检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Jiahao Zhou, Yipeng Wu, Di Hu, Miao Guizani, Mohsen Sheng, Quan Z. School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Computing Faculty of Science and Engineering Macquarie University Sydney Australia Abu Dhabi United Arab Emirates

Federated learning (FL) is an emerging machine learning paradigm for preserving data privacy. However, diverse client hardware often has varying computation resources. Such system heterogeneity limits the participation of resource-constrained clients in FL, and hence degrades the global model accuracy. To enable heterogeneous clients to participate in and contribute to FL training, previous works tackle this problem by assigning customized sub-models to individual clients with model pruning, distillation, or low-rank based techniques. Unfortunately, the global model trained by these methods still encounters performance degradation due to heterogeneous sub-model aggregation. Besides, most methods are heuristic-based and lack convergence analysis. In this work, we propose the FedLMT framework to bridge the performance gap, by assigning clients with a homogeneous pre-factorized low-rank model to substantially reduce resource consumption without conducting heterogeneous aggregation. We theoretically prove that the convergence of the low-rank model can guarantee the convergence of the original full model. To further meet clients' personalized resource needs, we extend FedLMT to pFedLMT, by separating model parameters into common and custom ones. Finally, extensive experiments are conducted to verify our theoretical analysis and show that FedLMT and pFedLMT outperform other baselines with much less communication and computation costs. Copyright 2024 by the author(s)

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

FHRDiff: Leveraging Diffusion Models for Conditional Fetal Heart Rate Signal Generation

FHRDiff: Leveraging Diffusion Models for Conditional Fetal H...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Li, Xiaoqing Lu, Yu Ngiam, Kee Yuan Yu, Zichang Furqan, Mohammad Shaheryar Shenzhen Technology University College of Big Data and Internet Shenzhen China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China National University of Singapore Yong Loo Lin School of Medicine Department of Surgery Singapore

ISBN: (纸本)9798350386226

Accurate analysis of Fetal Heart Rate (FHR) signal is often impeded by challenges such as data scarcity and label imbalance, which affect the reliability and robustness of deep learning models. To address these challenges, this study introduces FHRDiff, a novel diffusion model conditioned on Phase-Rectified Signal Averaging (PRSA) spectrograms for the creation of synthetic FHR signals. Our model integrates time encoding, condition generation from PRSA spectrograms, and residual blocks with dilated convolutions to effectively manage temporal dynamics and long-range dependencies. Extensive qualitative and quantitative experiments on FHR signal synthesis demonstrate the feasibility and effectiveness of FHRDiff. Compared to Generative Adversarial Networks (GANs) and image-based diffusion model, our method achieves the highest signal fidelity and distribution similarity, with key measures including 0.067 maximum mean deviation (MMD), 0.492 percent root mean square difference (PRD), 1.763 relative entropy (RE), and 0.160 Frechet distance (FD). Expert validation confirms the model's capacity to accurately generate data for normal and abnormal FHR signals based on the paired condition. In addition, an ablation study was conducted to highlight that the spectrogram paired condition can guide the diffusion model to produce synthetics FHR signals with greater diversity compared to unconditional models. The results emphasize diffusion models' potential for broad application in biomedical time series analysis, such as generation, imputation and noise removal. © 2024 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Research on the Mean-VaR-entropy Model in Uncertain Portfolio Optimization 12

Research on the Mean-VaR-entropy Model in Uncertain Portfoli...

引用

12th International Symposium on Project Management, ISPM 2024

作者： Meng, Jia Ning, Yufu Wang, Shuai Liu, Fengming Business School Shandong Normal University Jinan250399 China School of Information Engineering Shandong Youth University of Political Science Jinan250103 China Smart Healthcare Big Data Engineering and Ubiquitous Computing Characteristic Laboratory Universities of Shandong Jinan250103 China

ISBN: (纸本)9798331302344

This paper presents a mean-VaR-entropy model based on uncertainty theory, which combines return, VaR risk measurement, and portfolio diversity measured by entropy. It addresses the portfolio optimization problem by striking a balance between maximizing returns and minimizing risks. Numerical examples using stock, bond, and commodity futures market data are provided. Compared to common investment models, our mean-VaR-entropy model outperforms in portfolio performance, effectively balancing investment returns and risks. It offers a comprehensive and reliable basis for investment decision-making. © 2024 12th International Symposium on Project Management, ISPM 2024. All rights reserved.

