检索结果-内蒙古大学图书馆

Improving ECAPA-TDNN Performance with Coordinate Attention

Journal of Shanghai Jiaotong University (Science) 2024年 1-7页

作者： Liu, Shuanghong Song, Zhida He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Department of Electronic Engineering and Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The current mainstream networks, such as squeeze and excitation residual neural network (SE-ResNet) and emphasized channel attention, propagation and aggregation based time delay neural network (ECAPA-TDNN), enhance the capability of speaker embedding extractors to extract more discriminative speaker embeddings by incorporating squeeze and excitation (SE) attention within the convolutional blocks. However, the SE attention focuses solely on encoding inter-channel information, overlooking the importance of spatial positional information and time-frequency information, which are crucial for the model’s performance. In this paper, we first experimentally compare the effectiveness of several mainstream attention mechanisms in the computer vision domain for the ECAPA-TDNN model. Next, we focus on the substantial improvements that coordinate attention (CA) brings to the ECAPA-TDNN model. The introduction of CA can help the model embed time-frequency information into the channel representation. Even without using AS-Norm, our proposed model achieves relative reductions of about 5.3% equal error rate (EER) and 5.5% minimum detection cost function (minDCF) on both the Voxceleb-O and Voxceleb-H test sets compared to the ECAPA-TDNN baseline model. In addition, the EER is relatively reduced by 9.46% on the CN-Celeb1 test set. This result strongly demonstrates that the CA module can effectively improve the generalization ability of the ECAPA-TDNN model. © Shanghai Jiao Tong University 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework Integrating Knowledge and Data for Collaborative Root Cause Identification 5

A Unified Framework Integrating Knowledge and Data for Colla...

引用

5th International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2024

作者： Yu, Jiefei Cao, Zicheng He, Siyi Gu, Zuyi Xu, Yingcheng Zhong, Kai Institutes of Physical Science and Information Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui China School of Big Data and Statistics Anhui University Anhui China

ISBN: (纸本)9798331529192

Capturing the root cause and propagation path of the fault is critical to ensuring the safety and efficiency of industrial processes, especially those that inadequately utilize process knowledge and data. To address this issue, a unified framework integrating knowledge and data for collaborative root cause identification is proposed. First, the knowledge causal graph (KCG) is constructed using expert knowledge and industrial flow charts, providing a preliminary reference for subsequent causality analysis. Next, by replacing the traditional vector autoregression (VAR) model in Granger Causality (GC) with the gated recurrent unit (GRU), a more reliable causal relationship between variables is obtained. Additionally, a causality fusion propagation path identification method (CF-PPI) is designed to identify the root cause and propagation path of the fault, so that the obtained fault propagation path has less redundancy and higher accuracy. Finally, the method is validated using data from the ASHRAE RP-1043 centrifugal chiller. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

IMPULSE NOISE REMOVAL BY L1 WEIGHTED NUCLEAR NORM MINIMIZATION

引用

Journal of Computational Mathematics 2023年第6期41卷 1171-1191页

作者： Jian Lu Yuting Ye Yiqiu Dong Xiaoxia Liu Yuru Zou Shenzhen Key Laboratory of Advanced Machine Learning and Applications College of Mathematics and StatisticsShenzhen UniversityShenzhen 518060China Guangdong Key Laboratory of Intelligent Information Processing Pazhou LabGuangzhou 510335China Department of Applied Mathematics and Computer Science Technical University of Denmark2800 Kgs.LyngbyDenmark

In recent years,the nuclear norm minimization(NNM)as a convex relaxation of the rank minimization has attracted great research *** assigning different weights to singular values,the weighted nuclear norm minimization(WNNM)has been utilized in many ***,most of the work on WNNM is combined with the l 2-data-fidelity term,which is under additive Gaussian noise *** this paper,we introduce the L1-WNNM model,which incorporates the l 1-data-fidelity term and the regularization from *** apply the alternating direction method of multipliers(ADMM)to solve the non-convex minimization problem in this *** exploit the low rank prior on the patch matrices extracted based on the image non-local self-similarity and apply the L1-WNNM model on patch matrices to restore the image corrupted by impulse *** results show that our method can effectively remove impulse noise.

关键词： Image denoising Weighted nuclear norm minimization l 1-data-fidelity term Low rank analysis Impulse noise

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Framework for Secure Storage and Sharing of Resumes

引用

computers, Materials & Continua 2022年第9期72卷 5395-5413页

作者： Huanrong Tang Changlin Hu Tianming Liu Jianquan Ouyang Key Laboratory of Intelligent Computing and Information Processing Ministry of EducationComputer Science College of Xiangtan UniversityXiangtanHunan ProvinceChina Department of Computer Science The University of GeorgiaAthensGeorgiaUSA

In response to problems in the centralized storage of personal resumes on third-party recruitment platforms,such as inadequate privacy protection,inability of individuals to accurately authorize downloads,and inability to determine who downloaded the resume and when,this study proposes a blockchain-based framework for secure storage and sharing of *** can employ an authorized access mechanism to protect their privacy *** proposed framework uses smart contracts,interplanetary file system,symmetric encryption,and digital signatures to protect,verify,and share *** keys are split and stored in multiple depositories through secret-sharing technology to improve the security of these *** key escrow incentives are implemented using smart contracts to automatically verify the correctness of keys and encourage the active participation of honest key escrow *** framework combines blockchain and searchable symmetric encryption technology to realize multikeyword search using inverted indexing and Bloom filters and verify search results on the *** search service fees are charged through *** after the search results are verified can the search service provider obtain the search fee,thus ensuring fair and efficient search for encrypted *** framework is decentralized,secure,and tamper-evident,and achieves controlled sharing while protecting personal privacy and information security.

