检索结果-内蒙古大学图书馆

11th IEEE Region 10 Humanitarian technology Conference, R10-HTC 2023

作者： Chavda, Mudra Zeeshan, Mohammad Nayek, Rajdip Malik, Shahid Centre for Sensors Instrumentation and Cyber Physical System Engineering Indian Institute of Technology Delhi Delhi India Indian Institute of Technology Delhi Department of Applied Mechanics Delhi India

ISBN: (纸本)9798350326147

The underground mining environment is one of the most hazardous for workers. Monitoring the miner's location precisely is essential for the miner's safety in this situation. Roof collapses, toxic gas releases and crashes of vehicles in mines are some of the factors that make this occupation more hazardous to human life than others. In order to determine the location of miners, however, a positioning system must be accurate and precise. The synchronization signal between transmitters and receivers is crucial in emergency situations. By using the synchronization signal, it is possible to prevent both data loss and misinterpretation. This article describes a method for combining visible light with an acoustic-based 2D positioning system. The developed proof-of-concept makes use of loudspeakers and a microphone as an acoustic transmitter and receiver, respectively. In addition, LED and LDR are used as transmitter and receiver for visible light. Using a timer circuit, synchronization has been achieved, and the transmitters are turned on sequentially using time division multiplexing. For the safety of miners, the system establishes the viability of using visible light as a synchronization signal and locates the miner with an error of ± 3 cm. © 2023 IEEE.

关键词： Transmitters

来源：评论

学校读者我要写书评

暂无评论

CapsNet-FR: Capsule Networks for Improved Recognition of Facial Features

引用

Computers, Materials & Continua 2024年第5期79卷 2169-2186页

作者： Mahmood Ul Haq Muhammad Athar Javed Sethi Najib Ben Aoun Ala Saleh Alluhaidan Sadique Ahmad Zahid farid Department of Computer System Engineering University of Engineering&TechnologyPeshawar25000Pakistan College of Computer Science and Information Technology Al-Baha UniversityAlaqiq65779-7738Saudi Arabia REGIM-Lab:Research Groups in Intelligent Machines National School of Engineers of Sfax(ENIS)University of SfaxSfax3038Tunisia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia EIAS:Data Science and Blockchain Laboratory College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Computer Sciences Bahria University Karachi CampusKarachi541004Pakistan Department of Electrical Engineering Abasyn UniversityPeshawar25000Pakistan

Face recognition (FR) technology has numerous applications in artificial intelligence including biometrics, security,authentication, law enforcement, and surveillance. Deep learning (DL) models, notably convolutional neuralnetworks (CNNs), have shown promising results in the field of FR. However CNNs are easily fooled since theydo not encode position and orientation correlations between features. Hinton et al. envisioned Capsule Networksas a more robust design capable of retaining pose information and spatial correlations to recognize objects morelike the brain does. Lower-level capsules hold 8-dimensional vectors of attributes like position, hue, texture, andso on, which are routed to higher-level capsules via a new routing by agreement algorithm. This provides capsulenetworks with viewpoint invariance, which has previously evaded CNNs. This research presents a FR model basedon capsule networks that was tested using the LFW dataset, COMSATS face dataset, and own acquired photos usingcameras measuring 128 × 128 pixels, 40 × 40 pixels, and 30 × 30 pixels. The trained model outperforms state-ofthe-art algorithms, achieving 95.82% test accuracy and performing well on unseen faces that have been blurred orrotated. Additionally, the suggested model outperformed the recently released approaches on the COMSATS facedataset, achieving a high accuracy of 92.47%. Based on the results of this research as well as previous results, capsulenetworks perform better than deeper CNNs on unobserved altered data because of their special equivarianceproperties.

关键词： CapsNet face recognition artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Trusted Polarimetric Feature Fusion for Polsar Image Classification

Trusted Polarimetric Feature Fusion for Polsar Image Classif...

