检索结果-内蒙古大学图书馆

sensors and information Technology (ICSI), International conference on

作者： Lanlan Li Yongkui Zhu Jiajia Li Ting Zhang Nanchong Vocational College of Science and Technology Nanchong Sichuan China

ISBN: (数字)9798331542887

ISBN: (纸本)9798331542894

This paper addresses the issues of limited functionality and insufficient scalability in intelligent connected vehicle sensor training equipment within vocational education. A sensor training platform is designed, integrating traditional and intelligent sensors, which is applicable for competitions, teaching, innovation, and research. The platform utilizes the STM32 embedded system as the main control core, combined with LabVIEW upper computer software, to construct a multi-modal data acquisition, high-precision environmental perception, and intelligent processing system. Through modular hardware design, optimization of the embedded real-time system, and LabVIEW interactive design, the platform not only meets the needs of basic teaching but also supports innovative practices in engineering fields such as intelligent connected vehicles. It provides technical support for the integration of theory and practice in vocational education.

关键词： Training Technological innovation Connected vehicles Three-dimensional displays Scalability Robot sensing systems Real-time systems Hardware Software Design optimization

来源：评论

学校读者我要写书评

暂无评论

Received Signal-to-Noise Ratio Evaluation for Hybrid intelligent Reflecting Array Systems

Received Signal-to-Noise Ratio Evaluation for Hybrid Intelli...

引用

International conference on Electronics, information and Communications (ICEIC)

作者： Taehee Choi Jaehong Kim Jingon Joung School of Electrical and Electronics Engineering Chung-Ang University Seoul South Korea

ISBN: (数字)9798331510756

ISBN: (纸本)9798331510763

This study considers a direction-of-arrival (DOA)-based hybrid intelligent reflecting array (HIRA) phase shift method. Concretely, the HIRA sensors estimate the DOA of the signal transmitted from the user equipment (UE), and the phase shift values of the HIRA reflectors are calculated using the estimated DOA. Here, the DOA estimation accuracy and the HIRA beamforming gain are proportional to the numbers of the sensors and the reflectors, respectively. Thus, there exists a trade-off between the DOA estimation accuracy and the HIRA beamforming gain when the total number of sensors and reflectors is bounded. From the numerical simulation, the received signal-to-noise ratio was evaluated to verify the trade-off of the DOA-based HIRA phase shift method. Also, the optimal number of sensors was numerically demonstrated.

关键词： Phased arrays Direction-of-arrival estimation Accuracy Array signal processing Estimation Numerical simulation sensor systems intelligent sensors Signal to noise ratio sensor arrays

来源：评论

学校读者我要写书评

暂无评论

7th International Russian Automation conference, RusAutoCon 2024

7th International Russian Automation Conference, RusAutoCon ...

引用

7th International Russian Automation conference, RusAutoCon 2024

ISBN: (纸本)9783031824937

The proceedings contain 37 papers. The special focus in this conference is on Russian Automation. The topics include: Mapping and Path Planning Methods for Highly Automated Vehicles in Agriculture;morphological Analysis and Synthesis Features of Technological Processes;a Modern Method of Wireless Control of Unguarded Railway Crossings;duties and Obligations of the Railway Staff Concerned When the Microprocessorized Contactless Controlling Gauge Device Signal Is Triggered;integration of Automated Management Systems for Enterprises’ Transport and Technical Services;development of an Automation Module for Planning Trajectories for Painting Aircraft Fuselage Elements;identification of Metal Sheets in the Flow, Based on the Marking Imprint, Using Neural networks;study of the Performance of Adaptive sensor networks for Collecting and processing Thermoelectric Data;development and Research of a Cartographic Model for Municipal Planning as the Basis of an intelligent Geoinformation System;BIM Visual Programming of Bionic Architecture Construction Using Dynamo and Revit;development of a Model and Algorithms for Trigger Control of Technological Processes of Resource Provision;system for Statistical Assessment of Means of Controlling Engineers’ Qualification for information Support to Manage the Recruiting Process in Industry;smart Enumeration Technology;comparative Analysis of C-Band Conical Horn Antenna Sparse Structures Characteristics at Different Frequencies;software Implementation of Heuristic Methods of Optimization and Integration into a Cloud Service;computer System for Modeling Fluid Flow Around Bodies and Its Potential in Industry;the Effect of Regular and Irregular Segmentations on Characteristics and Charge Distribution Densities of Microstrip Lines;reinforcement Learning with External Teacher for Building Energy Management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vehicle information Monitoring and Identification on Highway Bridges Using an Array of Fiber Bragg Grating sensors and Deep Learning Algorithms 4

