检索结果-内蒙古大学图书馆

6th International conference on Electronics and Communication, Network and computer Technology, ECNCT 2024

作者： Zhai, Xuedong Han, Wenting Li, Xiaoxian Huang, Shenjin College of Mechanical and Electronic Engineering Northwest A&f University Shaanxi Yangling China Institute of Water-saving Agriculture in Arid Areas of China Northwest A&f University Shaanxi Yangling China Harbin Institute of Technology Faculty of Computing Harbin China

ISBN: (纸本)9798350366143

Precise crop remote sensing mapping is essential for effective agricultural management and planning. Although traditional deep learning methods, such as Convolutional Neural Network (CNN)-based semantic segmentation networks, have achieved considerable success in crop classification, they are constrained by the limited convolutional kernel size, which hinders their ability to capture the global contextual information of the image. Transformer networks have garnered attention due to their powerful global dependency modeling capabilities;however, their high computational complexity and the weakening of local features restrict their application in remote sensing image processing. To address these limitations, this study introduces a progressive local-global context-aware semantic segmentation network (PLGCA). The network integrates the strengths of CNNs and Transformers to improve the accuracy of crop remote sensing mapping. PLGCA employs an encoder-decoder structure, where the encoder effectively incorporates local and global contextual information through a combination of Channel-Spatial Attention (CSA) blocks and Vision Transformer (ViT) blocks. Experimental results on the GF-2 agricultural remote sensing dataset demonstrate that PLGCA surpasses existing state-of-the-art methods across multiple evaluation metrics, including mean Intersection over Union (mIoU), F1 Score, and Overall Accuracy (OA). The proposed approach offers a promising solution for accurate and efficient crop mapping in precision agriculture applications. © 2024 ieee.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of 2D Feature Descriptors for Object Classification

Performance Analysis of 2D Feature Descriptors for Object Cl...

引用

2024 ieee International conference on computer Vision and Machine Intelligence, CVMI 2024

作者： Sah, Dhrupad Sankar, Prasad Joshi, Piyush Indian Institute of Information Technology Sri City Department of Computer Science Chittoor India

ISBN: (纸本)9798350376876

Image descriptors play a pivotal role in image and video processing by furnishing precise descriptions of local image characteristics. These descriptors typically exhibit invariance to rotation, translation, and scaling, and in some cases, demonstrate partial invariance to illumination alterations and affine or 3D projection transformations. Unlike contemporary Machine and Deep Learning methodologies, they do not necessitate extensive datasets or substantial computational resources for application, as they operate without the need for training. Key interest points, known as keypoints, are located within images, each associated with its distinctive feature descriptor. These descriptors facilitate the comparison of features across different images, aiding in the identification of shared objects. In literature, image descriptors have primarily served in tasks such as feature matching and scene object detection. This paper aims to investigate the potential of leveraging feature descriptors for image classification tasks and to gauge their comparative performance. Specifically, we employ Support Vector Machine (SVM) and Convolutional Neural Network (CNN) classifiers to train on feature vectors extracted from images, thereby learning the local features of depicted objects. To the best of our knowledge, our study represents the pioneering effort to scrutinize the performance of top 2D descriptors for image classification. We conducted a series of experiments using widely recognized image descriptors and datasets to evaluate and compare their performances. Our objective was to ascertain the reliability of these feature descriptors for image classification tasks. © 2024 ieee.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

GraFPrint: A GNN-Based Approach for Audio Identification

GraFPrint: A GNN-Based Approach for Audio Identification

引用

2025 ieee International conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Bhattacharjee, Aditya Singh, Shubhr Benetos, Emmanouil School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom

ISBN: (纸本)9798350368741

This paper introduces GraFPrint, an audio identification framework that leverages the structural learning capabilities of Graph Neural networks (GNNs) to create robust audio fingerprints. Our method constructs a k-nearest neighbour (k-NN) graph from time-frequency representations and applies max-relative graph convolutions to encode local and global information. The network is trained using a self-supervised contrastive approach, which enhances resilience to ambient distortions by optimizing feature representation. GraFPrint demonstrates superior performance on large-scale datasets at various levels of granularity, proving to be both lightweight and scalable, making it suitable for real-world applications with extensive reference databases. © 2025 ieee.

关键词： audio fingerprinting audio identification graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A High Efficiency Task Allocation Method Based on Adaptive Hybrid Particle Swarm Optimization for Intelligent Unmanned Wireless Sensor networks 12

A High Efficiency Task Allocation Method Based on Adaptive H...

