检索结果-内蒙古大学图书馆

7th IEEE Advanced information technology, Electronic and Automation Control Conference, IAEAC 2024

作者： Cheng, Tonglin Li, Juan Luo, Jintao Li, Zhihui Beijing University of Technology Faculty of Information Technology China Beijing Engineering Research Center for LoT Software and Systems China

ISBN: (纸本)9798350339161

With the rapid development of computer vision and deep learning technologies, object detection plays a crucial role in various fields. Due to the complexity and diversity of underwater environments, underwater vision tasks face great challenges. In this paper, we improved the YOLOv8 detection model for the fish detection task in complex environments. Specifically, we proposed a multi-scale feature fusion method (MFANet) that combines multiscale weighted feature fusion with multiscale attention to efficiently capture multilevel features of fishes in complex environments. We designed a multiscale weighted feature fusion module that combines feature maps at different scales to enhance the model's representation of the target. By introducing a multi-scale attention mechanism, the model is able to pay more attention to important feature regions. We conducted experiments on real underwater complex environment datasets. The results show that our proposed improved method significantly enhances the performance of the YOLOv8 model in fish detection tasks and lays a good foundation for subsequent underwater detection tasks. © 2024 IEEE.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Multiple Impact Factor Based Accuracy Analysis for Power Quality Disturbance Detection

引用

CSEE Journal of Power and Energy Systems 2023年第1期9卷 88-99页

作者： Zijing Yang Haochen Hua Junwei Cao Electromechanical Engineering Beijing Institute of Graphic CommunicationBeijing 102600China College of Energy and Electrical Engineering Hohai University 211100China Beijing National Research Center for Information Science and Technology Tsinghua UniversityBeijing 100084China

Nowadays,power quality problems are affecting people’s daily life and production *** an aim to improve disturbance detection accuracy,a novel analysis approach,based on multiple impact factors,is proposed in this ***,a multiple impact factors analysis is implemented in which two perspectives,i.e.,the wavelet analysis and disturbance features are simultaneously *** key factors,including wavelet function,wavelet decomposition level,redundant algorithm,event type and disturbance intensity,and start and end moment of disturbance,have been ***,an impact factor based accuracy analysis algorithm is proposed,through which each factor’s potential impact on disturbance location accuracy is *** transforms,i.e.,the classic wavelet,lifting wavelet and redundant lifting wavelet are employed,and their superiority on disturbance location accuracy is ***,simulations are conducted for *** the proposed method,the wavelet based parameters can be validly selected in order to accurately detect power quality disturbance.

关键词： Disturbance location accuracy impact factors power quality wavelet analysis

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in physiological characteristics recognition for internet of things authentication

引用

Digital communications and Networks 2024年第3期10卷 740-755页

作者： Zhimin Zhang Huansheng Ning Fadi Farha Jianguo Ding Kim-Kwang Raymond Choo School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Beijing Engineering Research Center for Cyberspace Data Analysis and Applications Beijing100083China Faculty of Informatics Engineering Aleppo UniversityAleppoSyria Department of Computer Science Blekinge Institute of Technology37179KarlskronaSweden Department of Information Systems and Cyber Security University of Texas at San AntonioSan AntonioTX78249-0631USA

Effective user authentication is key to ensuring equipment security,data privacy,and personalized services in Internet of Things(IoT)***,conventional mode-based authentication methods(e.g.,passwords and smart cards)may be vulnerable to a broad range of attacks(e.g.,eavesdropping and side-channel attacks).Hence,there have been attempts to design biometric-based authentication solutions,which rely on physiological and behavioral *** characteristics need continuous monitoring and specific environmental settings,which can be challenging to implement in ***,we can also leverage Artificial Intelligence(AI)in the extraction and classification of physiological characteristics from IoT devices processing to facilitate ***,we review the literature on the use of AI in physiological characteristics recognition pub-lished after *** use the three-layer architecture of the IoT(i.e.,sensing layer,feature layer,and algorithm layer)to guide the discussion of existing approaches and their *** also identify a number of future research opportunities,which will hopefully guide the design of next generation solutions.

