检索结果-内蒙古大学图书馆

IEEE TRANSACTIONS ON RADAR SYSTEMS 2025年 3卷 332-348页

作者： Coutts, Fraser K. Thompson, John Mulgrew, Bernard Univ Edinburgh Inst Imaging Data & Commun IDCOM Edinburgh EH9 3BF Scotland

The efficient extraction of useful information from radio frequency (RF) sensors is one important application for artificial intelligence (AI) and machine learning (ML) approaches. In particular, there is a desire to maximize efficiency when sharing positioning, navigation, and timing (PNT) information captured by distributed networks of low size, weight, power, and cost (SWAP-C) RF sensors when operating in congested or contested electromagnetic environments (EMEs). By implementing effective PNT information-sharing strategies, these networks can more easily position the sensors or characterize targets of interest. In this work, we propose a novel ML-inspired compression design framework that improves efficiency when sharing PNT information in a network of sensors receiving radar waveforms. In addition, through novel learning procedures, the network can adapt to unforeseen EMEs such that network efficiency can be maintained in the presence of unforeseen RF waveforms and sensor surroundings. We show that our intelligent, model-driven, ML-inspired data reduction strategies can outperform alternative strategies that do not best-utilize the information content of waveforms in the EME. In addition, we demonstrate the ability of our strategies to adapt to changing mission goals by balancing different types of PNT information and learning from developing EMEs.

关键词： sensors Radar Radio frequency information sharing OFDM Data models Bandwidth sensor phenomena and characterization Image coding Distributed databases Contested electromagnetic environment (EME) distributed sensor networks mutual information (MI) positioning navigation and timing (PNT) projection design

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable intelligent Surface Aided Wireless sensor networks with Harvest-Then-Transmit Protocol

Reconfigurable Intelligent Surface Aided Wireless Sensor Net...

引用

2024 IEEE sensors conference

作者： Lee, Yinman Hsu, Li-Zhen Natl Chi Nan Univ Dept Elect Engn Puli Taiwan

ISBN: (纸本)9798350363524;9798350363517

In this paper, we investigate the use of reconfigurable intelligent surfaces (RIS) to enhance the multiple access and energy harvesting capabilities of wireless sensor networks (WSNs) with the harvest-then-transmit (HTT) protocol. Specifically, we utilize a random/opportunistic beamforming concept to adjust the phase-shift configurations of RIS elements. sensor nodes can then opportunistically select favorable RIS settings that improve channel conditions for both energy harvesting and data transmission without requiring complicated channel estimation, extensive information exchange, or centralized control. Simulation results demonstrate that this approach effectively increases the network's achievable rate and the amount of energy harvested by the sensor nodes.

关键词： Wireless sensor networks reconfigurable intelligent surface harvest-then-transmit protocol energy harvesting random/opportunistic beamforming

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent Image Recognition Algorithms Based on Optical sensors and Generative Adversarial networks

Design of Intelligent Image Recognition Algorithms Based on ...

引用

2024 International conference on Power, Electrical Engineering, Electronics and Control, PEEEC 2024

作者： Ye, Cong Suzhou College of Information Technology Department of Big Data and Internet Jiangsu215200 China

ISBN: (纸本)9798350378917

This paper presents the design of an intelligent image recognition algorithm based on optical sensors and Generative Adversarial networks (GAN). In today's digital era, the growth of image data is increasing exponentially, which puts higher requirements on image recognition algorithms. Optical sensors, as an important data acquisition tool, play an important role in the field of image processing. Generative Adversarial networks, on the other hand, is a powerful deep learning model that can learn and generate images with realistic features. In this paper, an intelligent image recognition algorithm is designed by combining optical sensors with GAN, which realizes efficient recognition and classification of images by taking full advantage of data acquisition and feature learning. This study first introduces the basic principles of optical sensor technology and its application in image recognition. With the development of technology, optical sensors have continuously improved the accuracy and speed of image acquisition, and have been widely used in industrial, medical and other fields. Then, this paper elaborates the working principle of Generative Adversarial networks (GAN) and its importance in image *** realizes the ability of learning from data and generating realistic images by means of competitive learning, which brings new breakthroughs in the field of image recognition. An intelligent image recognition algorithm design based on optical sensor and GAN is proposed. The algorithm realizes the effective extraction and learning of image features through the steps of data preprocessing, optical sensor feature extraction and GAN feature learning. In the process of algorithm design, the features and advantages of optical sensors and GAN in image processing are fully considered, which makes the algorithm have high recognition accuracy and robustness. Finally, this paper verifies the performance of the proposed algorithm in image classification and recognition

