检索结果-内蒙古大学图书馆

3rd International Conference on Laser, Optics, and Optoelectronic technology, LOPET 2023

作者： Zeng, Jianzhi Chen, Siyu Zhao, Jie Wei, Zhenjie Wang, Mouxin Liu, Zhiyue Hu, Haifeng School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China

ISBN: (纸本)9781510667624

In order to analyze the mechanism of optical chirality signal enhancement of chiral spherical particles, the scattering properties of chiral particles were studied based on the T-matrix method, and the optical chirality signal is calculated under different types of polarization vortex beams with orbital angular momentum (OAM). Firstly, for particles with fixed sizes, the enhancement effects of tightly focused light field of radial and azimuthally polarized polarization beams were explored. In addition, for particles with varying sizes, the enhancement of the optical chirality signal of particles was achieved by controlling the order of OAM carried by the beam. © 2023 SPIE.

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

FSD-Net: a fuzzy semi-supervised distillation network for noise-resistant classification of medical images

引用

Multimedia Tools and Applications 2024年第36期83卷 83661-83676页

作者： Du, Xiangtong Shen, Ao Wang, Ximing Li, Zongsheng Deng, Hai School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China School of Information Science and Engineering Hohai University Changzhou213022 China Department of Radiology First Affiliated Hospital of Soochou University Suzhou215006 China Department of Electrical and Computer Engineering Florida International University MiamiFL33174 United States

Deep Learning (DL)-based models have been successfully applied for medical image classifications. However, the performance of traditional medical image classifiers is limited by insufficient training samples and inaccurate annotations due to labeling noise. Numerous methods were proposed to address the issues, to no avail. To fill this gap, we propose a Fuzzy Semi-supervised Distillation Network (FSD-Net) to improve the noise-resistant classification performance. Firstly, with the aid of semi-supervised training based on the pseudo-labels, the problem of insufficient training samples can be alleviated by using unlabeled data to a certain extent. Then, a Confidence Filtering model (CF-model) is designed to improve the quality of the pseudo-labels and filter the noisy labeling data by combining the soft labels generated from the classification model and the improved Soft Fuzzy C-Means (SFCM) model. Compared with the setting thresholds, the data with low confidence are reclassified as unlabeled to participate in training, while the labeled and unlabeled data (generating pseudo-labels) with high confidences are added into the mixed dataset. Finally, the mixed data are fed to train a multi-model online distillation module consisting of the SFCM and two other student models. The weighted average value of the three student models is used as teacher knowledge to train the students and obtain the final classification results. Experimental results on multiple medical datasets show that the proposed FSD-Net can solve the problems of insufficient labeled samples and labeling noise simultaneously to some extent. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Belief Propagation List Decoding for Polar Codes:Performance Analysis and Software Implementation on GPU

引用

China Communications 2023年第9期20卷 115-126页

作者： Zhanxian Liu Wei Li Lei Sun Wei Li Jianquan Wang Haijun Zhang School of Computer&Communication Engineering University of Science and Technology BeijingBeijing 100083China Satellite Frequency and Orbit Resource Agency State Radio Monitoring CenterBeijing 100041China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services Institute of Artificial IntelligenceUniversity of Science and Technology BeijingBeijing 100083China

Belief propagation(BP)decoding outputs soft information and can be naturally used in iterative *** list(BPL)decoding provides comparable error-correction performance to the successive cancellation list(SCL)*** this paper,we firstly introduce an enhanced code construction scheme for BPL decoding to improve its errorcorrection ***,a GPU-based BPL decoder with adoption of the new code construction is ***,the proposed BPL decoder is tested on NVIDIA RTX3070 and *** results show that the presented BPL decoder with early termination criterion achieves above 1 Gbps throughput on RTX3070 for the code(1024,512)with 32 lists under good channel conditions.

关键词： polar code belief propagation SIMT list decoding GPU

来源：评论

学校读者我要写书评

暂无评论

Apple Detection and Yield Estimation Based on YOLOv5 7

Apple Detection and Yield Estimation Based on YOLOv5

引用

7th International Conference on Advanced Algorithms and Control engineering, ICAACE 2024

作者： Li, Zhaoyang Bai, Xue He, Chao Jiang, Pengfei School Of Earth And Space Science University Of Science And Technology Of China Hefei230026 China School Of Electrical And Information Engineering Zhengzhou University Zhengzhou450001 China College Of Computer Science And Engineering Shandong University Of Science And Technology Qingdao266590 China College Of Geodesy And Geomatics Shandong University Of Science And Technology Qingdao266590 China

