检索结果-内蒙古大学图书馆

29th International Conference on Computational Linguistics, COLING 2022

作者： Yang, Zhiwei Ma, Jing Chen, Hechang Lin, Hongzhan Luo, Ziyang Chang, Yi College of Computer Science and Technology Jilin University Changchun China Department of Computer Science Hong Kong Baptist University Hong Kong School of Artificial Intelligence International Center of Future Science Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education

Existing fake news detection methods aim to classify a piece of news as true or false and provide veracity explanations, achieving remarkable performances. However, they often tailor automated solutions on manual fact-checked reports, suffering from limited news coverage and debunking delays. When a piece of news has not yet been fact-checked or debunked, certain amounts of relevant raw reports are usually disseminated on various media outlets, containing the wisdom of crowds to verify the news claim and explain its verdict. In this paper, we propose a novel Coarse-to-fine Cascaded Evidence-Distillation (CofCED) neural network for explainable fake news detection based on such raw reports, alleviating the dependency on fact-checked ones. Specifically, we first utilize a hierarchical encoder for web text representation, and then develop two cascaded selectors to select the most explainable sentences for verdicts on top of the selected top-K reports in a coarse-to-fine manner. Besides, we construct two explainable fake news datasets, which is publicly available. Experimental results demonstrate that our model significantly outperforms state-of-the-art detection baselines and generates high-quality explanations from diverse evaluation perspectives. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Improved Adaptive Fairness-Indexed Technique for Congestion Control in Underwater Networks

Improved Adaptive Fairness-Indexed Technique for Congestion ...

引用

Communication, Control and Intelligent Systems (CCIS)

作者： Balaji Vijayan V K S Manojee Mohammed Ibrahim M Nivethitha R Thamaraimanalan T Ranjithkumar M Department of Information Science and Engineering HKBK College of Engineering Bengaluru Karnataka India Department of Information Technology Kongunadu College of Engineering and Technology Trichy Tamilnadu India Department of Computer Science and Engineering Sona College of Technology Salem Tamilnadu India Department of Computer Science and Engineering K.S.R. College of Engineering Thiruchengode Tamilnadu India Department of Electronics and Communication Engineering Sri Eshwar College of Engineering Coimbatore Tamilnadu India Department of Computer Science and Business Systems Knowledge Institute of Technology Salem Tamilnadu India

ISBN: (数字)9798331528201

ISBN: (纸本)9798331528218

In underwater acoustic sensor networks (UASNs), effective congestion control is essential for ensuring reliable data transmission and resource efficiency, especially in the face of challenging environmental factors such as water velocity, pressure, temperature, and salinity. This paper introduces a novel Adaptive Fairness-Indexed Congestion Control (AFICC) mechanism that employs Q-learning to dynamically adjust transmission rates among nodes, ensuring equitable resource distribution and minimizing congestion. Our simulations, conducted with 100 nodes at depths of up to 1000 meters, reveal that AFICC significantly outperforms two existing algorithms: Rate-Based Congestion Control (RBCC) and Energy-Aware Congestion Control (EACC). Specifically, AFICC achieved a Packet Delivery Ratio (PDR) of 93%, compared to 85% for RBCC and 80% for EACC. Additionally, the End-to-End Delay was reduced to an average of 150 milliseconds with AFICC, while RBCC and EACC recorded delays of 220 milliseconds and 210 milliseconds, respectively. AFICC also demonstrated a 25% improvement in Energy Efficiency over EACC and maintained a Jain’s Fairness Index of 0.92, surpassing the 0.82 and 0.78 indices achieved by RBCC and EACC, respectively. These results confirm that AFICC offers a robust framework for congestion control in UASNs, effectively adapting to fluctuating underwater conditions while ensuring reliable communication and equitable resource allocation.

关键词： Q-learning Salinity (geophysical) Dynamic scheduling Energy efficiency Delays Temperature control Resource management Reliability Underwater acoustics Water resources

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Global-View Reconstruction for Multi-View Multi-Label Feature Selection 39

Uncertainty-Aware Global-View Reconstruction for Multi-View ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Hao, Pingting Liu, Kunpeng Gao, Wanfu College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Department of Computer Science Portland State University Portland 97201 OR United States

ISBN: (纸本)157735897X

In recent years, multi-view multi-label learning (MVML) has gained popularity due to its close resemblance to real-world scenarios. However, the challenge of selecting informative features to ensure both performance and efficiency remains a significant question in MVML. Existing methods often extract information separately from the consistency part and the complementary part, which may result in noise due to unclear segmentation. In this paper, we propose a unified model constructed from the perspective of global-view reconstruction. Additionally, while feature selection methods can discern the importance of features, they typically overlook the uncertainty of samples, which is prevalent in realistic scenarios. To address this, we incorporate the perception of sample uncertainty during the reconstruction process to enhance trustworthiness. Thus, the global-view is reconstructed through the graph structure between samples, sample confidence, and the view relationship. The accurate mapping is established between the reconstructed view and the label matrix. Experimental results demonstrate the superior performance of our method on multi-view datasets. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-Resolution Framework for Scalable and Efficient Big Data Processing 7

