检索结果-内蒙古大学图书馆

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

Comprehensive Investigation and Evaluation of an Indoor 3D System Performance Based on Visible Light Communication 3

Comprehensive Investigation and Evaluation of an Indoor 3D S...

引用

3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023

作者： Faraj Al Khattat, Vailet Hikmat Ahmad Anas, Siti Barirah Saif, Abdu Faculty of Engineering Universiti Putra Malaysia Department of Computer and Communication Systems Engineering UPM Serdang Selangor 43400 Malaysia Taiz University Faculty of Engineering and It Department of Communication and Computer Engineering Yemen

ISBN: (纸本)9798350305333

The obvious and accelerator trend towards efficient green technology in a modern technological revolution time makes visible light communication (VLC) a solution key to meeting this growth. Besides the illumination function, VLC uses for data transmission at high speed with the lowest cost due to utilizing the infrastructure that already exists. As a result of VLC's multiple features, it had been used in the indoor positioning system (IPS) in many pieces of research to obtain a high accuracy without conflict with the Radio Frequency (RF) spectrum besides it providing high security from any penetrating. However, achieving good performance parameters is essential and fundamental in evaluating the effectiveness of any indoor system that many pieces of research neglected and concentrated more on the positioning accuracy aspect. This paper investigates and analyses the performance of the indoor system that is designed and developed based on a VLC and proves its effectiveness through a comprehensive evaluation. Signal-to-noise ratio (SNR) and path loss are the performance parameters that are investigated in this system by varying the transmitted power, incidence angles, and Lambertian mode number in the line of sight (LOS) scenario. The examined system consists of one light-emitting diode (LED) in a 3D typical room and one photodiode (PD) in different ten locations along the half-diagonal line towards the corner. Utilizing a single LED in this system is important to avoid the interference that occurs when utilizing multiple LEDs;besides, it is more convenient in the indoor environment. The obtained results by MATLAB simulation show the reliable and effective performance of the proposed developed VLC system design by achieving a good SNR with low path loss. Furthermore, the proposed system approach proves how the optimum position of PD is crucial to obtain a strong signal with the lowest ratio of noise and losses. © 2023 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review of Federated Learning Mechanism for The Internet of Medical Things 1

A Systematic Review of Federated Learning Mechanism for The ...

引用

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Aravind, P. Jerlin, M Asha Devarajan, Ganesh Gopal Nagarajan, Senthil Murugan School of Computer Science and Engineering Vellore Institute of Technology Chennai India SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Computer Science and Engineering Uttar Pradesh Ghaziabad201204 India Medicine University of Luxembourg Faculty of Science Technology Department of Mathematics Luxembourg

ISBN: (纸本)9798350353648

The rapid evolution of healthcare technology, no-tably the integration of the Internet of Medical Things (loMT), has revolutionized patient care, diagnosis, and treatment method-ologies. However, this progress introduces substantial challenges, primarily concerning the security, privacy, and interoperability of sensitive medical data. Federated Learning, a decentralized ma-chine learning approach, emerges as a possible solution to address these difficulties since it allows for collaborative model training without requiring raw patient data exchange. This systematic review explores and evaluates various FL mechanisms tailored for 10MT applications. The review examines existing literature, encompassing the amalgamation of loT and healthcare, the challenges faced in traditional health care systems, and the role of FL in mitigating these challenges. It highlights applications, privacy-preserving techniques, security measures, advantages, limitations, and potential enhancements in utilizing FL within 10MT environments. The review also presents a structured methodology for evaluating FL paradigms, encompassing performance metrics, privacy/security analysis, advantages/limitations assessment, and comparative analysis. Moreover, the paper pro-poses an innovative framework for federated learning in 10MT, detailing its architecture, modules, algorithms, functionalities, ethical considerations, and expected impact. Through a comprehensive analysis and synthesis of existing literature and proposed strategies, this review aims to provide insights for health care stakeholders in selecting and implementing optimal FL strategies for collaborative medical advancements while upholding stringent data privacy and security standards in 10MT. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

TELEX: Two-Level Learned Index for Rich Queries on Enclave-based Blockchain systems

