检索结果-内蒙古大学图书馆

IEEE SoutheastCon conference on Engineering the Future

作者： Vegesana, Sasank Penumatcha, Harsha Jaiswal, Chandra AlHmoud, Issa W. Gokaraju, Balakrishna North Carolina A&T State Univ Computat Data Sci & Engn Greensboro NC 27411 USA

ISBN: (纸本)9798350317107;9798350317114

This study explores the forefront of indoor autonomous robotics, combining cutting-edge computational technologies with precise sensor systems. The NVIDIA Jetson xavier Nx serves as the powerful computational core, efficiently processing complex data. This central unit is enhanced by two critical sensors: the Intel RealSense D435 for depth perception, and a LiDAR unit for detailed environmental mapping, an Inertial Measurement Unit (IMU) to ensure accurate path adherence, all integrated seamlessly through the Robot Operating System (ROS). A key aspect of our research is the implementation of the YOLOv5 model for recognizing indoor traffic signals, utilizing the Jetson Nx's prowess in PyTorch with CUDA. This feature is vital for the robot's navigation, enabling it to interpret and react to visual cues in complex indoor settings. Our approach significantly enhances the robot's navigational capabilities by utilizing a combination of advanced route planning and traffic light detection. The system employs the A* pathfinding algorithm to efficiently traverse between predefined coordinates. At each designated node, it employs the YOLOv5 model to detect traffic lights. The robot continues seamlessly upon detecting a green light or if there is no traffic light, whereas it stops 40cm before the light. Our goal is to showcase the effectiveness of combining multiple sensory technologies in autonomous robots. This system, when combined with the robot's depth sensing, advanced object detection via the YOLOv5 model, and LiDAR mapping, significantly streamlines the navigation process. Preliminary results indicate enhanced navigational precision and quicker response times, representing a step forward in sophisticated indoor autonomous navigation. This approach emphasizes the value of integrating different technologies, including efficient navigation systems, to achieve advanced and reliable autonomous movement, marking a significant contribution to the field of robotics technology.

关键词： Autonomous Robotics Differential Drive Robot Indoor Navigation Multi-sensor System NVIDIA Jetson xavier Nx Traffic Signal Detection Depth Sensing

来源：评论

学校读者我要写书评

暂无评论

Simulation-Based Performance Evaluation of 3D Object Detection Methods with Deep Learning for a LiDAR Point Cloud Dataset in a SOTIF-related Use Case 10

Simulation-Based Performance Evaluation of 3D Object Detecti...

引用

10th International conference on Vehicle Technology and Intelligent Transport systems, VEHITS 2024

作者： Patel, Milin Jung, Rolf Institute for Advanced Driver Assistance Systems and Connected Mobility Kempten University of Applied Sciences Benningen Germany Faculty of Computer Science Kempten University of Applied Sciences Kempten Germany

ISBN: (纸本)9789897587030

Safety of the Intended Functionality (SOTIF) addresses sensor performance limitations and deep learningbased object detection insufficiencies to ensure the intended functionality of Automated Driving systems (ADS). This paper presents a methodology examining the adaptability and performance evaluation of the 3D object detection methods on a LiDAR point cloud dataset generated by simulating a SOTIF-related Use Case. The major contributions of this paper include defining and modeling a SOTIF-related Use Case with 21 diverse weather conditions and generating a LiDAR point cloud dataset suitable for application of 3D object detection methods. The dataset consists of 547 frames, encompassing clear, cloudy, rainy weather conditions, corresponding to different times of the day, including noon, sunset, and night. Employing MMDetection3D and OpenPCDET toolkits, the performance of State-of-the-Art (SOTA) 3D object detection methods is evaluated and compared by testing the pre-trained Deep Learning (DL) models on the generated dataset using Average Precision (AP) and Recall metrics. Copyright © 2024 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Implementation of Backward Key Chain and Hill Cipher for Securing Messages in the Wireless sensor Networks

Implementation of Backward Key Chain and Hill Cipher for Sec...

