检索结果-内蒙古大学图书馆

advanced INTELLIGENT systems 2025年第3期7卷

作者： Kammarchedu, Vinay Alsiyabi, Monther Ebrahimi, Aida Penn State Univ Dept Elect Engn State Coll PA 16802 USA Penn State Univ Ctr Atom Thin Multifunct Coatings State Coll PA 16802 USA Penn State Univ Mat Res Inst State Coll PA 16802 USA Penn State Univ Dept Biomed Engn State Coll PA 16802 USA

Despite significant progress in developing wearable systems for hand tracking, most devices are still bulky, restrictive to the user or to the placement of the exoskeleton systems, and sensitive to skin preparation and impedance. In this work, we develop a wristband that integrates an array of 10 skin-conformal strain sensors based on laser-induced graphene, which is optimized for continuous measurement of skin strain. The device is characterized to identify several hand gestures and tasks while simultaneously using an optical camera-based hand-tracking system to estimate the joint locations for ground truth generation. Machine learning models are developed to predict gestures as well as specific hand joint angles with high accuracy of >90% and >95%, respectively. The findings show that the sensors placed closer to actuation-specific anatomical features contribute more toward the high accuracy. The sensor array is also integrated with a wearable readout system that wirelessly transmits the data in real time in order to control a robotic arm as a proof of concept for human-robot interaction applications. The developed skin-conformal device is expected to find wide applications in rehabilitation, sports sciences, and human-computer interaction, paving the way for low-profile prosthetic and orthotic control systems.

关键词： laser-induced graphene myography skin-conformal devices strain sensing wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Smart Card-Based Vehicle Ignition systems: Security, Regulatory Compliance, Drug and Impairment Detection, Through advanced Materials and Authentication Technologies

引用

PROCESSES 2025年第3期13卷 911-911页

作者： Vitiello, Vincenzo Benazzi, Alessandro Trucillo, Paolo Inventori Cavensi Via 25 Luglio 87 I-84013 Cava De Tirreni Italy Slim Architetti Via Savio 1087 I-47522 Cesena Italy Univ Naples Federico II Dipartimento Ingn Chim Mat & Prod Ind Ple V Tecchio 80 I-80125 Naples Italy

This study investigates the integration of smart card readers into vehicle ignition systems as a multifaceted solution to enhance security, regulatory compliance, and road safety. By implementing real-time driver verification, encryption protocols (AES-256, RSA), and multifactor authentication, the system significantly reduces unauthorized vehicle use and improves accident prevention. A critical advancement of this research is the incorporation of automated drug and impairment detection to prevent driving under the influence of substances, including illicit drugs and prescription medications. Risk models estimate that drug-related accidents could be reduced by 7.65% through the integration of these technologies into vehicle ignition systems, assuming high compliance rates. The study evaluates drug applications leveraging the same sensor-based monitoring technologies as used for impairment detection. These systems can facilitate the real-time tracking of medication intake and physiological responses, offering new possibilities for safety applications in medical transportation and assisted driving technologies. High-performance polymers such as polyetheretherketone (PEEK) enhance the durability and thermal stability of smart card readers, while blockchain-based verification strengthens data security and regulatory compliance. Despite challenges related to cost (USD 100-300 per unit) and adherence to ISO standards, these innovations position smart card-based ignition systems as a comprehensive, technology-driven approach to vehicle security, impairment prevention, and medical monitoring.

关键词： smart card readers vehicle ignition systems automotive security multifactor authentication encryption protocols blockchain technology CAN bus compatibility driver credential verification automotive cybersecurity frameworks

来源：评论

学校读者我要写书评

暂无评论

Thin Film Magnetic sensor for Magnetic Near-Field Measurement in Wireless Power Transfer System

引用

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 2024年第11期19卷 1763-1769页

作者： Tonthat, Loi Chakarothai, Jerdvisanop Suzuki, Ryota Fuji, Katsumi Yabukami, Shin Tohoku Univ Dept Elect Engn 6-6-05 Aramaki Aza Aoba Aoba Ku Sendai 9808579 Japan Natl Inst Informat & Commun Technol Appl Electromagnet Res Inst Electromagnet Compatibil Lab 4-2-1 Nukui-Kitamachi Koganei Tokyo 1848795 Japan