引用

2023 SAR in Big Data Era, BIGSARDATA 2023

作者： Han, Fangzhou Zhang, Lamei Dong, Hongwei Harbin Institute of Technology Department of Information Engineering Harbin150001 China Institute of Software Chinese Academy of Sciences Science & Technology on Integrated Information System Laboratory Beijing China

ISBN: (纸本)9798350326239

Benefiting from the rapid advancements in Deep Learning (DL), data-driven features exhibit remarkable separability in PolSAR image classification. However, data-driven features are challenging to interpret and susceptible to resolution and noise. On the contrary, polarimetric features based on the target decomposition not only have high robustness, but also has physical interpretability. Consequently, researchers have begun to explore ways to integrate both types of features to achieve enhanced performance, which typically concat the data-driven features and polarimetric features directly. However, polarimetric features are not stable in separability, which is because the inherent defects of the target decomposition algorithm. To mitigate the adverse effects of low-quality features, this paper proposes a trusted polarimetric feature fusion (TPFF). The new paradigm calculates the confidence of features and employs a novel feature fusion method. The proposed method has been tested on the EMISAR Foulum dataset, with experimental results demonstrating improved classification performance and robustness. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

GATreg - Graph Attention Networks with Regularization

GATreg - Graph Attention Networks with Regularization

引用

7th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2025

作者： Ishtiaq, Mariam Won, Jong-Un Park, Sangchan Korea Railroad Research Institute Transportation System Engineering University of Science and Technology AI Railroad Research Department Uiwang Korea Republic of The State University of New York Korea Department of Technology and Society Incheon Korea Republic of

ISBN: (纸本)9798331507022

To improve the applicability and performance of graph neural networks (GNNs);graph convolution networks (GCNs) and graph attention networks (GATs) have shown promising ways forward. However, lack of generalizability has been a major bottleneck for their widespread applications. To overcome this limitation of GNNs, we propose a regularization scheme for GAT, termed as GATreg. We use a novel loss function to achieve the optimal performance of GATreg. The proposed model has been analyzed using 3 benchmark datasets: Cora, Citeseer, and Pubmed. Our results show prominent improvements of classification accuracy, around 3%, compared to vanilla models and have the potential to be analyzed for further enhancements. Additionally, GATs can be explored to improve the reasoning ability of multimodal large language models (LLMs), particularly to eliminate hallucinations. They can also be used for the quantum information theory-based analysis of GATs, for which this work analyzes recent literature. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

TRACING THE MOTION IN HIGH-SPEED VIDEO FRAMES USING DEEP LEARNING

TRACING THE MOTION IN HIGH-SPEED VIDEO FRAMES USING DEEP LEA...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATE 2023

作者： Gayathri, R. Harsha, B.K. Sharmiladevi, D. Sajitha, L.P. Rao, Vuda Sreenivasa Nirmala, G. Department of ECE Rajalakshmi Engineering College Tamilnadu Chennai India Department of ECE CMR Institute of Technology Karnataka Bengaluru India Department of Electronics and Communication Engineering Sona College of Technology Tamilnadu Salem India Department of Computer Science and Business System R. M. K Engineering College Tamilnadu Kavaraipettai India Department of CSE Koneru Lakshmaiah Education Foundation AP Vaddeswaram India Department of Computer Science and Engineering R.M.D Engineering College Chennai India

ISBN: (纸本)9798350305708

One of the most important jobs of a self-driving vehicle's visual system is to identify and categorize obstacles along the route. Cars need to be detected, categorized, localized, and linked across frames if they are to be tracked. With the low cost and high utility of visual information, vision-based technologies have gained popularity for this purpose. In this paper, we develop a deep learning-based motion tracking from high-speed video frames. The model is developed using deep convolutional neural network that makes it to be applicable for classification of objects in the video frames. The deep convolutional neural network classifies the obstacles present in the pathway and offers a better classification pattern than the conventional models. © 2023 IEEE.

关键词： Application Convolutional Neural Network Deep Learning High-Speed Video Motion Vehicle Video Frames

来源：评论

学校读者我要写书评

暂无评论

Road Traffic Monitoring from Aerial Images Using Template Matching and Invariant Features

引用

Computers, Materials & Continua 2024年第3期78卷 3683-3701页

作者： Asifa Mehmood Qureshi Naif Al Mudawi Mohammed Alonazi Samia Allaoua Chelloug Jeongmin Park Department of Creative Technologies Air UniversityIslamabad46000Pakistan Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Department of Information Systems College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj16273Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Engineering Tech University of KoreaGyeonggi-do15073South Korea