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Optimized Design of EdgeBoard intelligent Vehicle Based on PP-YOLOE

引用

sensors 2024年第10期24卷 3180页

作者： Yao, Chengzhang Liu, Xiangpeng Wang, Jilin Cheng, Yuhua Shanghai Normal Univ Coll Informat Mech & Elect Engn Shanghai 201418 Peoples R China Peking Univ Shanghai Res Inst Microelect Shanghai 201203 Peoples R China

Advances in deep learning and computer vision have overcome many challenges inherent in the field of autonomous intelligent vehicles. To improve the detection accuracy and efficiency of EdgeBoard intelligent vehicles, we proposed an optimized design of EdgeBoard based on our PP-YOLOE+ model. This model innovatively introduces a composite backbone network, incorporating deep residual networks, feature pyramid networks, and RepResBlock structures to enrich environmental perception capabilities through the advanced analysis of sensor data. The incorporation of an efficient task-aligned head (ET-head) in the PP-YOLOE+ framework marks a pivotal innovation for precise interpretation of sensor information, addressing the interplay between classification and localization tasks with high effectiveness. Subsequent refinement of target regions by detection head units significantly sharpens the system's ability to navigate and adapt to diverse driving scenarios. Our innovative hardware design, featuring a custom-designed mainboard and drive board, is specifically tailored to enhance the computational speed and data processing capabilities of intelligent vehicles. Furthermore, the optimization of our Pos-PID control algorithm allows the system to dynamically adjust to complex driving scenarios, significantly enhancing vehicle safety and reliability. Besides, our methodology leverages the latest technologies in edge computing and dynamic label assignment, enhancing intelligent vehicles' operations through seamless sensor integration. Our custom dataset, specifically designed for this study, includes 4777 images captured by intelligent vehicles under a variety of environmental and lighting conditions. The dataset features diverse scenarios and objects pertinent to autonomous driving, such as pedestrian crossings and traffic signs, ensuring a comprehensive evaluation of the model's performance. We conducted extensive testing of our model on this dataset to thoroughly assess sensor

关键词： PP-YOLOE plus target detection EdgeBoard intelligent vehicle Pos-PID autonomous sensing optimal route determination

来源：评论

学校读者我要写书评

暂无评论

Favor the Tortoise Over the Hare: An Efficient Detection Algorithm for Cooperative networks

引用

IEEE TRANSACTIONS ON SIGNAL processing 2024年 72卷 3153-3170页

作者： Feitosa, Allan E. Nascimento, Vitor H. Lopes, Cassio G. Univ Sao Paulo Dept Elect & Syst BR-05508010 Sao Paulo Brazil

We develop a low-cost algorithm to decide the current state of an environment being monitored by a cooperative and fully distributed wireless network of intelligent sensors, with a low time to reach a given performance. We consider WSNs (Wireless sensor networks) deployed under stringent power conditions, a situation for which low computational complexity and low power consumption is highly desired. We model a multiple hypothesis test using the diffusion Least Mean Square (dLMS) algorithm, a well known estimation technique used in distributed networks, to process data and also share information among nodes across the network. Our first contribution is showing that the performance of this theoretical detector, given in terms of the average probability of error, approximates the optimal performance if the underlying estimator operates at a slow learning rate, which is achieved by a sufficiently small step size. Notably, the detector performance improves as the value of the this step size is reduced, without any reduction in the detection error convergence rate, despite the slower estimation convergence rate. This somewhat counter-intuitive behavior is explained theoretically and confirmed by simulations. From this theoretical formulation, we devise a new detector with low computational complexity whose performance also closely matches that of the optimal and shows the same aforementioned behavior, where the slowest learning rate provides the best detection performance in terms of both the probability of error and convergence rate. We also show that this performance can be easily achieved provided that an adequate initialization of the estimation algorithm is chosen.

关键词： Signal processing algorithms sensors Wireless sensor networks Vectors Task analysis Estimation Environmental monitoring Distributed detection wireless sensor networks detection in WSN diffusion-LMS Bayesian detection

来源：评论

学校读者我要写书评

暂无评论

Minimize Age of information for IRS-Aided sensor Systems: How Many IRS Elements Are Needed?