关键词： Physiological characteristics recognition Artificial intelligence Internet of things Biological-driven authentication

来源：评论

学校读者我要写书评

暂无评论

Online Aware Synapse Weighted Autoencoder for Recovering Random Missing Data in Wastewater Treatment Process

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 578-589页

作者： Han, Honggui Sun, Meiting Li, Fangyu Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Engineering Research Center of Digital Community Ministry of Education Beijing University of Technology Beijing100124 China Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing100124 China

Missing values in wastewater treatment process (WWTP) data hinder the monitoring and prediction of operational status. Therefore, various online imputation methods have been proposed to recover missing values from streaming data collected from WWTP from real time. However, existing methods tend to ignore previous learned knowledge. In this article, an online aware synapse weighted autoencoder imputation method (OASI) is proposed to impute random missing values. First, an online stacked autoencoder (OSAE) framework is constructed to capture the nonlinear structure of the recently collected data. The framework decreases the computational and storage consumption of the model training. Second, an aware synapses weighted parameter regularization strategy is presented to guide the update of model parameters and alleviate the forgetting of historical information in an online continual setup. In this way, the learned features offer a more comprehensive representation of the overall information and help enhance imputation performance. Third, two real WWTP datasets with strong nonstationarity, high-noise level and high-dimensionality are used to validate the performance of the proposed OASI. Experimental results show that the proposed OASI achieves superior performances over the existing methods even in the presence of random missing values with different missing ratios, and only costs a short running time. © 2023 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Single LED visible light positioning scheme based on intelligent reflecting surfaces

引用

Applied Optics 2025年第15期64卷 4438-4446页

作者： Shi, Jin Han, Yu Li, Yahui Gui, Xin Fu, Xuelei Li, Zhengying School of Information Engineering Wuhan University of Technology Wuhan430070 China Hubei Key Laboratory of Broadband Wireless Communication and Sensor Networks Wuhan University of Technology Wuhan430070 China National Engineering Research Center of Fiber Optic Sensing Technology and Networks Wuhan University of Technology Wuhan430070 China

Visible light positioning (VLP) systems have gained attention for their ability to operate without additional infrastructure. However, most positioning schemes rely on multiple LEDs, which presents a considerable challenge in scenarios where only a single-light-source is available. To address this issue, this work proposes using intelligent reflective surfaces (IRS) as virtual light sources for VLP. To our knowledge, a novel positioning scheme, referred to as the difference of received signal strength, is proposed to mitigate spatial interference from multiple IRS and accurately estimate their power, enabling positioning even with a blocked line-of-sight link. Unlike maximum likelihood estimators, this scheme eliminates the need for a precise noise model. Meanwhile, the Cramér–Rao lower bound is derived to analyze the impact of IRS parameters such as rotation angle, layout, and quantity, on positioning accuracy. Theoretical analysis indicates that IRS orientation and layout greatly influence positioning accuracy, with layout offering more significant improvement than IRS quantity. Simulation results demonstrate that the scheme achieves a positioning accuracy of 0.056 m with 16 IRS units, with further improvements through additional optimization. Moreover, the results align with theoretical analysis, with an optimized layout reducing the positioning error to 0.028 m, highlighting its pivotal role in enhancing IRS performance. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Maximum likelihood

来源：评论

学校读者我要写书评

暂无评论

Parallel Implementation of the CCSDS Turbo Decoder on GPU

引用

China communications 2024年第10期21卷 70-77页

作者： Liu Zhanxian Liu Rongke Zhang Haijun Wang Ning Sun Lei Wang Jianquan School of Computer&Communication Engineering University of Science and Technology BeijingBeijing 100083China School of Electronic and Information Engineering Beihang UniversityBeijing 100191China Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services Institute of Artificial IntelligenceUniversity of Science and Technology BeijingBeijing 100083China School of Information Engineering Zhengzhou UniversityZhengzhou 450001China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China

This paper presents a software turbo decoder on graphics processing units(GPU).Unlike previous works,the proposed decoding architecture for turbo codes mainly focuses on the Consultative Committee for Space Data Systems(CCSDS)***,the information frame lengths of the CCSDS turbo codes are not suitable for flexible sub-frame parallelism *** mitigate this issue,we propose a padding method that inserts several bits before the information frame *** obtain low-latency performance and high resource utilization,two-level intra-frame parallelisms and an efficient data structure are *** presented Max-Log-Map decoder can be adopted to decode the Long Term Evolution(LTE)turbo codes with only small *** proposed CCSDS turbo decoder at 10 iterations on NVIDIA RTX3070 achieves about 150 Mbps and 50Mbps throughputs for the code rates 1/6 and 1/2,respectively.

