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

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

A Serendipity Recommendation Method for Book Categories Using BERT to Strengthen the Web Service of the Book

引用

Journal of Web engineering 2025年第2期24卷 199-216页

作者： Kim, Youngmo Kim, Seok-Yoon Park, Byeongchan Dept. of Computer Science and Engineering Soongsil University South Korea

In the field of book search, research on a web service-based user-customized book recommendation system is being conducted to respond to increasingly diverse user requirements. The collaborative filtering algorithm, which is mainly used for book recommendation, has a problem in that it is difficult to reflect the user’s recent interest without considering the changes in preference over time, and the user’s satisfaction decreases because it repeatedly recommends only similar items. In this paper, we propose a book recommendation method using category similarity based on deep learning. The proposed method is to predict books to be used next time by inputting users’ past and current book usage history through BERT, a natural language processing model, and to recommend popular books in other categories with high similarity to the predicted book category in the BERT model to reflect serendipity. This method reflects serendipity, which can lead to users’ recent interests and practical preferences, so that recommendation accuracy and user satisfaction can be satisfied at the same time. © 2025 River Publishers.

关键词： BERT book category recommendation serendipity Web service

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Machine Learning and Deep Learning Models for Food Waste Detection Using Image Processing

Comparative Study of Machine Learning and Deep Learning Mode...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Rajagopal, R. Chaithanya, K. Sonth, Ankita Kallappagoudar, Prasanna Basanagouda Mohammadishaq Nadaf, Mohammadzaid Ananda Theertha, H. Dept of Computer Science Alliance College of Engineering and Design Alliance University Bangalore India Bangalore India Alliance College of Engineering and Design Dept of Computer Science Bangalore India Alliance College of Engineering and Design Dept of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331529833

For the purpose of reducing financial losses and environmental impacts, food waste detection is essential. Inorder to detect food waste using image processing, this study investigates the efficiency of several machine learning algorithms, including Convolutional Neural Network (CNN), K-Nearest Neighbors (KNN), Random Forest, and Inception Model (IV3). A set of images of food are then processed. Before each algorithm is used for classification, pre-processing methods like segmentation and feature extraction are used. © 2025 IEEE.

关键词： k-nearest neighbors

来源：评论

学校读者我要写书评

暂无评论

Brain Tumour Detection using MRI Images 1

Brain Tumour Detection using MRI Images

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Jayashree Mallick, Ahmed Faraz Das, Ashutosh Singh, Abhiraj Shivaprakash, T. Preethi Salian, K. Nitte Meenakshi Institute of Technology Dept of Computer Science and Engineering Bangalore India Nitte Meenakshi Institute of Technology Dept of Computer Science and Engineering India Vijaya Vittala Institute of Technology Dept of Computer Science and Engineering Bangalore India Nmamit Dept of Information Science and Engineering Nitte Udupi India

ISBN: (纸本)9798331529246

An essential diagnostic technique for brain tumors, Magnetic Resonance Imaging (MRI) enables early detection and improved patient outcomes. However, manual interpretation of MRI scans can be time-consuming and subject to human error. Deep learning has revolutionized medical image analysis by providing automated and accurate classifications, significantly enhancing diagnostic processes. This study leverages the pre-trained Convolutional Neural Network (CNN) model Xception to classify MRI brain data, demonstrating its effectiveness in identifying brain tumors. The model was trained and validated using a diverse dataset, achieving a high test accuracy of 98.78% and training accuracy of 99.96%. These findings highlight the potential of the Xception model in supporting clinical decision-making and reducing diagnostic workloads. The study contributes to the field by showcasing Xception's implementation, dataset preparation, model design, training, and evaluation. Furthermore, it emphasizes the importance of using deep learning techniques for reliable and efficient brain tumor classification, setting the groundwork for future advancements in automated diagnostic systems. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Detailed Analysis of Machine Learning Algorithm Performance in Heart Disease Prediction 4

A Detailed Analysis of Machine Learning Algorithm Performanc...

引用

4th International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2025

作者： Rabbi, Mohammad Ali Rijon, Rokibul Hasan Akhi, Sharmin Sultana Hossain, Alomgir Jeba, Samiha Maisha International University of Business Agriculture and Technology Dept of Computer Science and Engineering Bangladesh Monroe University Dept of Computer Science United States

ISBN: (纸本)9798331530938

Human deaths are natural events, but heart disease remains a leading cause of mortality worldwide. Predicting heart disease using machine learning can significantly benefit global health, though it presents clinical challenges requiring high accuracy and efficiency. Many countries face a shortage of cardiovascular experts and a high rate of misdiagnoses, which can be mitigated by accurately determining the stage of coronary disease and supporting medical decisions with automated patient records. This paper addresses the prediction of coronary disease based on input attributes using data mining techniques. The results showed that the CatBoost Classifier achieved the highest accuracy at 87.2%, followed closely by the Ridge Classifier at 86.3%. Other models, such as XGBoost and Gradient Boosting, performed similarly, achieving 84.0%, while the RandomForest Classifier had a slightly better performance with an accuracy of 85.6%. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Perturb, Attend, Detect and Localize (PADL): Robust Proactive Image Defense

引用

IEEE Access 2025年 13卷 81755-81768页

作者： Bartolucci, Filippo Masi, Iacopo Lisanti, Giuseppe University of Bologna Computer Science and Engineering Dept. CVLab Bologna Italy University of Rome Computer Science Dept. OmnAI Lab Sapienza Rome Italy

