检索结果-内蒙古大学图书馆

Interpretable foundation models as decryptors peering into the Earth system

The Innovation 2024年第5期5卷 21-22页

作者： Chenyu Li Danfeng Hong Bing Zhang Tianjun Liao Naoto Yokoya Pedram Ghamisi Min Chen Lizhe Wang Jon Atli Benediktsson Jocelyn Chanussot Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China School of Electronic Electricaland Communication EngineeringUniversity of Chinese Academy of SciencesBeijing 100049China College of Resources and Environment University of Chinese Academy of SciencesBeijing 100049China Academy of Military Sciences Beijing 100000China Graduate School of Frontier Sciences The University of TokyoChiba 277-8561Japan Helmholtz-Zentrum Dresden-Rossendorf Helmholtz Institute Freiberg for Resource Technology09599 FreibergGermany Key Laboratory of Virtual Geographic Environment(Ministry of Education of PRC) Nanjing Normal UniversityNanjing 210023China School of Computer Science China University of GeosciencesWuhan 430078China Faculty of Electrical and Computer Engineering University of Iceland102 ReykjavikIceland University Grenoble Alpes InriaCNRSGrenoble INPLJK38000 GrenobleFrance

THE EARTH SYSTEM AMID THE BIG DATA *** processes of the Earth system drive interactions between energy,matter,and life,and a comprehensive understanding of their full evolutionary trajectory is critical for sustainable human *** modeling primarily relies on a set of theoretical equations to simulate dynamic process such as the carbon-nitrogen cycle,solar radiation dynamics,and terrestrial ecosystem dynamics.1 Despite the extensive modeling experience of Earth scientists,the rapid advancement of Earth observation techniques has led to a significant increase in the volume of databases,with data accumulating daily or even *** has exacerbated the conflict between the capacity for data collection and utilization for big Earth ***,there is an urgent need to enhance the intelligent processing and analysis of big Earth data.

关键词： dynamics. system foundation

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Granule Density-Based Outlier Detection with Multi-Scale Granular Balls

arXiv

引用

arXiv 2025年

作者： Gao, Can Tan, Xiaofeng Zhou, Jie Ding, Weiping Pedrycz, Witold The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The School of Artificial Intelligence and Computer Science Nantong University Nantong226019 China The Faculty of Data Science City University of Macau Macau999078 China The Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Systems Research Institute Polish Academy of Sciences Warsaw Poland The Department of Electrical and Computer Engineering King Abdulaziz University Jeddah Saudi Arabia The Department of Computer Engineering Istinye University Istanbul Turkey

Outlier detection refers to the identification of anomalous samples that deviate significantly from the distribution of normal data and has been extensively studied and used in a variety of practical tasks. However, most unsupervised outlier detection methods are carefully designed to detect specified outliers, while real-world data may be entangled with different types of outliers. In this study, we propose a fuzzy rough sets-based multi-scale outlier detection method to identify various types of outliers. Specifically, a novel fuzzy rough sets-based method that integrates relative fuzzy granule density is first introduced to improve the capability of detecting local outliers. Then, a multi-scale view generation method based on granular-ball computing is proposed to collaboratively identify group outliers at different levels of granularity. Moreover, reliable outliers and inliers determined by the three-way decision are used to train a weighted support vector machine to further improve the performance of outlier detection. The proposed method innovatively transforms unsupervised outlier detection into a semi-supervised classification problem and for the first time explores the fuzzy rough sets-based outlier detection from the perspective of multi-scale granular balls, allowing for high adaptability to different types of outliers. Extensive experiments carried out on both artificial and UCI datasets demonstrate that the proposed outlier detection method significantly outperforms the state-of-the-art methods, improving the results by at least 8.48% in terms of the Area Under the ROC Curve (AUROC) index. The source codes are released at https://***/Xiaofeng-Tan/MGBOD. © 2025, CC BY.