关键词： CCSDS CUDA GPU parallel decoding turbo codes

来源：评论

学校读者我要写书评

暂无评论

A Reputation-Based AODV Protocol for Blackhole and Malfunction Nodes Detection and Avoidance

引用

Computers, Materials & Continua 2024年第8期80卷 1867-1888页

作者： Qussai M.Yaseen Monther Aldwairi Ahmad Manasrah Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjman346United Arab Emirates Department of Computer Information Systems Faculty of Computer and Information TechnologyJordan University of Science and TechnologyIrbid22110Jordan College of Technological Innovation Zayed UniversityAbu Dhabi144534United Arab Emirates Faculty of Information Technology and Computer Science Yarmouk UniversityIrbid21163Jordan Computer Information Systems Higher Colleges of TechnologySharjah341214United Arab Emirates

Enhancing the security of Wireless Sensor Networks(WSNs)improves the usability of their ***,finding solutions to various attacks,such as the blackhole attack,is crucial for the success of WSN *** paper proposes an enhanced version of the AODV(Ad Hoc On-Demand Distance Vector)protocol capable of detecting blackholes and malfunctioning benign nodes in WSNs,thereby avoiding them when delivering *** proposed version employs a network-based reputation system to select the best and most secure path to a *** achieve this goal,the proposed version utilizes the Watchdogs/Pathrater mechanisms in AODV to gather and broadcast reputations to all network nodes to build the network-based reputation *** minimize the network overhead of the proposed approach,the paper uses reputation aggregator nodes only for forwarding reputation ***,to reduce the overhead of updating reputation tables,the paper proposes three mechanisms,which are the prompt broadcast,the regular broadcast,and the light broadcast *** proposed enhanced version has been designed to perform effectively in dynamic environments such as mobile WSNs where nodes,including blackholes,move continuously,which is considered a challenge for other *** the proposed enhanced protocol,a node evaluates the security of different routes to a destination and can select the most secure routing *** paper provides an algorithm that explains the proposed protocol in detail and demonstrates a case study that shows the operations of calculating and updating reputation values when nodes move across different ***,the paper discusses the proposed approach’s overhead analysis to prove the proposed enhancement’s correctness and applicability.

关键词： AODV blackhole malfunction nodes pathrater reputation system wireless sensor networks(WSNs) watchdogs

来源：评论

学校读者我要写书评

暂无评论

Few-shot Object Detection with Fine-grained Support information Guidance 24

Few-shot Object Detection with Fine-grained Support Informat...

引用

2024 International Conference on Computer Vision and Deep Learning, CVDL 2024

作者： Ren, Kun Ren, Furong Han, Honggui Du, Yongping Hou, Ying Faculty of Information Technology Beijing University of Technology Engineering Research Center of Digital Community Ministry of Education Beijing Laboratory for Urban Mass Transit Beijing China Faculty of Information Technology Beijing University of Technology Engineering Research Center of Digital Community Ministry of Education Beijing China

ISBN: (纸本)9798400718199

Few-shot object detection (FSOD) shines in identifying novel category targets with limited support samples, making it well-suited for scenarios with restricted data availability. However, FSOD suffers challenges in acquiring indicative discrimination features due to the limited availability of support samples and the substantial variations in object shapes, sizes, and distributions. To tackle this problem, we present a novel few-shot object detector with fine-grained support information guidance based on Meta R-CNN. A support-commonalities enhancement module is proposed to highlight the commonality of support sample features channel-wise and preserve spatial information by external attention mechanism to extract more representative category features of support samples. Furthermore, a fine-grained aggregation module is designed to optimize pixel-wise spatial alignment of information between support and query features for generating high-quality proposals. In addition, the classification compensation module aggregated the enhanced support information in classification branches to enhance the model's classification accuracy for the proposed objects. Finally, the proposed detector's effectiveness is validated through ablation and comparison experiments performed on the MS COCO datasets. © 2024 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Dielectric Patch Resonator and Antenna

