检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Pang, Shanchen Wang, Ruiqian Wu, Wenhao Li, Hengxiao Wu, Jiarui Zhang, Yuanyuan Wang, Shudong College of Computer Science and Technology Qingdao Institute of Software Qingdao China Qingdao University of Technology School of Information and Control Engineering Qingdao China

ISBN: (纸本)9798350386226

Cluster assignment is crucial for analyzing single-cell RNA sequencing (scRNA-seq) data, essential for studying cell diversity and biological functions at the single-cell level. Deep learning-based clustering methods have been extensively applied in scRNA-seq data analysis. However, current deep models frequently overlook the deep exploration of potential gene correlation, resulting in networks lacking guidance from gene correlation information when learning hidden layer features. This paper proposes an adaptive feedback fuzzy clustering method based on deep gene correlation mining(scDCMAC). The deep gene correlation mining network employs contrast learning to compute the contrast loss on two cell similarity matrices, constructed from denoised autoencoder hidden layer features and original input features, to uncover potential gene correlation. The adaptive feedback clustering network further denoises the hidden layer features using a self-attention mechanism, computes the affiliation matrix, and supervises the denoising autoencoder's dimensionality reduction using the affiliation matrix. Experiments on 13 real scRNA-seq datasets demonstrate that scDCMAC excels in clustering accuracy and stability, showing great potential in scRNA-seq sample analysis. © 2024 IEEE.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Lag Synchronization and Lag H∞ Synchronization for Multiweighted Coupled Reaction-Diffusion Neural Networks Suffering Topology Attacks

引用

IEEE Transactions on control of Network Systems 2025年第2期12卷 1488-1499页

作者： Wang, Jin-Liang Zhao, Xin-Yu Ren, Shun-Yan Huang, Tingwen Tiangong University Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems School of Computer Science and Technology Tianjin300387 China Tiangong University School of Electronics & Information Engineering Tianjin300387 China University of Electronic Science and Technology of China School of Mechanical and Electrical Engineering Chengdu611731 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518055 China

This paper mainly discusses two kinds of coupled reaction-diffusion neural networks (CRNN) under topology attacks, that is, the cases with multistate couplings and with multiple spatial-diffusion couplings. On one hand, by adopting state feedback control scheme, the problem of the lag synchronization for the multistate coupled CRNN is addressed. Moreover, the influences of external disturbances for the lag synchronization of the CRNN with multistate couplings are also taken into consideration. On the other hand, several lag and lag H∞ synchronization conditions for CRNN with multiple spatial-diffusion couplings are derived under the help of the Kronecker product and the state feedback control method. Finally, two numerical examples are provided to verify the correctness of the derived criteria. © 2014 IEEE.

关键词： State feedback

来源：评论

学校读者我要写书评

暂无评论

Dual Sparse Variational Autoencoder-driven Interactive Estimation of Distribution Algorithm with User Generated Contents

Dual Sparse Variational Autoencoder-driven Interactive Estim...

引用

2024 International Conference on New Trends in Computational Intelligence, NTCI 2024

作者： Yang, Hang Bao, Lin Sun, XiaoYan Peng, YuMeng Jiangsu University of Science and Technology School of Automation Zhenjiang China China University of Mining and Technology School of Information and Control Engineering Xuzhou China

ISBN: (纸本)9798331517021

Personalized search and recommendation tasks in a big data environment have attracted wide attention from researchers while also presenting significant *** paper proposed a dual sparse variational autoencoder-driven interactive estimation of distribution algorithm with user generated contents, which considers digging deeper into user generated contents and combining with intelligent evolutionary optimization methods. Firstly, user generated contents in web are extensively collected to build a user interest preference model based on dual sparse variational autoencoders to extract users' preference features. Secondly, the distribution probability is reconstructed according to the neurons of the output layer of the sparse variational autoencoders in the user interest preference model. Combining with Gaussian probability density function, a estimation of distribution sampling probability model based on the user interest preferences is designed in the framework of an interactive estimation of distribution algorithm to generate new individuals with the user preference information. Meanwhile, a user evaluation surrogate model based on the user interest preferences is established by integrating matrix factorizations to participate in a personalized evolutionary search process. Finally, according to new user generated contents and model management mechanisms, the user interest preference model and related models are dynamically updated to guide the interactive personalized evolutionary search for personalized recommendation task. Extensive experiments on various actual public datasets are executed to validate the feasibility, effectiveness and interpretability of the proposed algorithm. It improves the performance of personalized search and recommendation methods. © 2024 IEEE.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Object Detection Methods for Autonomous Driving in Adverse Weather Conditions 3

Object Detection Methods for Autonomous Driving in Adverse W...