关键词： Project management

来源：评论

学校读者我要写书评

暂无评论

Feature selection using modified chaotic satin bowerbird algorithm with deep transfer learning for Multispectral Image Classification

引用

International Journal of Information Technology (Singapore) 2024年 1-13页

作者： Rajakani, M. Kavitha, R.J. Rajesh, S. Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology SRM Nagar Kattankulathur Chennai India Department of Electronics and Communication Engineering University College of Engineering Panruti Panruti 607106 India Department of Information Technology Mepco Schlenk Engineering College Sivakasi India

Multispectral image classification has received significant attention among research communities and academicians. Recently, several artificial intelligence (AI) models can be used for the extraction of prominent features. Besides, deep learning (DL) methods become more familiar and gained interest in the remote sensing community for the classification of multispectral and hyperspectral images. With this motivation, this paper presents an optimized feature learning with deep transfer learning enabled multispectral image classification (OFLDTL-MSIC) technique. The proposed OFLDTL-MSIC technique aims to categorize the different class labels of the multispectral images. Besides, the OFLDTL-MSIC technique applies multi-level discrete wavelet transform (DWT) based image decomposition technique. Moreover, the EfficientNet technique is applied as a feature extractor to generate a collection of features. Furthermore, selecting optimal features extracted by a EfficientNet involves identifying and retaining the most relevant and informative features The improved chaotic satin bowerbird optimization (CSBO) algorithm which uses dynamic population size is proposed for feature selection and kernel extreme learning machine (KELM) model is applied for the classification process. In order to ensure the enhanced performance of the OFLTDL-MSIC technique, a wide range of simulations take place using the Madurai LISS IV multispectral images and the results are examined under several aspects. The extensive comparative study highlighted the better performance of the OFLTDL-MSIC technique over the recent methods. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.

关键词： Deep learning Image classification Multispectral images Parameter tuning Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Artificial Intelligence-Driven Advanced Methods for Acute Lymphoblastic Leukemia Identification and Classification: A Systematic Review

引用

Computer Modeling in engineering & Sciences 2025年第2期142卷 1199-1231页

作者： Syed Ijaz Ur Rahman Naveed Abbas Sikandar Ali Muhammad Salman Ahmed Alkhayat Jawad Khan Dildar Hussain Yeong Hyeon Gu Department of Computer Science Islamia CollegePeshawar25120Pakistan Department of Information Technology The University of HaripurHaripur22620Pakistan College of Technical Engineering The Islamic UniversityNajaf100986Iraq School of Computing Gachon UniversitySeongnam13120Republic of Korea Department of AI and Data Science Sejong UniversitySeoul05006Republic of Korea

Automatic detection of Leukemia or blood cancer is one of the most challenging tasks that need to be addressed in the healthcare *** of white blood cells(WBCs)in the blood or bone marrow microscopic slide images play a crucial part in early identification to facilitate medical *** Acute Lymphocytic Leukemia(ALL),the most preferred part of the blood or marrow is to be analyzed by the experts before it spreads in the whole body and the condition becomes *** researchers have done a lot of work in this field,to demonstrate a comprehensive analysis few literature reviews have been published focusing on various artificial intelligence-based techniques like machine and deep learning detection of *** systematic review has been done in this article under the PRISMA guidelines which presents the most recent advancements in this *** image segmentation techniques were broadly studied and categorized from various online databases like Google Scholar,Science Direct,and PubMed as image processing-based,traditional machine and deep learning-based,and advanced deep learning-based models were *** Neural Networks(CNN)based on traditional models and then the recent advancements in CNN used for the classification of ALL into its subtypes.A critical analysis of the existing methods is provided to offer clarity on the current state of the ***,the paper concludes with insights and suggestions for future research,aiming to guide new researchers in the development of advanced automated systems for detecting life-threatening diseases.