引用

IEEE Transactions on Knowledge and Data engineering 2025年第07期37卷 4299-4313页

作者： Wu, Haotian Tang, Yuzhe Shen, Zhaoyan Tao, Jun Lin, Chenhao Peng, Zhe The Hong Kong Polytechnic University Department of Industrial and Systems Engineering Hong Kong Syracuse University Department of Electrical Engineering and Computer Science United States Shandong University School of Computer Science and Technology China Southeast University School of Cyber Science and Engineering China Xi'an Jiaotong University Faculty of Electronic and Information Engineering China The Hong Kong Polytechnic University Shenzhen Research Institute Hong Kong

Blockchain has become a popular paradigm for secure and immutable data storage. Despite its numerous applications across various fields, concerns regarding the user privacy and result integrity during data queries persist. Additionally, the need for rich query functionalities to harness the full potential of blockchain data remains an area ripe for exploration. In order to address these challenges, our paper first utilizes a framework based on the Trusted Execution Environment (TEE) and oblivious RAM technique to achieve both privacy and data integrity. To enhance the query efficiency over the entire blockchain, we then devise a two-level learned indexing methodology named TELEX within the TEE for both integer and string keys. We also propose different query processing algorithms for versatile query types, including exact queries, aggregate queries, Boolean queries, and range queries. By implementing the prototype and conducting extensive evaluation, we demonstrate the feasibility and remarkable improvement in efficiency compared to existing solutions. © 1989-2012 IEEE.

关键词： Query languages

来源：评论

学校读者我要写书评

暂无评论

Battery Monitoring System on IoT-Based Smart Micro Grid 4

Battery Monitoring System on IoT-Based Smart Micro Grid

引用

4th International Conference on Electronic and Electrical engineering and Intelligent System, ICE3IS 2024

作者： Iksan, Nur Widodo, Djoko Adi Djuniadi, Djuniadi Putri, Riana Defi Mahadji Suryanto, Agus Udayanti, Erika Devi Universitas Negeri Semarang Faculty of Engineering Department of Electrical Engineering Indonesia Universitas Dian Nuswantoro Faculty of Computer Science Department of Information System Indonesia

ISBN: (纸本)9798350378368

The use of batteries as an energy storage medium has a very important role in the installation of renewable energy power plants, such as photovoltaics to overcome intermittency in photovoltaics and to maintain stable power quality. In this study, the installation of solar plants that was used as the research object was a smart micro grid that integrates photovoltaic electrical energy sources with the Utility electricity network for residential scale. The battery monitoring system is used to manage the performance of existing batteries on the electricity grid through analysis of the battery's electrical values such as current, voltage, power and energy, so that it can function optimally in storing electrical energy and supplying electricity to users. Internet of things (IoT) technology is used to provide easy transfer of data obtained through the process of data acquisition to data visualization provided to be accessed by users in real time. This research aims to develop an IoT-based battery monitoring system. The development carried out focuses on the data acquisition process, the data transfer process using IoT technology, the process of analyzing and visualizing data on the IoT cloud and remote access to users. © 2024 IEEE.

关键词： Battery IoT Monitoring Smart Micro Grid

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Optimization of Time Series Models for Predicting Networks Traffic

引用

computers, Materials & Continua 2023年第4期75卷 427-442页

作者： Reem Alkanhel El-Sayed M.El-kenawy D.L.Elsheweikh Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Doaa Sami Khafaga Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Department of Computer Science Faculty of Specific EducationMansoura UniversityEgypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh 11671Saudi Arabia

Traffic prediction of wireless networks attracted many researchersand practitioners during the past decades. However, wireless traffic frequentlyexhibits strong nonlinearities and complicated patterns, which makes it challengingto be predicted accurately. Many of the existing approaches forpredicting wireless network traffic are unable to produce accurate predictionsbecause they lack the ability to describe the dynamic spatial-temporalcorrelations of wireless network traffic data. In this paper, we proposed anovel meta-heuristic optimization approach based on fitness grey wolf anddipper throated optimization algorithms for boosting the prediction accuracyof traffic volume. The proposed algorithm is employed to optimize the hyperparametersof long short-term memory (LSTM) network as an efficient timeseries modeling approach which is widely used in sequence prediction *** prove the superiority of the proposed algorithm, four other optimizationalgorithms were employed to optimize LSTM, and the results were *** evaluation results confirmed the effectiveness of the proposed approachin predicting the traffic of wireless networks accurately. On the other hand,a statistical analysis is performed to emphasize the stability of the proposedapproach.

