检索结果-内蒙古大学图书馆

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Du, Yanning Xu, Jinnan Zhang, Yaling Wang, Yichuan Wang, Zhoukai School of Computer Science and Engineering Xi’an University of Technology Xi’an China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an China

ISBN: (纸本)9789819615506

In many fields, such as healthcare, finance, and scientific research, data sharing and collaboration are critical to achieving better outcomes. However, the sharing of personal data often involves privacy risks, so privacy-preserving techniques are needed to ensure data security and privacy. The superior performance and flexibility of generative models in data representation have led to significant progress in the development of data privacy. This paper proposes a textual data de-privatization scheme based on generative adversarial networks that well combines generative adversarial networks with privacy protection. The generated de-privacy data retains the statistical properties of the original data and effectively removes sensitive information. Moreover, feature sorting and reshaping modules are introduced to enable the generator to better capture the relationships between features, thus improving the quality of synthetic data. In this paper, the utility of synthetic data is evaluated from three aspects, including similarity assessment, privacy assessment, and model utility assessment. Experimental results show that this method achieves a good trade-off in terms of textual data privacy protection and data quality maintenance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

AFuNet: an attention-based fusion network to classify texts in a resource-constrained language

引用

Neural computing and Applications 2025年第9期37卷 6725-6748页

作者： Hossain, Md. Rajib Hoque, Mohammed Moshiul Dewan, M. Ali Akber Hoque, Enamul Siddique, Nazmul Department of Computer Science & Engineering Chittagong University of Engineering & Technology Chittagong4349 Bangladesh School of Computing and Information Systems Faculty of Science and Technology Athabasca University AthabascaABT9S 3A3 Canada School of Information Technology York University TorontoONM3J 1P3 Canada School of Computing Engineering and Intelligent Systems Ulster University Coleraine United Kingdom

In the era of widespread Internet use and extensive social media interaction, the digital realm is accumulating vast amounts of unstructured text data. This unstructured data often contain undesirable information, necessitating time-consuming manual classification efforts. An intelligent text classification system capable of automatically categorizing digitized texts based on semantic meaning is crucial. However, this task is particularly challenging for low-resource languages like Bengali due to a shortage of annotated corpora, issues with out-of-vocabulary words, lack of domain-specific hyperparameter tuning, limited ability to extract generalized text features, and class imbalances within the corpus. AFuNet: an attention-based fusion network to classify texts in a resource-constrained language. AFuNet undergoes a comprehensive four-phase experimental process, including baseline model evaluation and hyperparameter tuning, late fusion and model selection, attention-based early fusion and model identification, and an ablation study with impact analysis. Fine-tuned based on five Bengali text classification corpora, AFuNet achieves impressive accuracies: 96.60 ± 0.2 (BTCC11), 85.37 ± 0.2 (OSBC), 97.35 ± 0.2 (BARD), 93.74 ± 0.2 (IndicNLP), and 96.51 ± 0.2 (ProthomAlo). In comparison with previous state-of-the-art models on these corpora, AFuNet demonstrates significant accuracy improvements ranging from 0.54% to 4.49%, showcasing its effectiveness in advancing text classification capabilities for the Bengali language. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Language Models over Large-Scale Knowledge Base: on Capacity, Flexibility and Reasoning for New Facts 31

Language Models over Large-Scale Knowledge Base: on Capacity...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： He, Qiyuan Wang, Yizhong Yu, Jianfei Wang, Wenya College of Computing and Data Science Nanyang Technological University Singapore Paul G. Allen School of Computer Science & Engineering University of Washington United States School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9798891761964

Advancements in language models (LMs) have sparked interest in exploring their potential as knowledge bases (KBs) due to their high capability for storing huge amounts of factual knowledge and semantic understanding. However, existing studies face challenges in quantifying the extent of large-scale knowledge packed into LMs and lack systematic studies on LMs' structured reasoning capabilities over the infused knowledge. Addressing these gaps, our research investigates whether LMs can effectively act as large-scale KBs after training over an expansive set of world knowledge triplets via addressing the following three crucial questions: (1) How do LMs of different sizes perform at storing world knowledge of different frequencies in a large-scale KB? (2) How flexible are these LMs in recalling the stored knowledge when prompted with natural language queries? (3) After training on the abundant world knowledge, can LMs additionally gain the ability to reason over such information to infer new facts? Our findings indicate that while medium-scaled LMs hold promise as world knowledge bases capable of storing and responding with flexibility, enhancements in their reasoning capabilities are necessary to fully realize their potential. © 2025 Association for Computational Linguistics.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Framework for Analyzing Grammar Error Correction with GPT -3.5