关键词： Resume blockchain interplanetary file system secret sharing searchable encryption

来源：评论

学校读者我要写书评

暂无评论

Mitigating Shortcut Learning via Smart Data Augmentation based on Large Language Model 31

Mitigating Shortcut Learning via Smart Data Augmentation bas...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Sun, Xinyi Tan, Hongye Guo, Yaxin Qiang, Pengpeng Li, Ru Zhang, Hu School of Computer and Information Technology Shanxi University Taiyuan China Institute of Intelligent Information Processing Shanxi University Taiyuan China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan China

ISBN: (纸本)9798891761964

Data-driven pre-trained language models typically perform shortcut learning wherein they rely on the spurious correlations between the data and the ground truth. This reliance can undermine the robustness and generalization of the model. To address this issue, data augmentation emerges as a promising solution. By integrating anti-shortcut data to the training set, the models' shortcut-induced biases can be mitigated. However, existing methods encounter three challenges: (1) Manual definition of shortcuts is tailored to particular datasets, restricting generalization. (2) The inherent confirmation bias during model training hampers the effectiveness of data augmentation. (3) Insufficient exploration of the relationship between the model performance and the augmented data quantity may result in excessive data consumption. To tackle these challenges, we propose a method of Smart Data Augmentation based on Large Language Models (SAug-LLM). It leverages the LLMs to autonomously identify shortcuts and generate their anti-shortcut counterparts. In addition, the dual validation is employed to mitigate the confirmation bias during the model retraining. Furthermore, the data augmentation process is optimized to effectively rectify model biases while minimizing data consumption. We validate the effectiveness and generalization of our method through extensive experiments across various natural language processing tasks, demonstrating an average performance improvement of 5.61%. © 2025 Association for Computational Linguistics.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Using Hybrid Penalty and Gated Linear Units to Improve Wasserstein Generative Adversarial Networks for Single-Channel Speech Enhancement

引用

computer Modeling in Engineering & Sciences 2023年第6期135卷 2155-2172页

作者： Xiaojun Zhu Heming Huang School of Computer Science Qinghai Normal UniversityXining810008China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining810008China School of Electronic and Information Engineering Lanzhou City UniversityLanzhou730000China

Recently,speech enhancement methods based on Generative Adversarial Networks have achieved good performance in time-domain noisy ***,the training of Generative Adversarial Networks has such problems as convergence difficulty,model collapse,*** this work,an end-to-end speech enhancement model based on Wasserstein Generative Adversarial Networks is proposed,and some improvements have been made in order to get faster convergence speed and better generated speech ***,in the generator coding part,each convolution layer adopts different convolution kernel sizes to conduct convolution operations for obtaining speech coding information from multiple scales;a gated linear unit is introduced to alleviate the vanishing gradient problem with the increase of network depth;the gradient penalty of the discriminator is replaced with spectral normalization to accelerate the convergence rate of themodel;a hybrid penalty termcomposed of L1 regularization and a scale-invariant signal-to-distortion ratio is introduced into the loss function of the generator to improve the quality of generated *** experimental results on both TIMIT corpus and Tibetan corpus show that the proposed model improves the speech quality significantly and accelerates the convergence speed of the model.

关键词： Speech enhancement generative adversarial networks hybrid penalty gated linear units multi-scale convolution

来源：评论

学校读者我要写书评

暂无评论

From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 624-638页

作者： Chen, Yin Li, Jia Shan, Shiguang Wang, Meng Hong, Richang Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Institute of Computing Technology Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Dynamic facial expression recognition (DFER) in the wild is still hindered by data limitations, e.g., insufficient quantity and diversity of pose, occlusion and illumination, as well as the inherent ambiguity of facial expressions. In contrast, static facial expression recognition (SFER) currently shows much higher performance and can benefit from more abundant high-quality training data. Moreover, the appearance features and dynamic dependencies of DFER remain largely unexplored. Recognizing the potential in leveraging SFER knowledge for DFER, we introduce a novel Static-to-Dynamic model (S2D) that leverages existing SFER knowledge and dynamic information implicitly encoded in extracted facial landmark-aware features, thereby significantly improving DFER performance. Firstly, we build and train an image model for SFER, which incorporates a standard Vision Transformer (ViT) and Multi-View Complementary Prompters (MCPs) only. Then, we obtain our video model (i.e., S2D), for DFER, by inserting Temporal-Modeling Adapters (TMAs) into the image model. MCPs enhance facial expression features with landmark-aware features inferred by an off-the-shelf facial landmark detector. And the TMAs capture and model the relationships of dynamic changes in facial expressions, effectively extending the pre-trained image model for videos. Notably, MCPs and TMAs only increase a fraction of trainable parameters (less than +10%) to the original image model. Moreover, we present a novel Emotion-Anchors (i.e., reference samples for each emotion category) based Self-Distillation Loss to reduce the detrimental influence of ambiguous emotion labels, further enhancing our S2D. Experiments conducted on popular SFER and DFER datasets show that we have achieved a new state of the art. © 2010-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Lightweight Monocular 3D Object Detection Based on Attention Mechanism 5

Lightweight Monocular 3D Object Detection Based on Attention...

