检索结果-内蒙古大学图书馆

2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

作者： Gao, Zu-Kang Ma, Le-Ming Li, Mei-Ting Zhao, Gen Li, Mark Jun-Jie College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9798350303780

Anomaly detection in dynamic graphs has drawn increasing attention in social networks, e-commerce, and cybersecurity etc. Capturing the evolution patterns using temporal features is crucial for dynamic graphs anomaly detection. However, existing approaches do not thoroughly consider the long-term and short-term temporal features, which lead to the loss of information about the evolution patterns of dynamic graphs. In this paper, we propose a end-to-end an anomaly detection algorithm in dynamic graphs via Long Short-term Temporal Attention network (GraphLSTA). GraphLSTA captures the evolution patterns of dynamic graphs by effectively extracting and fusing the long-term and short-term temporal features through a recurrent attention mechanism, improving the detection performance. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

MDEV Model:A Novel Ensemble-Based Transfer Learning Approach for Pneumonia Classification Using CXR Images

引用

computer Systems Science & engineering 2023年第7期46卷 287-302页

作者： Mehwish Shaikh Isma Farah Siddiqui Qasim Arain Jahwan Koo Mukhtiar Ali Unar Nawab Muhammad Faseeh Qureshi Department of Software Engineering Mehran University of Engineering and TechnologyJamshoroPakistan College of Software Sungkyunkwan UniversitySuwonKorea Department of Computer Systems Mehran University of Engineering and TechnologyJamshoroPakistan Department of Computer Education Sungkyunkwan UniversitySeoulKorea

Pneumonia is a dangerous respiratory disease due to which breathing becomes incredibly difficult and painful;thus,catching it early is *** physicians’time is limited in outdoor situations due to many patients;therefore,automated systems can be a *** input images from the X-ray equipment are also highly unpredictable due to variances in radiologists’***,radiologists require an automated system that can swiftly and accurately detect pneumonic lungs from chest *** medical classifications,deep convolution neural networks are commonly *** research aims to use deep pretrained transfer learning models to accurately categorize CXR images into binary classes,i.e.,Normal and *** MDEV is a proposed novel ensemble approach that concatenates four heterogeneous transfer learning models:Mobile-Net,DenseNet-201,EfficientNet-B0,and VGG-16,which have been finetuned and trained on 5,856 CXR *** evaluation matrices used in this research to contrast different deep transfer learning architectures include precision,accuracy,recall,AUC-roc,and *** model effectively decreases training loss while increasing *** findings conclude that the proposed MDEV model outperformed cutting-edge deep transfer learning models and obtains an overall precision of 92.26%,an accuracy of 92.15%,a recall of 90.90%,an auc-roc score of 90.9%,and f-score of 91.49%with minimal data pre-processing,data augmentation,finetuning and hyperparameter adjustment in classifying Normal and Pneumonia chests.

关键词： Deep transfer learning convolution neural network image processing computer vision ensemble learning pneumonia classification MDEV model

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-Inverse-Model-Based Networked Tracking control Frameworks of Time-Varying Signals

引用

IEEE/CAA Journal of Automatica Sinica 2024年第7期11卷 1708-1710页

作者： Shiwen Tong Dianwei Qian Keya Yuan Dexin Liu Yuan Li Jiancheng Zhang the College of Robotics Beijing Union UniversityBeijing 100101China the School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China

Dear Editor,Tracking control in networked environment is a very challenging problem due to the contradiction of rapid response to the time-varying signal and the inevitable delay introduced by networks. This letter has proposed several fuzzy-inverse-model-based network tracking control frameworks which are helpful in handling the system with nonlinear dynamics and uncertainties.

关键词： contradiction letter inverse

来源：评论

学校读者我要写书评

暂无评论

Towards Source-Free Domain Adaptive Semantic Segmentation Via Importance-Aware and Prototype-Contrast Learning

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-13页

作者： Cao, Yihong Zhang, Hui Lu, Xiao Xiao, Zheng Yang, Kailun Wang, Yaonan College of Computer Science and Electronic Engineering Hunan University Changsha China National Engineering Research Center of Robot Vision Perception and Control Technology School of Robotics Hunan University Changsha China College of Engineering and Design Hunan Normal University Changsha China

Domain adaptive semantic segmentation enables robust pixel- wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage limitations in typical unsupervised domain adaptation methods, making it especially relevant in the context of intelligent vehicles. It utilizes a well-trained source model and unlabeled target data to achieve adaptation in the target domain. However, in the absence of source data and target labels, current solutions cannot sufficiently reduce the impact of domain shift and fully leverage the information from the target data. In this paper, we propose an end-to-end source-free domain adaptation semantic segmentation method via Importance-Aware and Prototype-Contrast (IAPC) learning. The proposed IAPC framework effectively extracts domain-invariant knowledge from the well-trained source model and learns domain-specific knowledge from the unlabeled target domain. Specifically, considering the problem of domain shift in the prediction of the target domain by the source model, we put forward an importance-aware mechanism for the biased target prediction probability distribution to extract domain-invariant knowledge from the source model. We further introduce a prototype-contrast strategy, which includes a prototype-symmetric cross-entropy loss and a prototype-enhanced cross-entropy loss, to learn target intra-domain knowledge without relying on labels. A comprehensive variety of experiments on two domain adaptive semantic segmentation benchmarks demonstrates that the proposed end-to-end IAPC solution outperforms existing state-of-the-art methods. The source code is publicly available at https://***/yihong-97/Source-free-IAPC. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