关键词： Acute lymphoblastic bone marrow segmentation classification machine learning deep learning convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Asymmetric scattering behaviors of spin wave dependent on magnetic vortex chirality

引用

Chinese Physics B 2023年第10期32卷 635-640页

作者：张雪枫沈帝虎马晓萍宋成于海明朴红光 Hubei Engineering Research Center of Weak Magnetic-Field Detection China Three Gorges UniversityYichang 443002China Department of Physics College of ScienceYanbian UniversityYanji 133002China Key Laboratory of Advanced Materials(MOE) School of Materials Science and EngineeringTsinghua UniversityBeijing 100084China Fert Beijing Institute School of Integrated Circuit Science and EngineeringBeijing Advanced Innovation Center for Big Data and Brain ComputingBeihang UniversityBeijing 100191China

We investigate asymmetric spin wave scattering behaviors caused by vortex chirality in a cross-shaped ferromagnetic system by using the micromagnetic *** the system,four scattering behaviors are found:(i)asymmetric skew scattering,depending on the polarity of vortex core,(ii)back scattering(reflection),depending on the vortex core stiffness,(iii)side deflection scattering,depending on structural symmetry of the vortex circulation,and(iv)geometrical scattering,depending on waveguide *** first and second scattering behaviors are attributed to nonlinear topological magnon spin Hall effect related to magnon spin-transfer torque effect,which has value for magnonic exploration and application.

关键词： magnonics magnetic vortex spin wave magnetic chirality

来源：评论

学校读者我要写书评

暂无评论

A Multistage Framework for Detection of Very Small Objects 23

A Multistage Framework for Detection of Very Small Objects

引用

6th International Conference on Machine Vision and Applications, ICMVA 2023

作者： Don, Duleep Rathgamage Aygun, Ramazan Karakaya, Mahmut School of Data Science and Analytics College of Computing and Software Engineering Kennesaw State University MariettaGA30060 United States Department of Computer Science College of Computing and Software Engineering Kennesaw State University MariettaGA30060 United States

ISBN: (纸本)9781450399531

Small object detection is one of the most challenging problems in computer vision. Algorithms based on state-of-the-art object detection methods such as R-CNN, SSD, FPN, and YOLO fail to detect objects of very small sizes. In this study, we propose a novel method to detect very small objects, smaller than 8×8 pixels, that appear in a complex background. The proposed method is a multistage framework consisting of an unsupervised algorithm and three separately trained supervised algorithms. The unsupervised algorithm extracts ROIs from a high-resolution image. Then the ROIs are upsampled using SRGAN, and the enhanced ROIs are detected by our two-stage cascade classifier based on two ResNet50 models. The maximum size of the images used for training the proposed framework is 32×32 pixels. The experiments are conducted using rescaled German Traffic Sign Recognition Benchmark dataset (GTSRB) and downsampled German Traffic Sign Detection Benchmark dataset (GTSDB). Unlike MS COCO and DOTA datasets, the resulting GTSDB turns out to be very challenging for any small object detection algorithm due to not only the size of objects of interest but the complex textures of the background as well. Our experimental results show that the proposed method detects small traffic signs with an average precision of 0.332 at the intersection over union of 0.3. © 2023 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Spatio-Spectral Compression of Hyperspectral Images 14

Generative Adversarial Networks for Spatio-Spectral Compress...

