检索结果-内蒙古大学图书馆

26th International Conference on Distributed Computing and Networking, ICDCN 2025

作者： Das, Raja Goswami, Pritam Mondal, Brati Sau, Buddhadeb Department of Mathematics Jadavpur University West Bengal Kolkata India Department of Computer Science and Engineering Sister Nivedita University West Bengal Kolkata India

ISBN: (纸本)9798400710629

One of the fundamental problems of distributed systems that has been extensively studied is the exploration of different network topologies. In exploration, each node of the graph network has to be visited by at least one robot within a finite time. Existing literature typically assumes on various networks like lines, rings, tori, arbitrary networks, and rectangular grids. To the best of our knowledge, no existing work has addressed the exploration problem considering triangular grid. In this work the exploration problem is considered on rectangle enclosed triangular grid (RETG) with myopic robots, where the visibility of the robot is limited to a specific distance, denoted as φ, since infinite visibility becomes impractical for a very large network. The robots are luminous and work under FSYNC scheduler. Firstly the cases where the perpetual RETG exploration is not possible are discussed in three impossibility results. Then two algorithms are provided to solve the exploration problem on RETG. The first algorithm requires two robots without common chirality, φ = 1, and three colors of light. The second algorithm requires two robots with common chirality, φ = 2, and two colors of light. Using luminous robots to decrease both visibility and the number of robots is a nice trade-off from the implementation's point of view as increasing visibility is more expensive than using robots with a light having finite colors. © 2025 Copyright held by the owner/author(s).

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Powered Authenticated Key Agreement Scheme With Reputation-Incentive Mechanism for Vehicle-to-Vehicle Communication in IoV

引用

IEEE Internet of Things Journal 2025年

作者： Mukathe, Daniel Di, Wu Ahmed, Waheeb Worku, Tarik Dalian University of Technology School of Computer Science and Technology Dalian116024 China Tharaka University Department of Computer Science Marimanti193-60215 Kenya University of Aden Department of Computer Science and Engineering Aden009672 Yemen Injibara University Department of Computer Science Injibara6040 Ethiopia

The Internet of Vehicles (IoV) enhances road safety through real-time vehicle-to-vehicle (V2V) communication of traffic messages. However, V2V wireless connectivity poses security and privacy threats, as malicious adversaries can eavesdrop and modify V2V messages or compromise vehicle identity privacy. Existing authenticated key agreement (AKA) schemes attempt to address these threats but suffer from security flaws, computational inefficiency, high communication overhead, single points of failure, and trust deficits, making them unsuitable for resource-constrained and delay-sensitive IoV applications. To address the above challenges, we propose a blockchain-powered AKA scheme with a reputation-incentive mechanism (BAKARI) for V2V communication. BAKARI employs Schnorr signatures and lightweight elliptic curve cryptographic operations to improve computational efficiency, and minimizes communication overhead by completing the AKA phase with only two messages. BAKARI leverages blockchain ledger and smart contracts to maintain vehicle authentication information and V2V messages. Additionally, it incorporates a reputation-incentive model, where trustworthy vehicles are rewarded while malicious ones are penalized. A rigorous security analysis, including formal proof under the random or real model, informal analysis, and ProVerif verification, demonstrates BAKARI’s resilience against security and privacy threats. Performance evaluation shows that BAKARI balances computational efficiency, communication overhead, and security better than the benchmark schemes. Finally, simulations on Hyperledger Fabric and Veins frameworks validate BAKARI’s practicality in real-world IoV environments. © 2014 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Oral Cancer Classification Using a Hybrid Attention-Aided Deep Learning Model 5th

Oral Cancer Classification Using a Hybrid Attention-Aided D...