引用

IEEE sensors JOURNAL 2025年第8期25卷 14099-14111页

作者： Zhang, Yangyi Guan, Xinrong Wu, Qingqing Zhang, Ruoyu Ma, Yue Miao, Chen Wu, Wen Cai, Yueming Army Engn Univ PLA Coll Commun Engn Nanjing 210007 Peoples R China Shanghai Jiao Tong Univ Dept Elect Engn Shanghai 200240 Peoples R China Nanjing Univ Sci & Technol Sch Elect & Opt Engn Nanjing 210094 Peoples R China

In this article, we investigate an intelligent reflecting surface (IRS)-assisted sensor system, where the average age of information (AoI) is derived to characterize the information freshness of short packets. Although the IRS can enhance the beamforming gain which improves the AoI performance, it also introduces higher channel estimation overhead which impairs the AoI performance. The quantitative impact of IRS on AoI performance remains unclear. To this end, our work aims to characterize the relationship of the average AoI in terms of the number of IRS elements and optimize the latter to minimize the former. However, the average AoI expression is difficult to obtain due to the complex composite channel distribution. To tackle this difficulty, we use the moment matching (MM) technique to approximate the composite channel by Gamma distribution. The obtained average AoI expression is still complicated and it is intractable to directly obtain the optimal IRS elements' number. To overcome this challenge, we derive the approximated expressions of the average AoI for small and large IRS elements, and then obtain the intersection between the two approximated expressions as a suboptimal solution. Based on them, we prove that the average AoI first decreases and then increases as the number of IRS elements increases, which indicates there is an optimal number of IRS reflecting elements for attaining the optimal AoI performance. Simulation results verify our theoretical results and demonstrate that the proposed scheme for obtaining the number of IRS elements can achieve almost the same performance as the exhaustive search method and outperforms benchmarks.

关键词： sensors Communication systems Real-time systems Measurement Array signal processing Wireless communication Reliability Wireless sensor networks Throughput Hands Age of information (AoI) intelligent reflecting surface (IRS) short packet communication

来源：评论

学校读者我要写书评

暂无评论

Smart Farming Technologies: A Methodological Overview and Analysis

引用

IEEE ACCESS 2024年 12卷 164922-164941页

作者： Chicaiza, Kharol Paredes, Ricardo X. Sarzosa, Isaac Mateo Yoo, Sang Guun Zang, Naeun Escuela Politec Nacl Dept Informat & Ciencias Comp Quito 170525 Ecuador Escuela Politec Nacl Smart Lab Quito 170525 Ecuador Univ Fuerzas Armadas ESPE Dept Ciencias Comp Sangolqui 171103 Ecuador Sogang Univ Sogang Inst Convergence Educ Seoul 04107 South Korea

This paper presents a comprehensive examination of smart farming solutions through a systematic review of literature available in various digital repositories. Methodologically, we categorize the devices and technologies utilized in these solutions into sensors, actuators, gateways, power supplies, networking, data storage, data processing, and information delivery. Through this analysis, we identify the most commonly employed devices and technologies in smart farming solutions and discuss their utilization within the proposed categories. By synthesizing the gathered information, we offer insights into the current landscape of smart farming, accompanied by recommendations for the selection of devices and technologies tailored to each category. This research contributes to the understanding of smart farming technology and aids stakeholders in making informed decisions regarding the implementation of such solutions.

关键词： Smart agriculture Internet of Things sensors intelligent sensors Wireless sensor networks Protocols Metadata Real-time systems Libraries Farming Smart farming IoT LoRaWAN network sensors WiFi wireless communication

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization of intelligent Perception System in Maritime Traffic Sensing and Management

Performance Optimization of Intelligent Perception System in...

引用

2025 International conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Li, Daoke Navigation College Fujian Chuanzheng Communication College Fuzhou350007 China

ISBN: (纸本)9798331509828

The sea surface is often accompanied by a complex and fluctuating information environment. How to achieve the efficient and accurate water traffic management and perception is an important research branch of computer-aided maritime informatization. Therefore, this study analyzes the application and performance optimization of intelligent perception systems in water traffic management. First, this study expands the application of sensors in the ship hull by optimizing the perception of objects inside the ship. Then, a perception system with wide coverage and strong data processing capabilities is designed for the deployment of external sensor networks and the perception range of wireless sensor networks. At the same time, in response to the challenges of collecting, transmitting and analyzing complex dynamic data of ships, this paper proposes efficient data cleaning, fast data transmission technology and active routing protocol. In the experimental part, this study also verified the effectiveness of the designed system in ship dynamic trajectory prediction (GPS sensor information analysis) and conflict detection through MATLAB simulation. © 2025 IEEE.

