检索结果-内蒙古大学图书馆

2021 International Conference on Intelligent Power and Systems, ICIPS 2021

作者： Sun, X.M. Zhang, Y.J. Wang, H. Du, Y.X. School of Computer Science and Software Engineering University of Science and Technology Liao Ning China

In order to achieve ship target detection based on remote sensing images in complex backgrounds, this paper proposes a ship target detection algorithm based on YOLO V5. First, the improved Kmeans is used to cluster the data set, DIOU_loss is used for the candidate frame selection strategy, and finally the channel attention mechanism is introduced. The experimental results show that under the same conditions, the improved network has a slight decrease in detection speed compared with the original YOLOv5 network, and the effect of images with densely distributed small targets is significantly improved. On the same test set, the accuracy rate is reduced by 3.84%, the recall rate is increased by 32.73%, and mAP is increased by 22.48%. © Published under licence by IOP Publishing Ltd.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Improving Generalization for Hyperspectral Image Classification:The Impact of Disjoint Sampling on Deep Models

引用

computers, Materials & Continua 2024年第10期81卷 503-532页

作者： Muhammad Ahmad Manuel Mazzara Salvatore Distefano Adil Mehmood Khan Hamad Ahmed Altuwaijri Department of Computer Science National University of Computer and Emerging SciencesChiniot35400Pakistan Institute of Software Development and Engineering Innopolis UniversityInnopolis420500Russia Dipartimento di Matematica e Informatica—MIFT University of MessinaMessina98121Italy School of Computer Science University of HullHullHU67RXUK Department of Geography College of Humanities and Social SciencesKing Saud UniversityRiyadh11451Saudi Arabia

Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art(SOTA)models e.g.,Attention Graph and Vision *** training,validation,and test sets overlap or share data,it introduces a bias that inflates performance metrics and prevents accurate assessment of a model’s true ability to generalize to new *** paper presents an innovative disjoint sampling approach for training SOTA models for the Hyperspectral Image Classification(HSIC).By separating training,validation,and test data without overlap,the proposed method facilitates a fairer evaluation of how well a model can classify pixels it was not exposed to during training or *** demonstrate the approach significantly improves a model’s generalization compared to alternatives that include training and validation data in test data(A trivial approach involves testing the model on the entire Hyperspectral dataset to generate the ground truth *** approach produces higher accuracy but ultimately results in low generalization performance).Disjoint sampling eliminates data leakage between sets and provides reliable metrics for benchmarking progress in *** sampling is critical for advancing SOTA models and their real-world application to large-scale land mapping with Hyperspectral ***,with the disjoint test set,the performance of the deep models achieves 96.36%accuracy on Indian Pines data,99.73%on Pavia University data,98.29%on University of Houston data,99.43%on Botswana data,and 99.88%on Salinas data.

关键词： Hyperspectral image classification disjoint sampling Graph CNN spatial-spectral transformer

来源：评论

学校读者我要写书评

暂无评论

Predicting Travel Time in Complex Road Structures using Deep Learning 14

Predicting Travel Time in Complex Road Structures using Deep...

引用

2024 IEEE 14th Annual Computing and Communication Workshop and Conference, CCWC 2024

作者： Nampalli, Vignaan Vardhan Gudla, Charan Rana, Md Shohel Mississippi State University Computer Science and Engineering StarkvilleMS United States Florida Gulf Coast University Computing and Software Engineering Fort MyersFL United States

ISBN: (纸本)9798350360134

Vehicular traffic and congestion is a major challenge worldwide because of rapid growth in urban population. The congestion can be mitigated to enhance traffic management by predicting accurate travel time of the vehicles in the traffic. This research developed a novel methodology utilizing machine learning on real-time traffic data collected through Bluetooth sensors deployed at traffic intersections to estimate travel time. The research evaluates performance and accuracy of five different prediction systems for travel time estimation highlighting the effectiveness of the machine learning models in accurately predicting travel time. The research also explores the development of the machine learning model predicting the travel time during peak hours, considering traffic lights impact on travel time between intersections. This research findings contribute to the efficient and reliable travel time prediction systems development, helping commuters making informed decisions and improve traffic management strategies. © 2024 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Device Action Prediction Based on K-means and Apriori for Smart Home

Device Action Prediction Based on K-means and Apriori for Sm...

引用

2022 IEEE Asia-Pacific Conference on Image Processing, Electronics and computers, IPEC 2022

作者： Liu, Qinghua Shi, Tianwei Ren, Ling University of Science and Technology Liaoning School of Computer Science and Software Engineering Anshan China

ISBN: (纸本)9781665409025

This paper proposes to use K-means and Apriori to prediction device action based on time in Smart Home System. In the existing methods, the system provides services to human when conditions are met, such as high temperature and low humidity. However, those methods ignoring the correlation between device action and human activity time. In order to solve this problem, we combine K-means and Apriori algorithm to generate association rules with time information. First, calculate the appropriate K-value for K-means. We select consecutive data in weeks. The data contains the time information of device action. Second, run K-means to classify based on device action time information, and run Apriori to mine association rules based on classification. Finally, decode the associate rules and realize device action prediction. In our work, K-means experiments show that clustering according to the difference of working days is an effective way to process user time information;Apriori experiments proved that the association rules mined with the results of K-means can predict device actions in the Smart Home environment. © 2022 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

The Emergence of IIoT and its Cyber Security Issues in Critical Information Infrastructure 21

The Emergence of IIoT and its Cyber Security Issues in Criti...