Comprehensive Framework for Analyzing Grammar Error Correcti...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Munda, Rajni Kant Kumar, Abhishek Burman, Ravi Kumar Kumar, Biresh Alam, Md. Shoaib Sinha, Anurag Jharkhand University of Technology Computer Science and Engineering Ranchi India Amity University Computer Science and Engineering Jharkhand Ranchi India Ignou School of Computing and Information Science New Delhi India

ISBN: (纸本)9798331508685

This investigate assesses the viability and exactness of an error-correction approach utilizing GPT-3.5 compared to routine instruments. Letter set rectification plays a vital part in making strides the quality of and improving clarity in different scholastic and proficient situations. The consider utilizes appraisal criteria such as precision, exactness, review, and F1 score to how well GPT-3.5 performs relative to other language structure redress devices. Also, the information incorporates client input and daze testing to gage the viable convenience of the adjustments. Discoveries demonstrate that GPT-3.5 outperforms conventional instruments in taking care of relevant blunders and client fulfilment, illustrating a momentous capacity to redress syntactic botches, indeed in complex sentences with inconspicuous subtleties. Be that as it may, it does confront a few challenges, such as affectability to input varieties and intermittent overcorrection. The think about recommends entering on moving forward relevant understanding and diminishing overcorrection to development these calculations assist. It too investigates potential applications of GPT-3.5 for upgrading composing back and languagelearning assets, highlighting conceivable future investigate ranges to optimize AI-driven language structure rectification models. © 2025 IEEE.

关键词： Instrument errors

来源：评论

学校读者我要写书评

暂无评论

MLDA-Net: Multi-Level Deep Aggregation Network for 3D Nuclei Instance Segmentation

引用

IEEE Journal of Biomedical and Health Informatics 2025年第5期29卷 3516-3525页

作者： Hu, Bin Ye, Zhiwei Wei, Zimei Snezhko, Eduard Kovalev, Vassili Ye, Mang Hubei University of Technology School of Computer Wuhan China Hubei Provincial Key Laboratory of Green Intelligent Computing Power Network Wuhan China United Institute of Informatics Problems of the National Academy of Sciences of Belarus Belarus Wuhan University School of Computer Science Wuhan China

Segmentation of cell nuclei from three-dimensional (3D) volumetric fluorescence microscopy images is crucial for biological and clinical analyses. In recent years, convolutional neural networks have become the reliable 3D medical image segmentation standard. However, convolutional layers are limited by their finite receptive fields and weight-sharing mechanisms. Consequently, they struggle to effectively model long-range dependencies and spatial correlations, which may lead to inadequate nuclei segmentation. Moreover, the diversity in nuclear appearance and density poses additional challenges. This work proposes a lightweight multi-layer deep aggregation network, MLDA-Net, incorporating Wide Receptive Field Attention (WRFA). This module effectively simulates the large receptive field generated by self-attention in the Swin Transformer while requiring fewer model parameters. This design implements an extended global sensory field that enhances the ability to capture a wide range of spatial information. In addition, the multiple cross-attention (MCA) module in MLDA-Net enhances the output features of different resolutions from the encoder while maintaining global effectiveness. The Multi-Path Aggregation Feature Pyramid Network (MAFPN) receives multi-scale outputs from the MCA module, generating a robust hierarchical feature pyramid for the final prediction. MLDA-Net outperforms state-of-the-art networks, including 3DU-Net, nnFormer, UNETR, SwinUNETR, and 3DUXNET, on the 3D volumetric datasets NucMM and MitoEM. It achieves average performance improvements of 4% to 7% in F1 score, MIoU, and PQ metrics, thereby establishing new benchmark results. © 2013 IEEE.

