检索结果-内蒙古大学图书馆

ES-Net: Unet-based model for the semantic segmentation of Iris

Multimedia Tools and Applications 2025年第13期84卷 12395-12416页

作者： Pourafkham, Behnam Khotanlou, Hassan RIV Lab. Department of Computer Engineering Faculty of Engineering Bu-Ali Sina University Hamedan Iran

The segmentation of the iris is crucial and holds great importance within the medical image recognition area. Researchers have introduced many architectures and applied them to iris image segmentation, However, they are involved with some critical challenges like low accuracy, slow runtime, and high computational complexity. In this paper, we present ES-Net which is a fast and precise deep-learning architecture for the semantic segmentation of Iris. The U-Net model serves as the foundation for the proposed method. Furthermore, our primary objectives are to develop a lightweight neural network architecture capable of accurately segmenting irises in diverse environments. To accomplish this, we employ two key strategies. Firstly, we integrate an attention mechanism to enhance the accuracy of our model. This mechanism allows the network to focus on crucial iris features, improving segmentation precision. Secondly, we incorporate the efficient spatial pyramid (ESP) block, which effectively reduces the time complexity of the overall model. The performance of our model is evaluated on the CASIA-Iris-V4-Interval, IIT Delhi, and UBIRIS.v2 databases, along with, our model achieving MIOU of 96.29%, 96.02%, and 93.61% respectively. Our research reveals that the proposed network delivers exceptional levels of accuracy with high computational efficiency. Furthermore through comparative analysis with other models and methods, we established that our model is more accurate and cost-efficient than other state-of-the-art semantic segmentation architectures and methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A survey on cross-user federated recommendation

引用

Science China(Information Sciences) 2025年第4期68卷 7-32页

作者： Enyue YANG Yudi XIONG Wei YUAN Weike PAN Qiang YANG Zhong MING College of Computer Science and Software Engineering Shenzhen University School of Electrical Engineering and Computer Science The University of Queensland WeBank AI Lab WeBank Department of Computer Science and Engineering Hong Kong University of Science and Technology College of Big Data and Internet Shenzhen Technology University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.

关键词： cross-user federated recommendation federated recommendation federated learning recommender systems user privacy

来源：评论

学校读者我要写书评

暂无评论

Edge-aware Feature Aggregation Network for Polyp Segmentation

引用

Machine Intelligence Research 2025年第1期22卷 101-116页

作者： Tao Zhou Yizhe Zhang Geng Chen Yi Zhou Ye Wu Deng-Ping Fan PCA Lab Key Laboratory of Intelligent Perception and Systems for High-dimensional Information of Ministry of EducationSchool of Computer Science and EngineeringNanjing University of Science and TechnologyNanjing210094China School of Computer Science and Engineering Northwestern Polytechnical University(NPU)Xi’an710129China School of Computer Science and Engineering Southeast UniversityNanjing211189China Computer Vision Lab ETH ZürichZürich8092Switzerland

Precise polyp segmentation is vital for the early diagnosis and prevention of colorectal cancer(CRC)in clinical ***,due to scale variation and blurry polyp boundaries,it is still a challenging task to achieve satisfactory segmentation performance with different scales and *** this study,we present a novel edge-aware feature aggregation network(EFA-Net)for polyp segmentation,which can fully make use of cross-level and multi-scale features to enhance the performance of polyp ***,we first present an edge-aware guidance module(EGM)to combine the low-level features with the high-level features to learn an edge-enhanced feature,which is incorporated into each decoder unit using a layer-by-layer ***,a scale-aware convolution module(SCM)is proposed to learn scale-aware features by using dilated convolutions with different ratios,in order to effectively deal with scale ***,a cross-level fusion module(CFM)is proposed to effectively integrate the cross-level features,which can exploit the local and global contextual ***,the outputs of CFMs are adaptively weighted by using the learned edge-aware feature,which are then used to produce multiple side-out segmentation *** results on five widely adopted colonoscopy datasets show that our EFA-Net outperforms state-of-the-art polyp segmentation methods in terms of generalization and *** implementation code and segmentation maps will be publicly at https://***/taozh2017/EFANet.

关键词： Colorectal cancer polyp segmentation edge-aware guidance module scale-aware convolution module cross-level fusion module

来源：评论

学校读者我要写书评

暂无评论

RE-SEGNN:recurrent semantic evidence-aware graph neural network for temporal knowledge graph forecasting

引用

Science China(Information Sciences) 2025年第2期68卷 103-119页

作者： Wenyu CAI Mengfan LI Xuanhua SHI Yuanxin FAN Quntao ZHU Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and Technology