引用

14th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2024

作者： Fuchs, Martin Hermann Paul Byju, Akshara Preethy Walda, Alisa Rasti, Behnood Demir, Begum Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amritapuri India Technische Universität Berlin Faculty of Electrical Engineering and Computer Science Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Germany

ISBN: (纸本)9798331513139

Deep learning-based hyperspectral image (HSI) compression has recently attracted great attention in remote sensing due to the growth of hyperspectral data archives. Most of the existing models achieve either spectral or spatial compression and do not jointly consider the spatio-spectral redundancies present in HSIs. To address this problem, in this paper, we propose High Fidelity Compression (HiFiC)-based models for spatio-spectral compression of HSIs. In detail, we introduce two new models: i) HiFiC using Squeeze and Excitation (SE) blocks (denoted as HiFiCsE);and ii) HiFiC with 3D convolutions (denoted as HiFiC3D) in the framework of compression of HSIs. We analyze the effectiveness of HiFiCsE and HiFiC3D in compressing the spatio-spectral redundancies with channel attention and inter-dependency analysis. Experimental results show the efficacy of the proposed models in performing spatio-spectral compression, while reconstructing images at reduced bitrates with higher reconstruction quality. The code of the proposed models is publicly available at https://***/rsim/HSI-SSC. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

3D Based CNN for Improved Segmentation from the Hyperspectral Images 1

3D Based CNN for Improved Segmentation from the Hyperspectra...

引用

1st International Conference on Computer Science and Emerging Technologies, CSET 2023

作者： Narmadha, T. Arockia Raj, A. Saravanan, P. Kumar, A. Suresh Sekaran, Ramesh Gowri Shankar, J. School of Computer Science and Engineering Jain Deemed to Be University Bengaluru India Madanapalle Institute of Technology and Science Department of Computer Science and Engineering - Data Science Madanapalle India School of Computing Science and Engineering Galgotias University Delhi NCR India

ISBN: (纸本)9798350341737

In this paper, we develop a 3D based CNN for Improved Segmentation of Paddy Fields from the HSI. Within the scope of this research, we will investigate a unique deep learning model, specifically 3D-CNN. In order to evaluate the validity of the model, it is applied to three separate datasets, each of which is then subjected to one of four distinct dimensionality reduction strategies. The purpose of this is to determine which of these four models is the most effective at reducing the number of dimensions. According to the findings, the 3D-CNN model is superior to both the AlexNet and CNN models in terms of the accuracy of its segmentations. In addition to this, the findings demonstrate that the 3D-CNN models perform better than the other approaches in terms of segmentation accuracy with a smaller number of datasets. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Convergence-Privacy-Fairness Trade-Off in Personalized Federated Learning

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2025年 3卷 246-262页

作者： Zhao, Xiyu Cui, Qimei Li, Weicai Ni, Wei Hossain, Ekram Sheng, Quan Z. Tao, Xiaofeng Zhang, Ping School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China School of Computing Macquarie University SydneyNSW2109 Australia Department of Broadband Communication Peng Cheng Laboratory Shenzhen518055 China School of Electrical and Data Engineering University of Technology Sydney SydneyNSW2007 Australia Department of Electrical and Computer Engineering University of Manitoba WinnipegMBR3T 2N2 Canada

Personalized federated learning (PFL), e.g., the renowned Ditto, strikes a balance between personalization and generalization by conducting federated learning (FL) to guide personalized learning (PL). While FL is unaffected by personalized model training, in Ditto, PL depends on the outcome of the FL. However, the clients’ concern about their privacy and consequent perturbation of their local models can affect the convergence and (performance) fairness of PL. This paper presents PFL, called DP-Ditto, which is a non-trivial extension of Ditto under the protection of differential privacy (DP), and analyzes the trade-off among its privacy guarantee, model convergence, and performance distribution fairness. We also analyze the convergence upper bound of the personalized models under DP-Ditto and derive the optimal number of global aggregations given a privacy budget. Further, we analyze the performance fairness of the personalized models, and reveal the feasibility of optimizing DP-Ditto jointly for convergence and fairness. Experiments validate our analysis and demonstrate that DP-Ditto can surpass the DP-perturbed versions of the state-of-the-art PFL models, such as FedAMP, pFedMe, APPLE, and FedALA, by over 32.71% in fairness and 9.66% in accuracy. © 2023 CCBY.

关键词： Federated learning

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：