引用

International conference on advanced Creative Networks and Intelligent systems (ICACNIS) - Blockchain Technology, Intelligent systems, and the applications for Human Life

作者： Samosir, Timothy Jefrin Viali Afianti, Farah Yunanto, Prasti Eko Telkom Univ Sch Comp Bandung Indonesia

ISBN: (纸本)9798350334449

The development of the internet of things (IoT) has been growing, such as wireless sensor networks (WSN). The use of WSN in daily life has helped a lot in various fields. WSN has interconnected nodes with limited memory, resources, and computation. Because of these limitations, messages or data on these nodes are in danger of being tampered with or known by attackers. In this paper, a modification of the broadcast authentication scheme by adding confidentiality to the session key and message is proposed. The session key, produced by a backward key chain, is secured with a modified hill cipher encryption. The experiment results show that the average time required for the hill cipher method for encryption is higher than decryption with a difference of about 0.1579 sec. then the main result of the experiment is the comparison between the ECDH method and the Backward Keychain for both the encryption and decryption process, which results in the Backward Keychain method being better than the ECDH method.

关键词： backward key chain hill cipher IoT WSN

来源：评论

学校读者我要写书评

暂无评论

Optimization design method of super-size carbon fiber main bearing structure

Optimization design method of super-size carbon fiber main b...

引用

2023 advanced Fiber Laser conference, AFL 2023

作者： Sun, Jian Fang, Haijun Jia, Yongdan Wang, Weizhi Yang, Jukui Fu, Ruimin Beijing Institute of Space Mechanics and Electricity Beijing100094 China Beijing Key Laboratory of Advanced Optical Remote Sensing Technology China

ISBN: (纸本)9781510677661

An optimization design method based on the combination topology optimization and DOE experimental design is proposed. The relationship among weight, stiffness and deformation of key components of the balanced main bearing structure is continuously optimized by comprehensive optimization method. Through a large number of examples to complete the search for the optimal solution, and then to achieve the main bearing structure stiffness, stability and weight optimal solution design. The design results show that the optimization design method based on the combination of topology optimization and DOE experimental design can greatly improve the design efficiency and completion quantity. The specific product designed by this method has been applied to the main bearing structure of an optical remote sensor. The bearing structure size reaches 3m, the load capacity is 700kg, and the weight is less than 110kg, which has good stability. This design method can be extended to other large size, small weight requirements and high stability structural parts design process, and has to wider application prospect. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Optimal systems

来源：评论

学校读者我要写书评

暂无评论

Prospective UAV-Assisted Positioning Architecture and Technologies for 6G Network Edge

引用

IEEE NETWORK 2025年第2期39卷 61-68页

作者： Liu, Qirui Liu, Rongke xu, Chenren Peking Univ Sch Comp Sci Beijing 100871 Peoples R China Beihang Univ Sch Elect & Informat Engn Beijing 100191 Peoples R China Beihang Univ Shenzhen Inst Shenzhen 518063 Peoples R China Peking Univ Sch Comp Sci Minist Educ Beijing 100871 Peoples R China Peking Univ Key Lab High Confidence Software Technol Minist Educ Beijing 100871 Peoples R China

Positioning enhancement remains a pivotal technology in the evolution of both the fifth-generation advanced (5G-A) and 6G mobile communication networks, expected to offer users broader coverage, reduced latency, and more accurate and efficient positioning services based on 5G infrastructure. While in scenarios with inadequate coverage due to the sparse deployment of (both fixed and mobile) terrestrial base stations (BSs) or poor signal quality, uncrewed aerial vehicles (UAVs) can be flexibly deployed on a large scale. These UAVs act as edge reference BSs for 6G, providing on-demand positioning and other sensing-related services, such as logistics tracking and emergency search. In this article, we provide an extensive overview of UAV-assisted positioning architectures and summarize recent research advances, complete with detailed examples that illuminate the system operational processes. We also investigate key open issues and future research directions in UAV-assisted network systems, incorporating new 6 G features. This article outlines a road map for advancing various communication and sensing applications critical to 6G edge intelligence.