关键词： Fluorescence microscopy

来源：评论

学校读者我要写书评

暂无评论

DCTCS stack classifier-an integrated framework leveraging discrete cosine transformation, cuckoo search algorithm and stacked machine learning models for EEG-based eye state classification

引用

International Journal of Information technology (Singapore) 2025年第4期17卷 2015-2033页

作者： Chandralekha, M. Jayadurga, N. Priyadharshini Chen, Thomas M. Sathiyanarayanan, Mithileysh Department of Computer Science and Engineering Amrita School of Computing AmritaVishwaVidyapeetham Chennai India School of Science & Technology University of London London United Kingdom Research & Innovation MIT Square London United Kingdom

Accurate classification of eye state using Electroencephalogram (EEG) data reflects the high dimensionality and intricacy associated with the nature of the EEG signals. This state-of-the-art technique applies Discrete Cosine Transformation (DCT) for feature extraction, Cuckoo Search Algorithm (CSA) for optimal feature selection followed by a robust stacking algorithm integrating Adaptive Gradient Boosting Classifier (A-GBC) and k-Nearest Neighbors (k-NN) with Logistic Regression as meta-learner to improve the predictive accuracy and model performance. This model would strengthen the accuracy, reliability, and efficiency of eye state classification. DCT is used to compress the time series data into frequency domain for feature extraction, resulting in concentrating a vast amount of superficial signal energy. The next stage uses the Cuckoo Search Algorithm (CSA) in the selection of the optimal features. It thus optimizes the feature sub- set of the input in-order to get an optimal learning rate. The combination of these processes with a stacked ensemble using Adaptive Gradient Boosting Classifier (A-GBC) & k-Nearest Neighbors (k-NN) basal learners results in an immediate classification following the path of a Logistic Regression meta learner that achieves a remarkable classification accuracy of 96.96%. This strongly emphasizes the exceptional efficiency of the proposed framework when placed in context with existing approaches. It implies that the research not only reinforces the existing state of EEG eye state categorization but also provides for the optimization of its utility in other types of biomedical signal processing, thereby making it an example of a versatile medical tool. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Brain-computer Interface (BCI) Cuckoo Search Algorithm (CSA) DCTCS Stack Classifier Discrete Cosine Transformation (DCT) Electroencephalogram (EEG) Eye state Classification Stacked Machine Learning Model

来源：评论

学校读者我要写书评

暂无评论

Adaptive Attribute-Based Honey Encryption: A Novel Solution for Cloud Data Security

引用

computers, Materials & Continua 2025年第2期82卷 2637-2664页

作者： Reshma Siyal Muhammad Asim Long Jun Mohammed Elaffendi Sundas Iftikhar Rana Alnashwan Samia Allaoua Chelloug School of Computer Science and Engineering Central South UniversityChangsha410083China EIAS LAB College of Computer and Information Sciencesand Center of Excellence in Quantum and Intelligent ComputingPrince Sultan UniversityRiyadh11586Saudi Arabia Gianforte School of Computing Montana State UniversityBozemanMT 59717USA Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia

A basic procedure for transforming readable data into encoded forms is encryption, which ensures security when the right decryption keys are used. Hadoop is susceptible to possible cyber-attacks because it lacks built-in security measures, even though it can effectively handle and store enormous datasets using the Hadoop Distributed File System (HDFS). The increasing number of data breaches emphasizes how urgently creative encryption techniques are needed in cloud-based big data settings. This paper presents Adaptive Attribute-Based Honey Encryption (AABHE), a state-of-the-art technique that combines honey encryption with Ciphertext-Policy Attribute-Based Encryption (CP-ABE) to provide improved data security. Even if intercepted, AABHE makes sure that sensitive data cannot be accessed by unauthorized parties. With a focus on protecting huge files in HDFS, the suggested approach achieves 98% security robustness and 95% encryption efficiency, outperforming other encryption methods including Ciphertext-Policy Attribute-Based Encryption (CP-ABE), Key-Policy Attribute-Based Encryption (KB-ABE), and Advanced Encryption Standard combined with Attribute-Based Encryption (AES+ABE). By fixing Hadoop’s security flaws, AABHE fortifies its protections against data breaches and enhances Hadoop’s dependability as a platform for processing and storing massive amounts of data.

关键词： Cybersecurity data security cloud storage hadoop encryption and decryption privacy protection attribute-based honey encryption

来源：评论

学校读者我要写书评

暂无评论

A survey on textual emotion cause extraction in social networks

引用

Digital Communications and Networks 2025年第2期11卷 524-536页

作者： Peng, Sancheng Cao, Lihong Wang, Guojun Ouyang, Zhouhao Zhou, Yongmei Yu, Shui Laboratory of Language Engineering and Computing Center for Linguistics and Applied Linguistics Guangdong University of Foreign Studies Guangzhou510006 China School of English Education Guangdong University of Foreign Studies Guangzhou510006 China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou510006 China South China University of Technology Guangzhou510006 China School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou510006 China School of Computer Science University of Technology Sydney SydneyNSW2007 Australia