Road traffic monitoring is an imperative topic widely discussed among *** used to monitor traffic frequently rely on cameras mounted on bridges or ***,aerial images provide the flexibility to use mobile platforms to detect the location and motion of the vehicle over a larger *** this end,different models have shown the ability to recognize and track ***,these methods are not mature enough to produce accurate results in complex road ***,this paper presents an algorithm that combines state-of-the-art techniques for identifying and tracking vehicles in conjunction with image *** extracted frames were converted to grayscale,followed by the application of a georeferencing algorithm to embed coordinate information into the *** masking technique eliminated irrelevant data and reduced the computational cost of the overall monitoring ***,Sobel edge detection combined with Canny edge detection and Hough line transform has been applied for noise *** preprocessing,the blob detection algorithm helped detect the *** of varying sizes have been detected by implementing a dynamic thresholding *** was done on the first image of every ***,to track vehicles,the model of each vehicle was made to find its matches in the succeeding images using the template matching *** further improve the tracking accuracy by incorporating motion information,Scale Invariant Feature Transform(SIFT)features have been used to find the best possible match among multiple *** accuracy rate of 87%for detection and 80%accuracy for tracking in the A1 Motorway Netherland dataset has been *** the Vehicle Aerial Imaging from Drone(VAID)dataset,an accuracy rate of 86%for detection and 78%accuracy for tracking has been achieved.

关键词： Unmanned Aerial Vehicles(UAV) aerial images dataset object detection object tracking data elimination template matching blob detection SIFT VAID

来源：评论

学校读者我要写书评

暂无评论

Enhancing Predictive Emissions Monitoring Performance: Data Preprocessing for XGBoost-Based Model Algorithm 17

Enhancing Predictive Emissions Monitoring Performance: Data ...

引用

17th International Conference on Knowledge and Smart technology, KST 2025

作者： Winarto, Rudy Purnomo, Mauridhi Hery Anggraeni, Wiwik School of Interdisciplinary Management and Technology Sepuluh Nopember Institute of Technology Surabaya Indonesia Sepuluh Nopember Institute of Technology Department of Electrical Engineering Surabaya Indonesia Sepuluh Nopember Institute of Technology Department of Information System Surabaya Indonesia

ISBN: (纸本)9798331520403

Gas turbines play a crucial role in processing industries and power generation, but their emissions present significant environmental challenges. Accurate emissions prediction is essential, with research focusing on improving statistical models, machine learning algorithms, and hybrid systems. However, varying data quality and dynamic industrial environments often lead to inconsistent model performance. This study examines the impact of data cleaning and splitting on the accuracy of XGBoost-based emissions prediction models, emphasizing the importance of data pre-processing in enhancing performance. The tuning process significantly reduced errors across all metrics, with CO showing the most notable improvement despite high initial errors, while \text{SO}_{2} demonstrated substantial gains, particularly in MAPE. Hyperparameter tuning further enhanced the model's accuracy, reduced error magnitudes, and improved generalization. Regular monitoring and periodic retraining with updated data are recommended to maintain model effectiveness in production environments. If performance improvements plateau, simplifying the model by reducing trees or applying early stopping can optimize efficiency without compromising accuracy. © 2025 IEEE.

关键词： accuracy computational cost emissions prediction XGBoost

来源：评论

学校读者我要写书评

暂无评论

Singular topological edge states in locally resonant metamaterials

引用

Science Bulletin 2025年第7期70卷 1080-1086页

作者： Yeongtae Jang Seokwoo Kim Eunho Kim Junsuk Rho Department of Mechanical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea Division of Mechanical System Engineering Jeonbuk National UniversityJeonju 54896Republic of Korea Graduate School of Mechanical-Aerospace-Electric Convergence Engineering Jeonbuk National UniversityJeonju 54896Republic of Korea Department of Chemical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea Department of Electrical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea POSCO-POSTECH-RIST Convergence Research Center for Flat Optics and Metaphotonics Pohang 37673Republic of Korea

Band topology has emerged as a novel tool for material design across various domains,including photonic and phononic systems,and metamaterials.A prominent model for band topology is the Su-Schri effer-Heeger(SSH)chain,which reveals topological in-gap states within Bragg-type gaps(BG)formed by periodic *** from classical BGs,another mechanism for bandgap formation in metamaterials involves strong coupling between local resonances and propagating waves,resulting in a local resonance-induced bandgap(LRG).Previous studies have shown the challenge of topological edge state emergence within the ***,we reveal that topological edge states can emerge within an LRG by achieving both topological phase and bandgap transitions *** describe this using a model of inversion-symmetric extended SSH chains for locally resonant ***,this topological state can lead to highly localized modes,comparable to a subwavelength unit cell,when it emerges within the *** experimentally demonstrate distinct differences in topologically protected modesDhighlighted by wave localizationDbetween the BG and the LRG using locally resonant granulebased *** findings suggest the scope of topological metamaterials may be extended via their bandgap nature.

