检索结果-内蒙古大学图书馆

2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

作者： Wang, Jing-Hong Li, Chang-Xin Yang, Jia-Teng College of Computer and Cyber Security Hebei Normal University Shijiazhuang050024 China Hebei Normal University Hebei Key Laboratory of Network and Information Security Shijiazhuang050024 China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Security Hebei Normal University Shijiazhuang050024 China Hebei Polytechnic Institute Shijiazhuang050020 China

ISBN: (纸本)9798350303780

Graph Attention Network (GAT) is a popular method for graph embedding as they effectively leverage attention mechanisms to aggregate first-order neighborhood node information. However, they have limitations in their ability to consider high-order neighborhood nodes and structural information. Directly incorporating high-order neighborhood node information into traditional GAT may result in over-smoothing. To address this challenge, in this paper, we propose a joint attention graph embedding model based on similar networks and structural correlation. secondly, we introduce the concept of structural correlation to the original graph attentional method, and consider not only node content feature but also joint node topological structure feature when calculating the attention score. Finally, the graph attention mechanism module performs feature extraction to generate embedding representations of the nodes. The proposed algorithm achieved an accuracy of 85.7%, 74.30%, and 84.10% on the Cora, Citeseer, and Pubmed datasets respectively in node classification tasks. This represents an improvement of 2.70%, 3.94%, and 2.60% respectively compared to the traditional graph attention model. It can be seen that the proposed method can obtain a better representation of node embedding. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Community Discovery Algorithm via Reconstructed Graph Neural NEtwork

Unsupervised Community Discovery Algorithm via Reconstructed...

引用

2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

作者： Wang, Jinghong Wang, Hui Yang, Jiateng Wang, Xizhao College of Computer and Cyber Security Hebei Normal University Shijiazhuang050024 China Hebei Normal University Hebei Key Laboratory of Network and Information Security Shijiazhuang050024 China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Data Security Hebei Normal University Shijiazhuang050024 China College of Artificial Intelligence Big Data Hebei Polytechnic Institute Shijiazhuang050020 China College of Computer Science and Software Engineering ShenZhen University Shenzhen518060 China

ISBN: (纸本)9798350303780

Community discovery can help discover potential community structures in the network, which is a fundamental and important issue in network science. Graph neural network-based algorithms are receiving increasing attention. However, there is relatively little work on community discovery directly using graph neural networks in reconstruction design. This paper presents an Unsupervised Community Discovery Algorithm based on reconstructed graph neural network (UCDA) to resolve the above issues. To be specific, this paper proposes a framework that learns the representation based on network structure and attribute information. By designing input network features, encoders, decoders, this algorithm uses an unsupervised loss function to train neural networks to extract communities in an integrated way. These designs integrate higher-order modularity information with network features and use variational graph auto-encoders to train data end-to-end under the graph neural network framework. Based on a series of experiments with a wide range of datasets and advanced algorithms, UCDA has achieved superior performance and shows strong competitiveness. Finally, the last section reports the results analysis, t-SNE visualization and hyperparameter analysis, which depicts stable performance and powerful network modularity ability. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

PFD-Net: Pyramid Fourier Deformable Network for medical image segmentation

引用

Computers in Biology and Medicine 2024年 172卷 108302-108302页

作者： Yang, Chaorong Zhang, Zhaohui College of Computer and Cyber Security Hebei Normal University Shijiazhuang050024 China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Data Security Shijiazhuang050024 China Hebei Provincial Key Laboratory of Network & Information Security Hebei Normal University Shijiazhuang050024 China