MVDC: A Multi-view Dental Completion Model Based on Contrastive Learning

MVDC: A Multi-view Dental Completion Model Based on Contrast...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yang, Xunyu Deng, Qingxin Huang, Minghan Jiang, Landu Zhang, Dian College of Computer Science and Software Engineering Shenzhen University Guangdong China Guangdong China

ISBN: (纸本)9798350368741

Restoring the patient's occlusal function of broken teeth is a challenging task since tooth texture is very complex, a slight deviation may affect the patient's chewing function and temporomandibular joint function. Therefore, how to efficiently repair the complete shape and real surface of the crown is a critical problem. Traditional technologies are hard to restore complete shape of the dental crown or lack inlay surface details, due to dataset limitations and complexity of missing parts. In this paper, we propose a multi-view crown restoration framework MVDC based on contrastive learning. Specifically, MVDC contains: 1) a multi-view generator with a specially designed loss measurement by using contrastive learning;2) a multi-scale discriminator mechanism able to consider relation and consistency between teeth from different scales;3) an occlusal groove extraction network to extract the occlusal details. We conducted extensive experiments on existing public datasets. The results showcase the superior performance of MVDC. © 2025 IEEE.

关键词： Contrastive learning Multi-view Teeth completion

来源：评论

学校读者我要写书评

暂无评论

Inpainting Technique for Removing Vehicle Logos Using Haar-Like and Fast Marching Methods 8

Inpainting Technique for Removing Vehicle Logos Using Haar-L...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Durmus, Meryem Ergen, Burhan Durmus, Omer Atasoy, Ferhat Samsun University Center for Distance Education Samsun Turkey Firat University College of Engineering Department of Computer Engineering Elazig Turkey Samsun University College of Engineering Department of Software Engineering Samsun Turkey Karabuk University College of Engineering Department of Computer Engineering Karabuk Turkey

ISBN: (纸本)9798331531492

Inpainting is the process of removing an unwanted object or region in an image without degrading the image quality. Inpainting offers a solution to problems such as repairing damaged images or removing unwanted parts of the image. In this study, we focus on the detection of brand logos in vehicle images and the removal of these regions using inpainting. The study consists of two main phases: First, the Haar-like features method is used to detect vehicle logos. Then, the detected logos are removed from the image by applying inpainting with the Fast Marching Method. As a result of the experimental studies, it was found that the methods successfully detected and removed the logos with an accuracy of 98%, and the PSNR value ranged between 25.36 dB and 25.41 dB, and the SSIM value ranged between 0.96692 and 0.96994 while maintaining the image quality. These results show that the proposed method exhibits high performance in removing vehicle logos efficiently. © 2024 IEEE.

关键词： fast marching method haar-like inpainting logo recognition

来源：评论

学校读者我要写书评

暂无评论

Optimization Research on Pedestrian Multi Objects Tracking Model Based on TBD Strategy

Optimization Research on Pedestrian Multi Objects Tracking M...

引用

2023 International Conference on Algorithm, Imaging Processing, and Machine Vision, AIPMV 2023

作者： Wang, Shi Liu, XiangJu Liu, XinShu Chen, JiaHui Wang, XiaoHong Qilu Institute of Technology College of Computer and Communication Engineering Shandong Jinan250200 China College of Artificial Intelligence and Software Liaoning Petrochemical University Liaoning Fushun113001 China College of Information and Control Engineering Liaoning Petrochemical University Liaoning Fushun113001 China

ISBN: (纸本)9781510672444

The main task of pedestrian multi objects tracking technology is to continuously track multiple pedestrian objects simultaneously in video sequences and maintain their unique ID numbers. However, current pedestrian multi objects tracking models still have many problems, such as false detection, missed detection, and frequent ID number switching when pedestrians are obstructed or have overly similar appearances, ultimately leading to tracking failure. Therefore, this paper proposes a pedestrian multi objects tracking model based on TBD strategy. It mainly consists of two parts: pedestrian detector and pedestrian tracker. In terms of pedestrian detectors, this paper uses ES-YOLO pedestrian detectors. In terms of pedestrian trackers, this paper draws on the Omni-scale feature learning module in OSNet to redesign the StrongSORT pedestrian appearance feature extraction network, and ultimately obtains the StrongSORT pedestrian tracker based on omni-scale feature fusion, further enhancing its pedestrian feature extraction ability. In terms of experimental results. The experimental results of the pedestrian multi objects tracking model based on the TBD strategy in this paper on the MOT16 dataset show that the proposed pedestrian multi-objective tracking model can effectively improve the accuracy of pedestrian multi objects tracking and reduce the problem of frequent pedestrian ID number switching. © 2024 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Performance of pre-trained deep learning models for land use land cover classification using remote sensing imaging datasets