引用

21st European Conference on Cyber Warfare and Security, ECCWS 2022

作者： Bhaiyat, Humairaa Yacoob Sithungu, Siphesihle Philezwini Academy of Computer Science and Software Engineering Faculty of Science University of Johannesburg South Africa

ISBN: (纸本)9781914587405

The emergence of the Industrial Internet of Things (IIoT) can transform and improve industrial domain processes. This is achieved by IIoT’s ability to collect and process vast amounts of data using technology such as sensors. IIoT capabilities can improve the manufacturing processes of these sectors and contribute to the improved functioning of critical information infrastructure. In addition, current trends - such as the Fourth Industrial Revolution (4IR) - use IIoT to realise specific goals. While the emergence of IIoT systems does introduce many benefits, such as improved efficiency and sustainability, it can also introduce security concerns. These security concerns pose a significant threat to the industrial domain, including critical information infrastructures. The resulting threats emphasise the need to implement solutions to secure IIoT systems. The paper aims to discuss the emergence of IIoT and its cyber security issues within the context of critical information infrastructure. The research paper follows a theoretical research methodology to provide an improved understanding of the emergence of IIoT and its cyber security issues in critical information infrastructure. The paper contains an exhaustive discussion of what is IIoT. A discussion on where IIoT fits within the context of critical information infrastructure and its impact on 4IR is also highlighted in the paper. Due to the many vulnerabilities that IIoT systems can contain, the paper also discusses security concerns surrounding the emergence of IIoT. The security concerns make IIoT systems attractive targets for cyberattacks. Therefore, different approaches that can be applied to secure IIoT systems is also provided. Since IIoT capabilities can impact the critical information infrastructure of businesses and nations, the authors’ stance on how IIoT systems could transform the current understanding of critical information infrastructure is also discussed. © 2022 Curran Associates Inc.. All rights r

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Resilient and Reliable Communication for First Responders with Ad-Hoc Network and MPTCP

Resilient and Reliable Communication for First Responders wi...

引用

2022 International Conference on Networking and Network Applications, NaNA 2022

作者： Cui, Yue Lim, Alvin Yan, Yufei Kulkarni, Abhishek Lan, Tianhang Computer Science and Software Engineering Auburn University Auburn United States

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

In severe hazardous situations, reliable network communication is an important infrastructure for conveying vital real-time information from sensors embedded in first responders. Important communications and emergency information must be received quickly to make critical decisions, improve situation awareness, and save lives. It is always challenging to ensure that the network is continuously available. To ensure seamless, fault-tolerant, and secure communication, we propose a new communication system for first responders. In this novel architecture, we improve the reliability of our communication networks using three techniques: Multi-Path TCP (MPTCP), Optimized Linked State Routing Protocol (OLSR) and Message Queuing Telemetry Transport (MQTT) for portable devices and cloud services. MPTCP enables rapid recovery when a TCP connection fails. OLSR enables routes through Ad Hoc networks. MQTT enables efficient transmission of sensor data. We have implemented the above reliable communication network and conducted various experiments to show improvement in reliability. The results show that our proposed method can be quickly deployed and provides reliability in the communication network despite the failure of some network infrastructures. © 2022 IEEE.

关键词： Ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Modif-SegUnet: Innovatively Advancing Liver Cancer Diagnosis and Treatment through Efficient and Meaningful Segmentation of 3D Medical Images

Modif-SegUnet: Innovatively Advancing Liver Cancer Diagnosis...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Wang, Chenhang Jin, Yujian Liang, Jiayi Yang, YuHan Nie, Shanling Hai, Yang East China University of Science and Technology Department of Computer Science and Engineering Shanghai China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China The University of Sydney Faculty of Engineering Sydney Australia

ISBN: (纸本)9798350337488

Hepatocellular Carcinoma (HCC) holds a record of high incidence and severe global harm. In tasks of liver cancer segmentation based on 3D medical images, the majority of methods have endeavored to enhance the 3D U-net by integrating the latest modules from the field of computer Vision (such as the transformer), often overlooking the distinct characteristics of liver components. We introduced a novel deep learning architecture, Modif-SegUnet, to circumvent this limitation. This architecture extends the U-net model by incorporating a 3D-modifiable attention module, thereby fostering a heightened focus on distinguishing between normal liver sections and lesions. Furthermore, Modif-SegUnet ingeniously amalgamates the 3D-modifiable attention module with the Modif-transformer block, enabling efficient capture of relevant and valuable full-text information in CT images that contain liver or tumor regions. We subjected the proposed Modif-SegUnet to evaluation on the Liver Tumor Segmentation benchmark dataset. Experimental outcomes indicate that our methodology surpasses state-of-the-art approaches in liver tumor segmentation, suggesting potential pathways for advancing the diagnosis and treatment of liver cancer. © 2023 IEEE.