引用

China communications 2023年第8期20卷 209-219页

作者： Jianxin Chen Xueying Wang Shichang Tang Yongle Wu School of Information Science and Technology and Research Center for Intelligent Information TechnologyNantong UniversityNantong 226019China Nantong Research Institute for Advanced Communication Technologies Chongchuan DistrictNantong 226019China School of Electronic Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China

This paper presents an overview of dielectric patch(DP)antennas developed in recent *** employed DP resonator composed of a DP and a bottom substrate is analyzed comprehensively here,enabling the easy realization of a quasi-planar DP *** combines the dual advantages of the conventional microstrip patch(MP)antenna and dielectric resonator(DR)antenna in terms of profile,gain,bandwidth,radiation efficiency,and design ***,the DP antenna inherits the multi-mode characteristic of the DR antenna,thus it has a large number of high-order modes,including TMmn mode and TEmn *** high-order modes are widely applied,for example,by combining with the dominant TM10 mode to expand the bandwidth,or selecting multiple higher-order modes to implement a high-gain ***,the non-radiation high-order modes are also utilized to produce natural radiation null in filtering antenna *** this paper,the design theories and techniques of DP antenna are introduced and investigated,including calculation and control methods of the resonant mode frequencies,analysis of the radiation mechanism,and applications of the multi-mode *** overview could provide guidance for the subsequent antenna design,thus effectively avoid time-consuming optimization.

关键词： dielectric patch(DP)resonator DP antenna radiation mechanism multi-mode characteristic

来源：评论

学校读者我要写书评

暂无评论

Deep Transfer Learning Models for Mobile-Based Ocular Disorder Identification on Retinal Images

引用

Computers, Materials & Continua 2024年第7期80卷 139-161页

作者： Roseline Oluwaseun Ogundokun Joseph Bamidele Awotunde Hakeem Babalola Akande Cheng-Chi Lee Agbotiname Lucky Imoize Department of Multimedia Engineering Kaunas University of TechnologyKaunas44249Lithuania Department of Computer Science Landmark UniversityOmu Aran251103Nigeria Department of Computer Science Faculty of Information and Communication SciencesUniversity of IlorinIlorin240003Nigeria Department of Telecommunication Science University of IlorinIlorin230003Nigeria Department of Library and Information Science Fu Jen Catholic UniversityNew Taipei City24205TaiwanChina Department of Computer Science and Information Engineering Fintech and Blockchain Research CenterAsia UniversityTaichung City41354TaiwanChina Department of Electrical and Electronics Engineering Faculty of EngineeringUniversity of LagosAkokaLagos100213Nigeria Department of Electrical Engineering and Information Technology Institute of Digital CommunicationRuhr UniversityBochum44801Germany

Mobile technology is developing *** phone technologies have been integrated into the healthcare industry to help medical ***,computer vision models focus on image detection and classification ***2 is a computer vision model that performs well on mobile devices,but it requires cloud services to process biometric image information and provide predictions to *** leads to increased *** biometrics image datasets on mobile devices will make the prediction faster,but mobiles are resource-restricted devices in terms of storage,power,and computational ***,a model that is small in size,efficient,and has good prediction quality for biometrics image classification problems is *** pre-trained CNN(PCNN)MobileNetV2 architecture combined with a Support Vector Machine(SVM)compacts the model representation and reduces the computational cost and memory *** proposed novel approach combines quantized pre-trained CNN(PCNN)MobileNetV2 architecture with a Support Vector Machine(SVM)to represent models efficiently with low computational cost and *** contributions include evaluating three CNN models for ocular disease identification in transfer learning and deep feature plus SVM approaches,showing the superiority of deep features from MobileNetV2 and SVM classification models,comparing traditional methods,exploring six ocular diseases and normal classification with 20,111 images postdata augmentation,and reducing the number of trainable *** model is trained on ocular disorder retinal fundus image datasets according to the severity of six age-related macular degeneration(AMD),one of the most common eye illnesses,Cataract,Diabetes,Glaucoma,Hypertension,andMyopia with one class *** the experiment outcomes,it is observed that the suggested MobileNetV2-SVM model size is *** testing accuracy for MobileNetV2-SVM,InceptionV3,and MobileNetV2 is 90.11%,86.88%,a

关键词： Retinal images ocular disorder deep transfer learning disease identification mobile device

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：