ISBN: (纸本)9798350361445

With the continuous advancement of modernization and intelligence in agricultural production, precise orchard management is crucial for enhancing the efficiency of apple production. This study focuses on apple orchards, introducing the YOLOv5 deep learning model to address the issues of apple detection and quantity estimation in traditional orchard management. Through effective feature extraction and learning from orchard images, the model accurately detects and estimates the quantity of fruits, providing reliable data support for orchard management. Firstly, this research delves into the background of the apple detection problem, highlighting the limitations of traditional methods in dealing with complex lighting, shadows, and other environmental factors. Subsequently, leveraging the YOLOv5 model, a deep learning-based orchard image processing method is proposed. This method fully exploits the efficiency and accuracy of the YOLOv5 model in object detection, training the model to recognize apples and providing a more intelligent tool for orchard management. In the model-solving phase, the structure and training process of the YOLOv5 model are detailed. Through training on a large number of orchard images, the model successfully learns the feature representation of apples, demonstrating strong generalization capabilities. The results indicate the model's outstanding performance in apple detection and quantity estimation tasks. Finally, the study summarizes the advantages and innovations of the apple detection and quantity estimation method based on YOLOv5, and provides prospects for future research directions. This research offers an efficient and accurate tool for orchard management, contributing new ideas and methods to the development of agricultural intelligence. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Distributed Discrete-Time Exponential Sliding Mode Consensus Protocol for a Multi-Agent System 2

Distributed Discrete-Time Exponential Sliding Mode Consensus...

引用

2nd IEEE International Conference on Data, Decision and Systems, ICDDS 2023

作者： Joshi, Nikita Mehta, Axaykumar Institute of Infrastructure Technology Research and Management Electrical and Computer Science Engineering Ahmedabad380026 India

ISBN: (纸本)9798350314168

This paper presents a distributed discrete-Time exponential sliding mode consensus (DDESMC) protocol for a class of multi-Agent systems. A leader-following approach of a homogenous multi-Agent system (MAS) is exploited to derive the protocol. The discrete-Time exponential sliding mode control is proposed using the graph theory. The upper bound on the number of reaching steps for achieving the consensus among all the agents is derived. The protocol ensures the minimum width of the Quasi-Sliding Mode Band (QSMB) as compared to other classical approaches. Also, the protocol ensures the consensus effort in the order O (T3). The Lyapunov theory is then used to determine the global stability condition for the consensus, and finally, a numerical example is given to demonstrate the effectiveness of the protocol. Furthermore, the performance of the proposed protocol is compared to that of the standard DSMC protocol described in the literature for both the time and effort needed to reach consensus and the deviation from consensus after reaching consensus. It is inferred that the proposed DDESMC protocol outperforms the classical DSMC protocol. © 2023 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

3D layout of the Spidergon-Donut on-chip interconnection network

引用

International Journal of High Performance Systems Architecture 2023年第3期11卷 137-147页

作者： Sibai, Fadi N. Asaduzzaman, Abu Elmoursy, Ali Department of Electrical and Computer Engineering Gulf University for Science and Technology P.O. Box 7207 Hawally32093 Kuwait Department of Electrical and Computer Engineering Wichita State University WichitaKS67260 United States Department of Electrical and Computer Engineering University of Sharjah P.O. Box 27272 Sharjah United Arab Emirates

3D integration promises to resolve many of the heat and die size limitations of 2D integrated circuits. A critical step in the design of 3D many-cores and MPSOCs is the layout of their 3D network-on-chip (NoC). In this paper, we explore and present multiple 3D layouts of the Spidergon-Donut (SD) NoC and estimate their longest wire lengths and cost requirements. For a total of 64 cores, the 4×2×8 and 2×4×8 placements result in the best longest wire delays, with the former higher 3D integration costs, while the second requiring larger chip area and through-silicon-vias (TSV) array costs. Such study helps in guiding 3D integration direction and weighing 3D NoC layout and placement alternatives. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Network-on-chip

来源：评论

学校读者我要写书评

暂无评论

Multi-label and Multi-class Classification on a Custom Dataset using Convolution Neural Networks 7

Multi-label and Multi-class Classification on a Custom Datas...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Bonthu, Sridevi Kiran, Kompella Bhargava Deenakonda, Mamatha Rao, V.V.R. Maheswara Jagadeesh, S.V.V.D. Vishnu Institute of Technology Computer Science and Engineering Bhimavaram India Vishnu Institute of Technology Electrical and Electronics Enigneering Bhimavaram India Computer Science and Engineering Shri Vishnu Engineering College for Women Bhimavaram India

ISBN: (纸本)9798350397253

A multi-label image classification is a challenging task as it has to map an input image to a vector of outputs. This work presents a single and efficient model to perform multi-label and multi-class classification using Convolutional Neural Networks (CNN). A custom dataset is collected and annotated with eight labels to test the neural network. The classes for the labels in the dataset are a blend of balanced and unbalanced data. The proposed network is a two-stage network. The first stage is used for general training, whereas the second stage is used for specific training. The results show that the usage of a single model across multiple labels results in varying performance. The number of classes and the balance in the class distribution have a direct impact on the performance of the model. The code is available at https://***/sridevibonthu/FML. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Refining Pseudo Labels With a Teacher-Student Paradigm for Accurate Brain Lesion Segmentation

