检索结果-内蒙古大学图书馆

Hybrid CNN-ViT architecture to exploit spatio-temporal feature for fire recognition trained through transfer learning

引用

Multimedia Tools and Applications 2025年第8期84卷 4703-4732页

作者： Shahid, Mohammad Wang, Hong-Cyuan Chen, Yung-Yao Hua, Kai-Lung Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan Dept. of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan

Fires are becoming one of the major natural hazards that threaten the ecology, economy, human life and even more worldwide. Therefore, early fire detection systems are crucial to prevent fires from spreading out of control and causing destruction. Based on vision sensors, many fire detection techniques have evolved with the recent surge of curiosity in deep learning, which exploits the spatial features of individual images. However, fire can take different forms, scales, and combustion materials can produce different colors, making accurate fire detection from an image challenging. Small fires captured from long-distance cameras lack salient features, further complicating detection. This paper proposes a hybrid structure that uses attention-enhanced convolutional neural networks and vision transformers (CNN-ViT) to detect fire. The proposed CNN-ViT first pays spatial attention to every frame and then aggregates temporal contextual information from neighboring frames to improve detection performance. Due to the limited availability of training fire datasets, the study employs deep transfer learning for feature extraction using pre-trained CNN. We used various metrics to examine the efficacy of the proposed approach. The results showed that the CNN-ViT method outperformed previous models based on spatial-temporal characteristics by achieving a relative improvement in accuracy and F1 score. The satisfactory results on images contaminated with different intensities of noise confirm the robustness of the approach. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

J-NECORA: A Framework for Optimal Resource Allocation in Cloud-Edge-Things Continuum for Industrial Applications With Mobile Nodes

引用

IEEE Internet of Things Journal 2025年第11期12卷 16525-16542页

作者： Pettorali, Marco Righetti, Francesca Vallati, Carlo Das, Sajal K. Anastasi, Giuseppe Univ. of Pisa Dept. of Information Engineering Italy Missouri Univ. of Science and Technology Dept. of Computer Science RollaMO United States

In the Industrial Internet of Things (IIoT) landscape, where the Cloud-to-Things Continuum (C2TC) paradigm is now a reality, industrial applications need to cope with highly heterogeneous network and computing resources. Moreover, many industrial applications also involve Mobile Nodes (MNs). Efficient allocation of network and computing resources to meet the stringent requirements of such applications is often a very challenging task. In this paper, we propose J-NECORA (Joint NEtwork and COmputing Resource Allocation), a comprehensive analytical framework to derive the optimal joint allocation of network and computing resources in the C2TC, that guarantees the application requirements, even in the presence of MNs. If the optimal allocation does not exist, J-NECORA provides a best-effort allocation that minimizes the delay. The proposed framework is highly modular and flexible, and can be easily customized to different scenarios. We validated its effectiveness through simulation experiments, focusing on a specific use case. For the considered scenarios, the performance predicted by our framework matches quite closely the simulation results. © 2014 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Small object detection in diverse application landscapes: a survey

引用

Multimedia Tools and Applications 2024年第41期83卷 88645-88680页

作者： Iqra Giri, Kaisar J. Javed, Mohammed Department of Computer Science Islamic University of Science & Technology Pulwama India Computer Vision & Biometrics Lab Dept. of IT Indian Institute of Information Technology Allahabad India

The importance of object detection within computer vision, especially in the context of detecting small objects, has notably increased. This thorough survey extensively examines small object detection across various applications, consolidating and outlining the available methodologies. Traditional papers on small object detection have focused on specific domains. However, this survey paper incorporates insights from a multitude of domains, providing a comprehensive understanding of the versatility and applicability of small object detection techniques. This paper sheds light on the key challenges faced and delves into potential solutions to address the challenges, offering insights into viable solutions to enhance small object detection performance, setting it apart from existing literature. The strategies identified in our survey encompass a spectrum of approaches, categorized as transformer-based, CNN, and traditional methods. Also, this paper collates prevalent datasets relevant to small object detection, simplifying access to these resources. Further, it provides a succinct overview of diverse evaluation metrics used for performance assessment in this field, enhancing understanding of the effectiveness and proficiency of these methods. This survey paper not only consolidates established knowledge but also highlights innovative viewpoints, providing a comprehensive and enlightening compilation that contributes to the advancement of small object detection in the field of computer vision. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Integrated Framework with Enhanced Primitives for Post-Quantum Cryptography: HEDT and ECSIDH for Cloud Data Security and Key Exchange

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第11期49卷 165-176页

作者： Ilias, Shaik Mohammad Sharmila, V. Ceronmani Durga, V. Sathya Dept. of Computer Science and Engineering Hindustan Institute of Technology and Science Chennai India Department of Information Technology Hindustan Institute of Technology and Science Chennai India Department of Computer Science&Engineering Hindustan Institute of Technology and Science Chennai India

