检索结果-内蒙古大学图书馆

FSCIL-EACA: Few-Shot Class-Incremental Learning Network Based on Embedding Augmentation and Classifier Adaptation for Image Classification

引用

Chinese Journal of Electronics 2024年第1期33卷 139-152页

作者： Ruru ZHANG Haihong E Meina SONG School of Computer Science Beijing University of Posts and Telecommunications Education Department Information Network Engineering Research Center Beijing University of Posts and Telecommunications

The ability to learn incrementally is critical to the long-term operation of AI systems. Benefiting from the power of few-shot class-incremental learning(FSCIL), deep learning models can continuously recognize new classes with only a few samples. The difficulty is that limited instances of new classes will lead to overfitting and exacerbate the catastrophic forgetting of the old classes. Most previous works alleviate the above problems by imposing strong constraints on the model structure or parameters, but ignoring embedding network transferability and classifier adaptation(CA), failing to guarantee the efficient utilization of visual features and establishing relationships between old and new classes. In this paper, we propose a simple and novel approach from two perspectives: embedding bias and classifier bias. The method learns an embedding augmented(EA) network with cross-class transfer and class-specific discriminative abilities based on self-supervised learning and modulated attention to alleviate embedding bias. Based on the adaptive incremental classifier learning scheme to realize incremental learning capability,guiding the adaptive update of prototypes and feature embeddings to alleviate classifier bias. We conduct extensive experiments on two popular natural image datasets and two medical datasets. The experiments show that our method is significantly better than the baseline and achieves state-of-the-art results.

关键词： Few-shot class-incremental learning Embedding augmentation Classifier adaptation Image classification

来源：评论

学校读者我要写书评

暂无评论

Early Parkinson's Disease Detection and Classification using Machine Learning and Neutrosophic Sets

引用

Neutrosophic Sets and Systems 2025年 82卷 873-886页

作者： Oudah, Hasan H. Metwaly, Ahmed A. Eassa, Mohamed Abdelhafeez, Ahmed Nagm, Ahmad M. Salama, Ahmed S. College of Arts Department of Journalism Ahl Al Bayt University Karbala Iraq Department of Computer Science Faculty of Computers and Informatics Zagazig University Zagazig44519 Egypt Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer Engineering and Electronics Cairo Higher Institute for Engineering Computer Science and Management New Cairo Egypt

Optimizing therapy and rehabilitation for Parkinson's disease (PD) requires early identification and precise evaluation of the illness's course. However, there is disagreement about the best way to use gait analysis to categorize the severity of motor symptoms and identify early-stage Parkinson's disease. The precision of machine learning (ML) models in identifying early and intermediate stages of Parkinson's disease was assessed in this study. Six ML models are used in this study for the prediction of PD. Different metrics are used to evaluate ML models such as accuracy, precision, recall, f1-score, and AUC score. Then we propose a multi-criteria decision-making methodology (MCDM) to evaluate the ML models and select the best one. Two MCDM methods are used such as CRITIC method to compute the criteria weights and the TOPSIS method to rank the alternatives. These methods are used under the bipolar neutrosophic sets (BNSs) to deal with uncertainty information. The results show the support vector machine is the best ML model for the prediction of PD. © 2025, University of New Mexico. All rights reserved.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Build Yourself before Collaboration: Vertical Federated Learning with Limited Aligned Samples

引用

IEEE Transactions on Mobile Computing 2025年第07期24卷 6503-6516页

作者： Shen, Wei Ye, Mang Yu, Wei Yuen, Pong C. Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan China Hong Kong Baptist University Department of Computer Science Hong Kong Hong Kong