Adaptive Multi-Resolution Framework for Scalable and Efficie...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Asha, V. Rangaiah, Yagateela Pandu Nijhawan, Ginni Albawi, Ali Rani, K. Pushpa Kalyani, Susmita New Horizon College of Engineering Bangalore India Institute of Aeronautical Engineering Department of Electronics and Communication Enfineering Dundigal Hyderabad500043 India Lovely Professional University Phagwara India The Islamic University College of Medical Technology Radiology Techniques Department Najaf Iraq Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India Lloyd Law College Plot No. 11 Knowledge Park II Uttar Pradesh Greater Noida201315 India

ISBN: (纸本)9798350350067

The increasing applicability of the big data in different domains require the formulation of effective data collection and analysis framework that can accommodate complex and large datasets. This paper proposes the new DRAF that enhance both data aggregation and mining for large datasets. The Dynamic Resolution Adaptive Framework (DRAF) takes advantage of using multiple levels of representation of data, which makes it easy to expand the workload or scale down depending on the needs of the user. This proposed framework employs methods like hierarchical clustering, branching multi-level indexing and Adaptive Resolution Switching in order to optimize the trade-off of data accuracy and computational cost. Moreover, high level of detail is maintained in the DRAF, which supports mining necessary data and model details at multiple resolutions, making the DRAF specifically appropriate for operational environments where data come from numerous different sources and types. Substantial experiments in the book prove the efficiency of the DRAF-based algorithms in terms of speed and accuracy in comparison with other existing methods. The study establishes potentiality of the DRAF toward the application of big data problems in areas of high level of resolution and immediacy of decision making. © 2024 IEEE.

关键词： Data aggregation

来源：评论

学校读者我要写书评

暂无评论

Innovative Strategies for Ensuring Data Protection and Maintaining Integrity in Digital Systems 7

Innovative Strategies for Ensuring Data Protection and Maint...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Prakash, Shiva Rangaiah, Yagateela Pandu Nagpal, Amandeep Bhardwaj, Garima Mounika, T. Sharma, Saurabh New Horizon College of Engineering Department of Mechanical Engineeering Bangalore India Institute of Aeronautical Engineering Department of Electronics and Communication Enfineering Dundigal Hyderabad500043 India Lovely Professional University Phagwara India Amity University Amity Business School Greater Noida India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India Lloyd Law College Plot No. 11 Knowledge Park II Uttar Pradesh Greater Noida201314 India

ISBN: (纸本)9798350350067

Data security is difficult in the ever-changing digital world. Existing techniques may not provide comprehensive security, real-time hazard monitoring, and usercentred access management. Our response must be forceful and adaptable. The study led to the development of a five-part data safety technique. AEA, DTD, SIM, UCAC, and AAP are all part of this organisation. AAP makes identification fast and secure;AEA protects data;DTD detects hazards in real time;SIM tests security on a broad scale;and UCAC regulates access. Ablation can reveal systemic roles. New methods outperformed previous ones in some key aspects. Visual tools emphasise privacy, freedom, user experience, and connection to aid decisionmaking. In ever-changing digital situations, one may employ a powerful and adaptable data security solution. © 2024 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Advancing Image Segmentation, Analysis, and Feature Extraction Techniques 7

Advancing Image Segmentation, Analysis, and Feature Extracti...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Asha, V. Rangaiah, Yagateela Pandu Nijhawan, Ginni Kalyani, Susmita Rani, K. Pushpa Albawi, Ali New Horizon College of Engineering Bangalore India Institute of Aeronautical Engineering Department of Electronics and Communication Enfineering Dundigal Hyderabad500043 India Lovely Professional University Phagwara India Lloyd Law College Plot No. 11 Knowledge Park II Uttar Pradesh Greater Noida201315 India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India The Islamic University College of Medical Technology Radiology Techniques Department Najaf Iraq

ISBN: (纸本)9798350350067

This study centers on review, feature extraction, and image segmentation, integrated through the Dual-Path Convolutional Neural Network (DP-CNN). The DP-CNN is designed to accurately identify objects in images, even in the presence of intricate lines and discontinuities. The MAMAM technique efficiently prioritizes critical image regions, expediting the review process and enhancing accuracy in image analysis. Additionally, feature extraction is refined using the Adaptive Feature Selection (AFS) method, facilitating precise and adaptable image processing. Each component of this approach is systematically developed to meet the research objectives. The combined methodology demonstrates robustness and versatility, proving effective across diverse and challenging data scenarios, thereby presenting a promising solution for rapid and accurate complex image processing tasks. © 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

