检索结果-内蒙古大学图书馆

Research on the mechanical fault diagnosis method based on sound signal and IEMD-DDCNN

International Journal of Intelligent Computing and Cybernetics 2023年第3期16卷 629-646页

作者： Haoning Pu Zhan Wen Xiulan Sun Lemei Han Yanhe Na Hantao Liu Wenzao Li Chengdu University of Information Technology ChengduChina Education Department of Sichuan Province Education Informatization and Big Data CenterChengduChina Network and Data Security Key Laboratory of Sichuan Province UESTCChengduChina

Purpose–The purpose of this paper is to provide a shorter time cost,high-accuracy fault diagnosis method for water *** pumps are widely used in industrial equipment and their fault diagnosis is gaining increasing *** the time-consuming empirical mode decomposition(EMD)method and the more efficient classification provided by the convolutional neural network(CNN)method,a novel classification method based on incomplete empirical mode decomposition(IEMD)and dual-input dual-channel convolutional neural network(DDCNN)composite data is proposed and applied to the fault diagnosis of water ***/methodology/approach–This paper proposes a data preprocessing method using IEMD combined with mel-frequency cepstrum coefficient(MFCC)and a neural network model of ***,the sound signal is decomposed by IEMD to get numerous intrinsic mode functions(IMFs)and a residual(RES).Several IMFs and one RES are then extracted by MFCC ***,the obtained features are split into two channels(IMFs one channel;RES one channel)and input into ***–The Sound dataset for Malfunctioning Industrial Machine Investigation and Inspection(MIMII dataset)is used to verify the practicability of the *** results show that decomposition into an IMF is optimal when taking into account the real-time and accuracy of the *** with EMD,51.52% of data preprocessing time,67.25% of network training time and 63.7%of test time are saved and also improve *** limitations/implications–This method can achieve higher accuracy in fault diagnosis with a shorter time ***,the fault diagnosis of equipment based on the sound signal in the factory has certain feasibility and research ***/value–This method provides a feasible method for mechanical fault diagnosis based on sound signals in industrial applications.

关键词： Fault identification Neural nets DDCNN IEMD MFCC

来源：评论

学校读者我要写书评

暂无评论

An Approach of Multi-Comment Emotional Perception Based on K-Means Clustering towards Online Government Service System 2

An Approach of Multi-Comment Emotional Perception Based on K...

引用

2nd International Joint Conference on Information and Communication Engineering, JCICE 2023

作者： Yu, Peizhen Wang, Yue Liu, Hantao Li, Hanyun Li, Wenzao Chengdu University of Information Technology Communication Engineering Chengdu China Educational Informatization and Big Data Center Education Department of Sichuan Province Chengdu China

ISBN: (纸本)9798350325768

The service quality of online government services is related to the efficiency of government affairs. To cluster the sentiment of comments based on the quantification of user comments. Proposed methods and mechanisms for judging the direction of emotions and visualizing data. In this paper, we further enrich multidimensional information extraction and promote system intelligence by using K-means clustering algorithm based on comments quantification. It provides a quantitative basis and model for the government platform to implement web-Assisted services and provides strong data support for subsequent sensing tasks. We will promote the development of platforms and improve the control capabilities of platforms. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Approach for Emotion Recognition Using Image-Text Fusion 2

Deep Learning Based Approach for Emotion Recognition Using I...

引用

2nd International Joint Conference on Information and Communication Engineering, JCICE 2023

作者： Li, Hanyun Liu, Hantao Yu, Peizhen Zhao, Jiacheng Wan, Bing Li, Wenzao Chengdu University of Information Technology Chengdu China Education Informatization and Big Data Center Education Department of Sichuan Province Chengdu China Chengdu Polytechnic School of Software Chengdu China

ISBN: (纸本)9798350325768

To address the problem that traditional emotion recognition methods using only text data fail to adequately explore emotional information, unimodal data lacks comprehensive information and, therefore, fails to sufficiently reflect the true emotional state. Therefore, we propose an emotion recognition model with image-Text fusion. First, the model uses pre-Trained models uses pre-Trained Bidirectional Encoder Representations from Transformers (BERT) and ResNet to extract features from text data and image data, respectively. The final feature representation vectors of images and text are combined using a later fusion approach, and finally, Softmax performs emotion recognition. Comparative experimental results show that our model outperforms both unimodal and other multimodal models on emotion recognition tasks. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

DualStreamAttentionNet: A Multimodal Approach for Audio and Text sentiment analysis with Self and Cross Modal Attention Mechanisms 9

DualStreamAttentionNet: A Multimodal Approach for Audio and ...