Medical image segmentation is crucial for accurately locating lesion regions and assisting doctors in diagnosis. However, most existing methods fail to effectively utilize both local details and global semantic information in medical image segmentation, resulting in the inability to effectively capture fine-grained content such as small targets and irregular boundaries. To address this issue, we propose a novel Pyramid Fourier Deformable Network (PFD-Net) for medical image segmentation, which leverages the strengths of CNN and Transformer. The PFD-Net first utilizes PVTv2-based Transformer as the primary encoder to capture global information and further enhances both local and global feature representations with the Fast Fourier Convolution Residual (FFCR) module. Moreover, PFD-Net further proposes the Dilated Deformable Refinement (DDR) module to enhance the model's capacity to comprehend global semantic structures of shape-diverse targets and their irregular boundaries. Lastly, Cross-Level Fusion Block with deformable convolution (CLFB) is proposed to combine the decoded feature maps from the final Residual Decoder Block (DDR) with local features from the CNN auxiliary encoder branch, improving the network's ability to perceive targets resembling the surrounding structures. Extensive experiments were conducted on nine publicly medical image datasets for five types of segmentation tasks including polyp, abdominal, cardiac, gland cells and nuclei. The qualitative and quantitative results demonstrate that PFD-Net outperforms existing state-of-the-art methods in various evaluation metrics, and achieves the highest performance of mDice with the value of 0.826 on the most challenging dataset (ETIS), which is 1.8% improvement compared to the previous best-performing HSNet and 3.6% improvement compared to the next-best PVT-CASCADE. Codes are available at https://***/ChaorongYang/PFD-Net. © 2024 Elsevier Ltd

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Synthetic data for the Mitigation of Demographic Biases in Face Recognition

arXiv

引用

arXiv 2024年

作者： Melzi, Pietro Rathgeb, Christian Tolosana, Ruben Vera-Rodriguez, Ruben Morales, Aythami Lawatsch, Dominik Domin, Florian Schaubert, Maxim Biometrics and Data Pattern Analytics Laboratory Universidad Autonoma de Madrid Spain secunet Security Networks AG Essen Germany Hochschule Darmstadt Germany

This study investigates the possibility of mitigating the demographic biases that affect face recognition technologies through the use of synthetic data. Demographic biases have the potential to impact individuals from specific demographic groups, and can be identified by observing disparate performance of face recognition systems across demographic groups. They primarily arise from the unequal representations of demographic groups in the training data. In recent times, synthetic data have emerged as a solution to some problems that affect face recognition systems. In particular, during the generation process it is possible to specify the desired demographic and facial attributes of images, in order to control the demographic distribution of the synthesized dataset, and fairly represent the different demographic groups. We propose to fine-tune with synthetic data existing face recognition systems that present some demographic biases. We use synthetic datasets generated with GANDiffFace, a novel framework able to synthesize datasets for face recognition with controllable demographic distribution and realistic intra-class variations. We consider multiple datasets representing different demographic groups for training and evaluation. Also, we fine-tune different face recognition systems, and evaluate their demographic fairness with different metrics. Our results support the proposed approach and the use of synthetic data to mitigate demographic biases in face recognition. © 2024, CC BY-NC-ND.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Network security Situation Assessment Method Based on Multi-attention Mechanism and HHO-ResNeXt 8th

A Network Security Situation Assessment Method Based on Mult...

引用

8th International Symposium on security and Privacy in Social Networks and Big data, SocialSec 2022

作者： Zhao, Dongmei Ji, Guoqing Zeng, Shuiguang School of College of Computer and Cyber Security Hebei Normal University Shijiazhuang050024 China Hebei Provincial Key Laboratory of Network and Information Security Hebei Normal University Shijiazhuang050024 China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics and Data Security Hebei Normal University Shijiazhuang050024 China

ISBN: (纸本)9789811972416

Because the traditional convolutional neural network (CNN) cannot obtain the importance of each channel and its receptive field is limited, it is difficult to deal with the increasingly complex network environment. Aiming at the shortcomings, this paper combines the Contextual Transformer (COT) block and the Efficient Channel Attention (ECA) module with ResNeXt and uses Harris Hawks Optimization (HHO) algorithm to choose the most suitable hyperparameters to improve the model performance. This model enables the rich contexts among neighbor keys to be fully exploited and can obtain the importance of each channel to improve the weight of the useful channel and suppress the less useful channel, effectively making up for the shortcomings of the traditional convolutional neural network. The experiments on a network security dataset show that the model is superior to other models in the network security situation assessment effect and its comprehensive performance in accuracy, precision and F-score. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Salient Object Detection Based on Pyramid Vision Transformer Gated Network