关键词： Network traffic soft computing LSTM metaheuristic optimization

来源：评论

学校读者我要写书评

暂无评论

Adaptive isomap feature extractive gradient deep belief network classifier for diabetic retinopathy identification

引用

Multimedia Tools and Applications 2025年第9期84卷 6349-6370页

作者： Singh, Alka Kumar, Rakesh Gandomi, Amir H. Department of Computer Science and Engineering Madan Mohan Malaviya University of Technology Gorakhpur India Faculty of Engineering & Information Technology University of Technology Sydney SydneyNSW Australia Óbuda University Budapest1034 Hungary

Diabetic retinopathy (DR) is an infection that bases eternal visualization loss in patients with diabetes mellitus. With DR, the glucose level in the blood increases, as well as its viscosity, this results in fluid leakage into surrounding tissues in the retina. In other words, DR represents the pathology of capillaries and venules in the retina with leakage effects, being the main acute retinal disorder caused by diabetes. Many DR detection methods have been previously discussed by different researchers;however, accurate DR detection with a reduced execution time has not been achieved by existing methods. The proposed method, the Shape Adaptive box linear filtering-based Gradient Deep Belief network classifier (SAGDEB) Model, is performed to enhance the accuracy of DR detection. The objective of the SAGDEB Model is to perform an efficient DR identification with a higher accuracy and lower execution time. This model comprises three phases: pre-processing, feature extraction, and classification. The shape adaptive box linear filtering image pre-processing is carried out to reduce the image noise without removing significant parts of image content. Then, an isomap geometric feature extraction is performed to compute features of different natures, like shape, texture, and color, from the pre-processed images. After that, the Adaptive gradient Tversky Deep belief network classifier is to perform classification. The deep belief network is probabilistic and generative graphical model that consists of multiple layers such as one input unit, three hidden units, and one output unit. The extracted image featuresare considered in the input layer and these images are sent to hidden layers. Tversky similarity index is applied in hidden layer 1 to analyze the extracted features with testing features. Regarding the similarity value, the sigmoid activation function is determined in hidden layer 2 so different levels of DR can be identified. Finally, the adaptive gradient method is

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A DL-DeNoiseNet Framework for Robust Image Denoising and Artifact Reduction in Medical Image Diagnostics 2

A DL-DeNoiseNet Framework for Robust Image Denoising and Art...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication systems, ICIICS 2024

作者： Nanthini, S. Maindola, Meenakshi Madhu, R. Ravishankar, M.D. Gandhi, Jay Patil, Harshal Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Department of Mechanical Engineering The National Institute of Engineering Mysore India Faculty of Engineering and Technology Parul institute of Engineering and Technology Vadodara India School of Computer Science and Engineering IILM University Greater Noida India

ISBN: (纸本)9798331504960

For precise illness diagnosis and therapy planning, medical imaging diagnostics are necessary. Nevertheless, diagnostic errors can occur due to noise and aberrations that are inherent to imaging modalities including CT, MRI, and ultrasound, which can hide important features. In order to overcome this obstacle, we present a medical diagnostics-specific framework for deep learning-based picture denoising and artifact reduction. Our method improves feature extraction while maintaining picture integrity by combining a Convolutional Neural Network (CNN) with a Residual Dense Block (RDB). To guarantee optimal performance across varying degrees of noise and image types, the framework is trained on a broad dataset of medical photos, which includes images that are artifact-laden and noisy. A combination of supervised and adversarial learning techniques is used for this purpose. Adaptive filtering for preprocessing, the CNN-RDB network for denoising, and a refinement module that uses perceptual loss to keep things clinically relevant for postprocessing are the three primary steps in the methodology. The model outperforms traditional denoising methods when tested on various medical imaging metrics, including a PSNR of 40.3 dB and an SSIM of 0.97. Furthermore, the suggested architecture successfully mitigates artifacts by an average of 35% as assessed by the Normalized Root Mean Squared Error (NRMSE), guaranteeing that essential diagnostic characteristics are preserved. The results show that the model can improve image clarity, which means that diagnoses can be made more accurately and fewer scans are needed. Better healthcare outcomes are a direct result of the substantial enhancements to picture quality that this framework provides to physicians and radiologists. © 2024 IEEE.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Towards Non-Invasive Swallowing Assessment: An AI-Powered Interface for Swallowing Kinematic Analysis using High-Resolution Cervical Auscultation 46