关键词： Autonomous aerial vehicles 6G mobile communication Accuracy sensors 5G mobile communication Location awareness Global navigation satellite system Long Term Evolution Wireless sensor networks Wireless fidelity 6G network edge scenarios positioning enhancement unmanned aerial vehicle (UAV) base station on-demand services

来源：评论

学校读者我要写书评

暂无评论

Review on Adaptive Filtering Techniques in Cooperative Localization and Zone-based ECU Architectures for Automotive systems 9

Review on Adaptive Filtering Techniques in Cooperative Local...

引用

9th International conference on Communication and Electronics systems, ICCES 2024

作者： Jeeva Bharathi, K. Thirumoorthi, P. Prabhakaran, A. Kumaraguru College of Technology Coimbatore India Kumaraguru College of Technology Coimbatore India

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377972

This paper offers a state-of-the-art analysis of the most recent developments in cooperative location estimation using adaptive filters under adverse conditions including compass loss and non-Gaussian noise environment of vehicular networks. Cooperative localization is now an essential feature for autonomous and connected cars and requires reliable algorithms that can handle tricky sensor failures and noise interference. The study is dedicated to the examination of 'A Novel Adaptive Filtering for Cooperative Localization Under Compass Failure and Non-Gaussian Noise,' which describes an adaptive filtering approach aimed at reducing localization errors in systems that do not have compass data and when non-Gaussian noise appears. This approach involves the use of adaptive techniques for the accommodation of varying noise levels to improve the order, and accuracy of location characteristics in real-time. Thus, a comparative analysis of the performance and computational complexity of particle filters, Kalman filters, and extended Kalman filters is given based on the analysis of the performance of different adaptive filtering techniques. Further, we discuss the applications and consequences of the proposed filtering framework for autonomous vehicles' localization systems. These results suggest that the proposed adaptive filtering greatly enhances localization performance in the presence of off-nominal sensors to support more reliable car operations in actual environments. In the final section of the paper, some ideas for the further development of robust localization technologies and the application of advanced machine learning to improve the filtering approach and its adaptability are presented. © 2024 IEEE.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

A wearable and high-performance capacitive pressure sensor based on a biocompatible PVP nanofiber membrane via electrospinning and UV treatment

引用

JOURNAL OF MATERIALS CHEMISTRY C 2022年第29期10卷 10491-10499页

作者： Ren, Mengna Li, Jiamin Lv, Luyu Zhang, Mengqi Yang, xiaojun Zhou, Qihui Wang, Danyang Dhakal, Rajendra Yao, Zhao Li, Yuanyue Kim, Nam Young Qingdao Univ Coll Elect & Informat Qingdao 266071 Peoples R China Qingdao Univ Affiliated Hosp Inst Translat Med Qingdao 266003 Peoples R China Qingdao Univ Affiliated Hosp Dept Stomatol Qingdao 266003 Peoples R China Sejong Univ Dept Comp Sci & Engn Seoul 05006 South Korea Kwangwoon Univ Dept Elect Engn Seoul 01897 South Korea

In recent years, flexible pressure sensors have become an important part of soft electronics due to their tactile sensing abilities. However, manufacturing pressure sensors with high sensing performance and excellent applicability is still a great challenge. In this paper, we report the fabrication, sensing performance and applications of a flexible capacitive pressure sensor based on a polyvinyl pyrrolidone (PVP) nanofiber membrane (NM), which has a better biocompatibility and a wider applicability than the traditional dielectric layer materials. The cost-effective process of electrospinning and an ultra-violet (UV) photochemical aftertreatment are employed to prepare a PVP NM, which contribute to improving the performance of the sensor. The experimental results show that our sensor exhibits a fast response/recovery time (41/36 ms), a high sensitivity (0.278 kPa(-1) at 0-2 kPa), a wide pressure range (0-200 kPa), an ultra-low detection limit (similar to 50 Pa) and an excellent stability (8000 cycles). Thanks to its superior performance, the sensor can be used to monitor various subtle physiological and physical signals, such as pulse rate, respiration, mouse clicks, body movement and air flow. In addition, a 4 x 4 sensor array is fabricated that can map objects with various geometries, which demonstrates its ability to accurately identify the spatial pressure distribution. The developed high-performance and wide-applicative flexible sensor can provide new opportunities for innovative applications of advanced human-computer interface systems.