Vehicle Information Monitoring and Identification on Highway...

引用

4th International Computational Imaging conference, CITA 2024

作者： Duan, Zhenhui Zhang, Faxiang Jiang, Shaodong Sun, Zhihui Liu, Zhaoying Shen, Yongxu Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9781510688834

Traditional traffic management methods are increasingly inadequate in coping with the growing pressure on traffic systems. Consequently, there is a need for a more intelligent and efficient approach to monitoring and identifying vehicle information. Current vehicle monitoring methods often suffer from environmental interference and limited coverage.. To address these challenges, we propose a novel method for monitoring and identifying vehicle information on bridges using an array of Fiber Bragg Grating (FBG) strain sensors, combined with a hybrid deep learning algorithm based on Discrete Wavelet Transform (DWT) and Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM). Strain data were collected from a continuous hollow slab beam on a section of a highway bridge. Vehicles were classified and labeled using on-site video data to create a dataset, which was subsequently used to train and test the proposed CNN-LSTM model. The results demonstrate that the proposed method can accurately identify and classify the lane position, vehicle type, and vehicle speed category, achieving detection accuracies of 94.0%, 93.11%, and 90.67%, respectively. The DWT-CNN-LSTM method, utilizing the FBG strain sensor array, leverages existing strain monitoring platforms, supplements current traffic monitoring systems, and offers high efficiency and cost-effectiveness. This approach provides valuable data references for management and statistical analysis. © 2025 SPIE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Adaptive Asynchronous Gossip Algorithms for Consensus in Heterogeneous sensor networks

引用

IEEE Internet of Things Journal 2025年

作者： Ilic, Nemanja Vucetic, Miljan Makarov, Aleksej Petrovic, Ranko Punt, Marija College of Applied Technical Sciences School of Computing Union University Kruševac Belgrade Serbia Vlatacom Institute Belgrade Serbia VŠB - Technical University of Ostrava Ostrava Czech Republic University Singidunum Belgrade Serbia University of Belgrade School of Electrical Engineering Belgrade Serbia

The Internet of Things (IoT) connects a wide range of sensors and devices in environments that are often dynamic and resource-constrained, where efficient distributed solutions are essential for ensuring robust and scalable operation. This paper presents a novel adaptive consensus algorithm, tailored for distributed signal processing in heterogeneous sensor networks, with a focus on distributed estimation and target tracking. The algorithm addresses the challenge posed by networks where intelligent sensors have limited sensing, computation and communication capabilities, resulting in diverse quality of locally available information, and leading to neighbor-based information exchanges. It employs asynchronous gossip protocols to randomly exchange information between nodes, ensuring robustness to time synchronization and network topology uncertainties, while limiting computational and communication costs. The adaptation mechanism operates in two complementary ways. Firstly, we account for variations in the quality of local processing results, ensuring that asymptotic behavior of the consensus scheme accurately reflects this diversity. Secondly, we introduce a novel adaptation of the rates at which nodes initiate communication, using the available local information. This enables fast information dissemination, and provides a solution that is both effective and efficient. We show that, under appropriate network connectivity assumptions, the results obtained by the algorithm converge to the desired asymptotic values in the mean square sense. Numerical simulations demonstrate the algorithm's properties and effectiveness, particularly in modeling visual surveillance networks where fixed cameras are augmented by moving drones to extend the coverage area. © 2025 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-Resolution Mixer Network for Localization of Multiple sensors from Cumulative Power Measurements

Multi-Resolution Mixer Network for Localization of Multiple ...