Vertical Federated Learning (VFL) has emerged as a crucial privacy-preserving learning paradigm that involves training models using distributed features from shared samples. However, the performance of VFL can be hindered when the number of shared or aligned samples is limited, a common issue in mobile environments where user data are diverse and unaligned across multiple devices. Existing approaches use feature generation and pseudo-label estimation for unaligned samples to address this issue, unavoidably introducing noise during the generation process. In this work, we propose Local Enhanced Effective Vertical Federated Learning (LEEF-VFL), which fully utilizes unaligned samples in the local learning before collaboration. Unlike previous methods that overlook private labels owned by each client, we leverage these private labels to learn from all local samples, constructing robust local models to serve as solid foundations for collaborative learning. Additionally, we reveal that the limited number of aligned samples introduces distribution bias from global data distribution. In this case, we propose to minimize the distribution discrepancies between the aligned samples and the global data distribution to enhance collaboration. Extensive experiments demonstrate the effectiveness of LEEF-VFL in addressing the challenges of limited aligned samples, making it suitable for VFL in mobile computing environments. Codes are available at https://***/shentt67/LEEF-VFL. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Image Splicing Forgery Detection Using Feature-Based of Sonine Functions and Deep Features

引用

computers, Materials & Continua 2024年第1期78卷 795-810页

作者： Ala’a R.Al-Shamasneh Rabha W.Ibrahim Department of Computer Science College of Computer&Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Computer Science and Mathematics Lebanese American UniversityBeirut11022801Lebanon Department of Mathematics Mathematics Research CenterNear East UniversityNicosia99138Turkey Information and Communication Technology Research Group Scientific Research CenterAlayen UniversityDhi Qar64001Iraq

The growing prevalence of fake images on the Internet and social media makes image integrity verification a crucial research *** of the most popular methods for manipulating digital images is image splicing,which involves copying a specific area from one image and pasting it into *** were made to mitigate the effects of image splicing,which continues to be a significant research *** study proposes a new splicing detectionmodel,combining Sonine functions-derived convex-based features and deep *** stages make up the proposed *** first step entails feature extraction,then classification using the“support vector machine”(SVM)to differentiate authentic and spliced *** proposed Sonine functions-based feature extraction model reveals the spliced texture details by extracting some clues about the probability of image *** proposed model achieved an accuracy of 98.93% when tested with the CASIA V2.0 dataset“Chinese Academy of sciences,Institute of Automation”which is a publicly available dataset for forgery *** experimental results show that,for image splicing forgery detection,the proposed Sonine functions-derived convex-based features and deep features outperform state-of-the-art techniques in terms of accuracy,precision,and ***,the obtained detection accuracy attests to the benefit of using the Sonine functions alongside deep feature *** the regions or locations where image tampering has taken place is limited by the *** research will need to look into advanced image analysis techniques that can offer a higher degree of accuracy in identifying and localizing tampering regions.

关键词： Image forgery image splicing deep learning Sonine functions

来源：评论

学校读者我要写书评

暂无评论

A learning automata based edge resource allocation approach for IoT-enabled smart cities

引用

Digital Communications and Networks 2024年第5期10卷 1258-1266页

作者： Sampa Sahoo Kshira Sagar Sahoo Bibhudatta Sahoo Amir H.Gandomi Department of Computer Science and Engineering C.V.Raman Global UniversityBhubaneswarIndia Department of Computer Science and Engineering SRM UniversityAmaravatiIndia Department of Computing Science Umea UniversityUmea90187Sweden Department of Computer Science and Engineering NIT RourkelaIndia Faculty of Engineering and Information Technology University of Technology SydneyAustralia University Research and Innovation Center(EKIK) Obuda University1034 BudapestHungary

The development of the Internet of Things(IoT)technology is leading to a new era of smart applications such as smart transportation,buildings,and smart ***,these applications act as the building blocks of IoT-enabled smart *** high volume and high velocity of data generated by various smart city applications are sent to flexible and efficient cloud computing resources for ***,there is a high computation latency due to the presence of a remote cloud *** computing,which brings the computation close to the data source is introduced to overcome this *** an IoT-enabled smart city environment,one of the main concerns is to consume the least amount of energy while executing tasks that satisfy the delay *** efficient resource allocation at the edge is helpful to address this *** this paper,an energy and delay minimization problem in a smart city environment is formulated as a bi-objective edge resource allocation ***,we presented a three-layer network architecture for IoT-enabled smart ***,we designed a learning automata-based edge resource allocation approach considering the three-layer network architecture to solve the said bi-objective minimization *** Automata(LA)is a reinforcement-based adaptive decision-maker that helps to find the best task and edge resource *** extensive set of simulations is performed to demonstrate the applicability and effectiveness of the LA-based approach in the IoT-enabled smart city environment.

