检索结果-内蒙古大学图书馆

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

Accuracy-Aware Low-Complexity Deep Learning Models for Automatic Modulation Recognition 1

Accuracy-Aware Low-Complexity Deep Learning Models for Autom...

引用

1st International Conference on Computing, Internet of Things and Microwave Systems, ICCIMS 2024

作者： Vaziri, Mobin Vakili, Shervin Pierre Langlois, J.M. Polytechnique Montréal Department of Computer and Software Engineering Canada Montréal Canada

ISBN: (纸本)9798350351736

This paper explores the design of Deep Learning (DL) models for Automatic Modulation Recognition (AMR) in wireless communications. The primary goal is to enhance the efficiency and hardware compatibility of convolutional neural networks (CNNs) for AMR through hyperparameter tuning and model compression. The paper first examines the effectiveness of applying quantization and pruning on the accuracy and compu-tational cost of two prominent CNN models from the literature. It then introduces a new CNN model that achieves superior accu-racy with lower computational complexity compared to previous work. The design flow integrates TensorFlow Lite for pruning and quantization, and NVIDIA TensorRT for benchmarking on GPUs specialized for machine learning computing. Experimental results show significant reductions in model size and computational complexity while maintaining accuracy, rendering the proposed DL models suitable for real-time applications on edge devices. © 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

Understanding Blockchain Trilemma, Causes and Solutions 17

Understanding Blockchain Trilemma, Causes and Solutions

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart Data, SmartData 2024

作者： Chaudhary, Monu Bhunia, Suman Miami University Department of Computer Science and Software Engineering OxfordOH United States

ISBN: (纸本)9798350351637

With extensive research and development in blockchain technology, the concern about scalability, security, and decentralization is still evident. Blockchain trilemma describes that it is realistically impossible to simultaneously achieve a high level of decentralization, security, and scalability. However, new developments in the sector of blockchain are making progress in simultaneous achievement of these three aspects. Layer 1 blockchain is the base level of blockchain network architecture. It includes blockchain networks like Bitcoin, Ethereum, etc. However, the Layer 1 blockchain network faces scalability issues. Layer 2 blockchain is a network built on top of Layer 1 blockchain to help eliminate scalability issues. This paper presents a comparative analysis of Layer 1 and Layer 2 blockchain networks and different approaches to solving the blockchain trilemma in Layer 1 and Layer 2 blockchain networks. From the study, we found that Layer 2 blockchain networks are easier and faster to implement. © 2024 IEEE.

关键词： Blockchain Blockchain Trilemma Decentralization Scalability Security

来源：评论

学校读者我要写书评

暂无评论

PDC-ViT: source camera identification using pixel difference convolution and vision transformer

引用

Neural Computing and Applications 2025年第9期37卷 6933-6949页

作者： Elharrouss, Omar Akbari, Younes Almadeed, Noor Al-Maadeed, Somaya Khelifi, Fouad Bouridane, Ahmed Department of Computer Science and Software Engineering United Arab Emirates University Al Ain United Arab Emirates Department of Computer Science and Engineering Qatar University Doha Qatar Northumbria University Newcastle Newcastle upon Tyne United Kingdom University of Sharjah Sharjah United Arab Emirates

Source camera identification has emerged as a vital solution to unlock incidents involving critical cases like terrorism, violence, and other criminal activities. The ability to trace the origin of an image/video can aid law enforcement agencies in gathering evidence and constructing the timeline of events. Moreover, identifying the owner of a certain device narrows down the area of search in a criminal investigation where smartphone devices are involved. This paper proposes a new pixel-based method for source camera identification, integrating Pixel Difference Convolution (PDC) with a Vision Transformer network (ViT), and named PDC-ViT. While the PDC acts as the backbone for feature extraction by exploiting Angular PDC (APDC) and Radial PDC (RPDC). These techniques enhance the capability to capture subtle variations in pixel information, which are crucial for distinguishing between different source cameras. The second part of the methodology focuses on classification, which is based on a Vision Transformer network. Unlike traditional methods that utilize image patches directly for training the classification network, the proposed approach uniquely inputs PDC features into the Vision Transformer network. To demonstrate the effectiveness of the PDC-ViT approach, it has been assessed on five different datasets, which include various image contents and video scenes. The method has also been compared with state-of-the-art source camera identification methods. Experimental results demonstrate the effectiveness and superiority of the proposed system in terms of accuracy and robustness when compared to its competitors. For example, our proposed PDC-ViT has achieved an accuracy of 94.30%, 84%, 94.22% and 92.29% using the Vision dataset, Daxing dataset, Socrates dataset and QUFVD dataset, respectively. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Neural Transformers for Bias Detection: Assessing Pakistani News 5

Neural Transformers for Bias Detection: Assessing Pakistani ...