引用

IEEE conference on Wireless Communications and Networking

作者： Md Mahmuddun Nabi Murad Daniel Kwabena Yirenya-Tawiah Thomas Weller Yasin Yilmaz Electrical Engineering Department University of South Florida Tampa USA Electrical Engineering Department Oregon State University Corvallis USA

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Wireless sensor networks (WSNs) can consist of many inexpensive sensors that communicate using the same wireless channel. In some applications, localization of these sensors can be as crucial as collecting their monitoring data. As the number of sensors increases, the complexity of processing data in such large networks grows significantly. In general, localization methods in WSNs typically rely on data containing sensor-specific information. However, the problem becomes more challenging when data contains no sensor-specific information. To address this issue, we propose a mixer-based deep neural network to estimate sensor positions using the received cumulative signal strength that is devoid of explicit sensor-specific information. Our approach employs wavelet decomposition to extract information from the input time series, combined with patching, embedding, and mixer techniques for position estimation. We compare the performance of our model with a nonlinear Kalman filter-based state estimation method. Extensive evaluations using data generated from our simulator demonstrate that our method consistently outperforms the unscented Kalman filter (UKF) method across all scenarios.

关键词： Location awareness Wireless communication Wireless sensor networks Power measurement Time series analysis information filters sensors Kalman filters State estimation Mixers

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Enabled Secure IoT Module for Smart Agriculture in Diverse Environmental Conditions 14

Deep Learning Enabled Secure IoT Module for Smart Agricultur...

引用

14th IEEE International conference on Communication Systems and Network Technologies, CSNT 2025

作者： Ansari, Shaharyar Alam Ali, Salman Luqman, Mohammad Ahmad, Shahnawaz School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Computer Science Aligrah Muslim University Aligarh India

ISBN: (纸本)9798331531935

The Internet of Things (IoT) stands as a revolutionary technology which impacts smart agriculture and different sectors beyond it. The research describes an intelligent IoT-enabled monitoring system which uses sensors to bring improved agricultural performance through environmental real-time observations combined with artificial intelligence decision systems. The proposed system completes its operation by executing sensor data acquisition followed by deep learning-based analysis and secure data transmission procedures. The initial stage of IoT-enabled operation utilizes environment-sensing devices which collect essential parameters for precision farming. A Recurrent Neural Network (RNN) processing system applies classification methods to collected data to generate useful insights. Secure cloud data transmission takes place through an encryption system which combines Substitution-Caesar cipher with Improved Elliptic Curve Cryptography (IECC). The system demonstrates 99.64% accuracy, and the proposed encryption method proves efficiency through its average execution times of encryption at 0.3904 ms and decryption at 0.1102 ms which exceeds current models in speed and security performance. © 2025 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Infrared-Visible Image Fusion Method with an ISP Based Degradation Model

Enhanced Infrared-Visible Image Fusion Method with an ISP Ba...

引用

International conference on intelligent Control and information processing (ICICIP)

作者： Xueyi Guo Yisha Liu Weimin Xue Zhiwei Zhang Information Science and Technology College Dalian Maritime University Dalian China School of Control Science and Engineering Dalian University of Technology Dalian China

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

The performance of infrared (IR) and visible (VIS) image fusion tasks depends on the quality of source images, which are usually impacted by various degradation factors in real-world scenarios, leading to poor quality and visual effects of the fused images. By learning the mapping from low-quality (LQ) source images to high-quality (HQ) fused images, neural networks can remove the impacts of degradation factors, generating HQ fused images. However, the lack of paired LQ source images and corresponding HQ fused images poses a significant challenge in training a fusion network. Considering the effectiveness of the image processing pipeline (ISP) in processing IR and VIS images, reversing specific steps of ISP can accurately simulate the image degradation process. Building upon this research, we propose a novel ISP-based degradation model that reverses several ISP steps while incorporating various degradation factors, thereby generating LQ IR and VIS images from source images to train the fusion network. Experimental results on multiple image fusion datasets demonstrate that our method significantly enhances the quality and visual effects of fused images.