关键词： Edge computing IoT Learning automata Resource allocation Smart city

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Aware Provably Secure Smart Card Authentication Protocol Based on Physically Unclonable Functions

引用

IEEE Transactions on Dependable and Secure Computing 2024年第4期21卷 2766-2778页

作者： Fan, Chun-I Karati, Arijit Wu, Shou-Li National Sun Yat-sen University Department of Computer Science and Engineering Information Security Research Center The Intelligent Electronic Commerce Research Center Kaohsiung804 Taiwan National Sun Yat-sen University Department of Computer Science and Engineering Kaohsiung804 Taiwan

For many industrial applications, the smart card is a necessary safety component in user authentication. Smart cards provided to the users are used in open and public places, making them susceptible to physical and cloning attacks. Thus, the opponent can break the authentication process without the smart card if the information is exposed. In addition, many existing authentication systems employ challenge-response pairs (CRPs) to identify users by creating large numbers of data on the server and spending much time looking for and comparing responses. To address these concerns, we propose a lightweight privacy-preserving authentication protocol in which the physically unclonable function is considered a necessary tool. The suggested technique avoids creating a significant number of CRPs on the server to identify users uniquely. Under formal security models, the proposed protocol is resistant to user impersonation attacks and session key disclosure attacks and achieves robust mutual authentication. Nonetheless, it is immune to other essential security vulnerabilities. Empirical performance analysis demonstrates its viability in comparison to prior works. © 2023 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Enhanced MADM Strategy with Heptapartitioned Neutrosophic Distance Metrics

引用

Neutrosophic Sets and Systems 2025年 78卷 74-96页

作者： Eassa, Mohamed Myvizhi, M. Elkholy, Mohamed Abdelhafeez, Ahmed Elbehiery, Hussam Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan Department of Mathematics KPR Institute of Engineering and Technology Tamilnadu Coimbatore India Faculty of Computer Science& Engineering Alamein International University Egypt

In this work, a novel methodological approach to multi-attribute decision-making problems is developed and the notion of Heptapartitioned Neutrosophic Set Distance Measures (HNSDM) is introduced. By averaging the Penta-Partitioned Neutrosophic Distance Measures under particular conditional criteria, the suggested technique ranks the options. Additionally, we explore the fundamental characteristics of HNSDM and provide several illustrative theorems. The Heptapartitioned Neutrosophic Set Distance Measures are formulated based on the Hepta Neutrosophic Set. Lastly, a practical numerical example is provided to illustrate the efficacy of the suggested methodology. © 2025, University of New Mexico. All rights reserved.

关键词： Heptapartitioned Neutrosophic set Heptapartitioned Neutrosophic set and MADM strategy Heptapartitioned set Neutrosophic sine distance measure

来源：评论

学校读者我要写书评

暂无评论

Exploring Parameter-Efficient Fine-Tuning to Enable Foundation Models in Federated Learning

Exploring Parameter-Efficient Fine-Tuning to Enable Foundati...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Sun, Guangyu Khalid, Umar Mendieta, Matias Wang, Pu Chen, Chen University of Central Florida Center for Research in Computer Vision OrlandoFL United States University of North Carolina at Charlotte Department of Computer Science CharlotteNC United States