关键词： Granulation

来源：评论

学校读者我要写书评

暂无评论

Secure MIMO Communication Relying on Movable Antennas

arXiv

引用

arXiv 2024年

作者： Tang, Jun Pan, Cunhua Zhang, Yang Ren, Hong Wang, Kezhi The Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China National Mobile Communications Research Laboratory Southeast University Nanjing China The Department of Computer Science Brunel University London UxbridgeUB8 3PH United Kingdom

This paper considers a movable antenna (MA)-aided secure multiple-input multiple-output (MIMO) communication system consisting of a base station (BS), a legitimate information receiver (IR) and an eavesdropper (Eve), where the BS is equipped with MAs to enhance the system's physical layer security (PLS). Specifically, we aim to maximize the secrecy rate (SR) by jointly optimizing the transmit precoding (TPC) matrix, the artificial noise (AN) covariance matrix and the MAs' positions under the constraints of the maximum transmit power and the minimum distance between MAs. To solve this non-convex problem with highly coupled optimization variables, the block coordinate descent (BCD) method is applied to alternately update the variables. Specifically, we first reformulate the SR into a tractable form by utilizing the minimum mean square error (MMSE) method, and derive the optimal TPC matrix and the AN covariance matrix with fixed MAs' positions by applying the Lagrangian multiplier method in semi-closed forms. Then, the majorization-minimization (MM) algorithm is employed to iteratively optimize each MA's position while keeping others fixed. Finally, simulation results are provided to demonstrate the effectiveness of the proposed algorithms and the significant advantages of the MA-aided system over conventional fixed position antenna (FPA)-based system in enhancing system's security. Copyright © 2024, The Authors. All rights reserved.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

RIS-Enabled Joint Near-Field 3D Localization and Synchronization in SISO Multipath Environments

arXiv

引用

arXiv 2024年

作者： Yan, Han Chen, Hua Liu, Wei Yang, Songjie Wang, Gang Yuen, Chau The Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo315211 China The Zhejiang Key Laboratory of Mobile Network Application Technology Ningbo315211 China The School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom The National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China China The School of Electrical and Electronics Engineering Nanyang Technological University Singapore

Reconfigurable Intelligent Surfaces (RIS) show great promise in the realm of 6th generation (6G) wireless systems, particularly in the areas of localization and communication. Their cost-effectiveness and energy efficiency enable the integration of numerous passive and reflective elements, enabling near-field propagation. In this paper, we tackle the challenges of RIS-aided 3D localization and synchronization in multipath environments, focusing on the near-field of mmWave systems. Specifically, our approach involves formulating a maximum likelihood (ML) estimation problem for the channel parameters. To initiate this process, we leverage a combination of canonical polyadic decomposition (CPD) and orthogonal matching pursuit (OMP) to obtain coarse estimates of the time of arrival (ToA) and angle of departure (AoD) under the far-field approximation. Subsequently, distances are estimated using l1-regularization based on a near-field model. Additionally, we introduce a refinement phase employing the spatial alternating generalized expectation maximization (SAGE) algorithm. Finally, a weighted least squares approach is applied to convert channel parameters into position and clock offset estimates. To extend the estimation algorithm to ultra-large (UL) RIS-assisted localization scenarios, it is further enhanced to reduce errors associated with far-field approximations, especially in the presence of significant near-field effects, achieved by narrowing the RIS aperture. Moreover, the Cramér-Rao Bound (CRB) is derived and the RIS phase shifts are optimized to improve the positioning accuracy. Numerical results affirm the efficacy of the proposed estimation algorithm. © 2024, CC BY.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Research on Rice Disease Identification Based on Improved ShuffleNet V2 Network

Research on Rice Disease Identification Based on Improved Sh...