引用

5th International Conference on Medical Imaging and computer Aided Diagnosis, MICAD 2024

作者： Dutta, Srinjan Roy, Jibesh Mandal, Diptarka Kaplun, Dmitrii Shpakovskaya, Irina Sarkar, Ram Department of Computer Science and Engineering Jalpaiguri Government Engineering College Jalpaiguri India School of Computer Engineering and Mathematical Sciences Defence Institute of Advanced Technology Pune India Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Process Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia Department of Computer Science and Engineering Jadavpur University West Bengal Kolkata India I.P. Pavlov Saint Petersburg First State Medical University St. Petersburg Russia

ISBN: (纸本)9789819638628

Oral cancer remains a critical global health challenge, characterized by high morbidity and mortality due to late-stage diagnosis. This paper addresses the need for improved diagnostic accuracy by introducing a novel hybrid-attention aided deep learning model for oral cancer classification. Our approach integrates the EfficientNetB0 model for feature extraction with a customized hybrid attention module, combining self, spatial, and soft attention mechanisms to emphasize crucial features. The model has been trained and evaluated on both microscopic and macroscopic oral cancer datasets, demonstrating its generalizability. Our proposed model achieves an accuracy of 96.97% on a macroscopic dataset and 92% on a microscopic dataset, with respective F1-scores of 0.97 and 0.89, outperforming baseline models. This hybrid attention-aided deep learning model shows significant potential in improving early detection and treatment planning of oral cancer. Source code and additional results of this work can be found at the GitHub repository. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Guided Cross Attention Ensemble Mean Teacher for Semi-Supervised Medical Image Segmentation

Uncertainty-Guided Cross Attention Ensemble Mean Teacher for...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Karri, Meghana Arya, Amit Soni Biswas, Koushik Gennaro, Nicolo Cicek, Vedat Durak, Gorkem Velichko, Yuri S. Bagci, Ulas Northwestern University Department of Radiology ChicagoIL United States Bennett University School of Computer Science Engineering and Technology UP Greater Noida India

ISBN: (纸本)9798331510831

This work proposes a novel framework, UncertaintyGuided Cross Attention Ensemble Mean Teacher (UGCEMT), for achieving state-of-the-art performance in semisupervised medical image segmentation. UG-CEMT leverages the strengths of co-training and knowledge distillation by combining a Cross-attention Ensemble Mean Teacher framework (CEMT) inspired by Vision Transformers (ViT) with uncertainty-guided consistency regularization and Sharpness-Aware Minimization emphasizing uncertainty. UG-CEMT improves semi-supervised performance while maintaining a consistent network architecture and task setting by fostering high disparity between sub-networks. Experiments demonstrate significant advantages over existing methods like Mean Teacher and Crosspseudo Supervision in terms of disparity, domain generalization, and medical image segmentation performance. UG-CEMT achieves state-of-the-art results on multi-center prostate MRI and cardiac MRI datasets, where object segmentation is particularly challenging. Our results show that using only 10% labeled data, UG-CEMT approaches the performance of fully supervised methods, demonstrating its effectiveness in exploiting unlabeled data for robust medical image segmentation. The code is publicly available at https://***/Meghnak13/UG-CEMT © 2025 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Waterbody Area Segmentation of Satellite Images Using U-Net with Dense Block Enhanced Encoder 1

Waterbody Area Segmentation of Satellite Images Using U-Net ...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Kumar, L. T. Senthil Kalaiyarasi, M. Hemalatha, L.T. Saravanan, S. Department of Computer Science and Engineering Chennai602 105 India Chennai India Telangana India B V Raju Institute of Technology Telangana India