引用

5th International Conference on Advancements in Computational Sciences, ICACS 2024

作者： Ali, Owais Zaland, Zubair Bazai, Sibghat Ullah Ghafoor, Muhammad Imran Hussain, Laiq Haider, Arsalan Buitems Department of Software Engineering Quetta Pakistan Buitems Department of Computer Engineering Quetta Pakistan Pakistan Television Corporation Department of Engineering Lahore Pakistan Buitems Department of Electrical Engineering Quetta Pakistan

ISBN: (纸本)9798350394764

Political bias in the media poses a significant persuasive challenge within today's literary landscape, capable of reshaping individuals' perspectives and judgments. Therefore, it becomes imperative to categorize such biases in literature. One manifestation of bias is evident through word choice, a complex task due to the absence of standardized datasets and classification models. Transformer-based models proved highly effective in bias classification, and this research contributes to this field by evaluating classifiers, particularly ConvBERT, known for their exceptional performance in previous bias identification studies. Our models are trained using distant supervision and domain-aware pretraining, two successful techniques with impressive outcomes. Additionally, the study assesses various hyperparameters for ConvBERT and the most proficient models from prior research, revealing ConvBERT's remarkable potential in bias detection and achieving a peak macro F1 score of 0.815. Furthermore, the top-performing model was employed to discern the political bias in Pakistani media, classifying the Pakistani news dataset to elucidate prevailing political inclinations and leniencies within the current media landscape. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Method for Semi-Biometric Information Based User Identification in AR and VR Applications

A Multimodal Method for Semi-Biometric Information Based Use...

引用

2024 IEEE International Performance, Computing, and Communications Conference, IPCCC 2024

作者： Li, Han Lyu, Ke Dossett, Owen Feng, Xianglong Miami University Department of Computer Science and Software Engineering Oxford45056 United Kingdom

ISBN: (纸本)9798350367942

Virtual Reality (VR) and Augmented Reality (AR) have witnessed a surge in popularity, revolutionizing various industries and enhancing user experiences. As these technologies continue to evolve, ensuring secure user identification becomes increasingly important. However, existing identification methods often come with vulnerabilities or require costly hardware implementations. To address these challenges, we propose a novel semi-biometric information-based user identification approach leveraging multimodal techniques. By analyzing the user's viewing patterns and gaze behavior in the runtime, we can accurately identify individuals. This approach offers a promising solution for seamless user identification in VR and AR applications, without compromising on user experience or requiring expensive hardware modifications. To verify the efficiency of our proposed algorithm, we test our algorithm using a public dataset, the result of which shows a high classification accuracy. Additionally, beyond traditional evaluation metrics, we perform a transferability test, demonstrating the adaptability of our solution to new scenarios with robust generality. © 2024 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Detection of Conspiracy vs. Critical Narratives and Their Elements using NLP 25

Detection of Conspiracy vs. Critical Narratives and Their El...

引用

25th Working Notes of the Conference and Labs of the Evaluation Forum, CLEF 2024

作者： Albladi, Aish Seals, Cheryl D. Department of Computer Science and Software Engineering Auburn University AuburnAL United States

The growing use of digital media or social media has given a platform to the people to deliver their ideas and viewpoints openly. It is facilitating the rapid spread of contrasting opinions openly. Ultimately, this has developed echo chambers or polarized platforms. These platforms either encourage conspiracy theories or critical narratives. So, nowadays, it has become crucial for people to be aware of being part of such narratives. Moreover, it is also necessary for the organisations to identify the conspiracy creators or the ones who do not possess a conspiracy mentality. This can be made possible by the use of natural language processing techniques to do this task automatically. This study presents the solutions to the two most pressing challenges in today's era. The subtask one of this study provides a solution for the identification of conspiracy narratives and critical narratives using the BERT model. Our model achieved an MCC score of 0.80. Secondly, the other subtask helps to recognize the span of the topic relevant to the important constituents of both categories of oppositional narratives, i.e., agent, facilitator, victim, campaigner, objective, negative effect. The overall accuracy of the model is 95%. These models can be used for the development of an algorithm that can automatically classify the conspiracy theories and critical narratives. © 2024 Copyright for this paper by its authors.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Synergistic Integration of Blockchain and software-Defined Networking in the Internet of Energy Systems 6

Synergistic Integration of Blockchain and Software-Defined N...