Temporal knowledge graph(TKG) reasoning, has seen widespread use for modeling real-world events, particularly in extrapolation settings. Nevertheless, most previous studies are embedded models, which require both entity and relation embedding to make predictions, ignoring the semantic correlations among different entities and relations within the same timestamp. This can lead to random and nonsensical predictions when unseen entities or relations occur. Furthermore, many existing models exhibit limitations in handling highly correlated historical facts with extensive temporal depth. They often either overlook such facts or overly accentuate the relationships between recurring past occurrences and their current counterparts. Due to the dynamic nature of TKG, effectively capturing the evolving semantics between different timestamps can be *** address these shortcomings, we propose the recurrent semantic evidenceaware graph neural network(RE-SEGNN), a novel graph neural network that can learn the semantics of entities and relations simultaneously. For the former challenge, our model can predict a possible answer to missing quadruples based on semantics when facing unseen entities or relations. For the latter problem, based on an obvious established force, both the recency and frequency of semantic history tend to confer a higher reference value for the current. We use the Hawkes process to compute the semantic trend, which allows the semantics of recent facts to gain more attention than those of distant facts. Experimental results show that RE-SEGNN outperforms all SOTA models in entity prediction on 6 widely used datasets, and 5 datasets in relation prediction. Furthermore, the case study shows how our model can deal with unseen entities and relations.

关键词： knowledge graph reasoning temporal knowledge graph Hawkes process semantic evidence

来源：评论

学校读者我要写书评

暂无评论

Coordinated Jamming and Poisoning Attack Detection and Mitigation in Wireless Federated Learning Networks

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the Communications Society 2025年 6卷 3745-3759页

作者： Barkatsa, Sofia Diamanti, Maria Charatsaris, Panagiotis Voikos, Stefanos Tsiropoulou, Eirini Eleni Papavassiliou, Symeon Institute of Communication and Computer Systems School of Electrical and Computer Engineering National Technical University of Athens Zografou15780 Greece Arizona State University School of Electrical Computer and Energy Engineering Performance and Resource Optimization in Networks –PROTON Lab TempeAZ85287 United States

Wireless Federated Learning (FL) is a distributed Artificial Intelligence (AI) framework, enabling decision-making at the network edge where data are generated. However, wireless transmissions of model updates from edge nodes to the coordinating server are vulnerable to jamming, alongside the inherent risk of poisoning the learning process. In this paper, we tackle the problem of coordinated jamming and poisoning attacks in wireless FL networks, where malicious edge nodes disrupt transmissions of legitimate local model updates to the cloud server while injecting poisoned model updates to manipulate the global model. To this end, we introduce two complementary mechanisms operating alternately. First, a robust global model aggregation algorithm is developed to address poisoning attacks by weighting edge nodes’ local model updates using a novel contribution index. The calculation of the index is inspired by the Shapley value, but it offers polynomial complexity compared to existing methods. Subsequently, a distributed power control solution for jamming attack mitigation in the uplink of the FL network is introduced based on Bayesian games with incomplete information. Both legitimate and malicious nodes aim to successfully transmit their model parameters, minimizing transmission power and time to the server, while having probabilistic knowledge about the malicious behavior of the other nodes in the game. The proposed unified approach and each individual mechanism are assessed via modeling and simulation, verifying their effectiveness in mitigating both attacks while achieving a good tradeoff between global model accuracy and consumed time and energy compared to state-of-the-art approaches. © 2020 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Path Generative Model Based on Conditional β-Variational Auto Encoder for Four-Bar Mechanism Design

引用

Journal of Mechanisms and Robotics 2025年第6期17卷 061004页

作者： Nurizada, Anar Lyu, Zhijie Purwar, Anurag Computer-Aided Design and Innovation Lab Department of Mechanical Engineering Stony Brook University Stony BrookNY11794 United States Stony Brook University Computer-Aided Design and Innovation Lab Department of Mechanical Engineering Stony Brook University Stony BrookNY11794 United States

This article introduces a novel methodology based on conditional β-variational autoencoder (cβ-VAE) architecture to generate diverse types of planar four-bar mechanisms for a given coupler curve. Central to our contribution is the novel integration of cross- and self-attention layers within the VAE framework, facilitating an encoding and decoding process that captures the complex interdependencies of mechanism parameters and associated coupler curves. We propose a unified representation scheme for four-bar mechanisms with both revolute and prismatic joints, utilizing a consistent set of joints to describe each mechanism type. To support and validate our methodology, we have compiled an extensive dataset featuring both open and closed coupler curves of the aforementioned mechanism types. Furthermore, the article introduces three metrics aimed at quantifying the efficacy of our model, alongside an innovative algorithm designed to enhance the predictive outcomes by identifying and computing cognate mechanisms. Copyright © 2025 by ASME.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Purification Of Contaminated Convolutional Neural Networks Via Robust Recovery: An Approach with Theoretical Guarantee in One-Hidden-Layer Case

引用

IEEE Journal on Selected Topics in Signal Processing 2025年第3期19卷 507-519页

作者： Lu, Hanxiao Huang, Zeyu Wang, Ren Illinois Institute of Technology Trustworthy and Intelligent Machine Learning Research Lab Department of Electrical and Computer Engineering ChicagoIL60616 United States Illinois Institute of Technology Department of Electrical and Computer Engineering ChicagoIL60616 United States