ISBN: (纸本)9798331518578

This paper presents an advanced approach for waterbody segmentation in satellite images using a Dense U-Net model with a Dense Block-enhanced encoder. Accurate segmentation of water areas in satellite imagery is crucial for environmental monitoring, flood management, and resource planning. Traditional U-Net models are effective but often lack the capacity to capture fine details required for high-resolution satellite data. To address this, the proposed Dense U-Net replaces standard convolutional layers in the encoder with Dense Blocks, promoting feature reuse and deeper extraction of spatial information. Additionally, multi-scale fusion is incorporated to handle various spatial scales, enabling the model to accurately segment both large and small water regions. The simulation outcome shows that the proposed method segments the waterbody region with high Accuracy (96.7%), Recall (95.4%), and Dice coefficient (96.1%), with robust Specificity (99%) and F1 scores (96.6%), underscoring its balanced performance in segmenting water regions. Performance metrics indicate the model's effectiveness in isolating water areas with minimal false positives and accurate boundary delineation. This enhanced approach provides a reliable solution for detailed waterbody segmentation in satellite images. © 2025 IEEE.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Multiresolution Features for Sonic Log Classification

Multiresolution Features for Sonic Log Classification

引用

2025 International Conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Gupta, Parbhat Khalsa, Gurpreet Kour Kumar, Dinesh Gupta, Atulya Saxena, Megha Kumari, Rupam Srm Institute of Science and Technology Department of Computer Science and Engineering Delhi Ncr Campus Modinagar Uttar Pradesh Ghaziabad India

ISBN: (纸本)9798331527495

This study highlights the significance of precise DTC and DTS values for reservoir characterization and presents a unique method for sonic log prediction in the oil and gas sector. To improve prediction accuracy, the approach integrates signal processing-more especially, Wavelet transformation-with machine learning. Wavelet transformation on seismic signals, feature extraction, dataset preprocessing, and machine learning model training are all steps in the process. The accuracy of the results is an astonishing 87.5 percent, outperforming previous algorithms. The extensive and varied data set used guarantees the model's resilience in a range of geological situations. The suggested method improves reservoir characterization confidence by making a substantial contribution to precise wave velocity estimation. All things considered, the study provides a workable and efficient way to enhance sonic log forecasts, which will help with hydrocarbon exploration and petroleum industry decision-making. © 2025 IEEE.

关键词： Gasoline

来源：评论

学校读者我要写书评

暂无评论

TangibleMoments: Embedding XR Memories onto Physical Objects

TangibleMoments: Embedding XR Memories onto Physical Objects

引用

2025 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2025

作者： Khan, Omar Ahmed, Zaid Nam, Hyeongil Kim, Kangsoo University of Calgary Department of Computer Science Canada Engineering University of Calgary Department of Electrical and Software Canada

ISBN: (纸本)9798331514846

The increasing prevalence of Extended Reality (XR) and head-mounted displays (HMDs), alongside rapid advancements in 3D reality capture technology, unlocks a new paradigm for capturing and reliving past memories/experiences through XR. Current methods for accessing and interacting with these "XR Memories"still lack the ability to fully leverage the range of capabilities afforded by XR and HMDs. We introduce TangibleMoments, a novel framework that enables users to embed XR memories onto physical objects, transforming those objects into "Moments"- tangible user interfaces for accessing and interacting with XR memories. We describe and illustrate five interaction methods as part of this framework: Creating Moments, Recalling Moments, Sharing Moments, Copying Moments, and Clearing Moments. We showcase an initial prototype and discuss possible extensions. © 2025 IEEE.

关键词： Mixed reality

来源：评论

学校读者我要写书评

暂无评论

Counterfeit Currency Analysis Using Inception V3

Counterfeit Currency Analysis Using Inception V3

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： D. Maya K. Krishnan M. Premkumar V. Valliappan N. Vignesh Department of Computer Science and Engineering Builders Engineering College India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

This project introduces an advanced counterfeit currency detection system that is a combination of explainable deep learning technologies with practical implementation potential. Based on a Convolutional Neural Network (CNN) rooted in the Inception v3 architecture, the system deeply analyzes complex features like textures, patterns, and security marks to identify authentic notes and counterfeits accurately. The Inception v3 model's enhanced feature extraction ability provides high accuracy in the detection of even advanced forgeries. For increased transparency and trust in decision-making, the system integrates explainability tools like SHAP and Grad-CAM that visually highlight important features affecting predictions. Designed for real-time use, the detection system is made available through web and mobile interfaces, thereby ensuring scalability and efficiency for security agencies and financial institutions. By reducing dependency on human-verifiable methods prone to human error and inefficiency, this solution offers a quicker and more reliable method for detecting counterfeits. With adaptive learning capabilities to combat the dynamic nature of forgery methods, the system provides resilience in dynamic environments. Overall, this implementation best bridges the gap between state-of-the-art technology and operational feasibility, thereby offering a powerful tool to combat economic fraud on a large scale.