引用

3rd International Conference on Electronics and information technology, EIT 2024

作者： Wang, Yuantao Lu, Yuanyao Qiu, Yongsheng Yang, Chaochao North China University of Technology School of Electrical and Control Engineering Beijing China North China University of Technology School of Information Science and Technology Beijing China

ISBN: (纸本)9798350369151

Autonomous driving systems open up a new frontier in the automotive industry, offering new possibilities for future transportation with increased efficiency and a comfortable experience. However, object detection in adverse weather conditions remains a challenge that hinders the advancement of higher-level autonomous driving. This paper provides a detailed report on the latest developments in target detection algorithms under adverse weather conditions. It analyzes the impact of adverse weather on autonomous vehicle sensors, the establishment and use of related datasets, research on image restoration algorithms for adverse weather conditions and their effects on target detection tasks, and the application of domain adaptation methods in transfer learning for target detection. Additionally, the paper discusses future work and potential research areas in this field. © 2024 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Research on the Prediction of Academic Performance Based on ANN-BiLSTM Hybrid Neural Network Model 4

Research on the Prediction of Academic Performance Based on ...

引用

4th IEEE International Conference on information technology, Big Data and Artificial Intelligence, ICIBA 2024

作者： Song, Wei Xing, Jiaqi Ning, Keqing Guo, Wei North China University of Technology School of Information Science and Technology Beijing China North China University of Technology School of Electrical and Control Engineering Beijing China

ISBN: (纸本)9798350363586

With the popularity of online courses and e-learning, a large amount of data on online learning behaviour has been accumulated. How to use these data to predict early students' performance so as to improve teaching effectiveness and learning experience has become an important issue in educational research. Based on this, this paper constructs a hybrid ANN-BiLSTM neural network model by taking advantage of the feature extraction of Artificial Neural Network (ANN) and the advantages of Bi-directional Long Short-Term Memory (BiLSTM) in temporal feature processing. In order to verify the effectiveness of this model, this paper compares it with the Recurrent Neural Network (RNN) model, the Gate Recurrent Unit (GRU), and the ANN-LSTM hybrid neural network (ANN-LSTM) model. Experiments on the UK Open University Learning Analytics dataset showed that the ANN-BiLSTM model had significantly better prediction accuracy and the best predictive performance. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

An Improved Underwater Object Detection Method Based on YOLOv5 7

An Improved Underwater Object Detection Method Based on YOLO...

引用

7th International Conference on Advanced Algorithms and control engineering, ICAACE 2024

作者： Wang, Gang Zhuang, Sheng Zhao, Qiang College Of Mechanical And Control Engineering Jilin Communications Vocational And Technical College Changchun China College Of Mechanical And Control Engineering Baicheng Normal University Baicheng China College Of Information And Control Engineering Jilin Institude Of Chemical Technology Jilin China

ISBN: (纸本)9798350361445

To address the issue of lower accuracy in underwater biological recognition with the YOLOv5s model, we introduce several enhancements, including the Convolutional Block Attention Module (CBAM), Pyramid Pooling Module (PPM) structure, Receptive Field Block (RFB) module, and the Complete IoU (CIOU) loss function. Subsequently, we introduce the RFB module at the model's neck, effectively enhancing the model's perception of the receptive field and extracting multi-scale, rich feature information to improve recognition accuracy. Finally, the incorporation of the CIOU loss function mitigates issues related to gradient explosion or vanishing during model *** results demonstrate that our improved YOLOv5s-Ours model exhibits notable improvements in F1 score (%), precision (P %), recall (R %), and mean average precision (mAP %), with respective increases of 1.25%, 0.19%, 2.01%, and 2.28%. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

VLM-EMO: Context-Aware Emotion Classification with CLIP 5

VLM-EMO: Context-Aware Emotion Classification with CLIP

引用

5th International Seminar on Artificial Intelligence, Networking and information technology, AINIT 2024

作者： Yao, Yanyin Mei, Xue Xu, Jianping Sun, Zhichuang Zeng, Cheng Chen, Yuming Nanjing Tech University College of Electrical Engineering and Control Science Nanjing China Science and Technology On Information Systems Engineering Laboratory Nanjing China