引用

9th International Conference on Computer and Communications, ICCC 2023

作者： Jiang, Rui Wen, Zhan Liu, Hantao Liu, Chang Chengdu University of Information Technology School of Communication Engineering Chengdu China Education Informatization and Big Data Center Education Department of Sichuan Province Chengdu China Office of Chengdu Civil Affairs Bureau Sichuan Province Chengdu China

ISBN: (纸本)9798350317251

Sentiment analysis is a crucial task in natural language processing. While unimodal sentiment analysis relies on one modality, multimodal sentiment analysis combines features from various modalities to improve accuracy. However, many current models emphasize complex fusion techniques and neglect the importance of enhancing modality feature extraction. They also often overlook the interaction between modalities. In response, we introduce the DualStreamAttentionNet(DSAN), an innovative model tailored for joint text and audio sentiment analysis. Our architecture employs a Transformer encoder for robust textual feature extraction and processes audio using 1D convolutions followed by a bidirectional LSTM for enhanced audio feature representation. Crucially, by leveraging self and cross-attention mechanisms, our model not only amplifies the intrinsic features of each modality but also effectively captures the interrelated dynamics between text and audio. This dual-focus approach leads to a synergistic fusion of features, resulting in heightened emotion classification accuracy. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Component-Aware Chinese Font Generation Method Based on Multi-Scale Features 5

A Component-Aware Chinese Font Generation Method Based on Mu...

引用

5th International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2024

作者： Guo, Xiaoqi Wang, Cunrui Zhan, Guodong Zhou, Juxiang Dalian Minzu University Seac Key Laboratory of Big Data Applied Technology Dalian China Dalian Minzu University Dalian Chinese Font Design Technology Innovation Center Dalian China Yunnan Normal University Foundation of Key Laboratory of Education Informatization for Nationalities Kunming China

ISBN: (纸本)9798331528911

AI-assisted generation technology for Chinese characters can significantly improve the efficiency of font library development for designers. However, existing algorithms still encounter errors in glyph strokes and structures, even when incorporating stroke semantics or font component information. This paper deepens the utilization of structural and positional features of Chinese character components by capturing the characteristics of these components at different scales, constraining their positional relationships, and enhancing the stability and consistency of glyph structures. By leveraging the cross-scale features associated with Chinese character components, the coherence of glyphs across various spatial and hierarchical levels is reinforced, improving the expression of local features. This study conducts ablation experiments on a dataset comprising 20 Chinese character libraries and compares the results with CycleGAN, Zi2zi, MX-Font, and DG-Font. The findings indicate that the proposed method enhances both the local details and overall structure of generated glyphs, with specific evaluation metrics showing significant improvement. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Chinese Font Generation Algorithm with Redundant Feature Suppression 5

Chinese Font Generation Algorithm with Redundant Feature Sup...

引用

5th International Conference on Machine Learning and Computer Application, ICMLCA 2024

作者： Guo, Xiaoqi Wang, Cunrui Zhan, Guodong Zhou, Juxiang SEAC Key Laboratory of Big Data Applied Technology Dalian Minzu University Dalian China Dalian Chinese Font Design Technology Innovation Center Dalian Minzu University Dalian China Foundation of Key Laboratory of Education Informatization for Nationalities Yunnan Normal University Kunming China

ISBN: (纸本)9798331530334

Automated generation of Chinese character fonts can significantly enhance font library design efficiency and improve industrial productivity. Current algorithms for generating Chinese fonts often transmit redundant features from reference graphics into the model structure, alongside spatial and channel dimensions, resulting in pronounced redundancy in the generated outputs. This paper proposes a method that suppresses redundant features from both spatial and channel dimensions, reconstructs spatial features, and employs residual quantization to extract detailed font style characteristics. By mitigating redundant features, the overall stylistic expression of Chinese characters is reinforced, leading to the generation of high-quality font libraries. Experiments conducted on a dataset comprising 30 Chinese font libraries demonstrate the effectiveness of this method, with improvements observed in font feature expression metrics compared to CycleGAN, Zi i2zi, MX-Font, and DG-Font. © 2024 IEEE.

关键词： component font generation redundancy feature residual quantization

来源：评论

学校读者我要写书评

暂无评论

An Approach of Multi-Comment Emotional Perception Based On K-Means Clustering towards Online Government Service System

An Approach of Multi-Comment Emotional Perception Based On K...