If adversaries were to obtain quantum computers in the future, their massive computing power would likely break existing security schemes. Since security is a continuous process, more substantial security schemes must be developed. Current PQC schemes primarily focus on data security or key exchange, and further improvement towards enhanced PQC primitives is required. Our proposal in this research is an innovative paradigm for PQC-focused cloud data security. The proposed HEDT approach achieves encryption and decryption with significantly lower latency (20% improvement) and higher reliability than AES, DES, and RSA, as demonstrated through experimental results. Furthermore, ECSIDH, a hybrid key exchange mechanism combining SIDH and ECDH, improves security strength by 50% while maintaining computational costs within 1.13x of SIDH. Compared to individual key exchange schemes like SIDH, ECSIDH offers superior security as a PQC candidate. These results confirm the robustness and efficiency of the proposed framework in ensuring secure data outsourcing and key exchange in cloud environments. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Skin Melanoma diagnosis using machine learning and ABCD rule 4

Skin Melanoma diagnosis using machine learning and ABCD rule

引用

4th International Conference of science and information technology in Smart Administration, ICSINTESA 2024

作者： Kadeem, Zahra B. Mosa, Qusay O. College of Computer Science and Information Technology Dept. Computer Science Diwaniyah Iraq

ISBN: (纸本)9798350376111

Skin cancer, being the most predominant type of malignant growth, represents more than half of all cancer instances. While melanoma is less common than other skin cancers, it poses the highest risk due to its tendency to metastasize and potentially result in mortality. Nonetheless, early detection significantly increases the chances of curing melanoma. The detection of melanoma poses a considerable challenge, primarily attributed to the minimal interclass variance observed between images of melanoma and non-melanoma, alongside the heightened interclass variance within melanoma images. Hence, it is imperative to formulate a computer-aided Diagnosis (CAD) to identify such lesions and facilitate early disease diagnosis to enhance the probability of patient survival. The proposed methodology consists of a sequence of four distinct phases. The initial stage involves preprocessing, which incorporates the application of filtering and contrast enhancement algorithms such as the Median filter, Dull razor, and Histogram Equalization. The segmentation process proceeds by utilizing Otsu methods in order to detect any anomalies. Subsequently, the following phase involves the extraction of features through GLCM for textural attributes and ABCD base parameters, encompassing asymmetry, border irregularity, color, and diameter. Following this, a model based on artificial neural networks (ANN) is developed by leveraging these extracted traits to discern instances of skin cancer within the provided dataset. This methodology achieves a commendable overall accuracy rate of 99%. Dermatologists may derive significant assistance in their clinical decision-making procedures from this promising breakthrough. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A review on 3D image reconstruction on specific and generic objects

引用

Materials Today: Proceedings 2023年 80卷 2400-2405页

作者： Shalma, H. Selvaraj, P. Dept. of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Chennai India Dept. of Information Technology SRM Institute of Science and Technology Kattankulathur Chennai India

With the emergence of various techniques involved in deep learning the researchers of computer vision tends to focus on the strategies such as object recognition and segmentation of image. This has inclined to accomplish the deep learning techniques in 3D reconstruction of both specific and generic objects. As the space for reconstruction of 3D images either in single or multi view has envisioned the researchers to concentrate on the available technologies used for reconstruction. With the available built in methods and technologies in deep learning, the performance of the proposed methods were reviewed and analyzed using several parameters. As the remaking of 2D images is still in the beginning stage, it is important to study the 3D shape representations, various network architecture, methodologies and approaches behind 3D reconstruction. In this work a review of deep learning methods for single or multiple RGB images of specific and generic object 3D reconstruction was done. Several methods and their importance were also discussed along with the challenges encountered and with further research directions. This paper critically analyzes the various 3D Shaped Representations, 3D Data Network Architectures, dept. Estimation methods, Multi View Representations and the Data Representation Techniques. © 2021

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

From Data to Harvest through Machine Learning based Crop Yield Forecasting 2

From Data to Harvest through Machine Learning based Crop Yie...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Budarapu, Aadithya Vikram Gaddam, John Hyde Boyedi, Ramu Muthyala, Thoshan Kumer Kathirisetty, Nikhila Dept. of Information Technology Hyderabad India Dept. of Computer Science and Data Science Hyderabad India

ISBN: (纸本)9798350370188

The maintenance and enhancement of dynamic soil characteristics are the primary focus of soil management in agriculture to increase crop productivity. Higher productivity may result from efficient soil control of resources and corrective micronutrient treatments. Using CNN and 'KNN' algorithms, the 'soil land classification and crop prediction system' application was created. In this study, two datasets are used: one to obtain crop prediction and the other for soil land categorization. The kind of soils are trained using CNN ('VGG- 19') algorithm, and the accuracy of the model is calculated. The trained model is then utilized in the Flask web app to forecast the type of soil. Another data set with nitrogen, phosphorus, potassium, pH, and temperature as features and the class type of crop as a label is used to forecast crop production. These two algorithms are used to create the flask website, which accepts inputs such as soil picture, soil type prediction, and land parameter inputs for crop prediction. © 2024 IEEE.