引用

5th Asia-Pacific Conference on Image processing, Electronics and computers, IPEC 2024

作者： Zhan, Feng Zhang, Zhi Wuhan University of Science and Technology College of Computer Science and Technology Hubei Wuhan430065 China Information Processing and Real-time Industrial System Hubei Province Key Laboratory of Intelligent Hubei Wuhan430065 China Information Processing and Real-time Industrial System Hubei Province Key Laboratory of Intelligent Hubei Wuhan30065 China

ISBN: (纸本)9798350374407

In the field of autonomous driving, 3D target detection is an important technology. In view of the shortcomings of existing monocular 3D detection algorithms in terms of accuracy and real-time performance, we propose a lightweight 3D target detection algorithm based on the attention mechanism. In order to ensure the real-time performance of the model, we use depthwise separable convolutions in the backbone network. The feature maps of each scale are then connected to an EMA module, which can fuse spatial attention and cross-dimensional Coordinate attention is used to enhance the feature extraction capability of the network, and BiFPN is subsequently used for multi-scale feature fusion. Finally, experiments were conducted on the KITTI dataset, and the results showed that our algorithm was superior to other methods in both accuracy and speed. © 2024 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

IGED:Towards intelligent DDoS Detection Model Using Improved Generalized Entropy and DNN

引用

computers, Materials & Continua 2024年第8期80卷 1851-1866页

作者： Yanhua Liu Yuting Han HuiChen Baokang Zhao XiaofengWang Ximeng Liu College of Computer and Data Science Fuzhou UniversityFuzhou350108China Engineering Research Center of Big Data Intelligence Ministry of EducationFuzhou350108China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhou350108China College of Computer National University of Defense TechnologyChangsha410073China

As the scale of the networks continually expands,the detection of distributed denial of service(DDoS)attacks has become increasingly *** propose an intelligent detection model named IGED by using improved generalized entropy and deep neural network(DNN).The initial detection is based on improved generalized entropy to filter out as much normal traffic as possible,thereby reducing data *** the fine detection is based on DNN to perform precise DDoS detection on the filtered suspicious traffic,enhancing the neural network’s generalization *** results show that the proposed method can efficiently distinguish normal traffic from DDoS *** with the benchmark methods,our method reaches 99.9%on low-rate DDoS(LDDoS),flooded DDoS and CICDDoS2019 datasets in terms of both accuracy and efficiency in identifying attack flows while reducing the time by 17%,31%and 8%.

关键词： DDoS real-time improved generalized entropy DNN

来源：评论

学校读者我要写书评

暂无评论

Data secure transmission intelligent prediction algorithm for mobile industrial IoT networks

引用

Digital Communications and Networks 2023年第2期9卷 400-410页

作者： Lingwei Xu Hao Yin Hong Jia Wenzhong Lin Xinpeng Zhou Yong Fu Xu Yu Department of Information Science and Technology Qingdao University of Science and TechnologyQingdao266061China Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen UniversityXiamen361005China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control(Minjiang University) Fuzhou350121China Faculty of Information Science and Engineering Ocean University of ChinaQingdao266100China Shandong Provincial Key Laboratory of Computer Networks Shandong Computer Science Center(National Supercomputer Center in Jinan)JinanChina

Mobile Industrial Internet of Things(IIoT)applications have achieved the explosive growth in recent *** mobile IIoT has flourished and become the backbone of the industry,laying a solid foundation for the interconnection of all *** variety of application scenarios has brought serious challenges to mobile IIoT networks,which face complex and changeable communication *** data secure transmission is critical for mobile IIoT *** paper investigates the data secure transmission performance prediction of mobile IIoT *** cut down computational complexity,we propose a data secure transmission scheme employing Transmit Antenna Selection(TAS).The novel secrecy performance expressions are first ***,to realize real-time secrecy analysis,we design an improved Convolutional Neural Network(CNN)model,and propose an intelligent data secure transmission performance prediction *** mobile signals,the important features may be removed by the pooling *** will lead to negative effects on the secrecy performance prediction.A novel nine-layer improved CNN model is *** of the input and output layers,it removes the pooling layer and contains six convolution ***,Back-Propagation(BP)and LeNet methods are employed to compare with the proposed *** simulation analysis,good prediction accuracy is achieved by the CNN *** prediction accuracy obtains a 59%increase.

关键词： Mobile IIoT networks Data secure transmission Performance analysis intelligent prediction Improved CNN

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：