引用

Information and Communication Engineering (JCICE), International Joint Conference on

作者： Peizhen Yu Yue Wang Hantao Liu Hanyun Li Wenzao Li Communication Engineering Chengdu University of Information Technology Chengdu China Education Department of Sichuan Province Educational Informatization and Big Data Center Chengdu China

The service quality of online government services is related to the efficiency of government affairs. To cluster the sentiment of comments based on the quantification of user comments. Proposed methods and mechanisms for judging the direction of emotions and visualizing data. In this paper, we further enrich multidimensional information extraction and promote system intelligence by using K-means clustering algorithm based on comments quantification. It provides a quantitative basis and model for the government platform to implement web-assisted services and provides strong data support for subsequent sensing tasks. We will promote the development of platforms and improve the control capabilities of platforms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on the Distribution Characteristics of Standardized big data Resources Based on data Visualization - - Taking Standardization Practice in Shandong Province as an Example 9

Research on the Distribution Characteristics of Standardized...

引用

9th IEEE International Conference on data Science in Cyberspace, DSC 2024

作者： Sun, Jinyang Peng, Dongdong Lu, Zhe Zhai, Mengran Qi, Ning Qi, Yuanhua SHANDONG SCICOM Information and Economy Research Institute Co. Ltd. Jinan China Jinan Municipal Bureau of Big Data Jinan China Shandong Institute of Economy and Informatization Development Jinan China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan China

ISBN: (纸本)9798350391367

Standardized big data, as a product of the combination of big data and standardization work, objectively reflects the status quo and trends of standardization work. An in-depth study of the distribution characteristics of standardized big data resources has important value for improving the efficiency of standardization. Therefore, this paper explores the characteristics of the distribution of standardization resources from the dimensions of spatial and temporal distribution, industry distribution, standard type distribution, and distribution of think tank experts through visual analysis methods. The study shows that: (1) the distribution of standardization resources in Shandong Province presents significant hierarchical and geographical characteristics;(2) from the viewpoint of the distribution of industry types and standard types, the distribution of standardization resources in Shandong Province presents a typical "long-tailed distribution";(3) the distribution of think-tank experts presents obvious "agglomeration effect". © 2024 IEEE.

关键词： data consistency

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Approach for Emotion Recognition Using Image-text Fusion

Deep Learning Based Approach for Emotion Recognition Using I...

引用

Information and Communication Engineering (JCICE), International Joint Conference on

作者： Hanyun Li Hantao Liu Peizhen Yu Jiacheng Zhao Bing Wan Wenzao Li Chengdu University of Information Technology Chengdu China Education Department of Sichuan Province Education Informatization and Big Data Center Chengdu China School of Software Chengdu Polytechnic Chengdu China

To address the problem that traditional emotion recognition methods using only text data fail to adequately explore emotional information, unimodal data lacks comprehensive information and, therefore, fails to sufficiently reflect the true emotional state. Therefore, we propose an emotion recognition model with image-text fusion. First, the model uses pre-trained models uses pre-trained Bidirectional Encoder Representations from Transformers (BERT) and ResNet to extract features from text data and image data, respectively. The final feature representation vectors of images and text are combined using a later fusion approach, and finally, Softmax performs emotion recognition. Comparative experimental results show that our model outperforms both unimodal and other multimodal models on emotion recognition tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimization of Service Migration Decisions in Mobile Edge Computing Based on Markov Decision Processes

Optimization of Service Migration Decisions in Mobile Edge C...

引用

Information and Communication Engineering (JCICE), International Joint Conference on

作者： Xiaoming Zhang Zhan Wen Ran Tang Xiaoke Wang Hantao Liu Miao He Dehao Ren Wenzao Li School of Communication Engineering Chengdu University and Information Technology Chengdu China Education Department of Sichuan Province Education Informatization and Big Data Center Chengdu China Education Department of Sichuan Province Sichuan Province Higher Education Student Information Consultation and Employment Guidance Center Chengdu China

ISBN: (数字)9798350388725

ISBN: (纸本)9798350388732

In order to make optimal migration decisions promptly and accurately in the presence of uncertainty in service migration in mobile edge computing, we propose a service migration optimization model based on Markov Decision Processes (MDP) that abstracts the underlying spatial relationships between users and servers using the distance between them. Utilizing a value iteration algorithm based on differential equations, we further reduce the decision latency in service migration by treating the costs incurred in the decision-making process as value functions, calculating the minimum cost generated during service migration. Simulation results demonstrate that the decision time of this method is 0.1% of that of other traditional Markov decision models using standard value iteration and policy iteration. Moreover, compared with random migration and constant migration, the strategy obtained by this method is closer to the standard strategy obtained by using value iteration. This proves that the model has high efficiency and accuracy in the task of service migration in mobile edge computing.

关键词： Multi-access edge computing Costs Uncertainty Markov decision processes Simulation Optimization models Differential equations Servers Standards Optimization

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：