In this study, we employed a high-frequency-driven thin-film magnetic sensor to precisely measure the magnetic near field with enhanced spatial resolution, a challenge often faced by conventional loop antennas. Our study introduced an innovative approach utilizing this magnetic sensor to assess the magnetic near field in wireless power transfer systems, comparing its performance against that of a loop antenna. Our findings demonstrate that the magnetic sensor achieves its peak signal-to-noise ratio at a DC bias field of 4.7 Oe and carrier frequency of 0.5 GHz, boasting a detection limit for magnetic fields of similar to 0.4 A/m. Moreover, the magnetic field trend measured by the magnetic sensor closely aligns with simulation results, exhibiting sharper changes around the center compared to the loop antenna. These results highlight the superior sensitivity and spatial resolution of the magnetic sensor over conventional loop antennas. By enhancing the reliability of electronic systems across diverse applications, these sensors pave the way for advanced EMI/EMC evaluation techniques. (c) 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

关键词： magnetic sensor wireless power transfer electromagnetic wave loop antenna thin-film high-frequency

来源：评论

学校读者我要写书评

暂无评论

Development of Machine Intelligence for Self-Driving Vehicles Through Video Capturing 20

Development of Machine Intelligence for Self-Driving Vehicle...

引用

20th IEEE/ASME International Conference on Mechatronic and Embedded systems and applications (MESA)

作者： Lowe, Jordon Kuru, Kaya Univ Cent Lancashire Sch Engn & Comp Preston Lancs England

ISBN: (纸本)9798331516246;9798331516239

The automation of vehicles is progressing through several automation levels, with the goal of reaching full autonomy, i.e. level 5, which involves no steering wheel, brakes, pedals, or windshield. This is achieved by the vehicle taking on an increasing number of autonomous decision-making tasks under the guidance of smart control systems that are instilled with Artificial Intelligence (AI) and equipped with advanced sensor and actuator technologies. Major vehicle companies are competing to build the most talented driver, i.e. AI-agent. In this report, how the intelligence of Self-Driving Vehicles (SDVs) is being built by the automotive industry for the efficient deployment of handover wheels is analysed and applications of machine intelligence for SDVs are implemented through video capturing using Deep Learning (DL). The results show that i) the use of DL techniques as well as reinforcement learning (RL) - Deep RL approaches - can contribute to the intelligence of SDVs significantly and ii) SDVs, equipped with advanced mechatronics systems, can be fully autonomous with the level-5 automation as they are trained appropriately with proper datasets.

关键词： Autonomous driving self-driving vehicles Autonomous vehicles driverless vehicles sensor fusion vehicle automation deep learning neural networks

来源：评论

学校读者我要写书评

暂无评论

advanced Deep Learning Approaches for Fault Detection and Diagnosis in Inverter-Driven PMSM systems

引用

INTERNATIONAL JOURNAL OF advanced COMPUTER SCIENCE AND applications 2024年第12期15卷 912-924页

作者： Bacha, Abdelkabir El Idrissi, Ramzi Lmai, Fatima EL Hassani, Hicham Idrissi, Khalid Janati Benhra, Jamal Hassan II Univ Casablanca Sch Elect & Mech Engn LARILE Lab OSIL Team Casablanca Morocco Hassan II Univ Casablanca Fac Sci Ain Chock Phys Dept LPMAT Casablanca Morocco Sidi Mohamed Ben Abdellah Univ Fez Fac Sci & Technol Fez Lab Mech Engn Mech Engn Team Fes Morocco

THIS paper presents a comprehensive approach to fault detection and diagnosis (FDD) in inverter-driven Permanent Magnet Synchronous Motor (PMSM) systems through the innovative integration of transformer-based architectures with physics- informed neural networks (PINNs). The methodology addresses critical challenges in power electronics reliability by incorporating domain-specific physical constraints into the learning process, enabling both high accuracy and physically consistent predictions. The proposed system combines advanced sensor fusion techniques with real-time monitoring capabilities, processing multiple input streams including phase currents, temperatures, and voltage measurements. The architecture's dual-objective optimization approach balances traditional classification metrics with physics- based constraints, ensuring predictions align with fundamental electromagnetic and thermal principles. Experimental validation using a comprehensive dataset of 10,892 samples across nine distinct fault scenarios demonstrates the system's exceptional performance, achieving 98.57% classification accuracy while maintaining physical consistency scores above 0.98. The model exhibits robust performance across varying operational conditions, including speed variations (97.45-98.57% accuracy range) and load fluctuations (97.91-98.12% accuracy range). Notable achievements include perfect detection rates for certain critical faults, such as high-side short circuits and thermal anomalies, with area under ROC curve (AUC) scores of 1.0. This research establishes new benchmarks in condition monitoring and fault diagnosis for power electronic systems, offering practical implications for predictive maintenance and system reliability enhancement.