引用

Environmental Earth Sciences 2025年第11期84卷 1-36页

作者： Haider, Irfan Khan, Muhammad Attique Masood, Saleha Algamdi, Shabbab Ali Alasiry, Areej Marzougui, Mehrez Nam, Yunyoung Department of Computer Science HITEC University Taxila Pakistan Department of AI College of Computer Engineering and Science Prince Mohammad Bin Fahd University Al-Khobar Saudi Arabia IRC for Finance and Digital Economy King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia Department of Software Engineering College of Computer Science and Engineering Prince Sattam Bin Abdulaziz University Al Kharj Saudi Arabia College of Computer Science King Khalid University Abha61413 Saudi Arabia Department of Computer Science and Engineering Soonchunhyang University Asan31538 Korea Republic of

This study presents a comparative analysis of ten pre-trained convolutional neural network (CNN) models, evaluated across three remote sensing datasets: EuroSat, NWPU, and Earth Hazards (Land Sliding). We investigate the interplay between model architecture and classifier selection by incorporating five different neural network (NN) classifiers, emphasizing their impact on predictive accuracy and computational efficiency. Due to its densely connected architecture, DenseNet201 achieved the highest accuracy—97% on EuroSat, 99.40% on NWPU, and 97.80% on Earth Hazards. In contrast, MobileNetV2, while slightly less accurate, demonstrated superior computational efficiency, recording the shortest prediction times of 39.943 s on EuroSat, 27.482 s on NWPU, and 2.8986 s on Earth Hazards. Additionally, classifier choice significantly influenced performance, with the Wide NN classifier excelling in diverse datasets and the Medium NN classifier optimizing speed. Our findings underscore the importance of balancing accuracy and efficiency in selecting CNN models for remote sensing applications, suggesting future research should explore ensembling techniques and lightweight models to enhance performance. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

APT Detector: Detect and Identify APT Malware Based on Deep Learning Framework 23

APT Detector: Detect and Identify APT Malware Based on Deep ...

引用

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Tang, Binhui Yang, Jialin Li, Xin Cao, Yang Wang, Jie School of Computer and software Chengdu Jincheng College School of Cyber Science and Engineering Sichuan University China School of Computer and software Chengdu Jincheng College China

ISBN: (纸本)9781450399029

Advanced persistent threat (APT) attacks use sophisticated attack techniques and covert command and control (C&C) channels to conduct long-term sustained cyber attacks on specific targets as unobtrusively as possible. Over the past ten years, APT attacks have become increasingly frequent, gradually taking on a highly organized, nationalized, and militarized nature. Because APT malware is highly covert, has a long latency period, and presents characteristics such as diversification, high frequency, and sophistication. In the face of existing detection methods, it is easy for attackers to bypass detection by customizing malware and adapting and configuring tools to the target network. The continuous improvement of network technologies and tools and the complex and diverse attack process make it very difficult to detect unknown APT malware. To address the problems, this paper takes APT malware as the detection object and collects 6777 malware from 20 types of APT attack actors. Through the improved Convolutional Neural network (CNN) model combined with an attention mechanism to complete automatic extraction and weighting of static malware features, which can detect and discover APT malware. Meanwhile, the recognition effect for APT malware is better than other existing methods, which realize the attribution of APT attack groups. © 2023 Copyright held by the owner/author(s).

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimization of Asymmetric PM-Assisted Synchronous Reluctance Motor Based on NSGA-III 7

Multi-Objective Optimization of Asymmetric PM-Assisted Synch...

引用

7th IEEE International Electrical and Energy Conference, CIEEC 2024

作者： Wang, Weinan Wang, Shuo Zhao, Xiaokun Zhu, Liangkuan Liu, Yiqi Wei, Jian College of Computer and Control Engineering Northeast Forestry University Harbin China College of Mechanical and Electrical Engineering Northeast Forestry University Harbin China

ISBN: (纸本)9798350359558

Reluctance motor has the advantages of simple structure, low amount of permanent magnet and high stability. But reluctance motor's limited torque density hinders its widespread application. However, the problem of high torque ripple caused by the asymmetric topology of the permanent magnet still needs further optimization. Firstly, the structure of APMA-SynRM and the parameters to be optimized are introduced. The APMA-SynRM optimization steps are then designed. Then, the range of optimization variables is determined by parametric scanning of APMA-SynRM parameters, and the response surface of APMA-SynRM is established. The final optimal design was obtained by non-dominating genetic algorithm (NSGA-III), In conclusion, the comparison and analysis of the key performance indicators before and after APMA-SynRM optimization are presented. © 2024 IEEE.

关键词： Reluctance motors

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：