SSRN

引用

SSRN 2023年

作者： Huo, Lina Zhou, Xiaoli Wang, Wei Cao, Zhiyi Key Laboratory of Network & Information Security Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Data Security College of Computer and Cyber Security Hebei Normal University Hebei Shijiazhuang050024 China

Recently, vision transformers started to show impressive results that significantly outperform large convolution-based models. In this work, we propose a gating network based on Pyramid Vision Transformer for salient object detection. The Pyramid Vision Transformer (PVT) serves as the backbone network of this gating network, learning global and local representations with its self-attention mechanism. Multi-level gating units are used to recover more details of the saliency map by establishing cooperation among different levels of features, thus improving the discriminability of the whole network. With the help of multi-level gating units, the valuable context information from the encoder can be optimally transmitted to the decoder. The pyramid pooling module (PPM) collects high-level semantic information. Moreover, the semantic information of each level is integrated and decoded by the feature aggregation decoder (FAD). The experimental results on five challenging benchmark databases demonstrate that the proposed method achieves more favourable performance than the current state-of-the-art methods in terms of four evaluation criteria. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy

arXiv

引用

arXiv 2022年

作者： Ruan, Wenqiang Xu, Mingxin Fang, Wenjing Wang, Li Wang, Lei Han, Weili Laboratory of Data Analytics and Security Fudan University China Ant Group China

Secure multi-party computation-based machine learning, referred to as multi-party learning (MPL for short), has become an important technology to utilize data from multiple parties with privacy preservation. While MPL provides rigorous security guarantees for the computation process, the models trained by MPL are still vulnerable to attacks that solely depend on access to the models. Differential privacy could help to defend against such attacks. However, the accuracy loss brought by differential privacy and the huge communication overhead of secure multi-party computation protocols make it highly challenging to balance the 3-way trade-off between privacy, efficiency, and accuracy. In this paper, we are motivated to resolve the above issue by proposing a solution, referred to as PEA (Private, Efficient, Accurate), which consists of a secure differentially private stochastic gradient descent (DPSGD for short) protocol and two optimization methods. First, we propose a secure DPSGD protocol to enforce DPSGD, which is a popular differentially private machine learning algorithm, in secret sharing-based MPL frameworks. Second, to reduce the accuracy loss led by differential privacy noise and the huge communication overhead of MPL, we propose two optimization methods for the training process of MPL: (1) the data-independent feature extraction method, which aims to simplify the trained model structure;(2) the local data-based global model initialization method, which aims to speed up the convergence of the model training. We implement PEA in two open-source MPL frameworks: TF-Encrypted and Queqiao. The experimental results on various datasets demonstrate the efficiency and effectiveness of PEA. E.g. when ϵ = 2, we can train a differentially private classification model with an accuracy of 88% for CIFAR-10 within 7 minutes under the LAN setting. This result significantly outperforms the one from CryptGPU, one state-of-the-art MPL framework: it costs more than 16 hours to tra

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Estimating Smart Grid Stability with Hybrid RNN+LSTM Deep Learning Approach 12

Estimating Smart Grid Stability with Hybrid RNN+LSTM Deep Le...

引用

12th International Conference on Smart Grid, icSmartGrid 2024

作者： Oyucu, Saadin Sagiroglu, Seref Aksoz, Ahmet Bicer, Emre Faculty of Engineering Department of Computer Engineering Adiyaman Turkey Gazi University Artificial Intelligence and Big Data Analytics Security R&d Center Ankara Turkey Sivas Cumhuriyet University Mobilers Team Sivas Turkey Sivas University of Science and Technology Faculty of Engineering and Natural Sciences Battery Research Laboratory Sivas Turkey