引用

IEEE Access 2025年 13卷 84474-84487页

作者： Chatterjee, Pubali Das Sharma, Kaushik Chakrabarti, Amlan Department of Computer Science and Engineering Bhubaneswar751030 India University of Calcutta Electrical Engineering Section Department of Applied Physics Kolkata700073 India University of Calcutta A. K. Choudhury School of Information Technology Kolkata700073 India

In medical image segmentation, obtaining large volume of high quality labeled data is a persistent challenge, especially for intricate tasks like brain lesion segmentation, where annotations are time-consuming, costly, and require expert knowledge. This work introduces a novel learning framework where the abundance of labeled data is scarce, and the model learns from both limited number of annotated data as well as from unlabeled data. The framework initially leverages superpixel segmentation to group pixels with similar properties into compact, perceptually coherent regions while preserving critical structural details, and produce coarse segmentation mask on unlabeled data. In the next phase, a teacher-student model is employed, where the teacher module generates pseudo-labels for unlabeled data, and the student model learns from both of these pseudo-labels and minimal amount of annotated data. In addition, a feature refinement module is introduced to further strengthen the teacher-student framework, where the student module also learns from the mutual agreement between superpixel prediction and the pseudo label generated by the teacher module. The overall framework helps in efficiently using the unlabeled data with the help of handful amount of labeled data. Experimental results across multiple datasets demonstrate the effectiveness of the proposed framework in achieving precise, computationally efficient brain lesion segmentation. The integration of superpixel-based grouping and the student-teacher architecture not only improves segmentation accuracy but also offers a scalable solution for scenarios with limited annotated data. This method provides a promising pathway for advancing medical imaging applications, enabling accurate and efficient segmentation while addressing the challenges of data scarcity and annotation constraints. © 2013 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Software and Hardware Cooperative Implementation of the Rafflesia Optimization Algorithm 5th

Software and Hardware Cooperative Implementation of the R...

引用

5th International Conference on Smart Vehicular technology, Transportation, Communication and Applications, VTCA 2022

作者： Fu, Zonglin Pan, Jeng-Shyang Guo, Yundong Snášel, Václav College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Faculty of Electrical Engineering and Computer Science VŠB-Technical University of Ostrava Ostrava70032 Czech Republic

ISBN: (纸本)9789819908479

With the development of edge technology in the fields of transportation, wireless sensor networks, and the internet of things, more and more intelligent optimization algorithms are implemented in hardware structures. The Rafflesia optimization algorithm (ROA) is a novel intelligent optimization algorithm proposed recently. To observe its performance on hardware, this paper implements the ROA algorithm in a cooperative way of software and hardware, referred to as the FROA algorithm. To convenient testing and accelerated computing, the initialization module, fitness module, and update module of the FROA algorithm are deployed on the advanced RISC machine (ARM) platform and the field programmable gate array (FPGA) platform, respectively. In the experimental part, we test the FROA algorithm on nine different benchmark functions. The results are compared with those implemented in software. The experimental results demonstrate the effectiveness and superiority of the FROA algorithm. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled SAGIN Communication for Disaster Prediction and Management

Blockchain-Enabled SAGIN Communication for Disaster Predicti...

引用

2023 IEEE International Conference on Dependable, Autonomic and Secure Computing, 2023 International Conference on Pervasive Intelligence and Computing, 2023 International Conference on Cloud and Big Data Computing, 2023 International Conference on Cyber science and technology Congress, DASC/PiCom/CBDCom/CyberSciTech 2023

作者： Okoumassoun, Tagnon Privael Ridhawi, Ismaeel Al Abbas, Ali Al-Oqily, Ibrahim School of Electrical Engineering and Computer Science University of Ottawa Canada Kuwait College of Science and Technology Kuwait The Hashemite University Jordan

ISBN: (纸本)9798350304602

The Sixth Generation (6G) network will rely on the integration and cooperation of a plethora of communication and networking systems. Space-air-ground integrated networks (SA-GIN) which integrate satellites, aerial networks, and terrestrial communication, can provide seamless and continuous delivery of services and applications with high levels of performance. While SAGIN provides promising solutions for data collection and communication, it poses security concerns given that it may allow untrusted devices to be part of the cooperative system. In this paper we introduce a blockchain-enabled SAGIN framework that authenticates both devices and the data collected by SAGIN participants. Federated Learning (FL) is supported by the framework to enable network distribution and accurate real-time data analysis. As a proof-of-concept, the solution considers a use-case for earthquake event prediction and monitoring. Satellite sensors are used to collect data and identify the presence of thermal anomalies used for earthquake forecasting. Furthermore, a post-earthquake monitoring technique is used which relies on Unmanned Aerial Vehicles (UAVs) to provide access to remote places in order to collect high quality images. The collected images are then processed locally on UAV swarms or through edge devices for real-time decision making. An experimental study is conducted on models and approaches needed to increase prediction accuracy for earthquake events. © 2023 IEEE.

关键词： Decision making

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：