引用

12th ieee International conference on Information and Communication networks, ICICN 2024

作者： Zhang, Baitao Luo, Tao Zhu, Yuanjiao Chen, Zi Luo, Yunchen Zhou, Jie Xiao, Jing College of Information Science and Technology Shihezi University Shihezi China College of Computer Information and Security Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9798350355802

In recent years, with the continuous application of intelligent unmanned technology, network optimization of Intelligent Unmanned Wireless Sensor networks (IUWSNs) has emerged as a research hotspot. However, due to the limitations imposed by sensor size, the sensing capabilities of small wireless sensors in IUWSN s are restricted. To achieve higher network performance, it is crucial to devise suitable and efficient task allocation schemes. Therefore, a novel Adaptive Hybrid Particle Swarm Optimization algorithm (AHPSO) is proposed for efficient task allocation in IUWSN s. Firstly, AHPSO significantly enhances the efficiency of task distribution in IUWSN s, thereby markedly improving network benefits. Secondly, the new adaptive mechanism, by dynamically adjusting algorithm parameters, greatly increases the diversity of population solutions and accelerates the convergence speed of the algorithm. Additionally, a new simulated annealing strategy created in this study effectively prevents the algorithm from falling into local optima. Finally, extensive simulation experiments were conducted comparing AHPSO with Genetic Algorithms (GA) and Simulated Annealing (SA). The results demonstrate that AHPSO markedly outperforms other methods in enhancing task allocation efficiency and overall network performance of IUWSNs. © 2024 ieee.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

QaSAL: QoS-aware State-Augmented Learnable Algorithms for Coexistence of 5G NR-U/Wi-Fi 59

QaSAL: QoS-aware State-Augmented Learnable Algorithms for Co...

引用

59th Annual conference on Information Sciences and Systems, CISS 2025

作者： Fasihi, Mohammad Reza Mark, Brian L. George Mason University Dept. of Electrical and Computer Engineering and Wireless Cyber Center FairfaxVA United States

ISBN: (纸本)9798331513269

With the increasing demand for wireless connectivity, ensuring the efficient coexistence of multiple radio access technologies in shared unlicensed spectrum has become an important issue. This paper focuses on optimizing Medium Access Control (MAC) parameters to enhance the coexistence of 5G New Radio in Unlicensed Spectrum (NR-U) and Wi-Fi networks operating in unlicensed spectrum with multiple priority classes of traffic that may have varying quality-of-service (QoS) requirements. In this context, we tackle the coexistence parameter management problem by introducing a QoS-aware State-Augmented Learnable (QaSAL) framework, designed to improve network performance under various traffic conditions. Our approach augments the state representation with constraint information, enabling dynamic policy adjustments to enforce QoS requirements effectively. Simulation results validate the effectiveness of QaSAL in managing NR-U and Wi-Fi coexistence, demonstrating improved channel access fairness while satisfying a latency constraint for high-priority traffic. © 2025 ieee.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

IoT Modular Gateway Development for Multi-Standard Compatibility

IoT Modular Gateway Development for Multi-Standard Compatibi...

引用

2025 International conference on Electronics, Information, and Communication, ICEIC 2025

作者： Kaiyarach, Kattiya Taprik, Sopita Buathong, Bantita Chodkaveekityada, Peeramed School of Engineering King Mongkut 's Institute of Technology Ladkrabang Bangkok Thailand

ISBN: (纸本)9798331510756

Currently, IoT wireless communication technology plays a crucial role in connecting multiple devices. However, the diverse standards used limit their interoperability. To address the issue of incompatible communication protocols, this research presents a developed IoT system that seamlessly integrates various communication standards. The system comprises a central processing unit (Core Board) that functions as an IoT gateway. This core board connects local networks via LoRa and others, as well as public networks using 3G and Wi-Fi. The system utilizes the STM32H563ZI processor, which is based on the ARM Cortex M33 architecture. Additionally, it features expansion slots to accommodate future of others communication standards. The results show that the developed IoT system's effective support for a diverse range communication standards. © 2025 ieee.

关键词： Gateways (computer networks)

来源：评论

学校读者我要写书评

暂无评论

DGR: Delay-Guaranteed Routing Protocol 20

DGR: Delay-Guaranteed Routing Protocol

引用

20th ieee International conference on Mobile Ad Hoc and Smart Systems, MASS 2023

作者： Yang, Pu Cai, Lin Chang, Tianfang University of Victoria Department of Electrical & Computer Engineering Victoria Canada

ISBN: (纸本)9798350324334

This paper introduces Delay-Guaranteed Routing (DGR), a distributed routing protocol designed to provide network services with guaranteed delay. Traditional methods of ensuring delay guarantees rely on resource reservation or traffic engineering, which face challenges in efficiently utilizing resources in networks with mesh topologies and high dynamism. In contrast, DGR employs priority queue management and per-hop delay bounds to construct a shortest path forest, allowing for exploration of all forwarding directions while maintaining delay guarantees. A randomized back-pressure route selection strategy, utilizing local and neighborhood queue information, ensures load balancing in highly dynamic networks. Extensive simulations demonstrate the effectiveness of DGR in providing delay-guaranteed services, managing congestion and link failures, and coexisting harmoniously with existing routing protocols for non-time-sensitive services. © 2023 ieee.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Error Analysis on the TICER Approximation