Towards Non-Invasive Swallowing Assessment: An AI-Powered In...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Luo, Yuewen Anwar, Ayman Ren, Siyi Coyle, James L. Sejdic, Ervin University of Toronto Division of Engineering Science Faculty of Applied Science & Engineering TorontoON Canada University of Toronto Faculty of Applied Science & Engineering Department of Electrical and Computer Engineering TorontoON Canada University of Pittsburgh School of Health and Rehabilitation Sciences Department of Communication Science and Disorders PittsburghPA United States University of Toronto North York General Hospital Faculty of Applied Science & Engineering Department of Electrical and Computer Engineering TorontoON Canada

ISBN: (纸本)9798350371499

Swallowing is a pivotal physiological function for human sustenance and hydration. Dysfunctions, termed dysphagia, necessitate prompt and precise diagnosis. Videofluoroscopic swallowing studies (VFSS) remain the gold standard for swallowing assessment but pose accessibility and radiation exposure concerns. High-resolution cervical auscultation (HRCA) presents a non-invasive alternative with comparable accuracy. Yet, existing studies have only assessed HRCA in tandem with VFSS, without applying it to clinical settings. We propose an AI-enhanced PC software deploying HRCA for real-time bedside swallowing screening. This software proficiently detects abnormalities and precisely measures key kinematic events, including upper esophageal sphincter opening and laryngeal vestibule closure duration. The system was evaluated through two studies, encompassing a VFSS comparative analysis and a usability study. Our findings underscored the software's superior operational efficiency and diagnostic accuracy, positioning our HRCA-based system as a refined and pragmatic alternative for dysphagia assessment. © 2024 IEEE.

关键词： User centered design

来源：评论

学校读者我要写书评

暂无评论

A New Cybersecurity Approach Enhanced by xAI-Derived Rules to Improve Network Intrusion Detection and SIEM

引用

computers, Materials & Continua 2025年第5期83卷 1607-1621页

作者： Federica Uccello Marek Pawlicki Salvatore D'Antonio RafałKozik MichałChoras Centro Direzionale Department of EngineeringUniversity of Naples‘Parthenope’Isola C4Napoli80133Italy Department of Computer and Information Science Software and SystemsLinköping UniversityLinköping58183Sweden ITTI Sp.z o.o. Pozna´n61-612Poland Faculty of Telecommunications Computer Science and Electrical EngineeringBydgoszcz University of Science and TechnologyBydgoszcz85-796Poland

The growing sophistication of cyberthreats,among others the Distributed Denial of Service attacks,has exposed limitations in traditional rule-based Security Information and Event Management *** machine learning–based intrusion detection systems can capture complex network behaviours,their“black-box”nature often limits trust and actionable insight for security *** study introduces a novel approach that integrates Explainable Artificial Intelligence—xAI—with the Random Forest classifier to derive human-interpretable rules,thereby enhancing the detection of Distributed Denial of Service(DDoS)*** proposed framework combines traditional static rule formulation with advanced xAI techniques—SHapley Additive exPlanations and Scoped Rules-to extract decision criteria from a fully trained *** methodology was validated on two benchmark datasets,CICIDS2017 and *** rules were evaluated against conventional Security Information and Event Management systems rules with metrics such as precision,recall,accuracy,balanced accuracy,and Matthews Correlation *** results demonstrate that xAI-derived rules consistently outperform traditional static ***,the most refined xAI-generated rule achieved near-perfect performance with significantly improved detection of DDoS traffic while maintaining high accuracy in classifying benign traffic across both datasets.

关键词： Cybersecurity explainable artificial intelligence intrusion detection system rule-based SIEM distributed denial of service

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：