关键词： Electrospinning

来源：评论

学校读者我要写书评

暂无评论

MagRetract Robot Implementation and applications

MagRetract Robot Implementation and Applications

引用

Future of Information and Communication conference, FICC 2024

作者： Ayad, Mustafa Ibanez, Diego Ndiaye, Yahya Ibrahima State University of New York OswegoNY13126 United States

ISBN: (纸本)9783031539626

This paper presents an in-depth analysis of MagRetract, a robotic system designed to collect and dispose of metallic debris in various environments efficiently. Using manual and autonomous modes, MagRetract navigates through workspaces while detecting and retrieving small metallic objects such as nails and screws. The robot’s performance was evaluated across multiple trials, considering factors such as workspace size, obstacle presence, and the robot’s adaptability. Despite some challenges, including magnetic interference and limitations in handling heavier objects, MagRetract demonstrated promising results in manual and autonomous operations. By integrating a LiDAR sensor and a more advanced electromagnetic system, future improvements are anticipated to enhance the robot’s performance, adaptability, and efficiency in diverse settings. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Quality and Trust Indicators of Digital Road Infrastructure Data Are Essential to Improve Its Usability: An Intelligent Speed Assist (ISA) Study 11

Quality and Trust Indicators of Digital Road Infrastructure ...

引用

11th International conference on Vehicle Technology and Intelligent Transport systems, VEHITS 2025

作者： van de Sluis, Jacco Altgassen, Daniel Schackmann, Peter-Paul Networks Department TNO - ICT The Hague Netherlands Integrated Vehicle Safety Department TNO - Mobility & Build Environment Helmond Netherlands

ISBN: (纸本)9789897587450

The promise of a Digital Road Infrastructure (DRI) is to improve both road and vehicle safety. ADAS/ADS with DRI support, can help vehicles in overcoming certain sensor limitations, handle more complex operational situations and offer additional situational awareness. An effective DRI must be trusted and must offer the required data quality, both are currently lacking. Intelligent Speed Assist (ISA) is an interesting show case for the added value of DRI. In our approach camera-based traffic sign detections and map-based speed limit information, both occasionally wrong, are augmented with actual speed limit and road layout information coming from DRI. A Misbehaviour Detection and Reporting (MBD&R) concept tailored to the ISA sources is deployed in the vehicle to detect and report ISA related misbehaviour. Trust and quality indicators are calculated for data coming from camera, map and DRI, which are used to verify and compare theses sources and make improved ISA speed limit decisions. The vehicle implementation is tested under real-life traffic conditions. Our work is a first step in realizing a trusted DRI. The long-term goal is collaboration among all stakeholders to implement mechanisms that improve trust and the quality of shared data sources for use in traffic safety applications. Copyright © 2025 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Amber Gemstones Colour Classification by CNN 12

Amber Gemstones Colour Classification by CNN

引用

12th IEEE International conference on Intelligent Data Acquisition and advanced Computing systems: Technology and applications, IDAACS 2023

作者： Katkus, Dovydas MacIulevicius, Paulius Lipnickas, Arunas Kaunas University of Technology Department of Automation KaunasLT-51367 Lithuania

ISBN: (纸本)9798350358056

This paper demonstrates the implementation of a convolutional neural network (CNN) for classifying amber gemstone data. We show two strategies on how to solve multiclass color classification problem by CNN. At the beginning the data images are rescaled to 60x60 px and the network is trained by using a 5-fold approach to minimize categorical cross entropy loss. This resulted in an average accuracy of 88.5%, which was improved to 90% by adjusting the training loss function by adding Dice score component. In the second attempt, the original image data was split into 60x60 px patches and the predictions from these patches were combined using a majority voting rule. The final classification resulted to 89.6% of accuracy and was similar to that of the first attempt, but the advantage of the patching approach was a reduction of standard deviation, indicating that the trained classifier is less sensitive to data divisions and background noise. © 2023 IEEE.

关键词： computer vision convolutional neural networks expert systems image classification

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：