引用

computer Technology and Information Science (ISCTIS), International Symposium on

作者： Zhihuan Chen Shenming Gu Minghui Yu Zhaoquan Huang Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University Zhoushan China School of Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China College of Mathematics and Computer Science Zhejiang Normal University Jinhua China

ISBN: (数字)9798350354560

ISBN: (纸本)9798350354577

How to efficiently and accurately identify rice diseases plays a crucial role in rice planting and production. Deploying large convolutional neural networks in practical applications is challenging due to their complex model parameters, while lightweight networks often compromise accuracy to reduce model size. In this study, we introduce a lightweight and precise network called GM-ShuffleNet for rice disease recognition. Building upon the ShuffleNet V2 network, we integrated the Ghost module and MCA attention mechanism, adjusted the network structure and number of channels, and replaced the ReLU activation function with Mish. Through comparative experiments, the accuracy of GM-ShuffleNet algorithm proposed in this paper reaches 96.20%, which is superior to ShuffleNet V2 and other excellent lightweight networks. In addition, in terms of model complexity comparison, the number of model parameters and FLOPs decreased by 82.54% and 77.44% respectively compared with the original network.

关键词： Information science Accuracy Attention mechanisms Computational modeling Buildings Production Complexity theory Convolutional neural networks Diseases

来源：评论

学校读者我要写书评

暂无评论

Capacity Maximization for V2I-VLC System with Angular Diversity Receiver

Capacity Maximization for V2I-VLC System with Angular Divers...

引用

Communications and Networking (MeditCom), IEEE International Mediterranean Conference on

作者： Selma Yahia Yassine Meraihi Amar Ramdane- Cherif Hossien B. Eldeeb Sami Muhaidat Tu Dac Ho LIST Laboratory University of M’Hamed Bougara Boumerdes Boumerdes Algeria LISV Laboratory University of Versailles St-Quentin-en-Yvelines Velizy France Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi UAE Department of Electrical Engineering Faculty of Engineering Science and Technology UiT Arctic University of Norway

This paper investigates the effectiveness of angle diversity technology-based vehicle-to-infrastructure (V2I) visible light communication (VLC) system designed for a multi-lane road scenario. Cars use their headlights to transmit signals to a traffic light pole, which is equipped with an angle diversity receiver (ADR) comprising three photodetectors (PD) arranged in different directions to improve signal reception from various directions. We utilize an advanced ray tracing channel modeling approach and investigate the impact of the number of PDs and the elevation angles on the received power. Additionally, we conduct a comprehensive performance analysis in terms of capacity, considering different car positions along the road. The results demonstrate that the V2I-VLC system with ADR achieves a channel capacity of over 2.5 Mb/s at a transmission distance of 50 meters, highlighting its potential to enhance V2I-VLC connectivity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visual recognition of wheel hubs with convolutional neural network

Visual recognition of wheel hubs with convolutional neural n...

引用

Consumer Electronics and computer engineering (ICCECE), 2021 IEEE International Conference on

作者： Yining Dai Zaojun Fang Caiming Zhong Faculty of Electrical Engineering and Computer Science Ningbo University NingBo Zhejiang China Zhejiang Key Laboratory of Robotics and Intelligent Manufacturing Equipment Technology Ningbo Institute of Materials Technology & Engineering Chinese Academy of Sciences

The traditional recognition methods of wheel hubs are mainly based on extracted feature matching. In practical production, their accuracy, robustness and processing speed are usually greatly affected. To overcome these problems, this paper proposes a recognition method based on convolutional neural network. The basic steps include two parts: wheel image pre-processing and wheel model classification. The image processing method, mainly using the detection algorithm of hough circles, obtains the center coordinates and radius of the wheel. Then it maps the ring-shaped wheel in right-angle coordinates to polar coordinates by the center coordinates and radius. This stepcan extract the ring-shaped feature information of the wheel image and reduce the influence generated by redundant features. Then a network architecture with an improved Resnet is designed to classify the wheel models. Finally, the wheel model recognition algorithm is evaluated, and the effectiveness of the method is verified through the comparison experiments of SVM, KNN and other models. The experiments show that the recognition accuracy can reach about 99.8% for 10 kinds of wheels.