引用

CIRCUITS SYSTEMS AND SIGNAL PROCESSING 2023年第7期42卷 4390-4400页

作者： Yao, Wenhui Zheng, Chunxiong Zhou, Zhenya Tsinghua Univ Dept Math Sci Shuangqing Rd Beijing 100084 Peoples R China Empyrean Technol Co Ltd Lize Rd Beijing 100102 Peoples R China

Time constant equilibration reduction (TICER) is a local model reduction method based on Gaussian elimination for RC networks which was introduced in Sheehan (1999 ieee/ACM international conference on computer-aided design. Digest of technical papers (Cat. No.99CH37051), pp 200-203, 1999). The main idea of TICER is selectively removing the non-port nodes of the circuits to produce a smaller RC circuit. Since proposed, TICER has been widely used in the electronic engineering, and lots of practices validate its reliability and robustness. It is a practical method to meet the needs of reduction and can produce a realizable RC circuit with good accuracy, and this is the reason why TICER has been used until now. Later, many scholars proposed RC-realizable reduction methods based on TICER. Quite surprisingly, as far as the authors know, there exists no rigorous analysis on this simple but wonderful method in the literature. In this short communication, we prove the optimal first-order asymptotic accuracy of TICER and present numerical evidences to validate our theoretical results.

关键词： TICER Realizable reduction RC networks Asymptotic analysis

来源：评论

学校读者我要写书评

暂无评论

Towards MOOCs for Lipreading: Using Synthetic Talking Heads to Train Humans in Lipreading at Scale 23

Towards MOOCs for Lipreading: Using Synthetic Talking Heads ...

引用

23rd ieee/CVF Winter conference on Applications of computer Vision (WACV)

作者： Agarwal, Aditya Sen, Bipasha Mukhopadhyay, Rudrabha Namboodiri, Vinay Jawahar, C. V. IIIT Hyderabad Hyderabad India Univ Bath Bath Avon England

ISBN: (纸本)9781665493468

Many people with some form of hearing loss consider lipreading as their primary mode of day-to-day communication. However, finding resources to learn or improve one's lipreading skills can be challenging. This is further exacerbated in the COVID19 pandemic due to restrictions on direct interactions with peers and speech therapists. Today, online MOOCs platforms like Coursera and Udemy have become the most effective form of training for many types of skill development. However, online lipreading resources are scarce as creating such resources is an extensive process needing months of manual effort to record hired actors. Because of the manual pipeline, such platforms are also limited in vocabulary, supported languages, accents, and speakers and have a high usage cost. In this work, we investigate the possibility of replacing real human talking videos with synthetically generated videos. Synthetic data can easily incorporate larger vocabularies, variations in accent, and even local languages and many speakers. We propose an end-to-end automated pipeline to develop such a platform using state-of-the-art talking head video generator networks, text-to-speech models, and computer vision techniques. We then perform an extensive human evaluation using carefully thought out lipreading exercises to validate the quality of our designed platform against the existing lipreading platforms. Our studies concretely point toward the potential of our approach in developing a large-scale lipreading MOOC platform that can impact millions of people with hearing loss.

关键词： Training Vocabulary computer vision Statistical analysis Veins Pipelines Auditory system

来源：评论

学校读者我要写书评

暂无评论

Cost-Aware Hierarchical Federated Learning for Smart Healthcare 16

Cost-Aware Hierarchical Federated Learning for Smart Healthc...

引用

16th International conference on COMmunication Systems and networks, COMSNETS 2024

作者： Singh, Himanshu Singh, Moirangthem Biken Kagale, Pratik Prakash Pratap, Ajay Department of Computer Science and Engineering Varanasi India

ISBN: (纸本)9798350383119

Federated Learning (FL) enables local model training on devices while collaboratively updating a global model on a server, ensuring user data privacy by keeping it on the device and sharing only model updates. Although it has been widely employed in healthcare to address privacy concerns, still deployment faces challenges due to variations in device data and system capacities. Moreover, the substantial distance between a global cloud server and users leads to significant energy consumption during the exchange of local model weights and parameter aggregation. Therefore, this paper proposes a method for minimizing energy and time consumed during transmission and computation of health data generated by Wireless Body Area networks (WBANs) along with loss function using hierarchical FL. Through extensive evaluation, the proposed approach showcases an 11.13% reduction in total costs, encompassing latency, energy, and loss function, compared to the traditional Federated Averaging (FedAvg) algorithm. Moreover, the proposed model attains an accuracy of 95.85%, surpassing the 94.77% and 94.53% achieved by FedAvg and Federated Clustering (FedCluster), respectively. © 2024 ieee.

关键词： Energy Federated learning Healthcare Loss function WBAN

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：