检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： Junhao Li Huiling Shi Wei Zhang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

With the extensive application of network traffic encryption technology, the accurate and efficient classification of encrypted traffic has become a critical need for network management. Deep learning has become the predominant method for traffic classification, primarily involving the transformation of network traffic into grayscale images and their subsequent classification using Convolutional Neural networks (CNNs). However, traditional grayscale image generation methods are plagued with issues of redundant and lost information, and conventional channel attention mechanisms are still insufficient in capturing key traffic features, collectively hindering the enhancement of classification performance. To tackle these issues, this paper introduces a classification method based on Byte Transfer Probability and Coordinate Attention Mechanism in Residual Network (BTP-CAResNet). This method, on the foundation of the classic ResNet architecture, incorporates a new grayscale image generation method that utilizes Byte Transfer Probability, effectively overcoming the deficiencies of traditional approaches. Additionally, this paper integrates a Coordinate Attention Mechanism into the ResNet model, which effectively overcomes the limitations of traditional channel attention mechanisms and further improves the performance of traffic classification. Experimental validation on the ISCX VPN-nonVPN dataset demonstrates that, compared to previous CNN-based methods, the method proposed in this paper exhibits superior performance in key metrics such as accuracy, precision, recall, and F1 score. It provides a new perspective for traffic classification based on convolutional neural networks.

关键词： Measurement Attention mechanisms Accuracy Image synthesis Redundancy Telecommunication traffic Gray-scale Robustness Convolutional neural networks Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient CNN-Transformer Aggregation Network for Remote Sensing Image Change Detection

Efficient CNN-Transformer Aggregation Network for Remote Sen...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Bingjie Kong Qinglong Meng Fengqi Hao Jinqiang Bai Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Change detection is a crucial task in the field of remote sensing, focusing on identifying areas where significant changes occur between two remote sensing images captured at different time points. However, existing change detection methods based on CNNs or Transformers face two main challenges. Firstly, CNNs often lack the ability to effectively model long-range dependencies, resulting in diminished recognition performance for targets sharing the same semantics but having different features. Secondly, Transformers leverage self-attention mechanisms to capture long-range dependencies adeptly but struggle to capture local details and multi-scale features effectively. In response to these challenges, we propose a CNN and Transformer Aggregation Network (CTA-Net) for change detection in remote sensing images. Specifically, we devise two encoders based on Transformers and CNNs, respectively, facilitating the generation of complementary global and local features during the encoding phase. In the decoding phase, we design a pyramid-structured complementary decoder to aggregate multi-level complementary features from the CNN and Transformer branches. Furthermore, we propose a novel skip connection strategy to exploit the relationship between decoded features and multi-level complementary features, thereby enhancing the model's multi-scale invariance. Extensive experiments conducted on multiple benchmark datasets validate the effectiveness of our proposed CTA-Net model.

关键词： Target recognition Face recognition Semantics Focusing Transformers Feature extraction Encoding Decoding Remote sensing Cybernetics

来源：评论

学校读者我要写书评

暂无评论

GNN-ASG: A Double Feature Selection-based Adversarial Sample Generation Method in Industrial Control System

GNN-ASG: A Double Feature Selection-based Adversarial Sample...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Lijuan Xu Zhiang Yao Dawei Zhao Xin Li Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Key Laboratory of Computing Power Network and Information Security Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Due to the unique constraints of industrial control data, industrial control adversarial sample attacks are particularly challenging. Existing methods strive to conduct adversarial sample attacks under the conditions of satisfying industrial control data constraints, however, the results are not ideal. Therefore, this study proposes a new adversarial sample generation method GNN-ASG based on double feature selection. GNN-ASG uses data constraints to ensure the rationality of generated data, and uses Graph Deviation Network (GDN) and Autoencoder to improve the quality and versatility of adversarial samples. A new adversarial sample evaluation metrics Adversarial Sample Attack Impact Rate (ASAIR) is proposed to address the problem that existing evaluation metrics are difficult to accurately judge the effectiveness of adversarial sample attacks. This method considers the principle and application environment of adversarial samples, and fully demonstrates the practical effect of adversarial samples. In a comprehensive experiment conducted on three public datasets, GNN-ASG achieves an impressive ASAIR of 21.83%, higher than existing methods of 13.94%. This paper demonstrates the versatility and effectiveness of GNN-ASG by comparing its performance with three state-of-the-art adversarial sample generation methods on four anomaly detection models. GNN-ASG can maximally reduce the F1-Score of the detection model by 0.7605.