Convolutional neural networks (CNNs), one of the key architectures of deep learning models, have achieved superior performance on many machine learning tasks such as image classification, video recognition, and power systems. Despite their success, CNNs can be easily contaminated by natural noises and artificially injected noises such as backdoor attacks. In this paper, we propose a robust recovery method to remove the noise from the potentially contaminated CNNs and provide an exact recovery guarantee on one-hidden-layer non-overlapping CNNs with the rectified linear unit (ReLU) activation function. Our theoretical results show that both CNNs' weights and biases can be exactly recovered under the overparameterization setting with some mild assumptions. The experimental results demonstrate the correctness of the proofs and the effectiveness of the method in both the synthetic environment and the practical neural network setting. Our results also indicate that the proposed method can be extended to multiple-layer CNNs and potentially serve as a defense strategy against backdoor attacks. © 2025 IEEE. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A deep learning framework for enhanced mass spectrometry data analysis and biomarker screening

引用

computer Methods in Biomechanics and Biomedical engineering 2025年 1-13页

作者： Zhang, Shuyu Li, Zhiyu Peng, Weili Chen, Yuanyuan Wu, Yao Machine Intelligence Lab College of Computer Science Sichuan University Chengdu China National Engineering Research Center for Biomaterials School of Biomedical Engineering Sichuan University Chengdu China

Mass spectrometry (MS) serves as a powerful analytical technique in metabolomics. Traditional MS analysis workflows are heavily reliant on operator experience and are prone to be influenced by complex, high-dimensional MS data. This study introduces a deep learning framework designed to enhance the classification of complex MS data and facilitate biomarker screening. The proposed framework integrates preprocessing, classification, and biomarker selection, addressing challenges in high-dimensional MS analysis. Experimental results demonstrate significant improvements in classification tasks compared to other machine learning approaches. Additionally, the proposed peak-preprocessing module is validated for its potential in biomarker screening, identifying potential biomarkers from high-dimensional data. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Liver disease deep learning mass spectrometry pre-processing

来源：评论

学校读者我要写书评

暂无评论

Electrochemical sensor for dopamine detection based on multiwalled carbon nanotube/molybdenum disulfide quantum dots with machine learning integration and anti-interference capability

引用

Tungsten 2025年第1期7卷 137-151页

作者： Geethukrishnan Onkar Apte Kiran Kumar Tadi Energy Electrodics and Electrocatalysis (EEE) Lab Department of Chemistry School of Advanced Sciences Vellore Institute of Technology School of Computer Science and Engineering Vellore Institute of Technology

The precise detection and measurement of dopamine（DA）,a crucial neurotransmitter in the human body,plays a significant role in diagnosing,preventing,and treating neurological diseases associated with its levels.A highly sensitive DA electrochemical sensor was constructed by combining molybdenum disulfide quantum dots（MSQDs） with multiwalled carbon nanotubes（MWCNTs）.The MSQDs were synthesized using the shear exfoliation *** sensors consist of MSQDs with Mo-S edge catalytic centers for the DA redox reaction,and MWCNTs amplify the sensor *** linearity of the sensor for the detection of DA was tested in the presence of ascorbic acid(AA,50 μmol·L-1) and uric acid(UA,200 μmol·L-1),and exhibited linearity from 2 to 966 μmol·L-1of DA with 0.097 μA(mol·L-1)-1sensitivity and a low limit of detection of0.6 μmol·L-1（the ratio between signal and noise,S/N=3）.Moreover,the sensitivity and selectivity of the sensor were also studied using *** is no increase in amperometric current after adding the most potentially interfering *** sensor was successfully applied to recover DA in human blood sera ***,machine learning algorithms were operated to aid in the near-precise detection of DA in the heterogeneous mixture containing AA and *** algorithms facilitate the identification and quantification of DA amidst coexisting interferents,including AA,that are commonly present in biological matrices.

关键词： Dopamine MoS_2 Biosensor Multiwalled carbon nanotubes Machine learning Complex mixture

来源：评论

学校读者我要写书评

暂无评论

Hardware-Aware Quantization for Accurate Memristor-Based Neural Networks 24

Hardware-Aware Quantization for Accurate Memristor-Based Neu...

引用

43rd International Conference on computer-Aided Design, ICCAD 2024

作者： Diware, Sumit Yaldagard, Mohammad Amin Bishnoi, Rajendra Computer Engineering Lab Delft University of Technology Delft Netherlands

ISBN: (纸本)9798400710773

Memristor-based Computation-In-Memory (CIM) has emerged as a compelling paradigm for designing energy-efficient neural network hardware. However, memristors suffer from conductance variation issue, which introduces computational errors in CIM hardware and leads to a degraded inference accuracy. In this paper, we present a hardware-aware quantization to mitigate the impact of conductance variation on CIM-based neural networks. We achieve this using the inherent characteristics of fixed-point arithmetic in CIM hardware. By tuning the bit-precision of weights, we align the conductance variation-induced errors with lower-order output bits. This reduces their numerical impact on the fixed-point output. We further decrease the residual errors by selectively discarding bits with low information and high error. This leads to error-free computations and a high inference accuracy. Our proposed methodology achieves 5.6× correct operations per unit energy compared to the conventional approach, while incurring very low hardware overheads. © 2024 Copyright is held by the owner/author(s).

关键词： Fixed point arithmetic

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：