关键词： 3D medical image attention CT Liver cancer Segmentation transformer U-Net

来源：评论

学校读者我要写书评

暂无评论

Improved Kernel Fuzzy C-Means Clustering Method Based on Smart Grid 5

Improved Kernel Fuzzy C-Means Clustering Method Based on Sma...

引用

5th World Conference on Mechanical engineering and Intelligent Manufacturing, WCMEIM 2022

作者： Niu, Shuqi Zhang, Zhao Tian, Xintong Zhao, Xueyan School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

ISBN: (纸本)9781665473699

The improved kernel fuzzy clustering method is used to classify the load data of the smart grid accurately. It lays a good foundation for the subsequent work of power load forecasting and provides a more efficient, safe, and reliable direction for the operation of the power system. Firstly, the collected power load data is preprocessed to reduce data redundancy and improve data quality. Secondly, the kernel fuzzy C-means clustering algorithm based on particle swarm optimization is used to cluster the load data with the same power consumption characteristics. Finally, the improved kernel fuzzy clustering method is compared with the fuzzy C-means clustering method through a simulation example to verify the effectiveness of this method. © 2022 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Federated Learning-Assisted Self-supervised CNN for Monkeypox Diagnosis

Federated Learning-Assisted Self-supervised CNN for Monkeypo...

引用

2023 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2023

作者： Jahan, Nusrat Bajwa, Garima Akilan, Thangarajah Lakehead University Electrical and Computer Engineering Thunder Bay Canada Lakehead University Computer Science Thunder Bay Canada Lakehead University Software Engineering Thunder Bay Canada

ISBN: (纸本)9798350329698

Monkeypox (Mpox) is a contagious viral illness that affects both humans and animals, and its early diagnosis is critical for the effective management and prevention of this disease. This work proposes a federated learning-Assisted self-supervised convolutional neural network (CNN) for Mpox identification from skin lesion images. The demand for domain experts for ground truth annotations is reduced with the help of self-supervised learning, as it can process unlabeled data. The self-supervision is driven by a framework called simple contrastive learning for representations (SimCLR), which extracts discriminative patterns of Mpox from the skin lesion images. Federated learning (FL), on the other hand, enables a privacy-preserved collaborative training approach to build the Mpox classifier on vast diverse datasets from several healthcare institutions, remotely. Thorough experimental study on a publicly available benchmark dataset, the proposed approach achieves competitive performances. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Regularized forensic efficient net: a game theory based generalized approach for video deepfakes detection

引用

Multimedia Tools and Applications 2024年 1-44页

作者： Ain, Qurat Ul Javed, Ali Malik, Khalid Mahmood Irtaza, Aun Department of Computer Science University of Engineering and Technology-Taxila Punjab Taxila47050 Pakistan Department of Software Engineering University of Engineering and Technology-Taxila Punjab Taxila47050 Pakistan College of Innovation and Technology University of Michigan-Flint FlintMI48502 United States

Due to the advancements in cutting-edge generative AI algorithms, generating hyper realistic deepfake videos has become easier for the public. This hyperrealism consequently fails contemporary methods to reliably discriminate between original and fake videos. Therefore, to counter any threat caused by these next-generation artificially generated videos, dependable approaches are required to address this classification challenge. To achieve this objective this paper presents an interdisciplinary approach that integrates game theory with deep learning to bring a novel solution to the problem of deepfake detection and protect the detectors against anti-forensics attack. To the best of our knowledge, there does not exist any other work dedicated to video deepfake detection using the integrated approach of game theory and deep learning. The game is designed for two players to distinguish between pristine and deepfake videos. The game utilizes different strategies for the data manipulator as a player P1 and the deepfake detector as P2. Strategies used for P1 involve the formation of the subsets like open and close-set, combined subsets, imbalanced dataset, and post-processing attacks to create challenging strategies for P2. To counter the strategies of P1,we propose a novel Regularized Forensic Efficient Net (RFE Net) that employs regularization techniques, such as batch normalization, dropout, augmentation, and early stopping. Based on the P1 move, the detector chooses the regularization techniques by considering factors such as generalizability and efficiency. Regularization-based strategies improve the performance of our model when compared to contemporary methods. Computation of the Nash equilibrium with the proposed zero-sum game helps to effectively detect deepfakes and leads the game to maximum payoff. Performance of the proposed game theory-based RFE Net was measured on standard and diverse datasets of FaceForensic++, DFDC preview, CelebDF, DFFD, and the World lea

关键词： Nash equilibrium

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：