ISBN: (纸本)9798350385557

Emotion recognition is a pivotal component in various sectors, including medical care, education, service industries, and public safety, due to its potential to enhance interaction and understanding within these contexts. Historically, traditional methods of emotion recognition have primarily concentrated on analyzing facial expressions. While effective to a degree, this approach offers restricted capacity for encoding context, and unable to capture the breadth and depth of emotional responses. In this paper, we proposed the VLM-EMO Model, a novel approach that enhances the capabilities of VLM (Visual Language Model) in the domain of emotion recognition. While VLM itself is a powerful tool for understanding the correlation between images and text, the VLM-EMO Model fine-tunes this ability to focus more intricately on emotional aspects within visual data. This is achieved by integrating emotional intelligence into the model's architecture, allowing it to discern subtle emotional cues and contexts within images. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Integrated Multimodal Fault Diagnosis of Industrial Gearboxes Using Vibration Signals and Infrared Thermal Imaging 15

Integrated Multimodal Fault Diagnosis of Industrial Gearboxe...

引用

15th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Beijing 2024

作者： Cao, Xunqi Li, Yan Yu, Kun Zhang, Yongchao School of Information and Control Engineering China University of Mining and Technology Xuzhou China School of Mechanical Engineering and Automation Northeastern University Shenyang China

ISBN: (纸本)9798350354010

With the increasing demand for precision in fault diagnosis of gearboxes in complex systems, diagnostic methods based solely on vibration signal characteristics have shown limitations. Therefore, multimodal information fusion technology has become a new trend in the field of gearbox fault diagnosis. This article innovatively proposes a multimodal diagnostic method that combines vibration signals with thermal images, aiming to use thermal imaging technology to intuitively capture the thermal changes during gearbox operation and integrate vibration signals to comprehensively reflect fault characteristics. By introducing Convolutional Neural Networks (CNN) for feature depth extraction, this method effectively improves the parsing ability of fault information, thereby enhancing the accuracy and reliability of fault diagnosis. Experimental data confirms that compared to diagnostic methods using a single signal source, the method proposed in this paper performs well in fault detection of helical gearboxes, significantly improving diagnostic accuracy and precision. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Finite Sample Frequency Domain Identification 63

Finite Sample Frequency Domain Identification

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Tsiamis, Anastasios Abdalmoaty, Mohamed Smith, Roy S. Lygeros, John Automatic Control Laboratory Department of Information Technology and Electrical Engineering Eth Zürich Zürich8092 Switzerland

ISBN: (纸本)9798350316339

We study non-parametric frequency-domain system identification from a finite-sample perspective. We assume an open loop scenario where the excitation input is periodic and consider the Empirical Transfer Function Estimate (ETFE), where the goal is to estimate the frequency response at certain desired (evenly-spaced) frequencies, given input-output samples. We show that under sub-Gaussian colored noise (in timedomain) and stability assumptions, the ETFE estimates are concentrated around the true values. The error rate is of the order of O((du+Sdu dy) SM / N tot ), where N tot is the total number of samples, M is the number of desired frequencies, and du, dy are the dimensions of the input and output signals respectively. This rate remains valid for general irrational transfer functions and does not require a finite order state-space representation. By tuning M, we obtain a N tot -1 / 3 finite-sample rate for learning the frequency response over all frequencies in the H∞ norm. Our result draws upon an extension of the Hanson-Wright inequality to semi-infinite matrices. We study the finite-sample behavior of ETFE in simulations. © 2024 IEEE.

关键词： Frequency response

来源：评论

学校读者我要写书评

暂无评论

Fuzzing:Progress,Challenges,and Perspectives

引用

Computers, Materials & Continua 2024年第1期78卷 1-29页

作者： Zhenhua Yu Zhengqi Liu Xuya Cong Xiaobo Li Li Yin Institute of Systems Security and Control College of Computer Science and TechnologyXi'an University of Science and TechnologyXi'an710054China School of Mathematics and Information Science Baoji University of Arts and SciencesBaoji721013China Institute of Systems Engineering Macao University of Science and TechnologyTaipaMacaoChina

As one of the most effective techniques for finding software vulnerabilities,fuzzing has become a hot topic in software *** feeds potentially syntactically or semantically malformed test data to a target program to mine vulnerabilities and crash the *** recent years,considerable efforts have been dedicated by researchers and practitioners towards improving fuzzing,so there aremore and more methods and forms,whichmake it difficult to have a comprehensive understanding of the *** paper conducts a thorough survey of fuzzing,focusing on its general process,classification,common application scenarios,and some state-of-the-art techniques that have been introduced to improve its ***,this paper puts forward key research challenges and proposes possible future research directions that may provide new insights for researchers.

关键词： Fuzzing vulnerability software testing software security

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：