With the rapid development of web technology, Social Networks (SNs) have become one of the most popular platforms for users to exchange views and to express their emotions. More and more people are used to commenting on a certain hot spot in SNs, resulting in a large amount of texts containing emotions. Textual Emotion Cause Extraction (TECE) aims to automatically extract causes for a certain emotion in texts, which is an important research issue in natural language processing. It is different from the previous tasks of emotion recognition and emotion classification. In addition, it is not limited to the shallow-level emotion classification of text, but to trace the emotion source. In this paper, we provide a survey for TECE. First, we introduce the development process and classification of TECE. Then, we discuss the existing methods and key factors for TECE. Finally, we enumerate the challenges and developing trend for TECE. © 2024 Chongqing University of Posts and Telecommunications

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Telugu Language Analysis with XLM-RoBERTa: Enhancing Parts of Speech Tagging for Effective Natural Language Processing

引用

SN computer science 2025年第2期6卷 1-13页

作者： Bharathi Mohan, G. Prasanna Kumar, R. Krishna Jayanth, K. Doss, Srinath Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Faculty of Engineering and Technology Botho University Gaborone Botswana

This research investigates the efficacy of XLM-RoBERTa, a potent deep learning architecture rooted in transformer networks, for Part-of-Speech (POS) tagging—a foundational task in Natural Language Processing (NLP). The study narrows its focus to address the formidable UCD Telugu dataset, renowned for its intricate morphological characteristics that pose challenges to accurate tagging. Through meticulous fine-tuning of the pre-trained XLM-RoBERTa model. This study adeptly discerns and exploit intricate syntactic and semantic patterns underpinning the interplay between lexical elements and their respective POS tags. The rigorous evaluation regimen, complemented by a comprehensive statistical comparison with the Multilingual BERT model, conclusively establishes XLM-RoBERTa’s superiority. This advanced model attains a remarkable accuracy score of 91%, decisively surpassing the Multilingual BERT model, which achieves an accuracy of 88%. These findings not only underscore XLM-RoBERTa’s prowess in precise POS tagging, especially in the context of morphologically rich languages like Telugu, but also carry significant implications for the broader NLP community. This research unlocks valuable insights and positions XLM-RoBERTa as an exemplar of reliability and robustness in POS tagging. Furthermore, it extends an invitation for further exploration and innovation in deep learning architectures within the NLP domain. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bert Multilingual Bert NLP Parts-of-speech tagging Telugu XLM-RoBERTa

来源：评论

学校读者我要写书评

暂无评论

Multiple Edge Data Integrity Verification with Multi-Vendors and Multi-Servers in Mobile Edge computing

引用

IEEE Transactions on Mobile computing 2025年第6期24卷 4668-4683页

作者： Islam, Md Rashedul Xiang, Yong Uddin, Md Palash Zhao, Yao Kua, Jonathan Gao, Longxiang The School of Information Technology Deakin University GeelongVIC3220 Australia The Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

Ensuring Edge Data Integrity (EDI) is imperative in providing reliable and low-latency services in mobile edge computing. Existing EDI schemes typically address single-vendor (App Vendor, AV) single-server (Edge Server, ES), single-vendor multi-server, and multi-vendor multi-server scenarios, which consider a single data replica cached by an ES from the AVs. However, the most practical scenario of Multi-Vendors and Multi-Servers with Multiple Data (MVMS-MD) cached by an ES from different AVs remains unexplored. Current solutions struggle when applied to this scenario due to increased computation and communication costs in the verification process across all ESs using the classical challenge-response per-data multi-round strategy. To tackle this issue, we propose a Multiple EDI-Verification (MEDI-V) approach in this paper. In particular, our MEDI-V utilizes an adaptive Merkle Hash Tree (ad-MHT) to efficiently generate a tree of multiple data replicas within each AV. Next, the dynamic mechanism computes minimal verification information using ad-MHT to create a challenge for individual ESs to produce EDI proofs. The ES then leverages its ad-MHT and the ES’s proof to send the reconstructed ad-MHT root to the AV for verification. Theoretical insights into MEDI-V’s correctness, efficiency, security, and comprehensive evaluations demonstrate its superiority in addressing MEDI issues in the MVMS-MD scenario. © 2002-2012 IEEE.

关键词： Data integrity

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：