关键词： intelligent perception Maritime traffic sensing Performance optimization Sensing and management

来源：评论

学校读者我要写书评

暂无评论

AI-Integrated Traffic information System: A Synergistic Approach of Physics Informed Neural Network and GPT-4 for Traffic Estimation and Real-Time Assistance

引用

IEEE ACCESS 2024年 12卷 65869-65882页

作者： Gebre, Tewodros Syum Beni, Leila Tsehaye Wasehun, Eden Dorbu, Freda Elikem North Carolina A&T State Univ Coll Sci & Technol Appl Sci & Technol Program Greensboro NC 27411 USA North Carolina A&T State Univ Coll Sci & Technol Geomat Program Greensboro NC 27411 USA North Carolina A&T State Univ Dept Computat Data Sci & Engn Greensboro NC 27411 USA

Traffic management systems have primarily relied on live traffic sensors for real-time traffic guidance. However, this dependence often results in uneven service delivery due to the limited scope of sensor coverage or potential sensor failures. This research introduces a novel approach to overcome this limitation by synergistically integrating a Physics-Informed Neural Network-based Traffic State Estimator (PINN-TSE) with a powerful Natural Language processing model, GPT-4. The purpose of this integration is to provide a seamless and personalized user experience, while ensuring accurate traffic density prediction even in areas with limited data availability. The innovative PINN-TSE model was developed and tested, demonstrating a promising level of precision with a Mean Absolute Error of less than four vehicles per mile in traffic density estimation. This performance underlines the model's ability to provide dependable traffic information, even in regions where conventional traffic sensors may be sparsely distributed or data communication is likely to be interrupted. Furthermore, the incorporation of GPT-4 enhances user interactions by understanding and responding to inquiries in a manner akin to human conversation. This not only provides precise traffic updates but also interprets user intentions for a tailored experience. The results of this research showcase an AI-integrated traffic guidance system that outperforms traditional methods in terms of traffic estimation, personalization, and reliability. While the study primarily focuses on a single road segment, the methodology shows promising potential for expansion to network-level traffic guidance, offering even greater accuracy and usability. This paves the way for a smarter and more efficient approach to traffic management in the future.

关键词： sensors Biological neural networks Real-time systems Mathematical models Predictive models information systems sensor systems Traffic control Traffic congestion intelligent transportation systems Artificial intelligence Natural language processing AI-integrated traffic information system physics informed neural network (PINN) traffic state estimation (TSE) traffic data processing GPT-4 prompt engineering natural language processing (NLP) large language models (LLM) foundation models

来源：评论

学校读者我要写书评

暂无评论

Helicopter Turboshaft Engines' Neural Network System for Monitoring sensor Failures

引用

sensors 2025年第4期25卷 990-990页

作者： Vladov, Serhii Scislo, Lukasz Szczepanik-Scislo, Nina Sachenko, Anatoliy Perzynski, Tomasz Vasylenko, Viktor Vysotska, Victoria Kharkiv Natl Univ Internal Affairs 27 L Landau Ave UA-61080 Kharkiv Ukraine Cracow Univ Technol Fac Elect & Comp Engn 24 Warszawska St PL-31155 Krakow Poland Cracow Univ Technol Fac Environm Engn & Energy 24 Warszawska PL-31155 Krakow Poland European Org Nucl Res CERN 1 Esplanade Particules CH-1211 Geneva 23 Switzerland West Ukrainian Natl Univ Res Inst intelligent Comp Syst 11 Lvivska St UA-46009 Ternopol Ukraine Casimir Pulaski Radom Univ Fac Transport Elect Engn & Comp Sci PL-26600 Radom Poland Lviv Polytech Natl Univ Informat Syst & Networks Dept 12 Bandera St UA-79013 Lvov Ukraine Osnabruck Univ Inst Comp Sci 1 Friedrich Janssen St D-49076 Osnabruck Germany

An effective neural network system for monitoring sensors in helicopter turboshaft engines has been developed based on a hybrid architecture combining LSTM and GRU. This system enables sequential data processing while ensuring high accuracy in anomaly detection. Using recurrent layers (LSTM/GRU) is critical for dependencies among data time series analysis and identification, facilitating key information retention from previous states. Modules such as sensorFailClean and sensorFailNorm implement adaptive discretization and quantisation techniques, enhancing the data input quality and contributing to more accurate predictions. The developed system demonstrated anomaly detection accuracy at 99.327% after 200 training epochs, with a reduction in loss from 2.5 to 0.5%, indicating stability in anomaly processing. A training algorithm incorporating temporal regularization and a combined optimization method (SGD with RMSProp) accelerated neural network convergence, reducing the training time to 4 min and 13 s while achieving an accuracy of 0.993. Comparisons with alternative methods indicate superior performance for the proposed approach across key metrics, including accuracy at 0.993 compared to 0.981 and 0.982. Computational experiments confirmed the presence of the highly correlated sensor and demonstrated the method's effectiveness in fault detection, highlighting the system's capability to minimize omissions.

关键词： sensor failures neural network system helicopter turboshaft engines sensors recurrent layers approximation anomaly detection

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：