引用

6th International Conference on Blockchain Computing and Applications, BCCA 2024

作者： Hayyolalam, Vahideh Zekiye, Abdulrezzak Abuzahra, Hamza Özkasap, Öznur Karakus, Murat Guler, Evrim Uludag, Suleyman Department of Computer Engineering Koç University İstanbul Turkey Department of Software Engineering Ankara University Ankara Turkey Department of Computer Engineering Bartin University Bartin Turkey Department of Computer Science University of Michigan FlintMI United States

ISBN: (纸本)9798350351538

Peer-to-peer (P2P) energy trading, Smart Grids (SG), and electric vehicle energy management are integral components of the Internet of Energy (IoE) field. The integration of software-Defined Networks (SDNs) and Blockchain (BC) technologies into the IoE domain offers potential benefits that have only been studied in the literature in a few works. In this paper, we investigate the state-of-art solutions that leverage both SDNs and blockchain within the realm of the IoE. We categorize these solutions based on the method of integrating SDN and BC into two categories. The first category is the blockchain for SDN, where blockchain enhances the SDN directly. The second category is blockchain and SDN, where both technologies are used to enhance the proposed solutions. We identify three distinct blockchain applications based on their usage: decentralizing the SDN control plane, serving as a decentralized platform, and improving security measures. Similarly, we observe that SDN serves as a performance enhancer, a substitute for traditional networking, and solely as a control and management framework. It is posited that integrating SDNs and blockchain into IoE leads to performance enhancements, improves security, enables decentralized operations, and eliminates single points of failure in the SDN control plane. Additionally, some unaddressed issues, such as energy efficiency, smart contract management, and scalability, are discussed as potential future directions. © 2024 IEEE.

关键词： Internet of Energy

来源：评论

学校读者我要写书评

暂无评论

ACDD: Automated COVID Detection using Deep Neural Networks

引用

IEIE Transactions on Smart Processing and Computing 2023年第6期12卷 518-525页

作者： Raza, Ghulam Musa Shoaib, Muhammad Kim, Byung-Seo Department of Software and Communications Engineering Hongik University Sejong Korea Republic of School of Electrical Engineering and Computer Science National University of Science and Technology Islamabad Pakistan

December 2019 witnessed the outbreak of a novel coronavirus, thought to have started in the Chinese city of Wuhan. The situation worsened owing to its quick spread across the globe, leading to a worldwide pandemic that became known as COVID-19. To suppress the pandemic, early detection of positive COVID-19 patients has become highly important. There is a lack of precise automated tool kits available for use in diagnosing medical conditions, so auxiliary diagnostic tools are in high demand. Important information about this virus can be extracted from X-ray images, which can be used in conjunction with advanced artificial intelligence. This study addresses the unavailability of physicians in remote areas, and the complex algorithm proposed in this study can find potential matches for patients in rural areas who need care. This could help to improve access to care for those who need it most. The purpose of this study is to develop a novel model that can automatically detect COVID-19 by utilizing chest X-ray images. The proposed model incorporates binary and multi-class classification and can be employed by radiologists for timely detection of the COVID-19 virus in an effective manner. © 2023 The Institute of Electronics and Information Engineers.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Distance Measurement of Tunnel Facilities for Monocular Camera-based Localization

引用

Journal of Institute of Control, Robotics and Systems 2023年第1期29卷 7-14页

作者： Kim, Jongkwang Kim, Hyoungrae Oh, Jangsub Li, Xingyou Jang, Kyeongjun Kim, Hakil Department of Electrical and Computer Engineering Inha University Korea Republic of Program in Future Vehicle Engineering Inha University Korea Republic of Department of Smart Mobility Engineering Inha University Korea Republic of

The GNSS signal used for vehicle localization exhibits a shaded area such as a tunnel. To accurately estimate the location in the shaded area, the accumulated position error must be compensated with information obtained from a separate sensor. When a monocular camera is selected as an additional sensor, the process of measuring the relative distance after detecting objects in a tunnel should be performed before using these data as an indicator. This paper presents a modified inverse perspective transformation model that projects image pixels to the plane parallel to the ground. The image pixels are projected to the plane accounting for the distance and the height of the facility in the tunnel. Then, through the transformation model, the distance of the facility in the tunnel can be measured using a single camera sensor. The Samsungsan Tunnel located on National Highway 110 in South Korea was chosen for the experiment. The estimated distance results by the proposed method were compared with the LiDAR measurements obtained real-time time by computing the position errors for the longitudinal and lateral directions, separately. This study demonstrates the possibility of estimating a distance with only a monocular camera for precise positioning even in a tunnel. © ICROS 2023.

关键词： Optical radar

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：