关键词： Scalability Market research Forgery Real-time systems Convolutional neural networks Security Reliability Informatics Currencies Resilience

来源：评论

学校读者我要写书评

暂无评论

Robust Graph Learning Against Camouflaged Malicious Actors 25th

Robust Graph Learning Against Camouflaged Malicious Actors

引用

25th International Conference on Web Information Systems engineering, WISE 2024

作者： Haghighi, Venus Shabani, Nasrin Soltani, Behnaz Yao, Lina Sheng, Quan Z. Yang, Jian Beheshti, Amin School of Computing Macquarie University SydneyNSW2109 Australia School of Computer Science and Engineering University of New South Wales KensingtonNSW Australia

ISBN: (纸本)9789819605668

Graph Neural Networks (GNNs) have achieved great success in various graph-related applications such as fraud detection. However, GNN-based fraud detection models suffer from the camouflage behavior of malicious actors. Camouflaged fraudsters establish many normal connections to benign entities in the network to alleviate their suspiciousness, and eventually bypass the detection systems. To tackle this problem, we propose a new Multiple Adaptive Channels Aggregation Graph Neural Network for Detecting Camouflaged Fraudsters (named MAGNET for short). First, MAGNET includes a graph-agnostic edge labeling module to generate edge labels and domination signals (i.e., homophily-domination or heterophily-domination) for a given neighborhood. Second, MAGNET leverages multiple adaptive aggregation channels to improve graph learning against camouflaged fraudsters. Third, MAGNET adopts a multi-relational combination module to obtain final representations based on different relations for a multi-relational fraud graph. We conduct extensive experiments on two real-world fraud datasets, and our results show that MAGNET outperforms the state-of-the-art baselines. The source codes and datasets of our work are available at https://***/VenusHaghighi/MAGNET. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

CKGLD: Curating Knowledge Graph for Linked Open Data Generation for Cyber Law and Ethics 4th

CKGLD: Curating Knowledge Graph for Linked Open Data Generat...

引用

4th International Conference on Emerging Trends and Technologies on Intelligent Systems, ETTIS 2024

作者： Aravind Krishnan, A. Deepak, Gerard Santhanavijayan, A. Venugopal, K.R. Department of Computer Science and Engineering BMS Institute of Technology and Management Bengaluru India National Institute of Technology Tiruchirappalli India Bangalore University Bengaluru India

ISBN: (纸本)9789819757022

This paper introduces a knowledge graph curation framework for the generation of linked open data in the domain of cyber law and ethics called the CKGLD. This framework utilizes both static metadata and dynamically acquired knowledge from Web 3.0. With advanced methods of term and category extraction, classification using both lightweight machine learning and strong deep learning methods, and clustering, the framework can exceed all similar frameworks in terms of performance. Initial terms are processed from the documents using the TF-IDF strategy. Static metadata stack is established from e-books, query logs, and glossaries. Renyi entropy is used to guide informative term selection for a decision tree classification;in this manner, the scale of the generated knowledge is managed by lightweight computing requirements. Dynamic knowledge from Web 3.0 is classified using GANs and is subjected to DBSCAN clustering. A multi-agent setup with parallelization enhances the efficiency of the clustering process. The knowledge graph is finally created using the Co-SIM rank and is evaluated for specificity using Hellinger's distance and volume of intersection index. These paradigms contribute to this framework significantly outperforming the baseline frameworks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Knowledge graph

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：