关键词： Soils

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Quantum Convolutional Neural Networks for Student Facial Expression Identifcation and Mode Assessments 4

Leveraging Deep Quantum Convolutional Neural Networks for St...

引用

4th International Conference on Ubiquitous Computing and Intelligent information Systems, ICUIS 2024

作者： Hossain, Javed Alam, Md. Nur Akib, Mohammad Yasin Nur Kogoya, Krisdahim Nanjing University of Information Science and Technology Dept. of Artificial Intelligence Nanjing China Nanjing University of Information Science and Technology Dept. of Computer Science and Technology Nanjing China

ISBN: (纸本)9798331529635

The incorporation of modern technologies into education has transformed how learning is seen and assessed, with a rising emphasis on understanding student behavior using facial expression recognition (FER). Recognizing students' emotional and cognitive states can provide vital insights into their engagement and learning styles, allowing teachers to adjust their teaching tactics in real time. Traditional machine learning algorithms have been used to solve this problem, but they frequently struggle with the complexity of facial expressions and big datasets, resulting in limitations in accuracy and processing efficiency. This study explores the potential of quantum computing in addressing these challenges through the development of a Deep Quantum Convolutional Neural Network (QCNN) architecture. By combining the advanced image processing capabilities of convolutional neural networks (CNNs) with the computational power of quantum features such as superposition and entanglement, we aim to enhance the detection of facial expressions that reflect students' engagement, concentration, frustration, and satisfaction. Finally, the result demonstrates a classification accuracy of 91.58 © 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

Active Element Arrangement and Prediction Model for Channel Estimation in IRS-Assisted Systems

Active Element Arrangement and Prediction Model for Channel ...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Tsuchiya, Yoshihiko Suga, Norisato Uruma, Kazunori Fujisawa, Masaya Tokyo University of Science Dept. of Information and Computer Technology Tokyo Japan Shibaura Institute of Technology Dept. of Information and Communication Engineering Tokyo Japan Kogakuin University Dept. of Computer Science Tokyo Japan

ISBN: (纸本)9798350350821

Intelligent reflecting surfaces (IRS) that can dynamically control the phase of radio waves and reflect them are attracting attention to realize non line-of-sight communication in the high-frequency band. Channel state information (CSI) is estimated to properly control the phase, however the overhead of the estimation reduces communication efficiency. To reduce the overhead, IRS systems with active elements that perform channel estimation are considered. One approach treats the partial CSI obtained from the active elements as an image and utilizes a super-resolution technique to predict the entire CSI. However, because the active elements are arranged in grid, prediction is difficult when the active elements spacing and the CSI fluctuation period match. In this study, we propose a new arrangement that gathers the active elements in the center of the IRS. Furthermore, we regard prediction as an image-inpainting problem that recovers missing pixels from known pixel values, and we propose applying the U-Net to solve this problem. Numerical experiments show that the proposed method outperforms conventional methods in prediction accuracy and spectral efficiency. © 2024 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Detection Systems for Distributed Denial-of-Service (DDoS) Attack Based on Time Series: A Review 21

Detection Systems for Distributed Denial-of-Service (DDoS) A...

引用

21st International Multi-Conference on Systems, Signals and Devices, SSD 2024

作者： Adil Nafea, Ahmed Maad Hamdi, Mustafa Abdulhakeem, Baraa Saad Shakir, Ahmed Thair Alsumaidaie, Mustafa S. Ibrahim Shaban, Ali Muwafaq College of Computer Science and Information Technology University of Anbar Ramadi Dept. Artificail Inteligence Iraq College of Computer Science and IT University of Anbar Ramadi Dept. of Computer Science Iraq College of Computer Science and IT University of Anbar Ramadi Dept. of Information System Iraq College of Applied Sciences University of Anbar Ramadi Dept. of Biophysics Iraq College of Computer Science and Information Technology University of Anbar Ramadi Dept. Information System Iraq

ISBN: (纸本)9798350374131

The Distributed Denial-of-Service (DDoS) attacks are one of the most critical threats to the stability and security of the Internet. With the increasing number of devices connected to the Internet, the frequency and severity of DDoS attacks are also increasing. To mitigate the impact of DDoS attacks, intelligent detection systems are becoming increasingly important. This paper reviews the recent literature on intelligent techniques, including machine learning (ML), Deep Learning (DL), and artificial intelligence (AI), for detecting DDoS attacks. We will provide an overview of the existing research in the field and analyse the trends in using time series data analysis for DDoS attack detection. A taxonomy and conceptual framework for DDoS mitigation are presented. This study highlights the use of several intelligent techniques for detecting DDoS attacks and evaluates the performance utilizing real datasets and also discusses future research directions in this field. © 2024 IEEE.

关键词： Time series analysis

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：