关键词： Measurement Federated learning Industrial control Feature extraction Anomaly detection Glass box

来源：评论

学校读者我要写书评

暂无评论

Lightweight Malicious Encrypted Traffic Detection Method Based on KL Image Compression

Lightweight Malicious Encrypted Traffic Detection Method Bas...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Yuecheng Wen Xiaotong Li Haiqing Lv Menglu Wang Wenbo Zuo Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Timely and accurate detection of and response to potentially malicious encrypted traffic is crucial in cybersecurity strategies. Convolutional neural network-based approaches that convert traffic loads into images for analysis have made significant progress in malicious encrypted traffic detection, but they suffer from the challenges of large number of participants, large network size, and high demand for computational resources, especially when edge computing devices are limited. Therefore, there is an urgent need for a lightweight, efficient and accurate malicious encrypted traffic detection model. This paper proposes a malicious encrypted traffic detection model whose core idea is to utilize KL image compression technique. The model first converts the raw traffic data into grayscale images and applies KL transform to compress the images efficiently. Subsequently, a convolutional neural network model with lightweight design is used to classify the compressed image for fast and accurate malicious encrypted traffic detection. After validating on both the public traffic dataset and the lab’s self-collected dataset, the results indicate that our method requires just 0.0216 seconds to process a single input sample, achieving an average classification accuracy of 98%. These findings highlight its practicality and excellence in addressing the real-world challenges of malicious encrypted traffic.

关键词： Image coding Accuracy Computational modeling Transforms Telecommunication traffic Gray-scale Data models Mobile handsets Cryptography Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MMFI-Net: Multilevel Multimodal Feature Injection Network for Infrared and Visible Image Fusion

MMFI-Net: Multilevel Multimodal Feature Injection Network fo...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Rundong Du Jinyong Cheng Huixuan Zhao Ying Guo Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Infrared and visible image fusion aims at a better transfer of feature information from both modalities into the fused image. However, almost all existing methods currently focus on the performance of only one part of a single-modal feature extraction or image reconstruction, and do not link multimodal and multilevel features well. This leads to the problem of insufficient feature information in the image reconstruction process, and the resulting fused image lacks texture details and edge information. In this paper, we propose a multilevel multimodal feature injection network (MMFI-Net). First, the DMII module is used to complement the information of the difference modals. Then, the complemented feature information is decomposed more specifically into basic and detail information by fuzzy filtering and Laplace filtering. Next, in the final image reconstruction section, we concatenate the multi-level features from the feature extraction section with the low-level feature information from the image reconstruction section. In this way, the network is better able to capture information in the image and mitigate the problem of feature information loss. Our method demonstrates significant superiority in terms of contrast, edge information, and texture details, as evidenced by experimental results on publicly available datasets.

关键词： Visualization Filtering Image edge detection Neural networks Feature extraction Image reconstruction Image fusion

来源：评论

学校读者我要写书评

暂无评论

Lightweight Fusion Model with Time-Frequency Features for Speech Emotion Recognition

Lightweight Fusion Model with Time-Frequency Features for Sp...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Peng Zhang Meijuan Li Hui Zhao Yida Chen Fuqiang Wang Ye Li Wei Zhao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Automatic speech emotion recognition (SER) is the task to predict the emotional state from speech, and has become a vital part of human-machine interaction. Recent studies focus on learning from multiple features via feature fusion. This paper proposes a lightweight fusion model with time-frequency features for SER. First, time-frequency features are extracted from the Mel frequency cepstral coefficients (MFCC) of speech by using parallel convolutional neural networks, and enhanced by using a dimension-specific weighting method. Then, a two-stage feature fusion model is proposed to fully capture the complementary information between time and frequency features and to reduce the redundancy. It consists of an adaptive fusion module to redistribute the features for a local fusion, and a global fusion module to enhance the cross-dimension feature communication. Experimental results show that our model achieves competitive performance on the datasets of IEMOCAP and RAVDESS, with recognition accuracies of 74.62% and 86.11%, respectively. The model contains only 0.82M and 0.85M parameters for the two datasets, which is lightweight for SER tasks.

关键词： Adaptation models Time-frequency analysis Emotion recognition Accuracy Computational modeling Redundancy Speech recognition

来源：评论

学校读者我要写书评

暂无评论

CB-YOLO: A Small Object Detection Algorithm for Industrial Scenarios

CB-YOLO: A Small Object Detection Algorithm for Industrial S...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Hao Chen Xiaoming Wu Zhanzhi Su Ying Zhao Yunfeng Dong Xiangzhi Liu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