Reconsidering Feature Structure Information and Latent Space Alignment in Partial Multi-label Feature Selection

arXiv

引用

arXiv 2025年

作者： Pan, Hanlin Liu, Kunpeng Gao, Wanfu College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Department of Computer Science Portland State University PortlandOR97201 United States

The purpose of partial multi-label feature selection is to select the most representative feature subset, where the data comes from partial multi-label datasets that have label ambiguity issues. For label disambiguation, previous methods mainly focus on utilizing the information inside the labels and the relationship between the labels and features. However, the information existing in the feature space is rarely considered, especially in partial multi-label scenarios where the noises is considered to be concentrated in the label space while the feature information is correct. This paper proposes a method based on latent space alignment, which uses the information mined in feature space to disambiguate in latent space through the structural consistency between labels and features. In addition, previous methods overestimate the consistency of features and labels in the latent space after convergence. We comprehensively consider the similarity of latent space projections to feature space and label space, and propose new feature selection term. This method also significantly improves the positive label identification ability of the selected features. Comprehensive experiments demonstrate the superiority of the proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Reconsidering Feature Structure Information and Latent Space Alignment in Partial Multi-label Feature Selection 39

Reconsidering Feature Structure Information and Latent Space...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

ISBN: (纸本)157735897X

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Computational Models for Enhanced Interpretation of Biospeckle Images Leveraging Deep Learning and Fourier Transform Techniques in Biomedical Applications 7

Next-Generation Computational Models for Enhanced Interpreta...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Gowtham Raj, R. Sreekanth, S. Nijhawan, Ginni Gupta, Shubhi Sharma, Saurabh Mounika, T. New Horizon College of Engineering Deparment of Mechanical Engineering Bangalore India Institute of Aeronautical Engineering Dundigal Hyderabad500043 India Lloyd Law College Plot No. 11 Knowledge Park II Greater Uttar Pradesh Noida201314 India Lovely Professional University Phagwara India Amity University Amity School of Engineering & Technology Greater Noida India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350350067

This study looks at advanced computational techniques that enhance the understanding of biospeckle images in biological contexts. Our models use Fourier transform and deep learning techniques to achieve improved specificity, recall, accuracy, and precision. The Fourier transform may provide a more accurate description of frequency domain data as biological processes evolve over time. Deep learning algorithms recognise patterns in biospeckle images, facilitating analysis, memory, and response. The analysis research delineates the several components that influence the outcome and provides evidence of their respective roles. This research shows how helpful the models are and offers suggestions on how to make them better. Non-invasive biomedical testing uses these computer models to illustrate the temporal evolution of biological cells. Our techniques improve the interpretation of biospeckle images, potentially revolutionising non-invasive biomedical imaging. Future researchers may evaluate these models using different datasets and testing conditions. This guarantees their adaptability and power in biological contexts. © 2024 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Unified Security Framework for Cloud Applications with IoT Fusion via Decentralized Blockchain

Unified Security Framework for Cloud Applications with IoT F...

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： B Mohanraj M Kalpana A M Priya D Abdul Jaleel N Karthikeyan A A Velusamy Department of Information Technology Sona College of Technology Salem India Department of Computer Science Engineering Government College of Engineering Salem India Department of Information Technology Knowledge Institute of Technology Salem India Department of Computer Science & Technology Madanapalle Institute of Technology & Science Madanapalle India Department of CSE - Artificial Intelligence Sri Venkateshwara College of Engineering Vidyanagar India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

Recent advancements in blockchain-based cloud computing highlight its potential in providing robust data security, integrity, and confidentiality. While cloud computing is increasingly utilized for remote resource access, it presents significant security challenges that necessitate innovative solutions. This research proposes a novel SecureCloudChain IoT (SCC-IoT) architecture, which integrates blockchain technology into cloud-supportive platforms to enhance security measures. The SCC-IoT architecture includes a distributed blockchain approach to ensure data security while maintaining privacy and integrity. This system is designed to be adaptable and scalable, meeting real-world requirements effectively. By promoting a decentralized and efficient environment, SCC-IoT improves the reliability, stability, and load balancing of cloud services. Performance assessments through various experimental conditions have been conducted to evaluate the proposed system. The results demonstrate SCC-IoT’s effectiveness in mitigating potential attacks and ensuring secure and reliable cloud computing. This research highlights the significance of integrating blockchain technology into cloud platforms, paving way for more secure and efficient cloud computing solutions.

关键词： Cloud computing Data privacy Data security computer architecture Load management Blockchains Reliability

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：