patterns. The source code will be available in https://***/GISec-Team/Meta-IFD. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

AUV Underwater Docking Guidance Method Based on Rotating Current Field

AUV Underwater Docking Guidance Method Based on Rotating Cur...

引用

IEEE/OES China Ocean Acoustics (COA)

作者： Jiahui Liu Zuoshuai Wang Wentie Yang Lanyi Liu Yidong Xu College of Information and Communication Engineering Harbin Engineering University Harbin China Hubei Key Laboratory of Marine Electromagnetic Detection and Control Wuhan Second Ship Design and Research Institute Wuhan China Hygon Information Technology Co. Ltd. Wuhan China Yantai Research Institute of Harbin Engineering University Yantai China

ISBN: (数字)9798350340297

ISBN: (纸本)9798350340303

Autonomous underwater vehicles (AUV) have been increasingly employed in marine resource exploration and development tasks; however, maintaining of long-term operations requires energy supplementation, which mandates docking with platforms. To address the challenges of AUV docking in intricate oceanic environments, this study proposes a novel docking guidance solution, grounded in the rotating current field mechanism. This approach employs multiple pairs of dipoles to transmit fixed phase difference signals, thereby creating a stable and uniform low-frequency current field region. Furthermore, based on the signal amplitude and phase characteristics relative to position, this paper introduces three AUV docking guidance methods able to achieve precise positioning and expedite the docking process. Experimental findings demonstrate that the proposed docking guidance method offers notable advantages in terms of positioning accuracy and feasibility of implementation, thus presenting a novel technical avenue for AUV underwater docking guidance.

关键词： Electrodes Autonomous underwater vehicles Accuracy Oceans Voltage Software Mathematical models Acoustics Marine vehicles

来源：评论

学校读者我要写书评

暂无评论

A flexible analytic wavelet transform and ensemble bagged tree model for electroencephalogram-based meditative mind-wandering detection

引用

Healthcare Analytics 2024年 5卷 100286-100286页

作者： Dadhich, Ajay Patel, Jaideep Tiwari, Rovin Verma, Richa Mishra, Pratha Jain, Jay Kumar Department of Electronics Instrumentation and Control Engineering Engineering College Ajmer Rajasthan Ajmer India Department of Computer Science and Engineering Sagar Institute of Research & Technology MP Bhopal India Department of Electronics & Communication Engineering Amity University MP Gwalior India Department of Computer Science and Application Makhanlal Chaturvedi University of Journalism and Mass Communication MP Bhopal India Department of Electronics & Communication Engineering Technocrats TIT Group Madhya Pradesh Bhopal India Department of Computer Science & Engineering Indian Institute of Information Technology (IIIT) MP Bhopal India

Mind-wandering (MW) is when an individual's concentration drifts away from the task or activity. Researchers found a greater variability in electroencephalogram (EEG) signals due to MW. Collecting more nuanced information from raw EEG data to examine the harmful effects of MW is time-consuming. This study proposes a multi-resolution assessment of EEG signals using the flexible analytic wavelet transform (FAWT). The FAWT algorithm decomposes raw EEG data into more representative sub-bands (SBs). Several statistical characteristics are derived from the obtained SBs, and the effects of MW during meditation on the EEG signals are investigated. A set of significant characteristics is chosen and fed into the machine learning modules using a 10-fold validation approach to detect MW subjects automatically. Our proposed framework attained the highest classification accuracy of 92.41%, the highest sensitivity of 93.56%, and the highest specificity of 91.97%. The proposed framework can be used to design a suitable brain-computer interface (BCI) system to reduce MW and increase meditation depth for holistic and long-term health in society. © 2023 The Author(s)

关键词： Brain–computer interface Classification Electroencephalogram signals Flexible analytic wavelet transform Machine learning Mind-wandering

来源：评论

学校读者我要写书评

暂无评论

EEG Based Deep Learning Model for Automated Classification of Frequent and Infrequent Readers

EEG Based Deep Learning Model for Automated Classification o...

引用

Brain Computer Interface & Healthcare Technologies (iCon-BCIHT), International Conference on

作者： Sridevi Veerasingam Kiran Boby Amal P Paulose V Varsha Dhole Shubham Raju Anisha S Rahul D. R R Joseph Ponniah Department of Instrumentation and Control Engineering NIT Tiruchirappalli Tiruchirappalli India Department of Electronics and Communication Engineering RIT Kottayam Kottayam India Department of Biomedical Engineering SSN College of Engineering Chennai India Department of English and Social Sciences PSG College of Arts and Science Coimbatore India Department of Humanities and Social Sciences Indian Institute of Technology Dhanbad India Department of Humanities and Social Sciences NIT Tiruchirappalli Tiruchirappalli India

ISBN: (数字)9798331540067

ISBN: (纸本)9798331540074

Reading comprehension is a complex cognitive process that involves semantic decoding, and schema integration influenced by reading practice. This study investigates the neural correlates of reading comprehension and explores how brain activation patterns differ between frequent and infrequent readers. Using Electroencephalography (EEG), the brain activation patterns were recorded from participants while performing the reading comprehension tasks. The EEG signal is recorded with a sampling rate of 1024 Hz to capture the dynamic changes in brain activation during reading tasks, revealing how frequent and infrequent readers differ in their cognitive processing and neural efficiency. The 21 channels of EEG signal acquired from 9 participants were pre-processed to obtain a 512 Hz band-limited signal. The pre-processed EEG signals were segmented before being fed into a twenty-four-layered convolutional neural network (CNN) model. The convolution stage extracts the temporal and spatial features, and the most significant features are extracted at the max-pooling stage. Frequent and infrequent readers are classified using the fully connected layer based on their EEG signals. The proposed model obtained a classification accuracy of 93.94%.

关键词： Cognitive processes Semantics Neural activity Medical services Brain modeling Feature extraction Dyslexia Electroencephalography Convolutional neural networks Reliability

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：