ISBN: (纸本)9798350362480

Federated learning (FL) has emerged as a promising paradigm for enabling the collaborative training of models without centralized access to the raw data on local devices. In the typical FL paradigm (e.g., FedAvg), model weights are sent to and from the server each round to participating clients. Recently, the use of small pre-trained models has been shown to be effective in federated learning optimization and improving convergence. However, recent state-of-the-art pre-trained models are getting more capable but also have more parameters, known as the "Foundation Models."In conventional FL, sharing the enormous model weights can quickly put a massive communication burden on the system, especially if more capable models are employed. Can we find a solution to enable those strong and readily available pre-trained models in FL to achieve excellent performance while simultaneously reducing the communication burden? To this end, we investigate the use of parameter-efficient fine-tuning in federated learning and thus introduce a new framework: FedPEFT. Specifically, we systemically evaluate the performance of FedPEFT across a variety of client stability, data distribution, and differential privacy settings. By only locally tuning and globally sharing a small portion of the model weights, significant reductions in the total communication overhead can be achieved while maintaining competitive or even better performance in a wide range of federated learning scenarios, providing insight into a new paradigm for practical and effective federated systems. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Masked Generative Light Field Prompting for Pixel-Level Structure Segmentations

引用

research 2024年第4期2024卷 533-544页

作者： Mianzhao Wang Fan Shi Xu Cheng Shengyong Chen The Engineering Research Center of Learning-Based Intelligent System(Ministry of Education) Tianjin University of TechnologyTianjin 300384China Key Laboratory of Computer Vision and System(Ministry of Education) Tianjin University of TechnologyTianjin 300384China School of Computer Science and Engineering Tianjin University of TechnologyTianjin 300384China

Pixel-level structure segmentations have attracted considerable attention,playing a crucial role in autonomous driving within the metaverse and enhancing comprehension in light field-based machine ***,current light field modeling methods fail to integrate appearance and geometric structural information into a coherent semantic space,thereby limiting the capability of light field transmission for visual *** this paper,we propose a general light field modeling method for pixel-level structure segmentation,comprising a generative light field prompting encoder(LF-GPE)and a prompt-based masked light field pretraining(LF-PMP)*** LF-GPE,serving as a light field backbone,can extract both appearance and geometric structural cues *** aligns these features into a unified visual space,facilitating semantic ***,our LF-PMP,during the pretraining phase,integrates a mixed light field and a multi-view light field *** prioritizes considering the geometric structural properties of the light field,enabling the light field backbone to accumulate a wealth of prior *** evaluate our pretrained LF-GPE on two downstream tasks:light field salient object detection and semantic *** results demonstrate that LF-GPE can effectively learn high-quality light field features and achieve highly competitive performance in pixel-level segmentation tasks.

关键词： prompt backbone integrate

来源：评论

学校读者我要写书评

暂无评论

5G Resource Allocation Using Feature Selection and Greylag Goose Optimization Algorithm

引用

computers, Materials & Continua 2024年第7期80卷 1179-1201页

作者： Amel Ali Alhussan S.K.Towfek Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Computer Science and Intelligent Systems Research Center BlacksburgVA 24060USA

In the contemporary world of highly efficient technological development,fifth-generation technology(5G)is seen as a vital step forward with theoretical maximum download speeds of up to twenty gigabits per second(Gbps).As far as the current implementations are concerned,they are at the level of slightly below 1 Gbps,but this allowed a great leap forward from fourth generation technology(4G),as well as enabling significantly reduced latency,making 5G an absolute necessity for applications such as gaming,virtual conferencing,and other interactive electronic *** of this change are not limited to connectivity alone;it urges operators to refine their business strategies and offers users better and improved digital *** essential factor is optimization and the application of artificial intelligence throughout the general arrangement of intricate and detailed 5G *** Binary Greylag Goose Optimization(bGGO)to achieve a significant reduction in the feature set while maintaining or improving model performance,leading to more efficient and effective 5G network management,and Greylag Goose Optimization(GGO)increases the efficiency of the machine ***,the model performs and yields more accurate *** work proposes a new method to schedule the resources in the next generation,5G,based on a feature selection using GGO and a regression model that is an ensemble of K-Nearest Neighbors(KNN),Gradient Boosting,and Extra Trees *** ensemble model shows better prediction performance with the coefficient of determination R squared value equal *** proposed framework is supported by several Statistical analyses,such as theWilcoxon signed-rank *** of the benefits of this study are the introduction of new efficient optimization algorithms,the selection of features and more reliable ensemble models which improve the efficiency of 5G technology.

关键词： Optimization ensemble learning 5G technology artificial intelligence greylag goose optimization ANOVA test

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：