ISBN: (纸本)9798350361612

Smart grids are faced with a range of challenges, such as the development of communication infrastructure, cybersecurity threats, data privacy, and the protection of user information, due to their complex structure. Another key challenge faced by smart grids is the stability issues arising from variable energy sources and consumption patterns. In these complex grid systems where energy demand and supply need to be balanced instantly, stability predictions play a significant role in foreseeing potential disruptions and optimizing energy flow. Therefore, within the scope of this study, a hybrid structure utilizing Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) networks is employed for stability classification to predict grid stability. This hybrid model combines the ability of RNN to recognize relationships between consecutive data points with LSTM's capability to preserve long-term dependencies. The results obtained indicate that the model exhibited stable performance with accuracy rates of 98.06% and 98.02% at 50 and 100 epochs, respectively. The findings of this study contribute valuable insights to research on the management and stability of smart grids, enabling energy systems to be operated more reliably and efficiently. © 2024 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Analysis of Interpretable Spiking Neural Networks for Motor Imagery Recognition Tasks

SSRN

引用

SSRN 2023年

作者： Wang, Xiuqing Yang, Yunpeng Li, Qingru Li, Qiuting An, Yang Ye, Xiaoya Key Laboratory of Network & Information Security College of Computer and Cyber Security Hebei Normal University Shijiazhuang China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Data Security Hebei Normal University Shijiazhuang China

Brain-computer interface (BCI) is an important aspect of human-computer interaction (HCI). Motor imagery (MI) EEG-based BCI has great application potential for assisting disabled people in motor function reconstruction and restoration. To fulfill the given tasks based on MI-EEG signals successfully, decoding MI-EEG signals accurately is important. Although deep learning (DL) can be used to analyze EEG signals, it still lacks interpretability. Compared with traditional artificial neural networks (ANNs), spiking neural networks (SNNs) can use spiking neurons which are bio-plausible for the neurons in the brain to communicate with each other, and analyze EEG signals by spike trains with better bio-interpretability. We propose a deep spiking convolutional neural network based on a self-attention (DSCNN-SA) mechanism for EEG-based MI recognition. The DSCNN-SA model is first used to extract the high-level spatio-temporal features of the EEG signal and transform the extracted features into spike trains as input to the deep spiking convolutional neural networks (DSCNNs), and analyze the EEG signal for MI according to the firing patterns of spiking neurons. The classification of 2-class motor imagery tasks is evaluated by the BCI Competition IV-2a and IV-2b datasets, and the average accuracy of the DSCNN-SA model is 85.53% and 81.52% respectively, which is better than that of the comparison models, such as KNN, MLP, DCNN-SA, ECCSP-TB2B, CNN-SAE, EEGNet, KLD and STNN, etc. The experimental results show that the DSCNN-SA model is effective for EEG-based MI recognition. © 2023, The Authors. All rights reserved.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

GANDiffFace: Controllable Generation of Synthetic datasets for Face Recognition with Realistic Variations

GANDiffFace: Controllable Generation of Synthetic Datasets f...

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Pietro Melzi Christian Rathgeb Ruben Tolosana Ruben Vera-Rodriguez Dominik Lawatsch Florian Domin Maxim Schaubert Biometrics and Data Pattern Analytics Laboratory Universidad Autonoma de Madrid Spain Secunet Security Networks AG Essen Germany Hochschule Darmstadt Germany

Face recognition systems have significantly advanced in recent years, driven by the availability of large-scale datasets. However, several issues have recently came up, including privacy concerns that have led to the discontinuation of well-established public datasets. Synthetic datasets have emerged as a solution, even though current synthesis methods present other drawbacks such as limited intraclass variations, lack of realism, and unfair representation of demographic groups. This study introduces GAN-DiffFace, a novel framework for the generation of synthetic datasets for face recognition that combines the power of Generative Adversarial Networks (GANs) and Diffusion models to overcome the limitations of existing synthetic datasets. In GANDiffFace, we first propose the use of GANs to synthesize highly realistic identities and meet target demographic distributions. Subsequently, we fine-tune Diffusion models with the images generated with GANs, synthesizing multiple images of the same identity with a variety of accessories, poses, expressions, and contexts. We generate multiple synthetic datasets by changing GANDiffFace settings, and compare their mated and non-mated score distributions with the distributions provided by popular real-world datasets for face recognition, i.e. VGG2 and IJB-C. Our results show the feasibility of the proposed GANDiffFace, in particular the use of Diffusion models to enhance the (limited) intra-class variations provided by GANs towards the level of real-world datasets.

关键词：

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：