关键词： Band topology Metamaterials Singular topological edge states Local resonance Woodpile metamaterials

来源：评论

学校读者我要写书评

暂无评论

Ga/GaSb nanostructures:Solution-phase growth for highperformance infrared photodetection

引用

Nano Research 2023年第2期16卷 3304-3311页

作者： Huanran Li Su You Yongqiang Yu Lin Ma Li Zhang Qing Yang Hefei National Research Center of Physical Sciences at the Microscale Department of ChemistryLaboratory of Nanomaterials for Energy Conversion(LNEC)University of Science and Technology of China(USTC)Hefei 230026China Micro Electromechanical System Research Center of Engineering and Technology of Anhui Province School of Electrical Science and Applied Physics Hefei University of Technology(HFUT)Hefei 230009China Nano Science and Technology Institute University of Science and Technology of China(USTC)Suzhou 215123China

Gallium antimonide(GaSb)-based nanostructures have been reported via various vapor-phase synthetic routes while there is not a report on the growth of GaSb nanostructures via a complete one-step solution-phase synthetic *** we report the design and synthesis of tadpole-like Ga/GaSb nanostructures by a one-step solution-phase synthetic route typically from the precursors of commercial triphenyl antimony(Sb(Ph)_(3))and trimethylaminogallium(Ga(NMe_(2))_(3))at 260°C in *** GaSb nanocrystals are grown based on a solution–liquid–solid(SLS)mechanism with zinc blende phase,and their size and shape can be controlled in the procedures via manipulating the reaction ***,the tadpole-like Ga/GaSb nanostructures can be applied for the fabrication of a GaSb/Si nanostructured heterojunction-like photodetector over silicon wafer,which demonstrates excellent photoresponse and detection performances from wavelength of 405 to 1,064 nm with high photoresponding ***,the photodetector exhibits a high responsivity of 18.9 A·W^(−1),a superior detectivity of 1.1×10^(13)Jones,and an ultrafast response speed of 44 *** present work provides a new strategy to group III–V antimonide-based semiconducting nanostructures that are capable for the fabrication of photodetector with broadband,high-detectivity,and high-speed photodetecting performances.

关键词： Ga/GaSb nanostructure metal-semiconductor heterojunction narrow bandgap semiconductor solution-liquid-solid(SLS)growth model GaSb/Si heterojunction photodetector hybrid nanostructured photodetector infrared photodetection

来源：评论

学校读者我要写书评

暂无评论

Optimized Moderator Design and Analysis of a Pin-Type Supercritical Carbon Dioxide Reactor Based on Reactor Monte Carlo Code

Optimized Moderator Design and Analysis of a Pin-Type Superc...

引用

作者： Zhao, Xingyu Liu, Minyun Cui, Rongyi Huang, Shanfang Wang, Kan Lu, Chuan Department of Engineering Physics Tsinghua University Beijing100084 China Department of Engineering Physics Tsinghua University Beijing100084 China China Nuclear Power Engineering Co. Ltd. Beijing100840 China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu610213 China

This study analyzed an yttrium hydride (YH2) moderated supercritical carbon dioxide cooled reactor loaded with pin-type, beryllium oxide diluted oxide fuel elements to reduce the critical enrichment. The impact of the YH2 on the coolant void reactivity was studied along with a moderator zoning scheme to flatten the radial power distribution. The YH2 was added as hexagonal moderating rods at the center of the fuel assemblies. The core was modeled using the continuous-energy Reactor Monte Carlo code (RMC) with the on-the-fly cross sections treatment. The results showed that the YH2 moderator increased the thermal fission and reduced the critical enrichment of the core with the same diluent volume fraction by more than 30%. The YH2 moderator significantly softened the neutron energy spectrum and reduced the neutron leakage upon core voiding, resulting in both a weaker positive spectral reactivity feedback and a weaker negative leakage reactivity feedback during core depressurization. For an UO2-loaded core, the YH2 gave a lower negative coolant void reactivity, while for a mixed oxide fuel (MOX)-loaded core with diluent volume fractions smaller than 35%, the spectral feedback was more important and the YH2 strongly reduced the positive coolant void reactivity to less than $1. Arranging the YH2 in the peripheral assemblies reduced the radial power peaking factor to 1.319. The study shows that the YH2 moderator can reduce the critical enrichment, make the core less sensitive to voiding, and can flatten the radial power distribution of a single-enrichment core through moderator zoning. [DOI: 10.1115/1.4056772] © 2023 American Society of Mechanical Engineers (ASME). All rights reserved.

关键词： Carbon dioxide

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：