关键词： -Fault detection and diagnosis PMSM deep learn- ing transformers physics-informed neural networks power elec- tronics

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Optical Materials for sensor Protection against Pulsed Laser Radiation in the Visible Spectral Region 2

Nonlinear Optical Materials for Sensor Protection against Pu...

引用

advanced Materials, Biomaterials, and Manufacturing Technologies for Security and Defence ii 2024

作者： Dengler, Stefanie Henrichsen, Michael Fraunhofer IOSB Fraunhofer Institute of Optronics System Techhnologies and Image Exploitation Gutleuthausstr. 1 Ettlingen76275 Germany

ISBN: (纸本)9781510681187

The growing use of lasers increases the risk of accidental or intentional damage to human eyes and optical sensor systems. Current protection equipment is based on optical filters with fixed spectral transmission bands or shutter systems, but optical filters only work in predefined wavebands and shutter-systems are too slow to protect against pulsed laser radiation. Passive self-activated devices, in contrast, offer the potential for short response times with a simple design. Nonlinear optical materials with the capability to strongly attenuate intense laser beams are particularly interesting. In this work, we present our research on the protection capability of C60 and self-produced silver nanoparticles as functional materials in a real application case. A camera with CMOS sensor can be completely protected from being damaged up to a maximum measured input energy of 2 mJ. Therefore, it has been demonstrated that optical limiting materials can be suitable in laser protection applications. © 2024 SPIE.

关键词： Silver nanoparticles

来源：评论

学校读者我要写书评

暂无评论

Overview of Smart Parking: Types, sensors Technologies and Energy Efficiency Strategies 4th

Overview of Smart Parking: Types, Sensors Technologies and E...

引用

4th International Conference on Digital Technologies and applications (ICDTA)

作者： Alaoui, Hind Kadim Coulibaly, Moussa Errami, Ahmed II Univ Casablanca ENSEM LRILab NEST Res Grp BP 8118 Oasis Casablanca Hassan Morocco

ISBN: (纸本)9783031686528;9783031686535

As we realize today, especially in metropolitan cities, locating a proper parking space for a car is the biggest hassle. The time wasted searching for a parking space amplifies the already existing problems of congestion and leads to consumption of an unnecessary amount of fuel. This problem can be solved by using advanced communication technology known as smart parking systems. These systems use sophisticated sensing techniques to inform drivers, in real terms, of the availability of parking spaces. This paper presents a comprehensive study of various smart parking elements with a focus on the sensing side of smart parking systems that helps in detecting the presence of vehicles in various parking situations, it also clearly defines the classification of parking spots by differentiating between open-air and enclosed facilities, and highlight methods to reduce sensor energy consumption in order to ensure the smart parking infrastructure operates sustainably and effectively.

关键词： sensors WSN Smart parking Energy guidance

来源：评论

学校读者我要写书评

暂无评论

A proposed plant classification framework for smart agricultural applications using UAV images and artificial intelligence techniques

引用

ALEXANDRIA ENGINEERING JOURNAL 2024年 109卷 466-481页

作者： Eladl, Shymaa G. Haikal, Amira Y. Saafan, Mahmoud M. Eldin, Hanaa Y. Zain Mansoura Univ Fac Engn Comp & Control Syst Engn Mansoura Egypt Nile Higher Inst Sci & Comp Technol Cairo Egypt

Utilizing Wireless sensor Networks (WSNs), Internet of Things (IoTs) sensors, and Unmanned Aerial Vehicles (UAVs), in conjunction with optimization techniques and machine learning algorithms, can present a novel approach to Precision Agricultural (PA) crops. Agriculture has transitioned from traditional legacy systems to incorporate advanced smart technologies. Several complex farming problems are utilized to promote a variety of UAV sensing and Artificial Intelligence (AI) algorithms in PA applications of smart agriculture, especially in developing countries. This paper proposes the design of a conceptual UAV sensing system for crop management using a novel classification framework. UAV-based image datasets can be implemented and expanded to various types of crops. In addition, it can classify various types of rice species and detect weed farms as it consists of a multistage process for identifying and monitoring different crops. The proposed classification framework is evaluated using three different real UAV image datasets compared with Naive Bayes, Decision Tree (DT), Bagging, and Random Forest (RF) techniques. The classification performance metrics obtained are as follows: i) the WeedNet dataset with 100% F1-score, 100% recall, 100% precision, and 100% accuracy;ii) the Rice Seedling dataset with 99.5% F1-score, 99.5% recall, 99.5% precision, and 99.5% accuracy;and iii) the Rice Varieties dataset with 97.99% F1-score, 97.99% recall, 98.14% precision, and 97.99% accuracy. The success rates achieved by the proposed classification framework outperform those of other recent state-of-the-art techniques, demonstrating its efficacy in crop management applications.