In certain specific industrial scenarios, smoking and cellphone usage are strictly prohibited behaviors. In these scenarios, it is crucial to rapidly and accurately detect smoking and cell phone usage, and promptly issue warnings, to ensure industrial safety. The detection of prohibited behaviors using computer vision has gained attention from researchers with the development of artificial intelligence. However, detecting small objects like cigarettes and cell phones in complex backgrounds and varying angles poses a challenge due to their changing shapes. In this paper, we propose a detection model called CB-YOLO, which utilizes YOLOv7 as the baseline model, for detecting smoking and mobile phone usage behavior. Firstly, we propose a new channel space pyramid network called CSPPF that pools features at different scales and introduces scale focusing on improving the perceptual ability of the network to better handle targets at various scales and locations. Secondly, we propose an enhanced feature pyramid called AWBFPN. This introduces additional learnable weight parameters to improve the model's ability to fuse multi-scale features effectively. Finally, we have also proposed a new loss function called Size-IoU. The experimental results demonstrate that our algorithm outperforms the baseline model. Specifically, it achieves a 3.9% improvement in Precision, a 2.1% improvement in Recall, a 6.4% improvement in mAP@0.5, and a 2% improvement in mAP@0.5:0.95 on the Phone_check dataset. Similarly, on the Smoking dataset, our algorithm achieves a 3.3% improvement in Precision, a 1.9% improvement in Recall, a 1.7% improvement in mAP@0.5, and a 0.3% improvement in mAP@0.5:0.95.

关键词： Fuses Shape Cellular phones Focusing Object detection Robustness Mobile handsets Safety Iterative methods Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition

arXiv

引用

arXiv 2024年

作者： Zhou, Zi-Hao Fang, Siyuan Zhou, Zi-Jing Wei, Tong Wan, Yuanyu Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China Xiaomi Inc. China School of Software Technology Zhejiang University Ningbo China

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality pseudo-labels for large-scale unlabeled data. However, these methods often neglect the impact of representations learned by the neural network and struggle with real-world unlabeled data, which typically follows a different distribution than labeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. Our framework derives the class-balanced contrastive loss through Gaussian kernel density estimation. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels. By progressively estimating the underlying label distribution and optimizing its alignment with model predictions, we tackle the diverse distribution of unlabeled data in real-world scenarios. Extensive experiments across multiple datasets with varying unlabeled data distributions demonstrate that CCL consistently outperforms prior state-of-the-art methods, achieving over 4% improvement on the ImageNet-127 dataset. Our source code is available at https://***/zhouzihao11/CCL. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Collaborative Prediction of Drug-target Interaction using Sequence-based CNN and Transformer

Collaborative Prediction of Drug-target Interaction using Se...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Huiting Li Weiyu Zhang Yong Shang Wenpeng Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Drug-target interaction (DTI) prediction is a critical step in drug discovery. Deep learning has shown great potential in DTI prediction. In recent years, many sequence-based DTI prediction methods have been proposed. However, the current methods do not fully represent drugs and proteins and ignore the local and global features of these molecules. In response to these challenges, we propose a sequence-based CNN and Transformer collaborative prediction method (SCTDTI) for drug-target interaction. We train and evaluate our proposed approach on two public drug-target datasets, and experimental results show that SCTDTI improves DTI prediction performance compared to state-of-the-art baselines.

关键词： Proteins Drugs Deep learning Federated learning Computational modeling Neural networks Collaboration

来源：评论

学校读者我要写书评

暂无评论

OCF-HP: An Offline Compaction Framework Based on Hotspot Prediction for Data Lakehouse

OCF-HP: An Offline Compaction Framework Based on Hotspot Pre...

引用

Electronic Technology and information Science (ICETIS), International Conference on

作者： Bowen Sun Xiaohan Yang Ying Guo Zhihao Zhao Jing Chen Hu Zhang Jibin Wang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350388343

ISBN: (纸本)9798350388350

With the rapid advancement of information technologies, the global data volume is increasing at an unprecedented speed. Data Lakehouse has become an effective solution for real-time aggregation of multimodal heterogeneous data and supporting multiple query modes. It is worth noting that due to the column-based storage commonly employed in Data Lakehouse and the resulting mechanisms such as Copy-on-Write and Merge-On-Read, data query speed, data freshness, and storage costs have become huge challenges. In this paper, an Offline Compaction Framework based on Hotspot Prediction (OCF-HP) was designed to address the above challenges. Specifically, we analyzed the Timeline data in Hudi which is the mainstream Data Lakehouse framework, then predicted the hotspot periods of data writing based on the improved LSTM model using such data, and realized automatic trigger of Hudi offline compaction tasks in reasonable non-hot periods. The experiment results show that OCF-HP provides Hudi with a more optimized offline compaction solution so that data lakehouse managers could achieve better query speed and data freshness with reducing storage costs in Hudi's read optimized mode.

关键词： Analytical models Costs Data integrity Predictive models Writing Data models Compaction

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：