关键词：

来源：评论

学校读者我要写书评

暂无评论

One-Click Total Bacterial Quantification: An All-in-One Automatic Microfluidic Platform for Simple Liquid Food Samples

引用

IEEE Sensors Journal 2025年第12期25卷 22667-22676页

作者： Yang, Ping Liang, Baihui Yuan, Haojun Zheng, Junmei Zou, Tinglang Xin, Pengfei Yan, Xinxin Wu, Jinlei Luo, Zhiquan Jin, Qinghui Gao, Wanlei Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China Healthy & Intelligent Kitchen Engineering Research Center of Zhejiang Province Zhejiang Ningbo315336 China Zhejiang Fashion Institute of Technology Mechanical and Electrical Engineering School Zhejiang Ningbo315211 China Ningbo Polytechnic Zhejiang Ningbo315800 China Chinese Academy of Sciences State Key Laboratory of Transducer Technology Shanghai Institute of Microsystem and Information Technology Shanghai200050 China

Food safety detection is essential for disease prevention and public health protection. However, current bacterial detection technologies generally face challenges including complex operation, long detection cycles, and large sample requirements. While ATP bioluminescence technology offers rapid, sensitive microbial quantification, traditional processes remain inefficient. To address these challenges, this study developed a fully automated integrated ATP bioluminescence bacterial quantification platform. The system integrates a microfluidic chip, automatic sample injection module, and real-time luminescence analysis photoelectric module, achieving an end-to-end workflow of mixing, on-chip reaction, analysis, and cleaning, eliminating manual intervention and improving convenience and efficiency. Chip’s advanced structures ensure high mixing efficiency of 98.9%, significantly reducing required sample volume and cost. With detection time under 10 minutes, experimental validation demonstrated excellent inter-batch consistency and repeatability (RSD 2 = 0.9995), and detection limit of 4.86 pM. For Vibrio parahaemolyticus, the system achieved a detection range of 102 to 108 CFU/mL (R2 = 0.996). In spiked Coca-Cola samples, the system maintained excellent anti-interference ability and accuracy (R2 = 0.941), with standard curve slopes differing by only 11.3% from PBS buffer. This portable platform with high sensitivity, stability, and repeatability is suitable for field testing of water and simple liquid foods.. In the future, by integrating specific bacterial capture technology and sample pretreatment modules, the system is expected to extend to more complex matrix sample detection, further enhancing its application value in food safety. © 2001-2012 IEEE.

关键词： Microfluidic chips

来源：评论

学校读者我要写书评

暂无评论

A Multi-Layer Software Architecture for Aerial Cognitive Multi-Robot Systems in Power Line Inspection Tasks

arXiv

引用

arXiv 2023年

作者： Silano, Giuseppe Bednar, Jan Nascimento, Tiago Capitan, Jesus Saska, Martin Ollero, Anibal The Faculty of Electrical Engineering Czech Technical University in Prague Czech Republic Department of Computer Systems Universidade Federal da Paraiba Brazil The GRVC Robotics Laboratory University of Seville Spain

This paper presents a multi-layer software architecture to perform cooperative missions with a fleet of quad-rotors providing support in electrical power line inspection operations. The proposed software framework guarantees the compliance with safety requirements between drones and human workers while ensuring that the mission is carried out successfully. Besides, cognitive capabilities are integrated in the multi-vehicle system in order to reply to unforeseen events and external disturbances. The feasibility and effectiveness of the proposed architecture are demonstrated by means of realistic simulations. Copyright © 2023, The Authors. All rights reserved.

关键词： Software architecture

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Robust Control for A Capacitive-Coupling Grid-Connect Inverter (CGCI) in Power Quality Compensation

Model Predictive Robust Control for A Capacitive-Coupling Gr...

引用

Annual Conference of Industrial Electronics Society

作者： Pak-Ian Chan Wai-Kit Sou Chi-Seng Lam State Key Laboratory of Analog and Mixed-Signal VLSI University of Macau Macau China Institute of Microelectronics University of Macau Macau China Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macau China

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

In this paper, a model predictive robust control (MPRC) is proposed for a three-phase capacitive-coupling grid-connect inverter (CGCI) to improve the power quality compensation performance under deviating system parameters. A detail stability study and parameter design of the proposed MPRC is provided, while the robustness and power quality compensation performance of the proposed MPRC are verified by the simulation in comparison to the conventional model predictive control (MPC).

关键词： Robust control Simulation Power quality Predictive models Power system stability Robustness Inverters Stability analysis Voltage control Predictive 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：