Image manipulation detection has gained significant attention due to the rise of Generative Models (GMs). Passive detection methods often overfit to specific GMs, limiting their effectiveness. Recently, proactive approaches have been introduced to overcome this limitation. However, these methods suffer from two vulnerabilities: i) the manipulation detector is not robust to noise and hence can be easily fooled;ii) they rely on fixed perturbations for image protection, which offers an exploit for malicious attackers, enabling them to evade detection. To overcome these issues, we propose PADL, a novel solution that is able to create image-specific perturbations for protecting images. PADL's key objective is to provide a secure and adaptive protection mechanism that ensures the authenticity of images by detecting and localizing manipulations, drastically reducing the possibility of reverse engineering. The method consists of two key components: an encoder, which conditions a learnable perturbation on the input image to ensure uniqueness and robustness against attacks, and a decoder, which extracts the perturbation and leverages it for manipulation detection and localization. PADL can detect manipulation of a protected image and pinpoint regions that have undergone alterations. Unlike previous proactive defenses that rely on a finite set of perturbations, PADL's tailored protection significantly reduces the risk of reverse engineering. Although being trained only on images of faces manipulated with STGAN, PADL generalizes to a range of unseen models with diverse architectural designs, such as StarGANv2, CycleGAN, BlendGAN, DiffAE, StableDiffusion, and StableDiffusionXL and also to unseen data domains. Finally, we propose a novel evaluation protocol that fairly assesses localization performance in relation to detection accuracy, providing a better reflection of real-world scenarios. Future research will aim to extend PADL to work on more challenging scenarios, including v

关键词： Reverse engineering

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient LEDCA Analysis for Improved Throughput in Wireless Sensor Networks 6

Energy Efficient LEDCA Analysis for Improved Throughput in W...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Padmageetha, B.G. Naik, Pramod Kumar Patil, Mallanagouda Dept.of Computer Applications Dayananda Sagar University Bengaluru India Dept. of Computer science and Engineering Dayananda Sagar University Bengaluru India Dept. of Computer science and Engineering RVITM Bengaluru India

ISBN: (纸本)9798331522667

Wireless Sensor Networks (WSNs) face significant challenges in terms of energy conservation, scalability, and data throughput owing to their limited node energy resources. This paper presents a low-energy data-centric algorithm (LEDCA), a novel energy-aware clustering and routing protocol designed to optimize energy efficiency and improve throughput in WSNs. Through simulations, LEDCA demonstrated a Packet Delivery Ratio (PDR) of up to 90%, throughput of 255,217 bps, and average latency of 159 ms, validating its efficiency in resource-constrained environments. The algorithm integrates residual energy awareness by prioritizing high-energy nodes for Cluster Head (CH) roles, dynamically adjusting routing paths, and balancing the network load to prevent premature node failure. By applying an Energy Mapping Node and a real-time Energy Mapping Table, LEDCA minimizes re-clustering, reduces data redundancy, and ensures stable data transmission even under high-density networks. Simulation results also show LEDCA's scalability of LEDCA, with A9_T_200 achieving the highest throughput under extended transmission ranges and A3_T_200 achieving the lowest latency, making it suitable for energy-sensitive and latency-critical applications. Future enhancements, such as integrating Non-Orthogonal Multiple Access (NOMA) and dynamic resource allocation, could further improve LEDCA’s interference management and scalability of LEDCA for IoT and 5G/6G networks, addressing the needs of next-generation applications. © 2025 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Quantum Network Routing with Heterogeneous Nodes 17

Quantum Network Routing with Heterogeneous Nodes

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Pandey, Anoop Kumar Tamma, Bheemarjuna Reddy Rao, M.V. Panduranga IIT Hyderabad Dept. of Computer Science and Engineering India

ISBN: (纸本)9798331531195

Deciding a route for the transfer of quantum information (namely, qubits) on a quantum network is a significant problem that is being studied extensively. In this work, we investigate the problem of routing on a quantum network of heterogeneous nodes both with and without fidelity and timing *** propose a Path Request Packet (PRP) based routing scheme for dynamically selecting a path that maximizes the overall probability of transmission success while maintaining fidelity above a threshold and adhering to time constraints. While the proposed scheme can perform suboptimally under fidelity and timing constraints, we discuss a straightforward proof of optimality in the absence of these constraints. Simulations on random graphs demonstrate that the PRP-based scheme performs better, both in terms of reliability and fidelity, than a non-trivial baseline routing algorithm. © 2025 IEEE.

关键词： Quantum electronics

来源：评论

学校读者我要写书评

暂无评论

Advancing Multilingual Speaker Identification and Verification for Indo-Aryan and Dravidian Languages 1

Advancing Multilingual Speaker Identification and Verificati...

引用

1st Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages, IndoNLP 2025

作者： Sritharan, Braveenan Thayasivam, Uthayasanker Dept. of Computer Science & Engineering University of Moratuwa Sri Lanka

ISBN: (纸本)9798891762145

Multilingual speaker identification and verification is a challenging task, especially for languages with diverse acoustic and linguistic features such as Indo-Aryan and Dravidian languages. Previous models have struggled to generalize across multilingual environments, leading to significant performance degradation when applied to multiple languages. In this paper, we propose an advanced approach to multilingual speaker identification and verification, specifically designed for Indo-Aryan and Dravidian languages. Empirical results on the Kathbath dataset show that our approach significantly improves speaker identification accuracy, reducing the performance gap between monolingual and multilingual systems from 15% to just 1%. Additionally, our model reduces the equal error rate for speaker verification from 15% to 5% in noisy conditions. Our method demonstrates strong generalization capabilities across diverse languages, offering a scalable solution for multilingual voice-based biometric systems. © 2025 Association for Computational Linguistics.

关键词： Speech recognition

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：