关键词： Degradation Training Pipelines Neural networks Noise Process control sensor fusion Visual effects sensors Image fusion

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient and Trust Based Multi-hop Routing Using Particle Swarm Induced Tunicate Swarm Optimisation Algorithm in Internet of Things Based Wireless sensor networks

Energy Efficient and Trust Based Multi-hop Routing Using Par...

引用

International conference on 6G Communications Networking and Signal processing, SGCNSP 2023

作者： Lande, Jayapal Borra, Subba Reddy Abood, Baydaa S. Z. Dineshkumar, P. Geetha, K. School of Computer Science and Artificial Intelligence SR University Warangal India Maisammaguda Telangana Hyderabad India National University of Science and Technology Dhi Qar Iraq Department of Information Technology K.S.Rangasamy College of Technology Tiruchengode India Department of Computer Science and Engineering Excel Engineering College Komarapalayam India

ISBN: (纸本)9789819778751

Internet of Things (IoT)-Wireless sensor networks (WSNs) depend heavily on routing, particularly multi-hop routing, which makes large-scale deployments of data transmission efficient. Multi-hop routing increases overall dependability, extends network lifetime, and enables communication between sensors through intermediary nodes. In order to solve energy problems in WSN, a multi-hop routing architecture is developed that is both secure and energy efficient. The two key stages of the framework are transmission and clustering. Energy-efficient cluster heads are chosen during the clustering phase based on a number of factors, including throughput, security, packet delivery ratio (PDR), communication cost, intra- and inter-cluster distances, and residual energy. For optimal Cluster Head (CH) selection based on various objectives, the novel Particle Swarm Induced Tunicate Swarm Optimisation Algorithm (PITSO), a combination of Particle Swarm Optimisation Algorithm (PSO) and Tunicate Swarm Algorithm (TSA), is utilised. Furthermore, choosing the shortest path between CHs determines multi-hop communication. As a result, the proposed model develops a multi-hop routing framework for WSNs that is safe and energy efficient, improving the reliability and efficiency of the network resulting 0.09 J of energy consumption, 1.325 ms end to end delay, 2156.23kbps of throughput, and 0.82 trust at 100 nodes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： sensor nodes

来源：评论

学校读者我要写书评

暂无评论

A.I. at the Edge of the Edge: intelligent sensor Falling Detection for Humanoid Robot

A.I. at the Edge of the Edge: Intelligent Sensor Falling Det...

引用

IEEE International conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)

作者： Giuseppe Messina Yuri Filistad Corrado Santoro System Research and Application STMicroelectronics Catania Italy Dep. of Mathematics and Comp.Science University of Catania Catania Italy

ISBN: (数字)9798331516857

ISBN: (纸本)9798331516864

This work addresses the problem of fall detection for humanoid robots using an intelligent sensor processing Unit (ISPU). The ISPU offloads the computational burden of robot movement tracking from the main microcontroller. An ad hoc dataset was created and used to train a Convolutional Neural Network (CNN) model for activity recognition. To accommodate the ISPU’s limited RAM, the CNN model was quantized. The system detects falls in real-time, enabling the robot to activate specific protection strategies based on the predicted fall direction. This innovative approach brings AI to the extreme edge, leveraging intelligent sensors to classify robot behaviors and reduce computational load on the microcontroller.

关键词： Microcontrollers Computational modeling Image edge detection Humanoid robots Robot sensing systems Real-time systems Convolutional neural networks Protection intelligent sensors Load modeling

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：