关键词： Precision agriculture Crop management Plant classification Federated learning Deep learning Remote sensing Weed monitoring Rice seeding Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Brief Introduction to Intelligent Point Cloud Processing, Sensing, and Understanding: Part ii

引用

sensorS 2025年第5期25卷 1310-1310页

作者： Wang, Miaohui Tian, Sukun Shenzhen Univ Coll Elect & Informat Engn Guangdong Key Lab Intelligent Informat Proc Shenzhen 518052 Peoples R China Peking Univ Sch Stomatol Beijing 100081 Peoples R China

Point cloud, which represents the three-dimensional (3D) digital world, is one of the fundamental data carriers in many emerging applications [1], including the autonomous driving, robotics, and geospatial fields. Advancements in sensor technologies have facilitated the acquisition of point clouds from diverse platforms [2], perspectives, and spectra. This progress has underscored the necessity to address the generation [3], processing [4], analysis [5], and quality evaluation [6] of point cloud *** 1 introduces an innovative framework to enhance LiDAR-based datasets for advanced driver-assistance systems (ADASs), improving the representation of distant objects by generating synthetic object points from real point clouds. The proposed framework consists of three key modules: (1) position determination identifies optimal locations and orientations for synthetic objects, employing ground filtering to separate ground and non-ground points; selects candidate positions; resolves collisions; and determines object poses; (2) object generation converts LiDAR data from Cartesian to spherical coordinates to generate synthetic points, where a spherical point-tracking technique and a “point wall” method mitigate excessive data loss, preserving object shape fidelity; (3) synthetic annotation automatically labels object points with attributes such as position, size, pose, and occlusion, ensuring consistency with datasets such as KITTI-360. Experimental results show that integrating these synthetic objects into training datasets enhances the performance of 3D detection *** evolution of point cloud acquisition and analysis has been propelled by AI advancements. This Special Issue compiles a diverse portfolio of contributions that address critical challenges in point cloud processing, sensing, and understanding. The selected studies push the boundaries of current knowledge by offering innovative solutions to existing challenges and unlocking new 3D applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigation into auto-labeling a novel dataset for off-road autonomy using transfer learning 2

Investigation into auto-labeling a novel dataset for off-roa...

引用

Artificial Intelligence for Security and Defence applications ii 2024

作者： Honigfort, Haley B. Price, Stanton R. Carley, Samantha S. Butler, Samantha J. Davis, Trenton G. Dabbiru, Lalitha Ball, John E. Price, Stephanie J. Fairley, Joshua R. United States Army Corps of Engineers Engineer Research and Development Center VicksburgMS United States Mississippi State University Center for Advanced Vehicular Systems StarkvilleMS United States

ISBN: (纸本)9781510681200

In autonomous driving, utilizing deep learning models to help make decisions has become a popular theme, particularly in the realm of computer vision. These models are heavily geared to make decisions based on the environment in which they are trained. Currently, there are very few datasets that exist for off-road autonomy. In order for autonomous vehicles to traverse off-road or unstructured settings, the vehicles must have an understanding of these environments. This paper seeks to lay the groundwork for a new, off-road, multi-modality dataset, with initial data being collected at Mississippi State University’s Center for advanced Vehicular systems (MSU CAVS). This dataset will include co-aligned and co-registered LiDAR, thermal, and visual sensor data. Additionally, this dataset will include semantic segmented visual data as well as object detection and classification labels for all three modalities. However, to perform semantic segmentation on each image individually would be strenuous and time-consuming due to the large quantity of images. Thus, this paper will explore the utility of transfer learning for auto-labeling. Specifically, this paper considers how transfer learning for a unique and under-represented (data-wise) domain performs in reducing the burden associated with hand-annotation datasets for deep learning applications. © 2024 SPIE.

关键词： Semantic Segmentation

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：