检索结果-内蒙古大学图书馆

7th Workshop on Computational Models of Reference, Anaphora and Coreference, CRAC 2024

作者： Pražák, Ondřej Konopík, Miloslav Department of Computer Science and Engineering NTIS - New Technologies for the Information Society Faculty of Applied Sciences University of West Bohemia Technická 8 Plzeň306 14 Czech Republic

ISBN: (纸本)9798891761711

This paper describes our approach to the CRAC 2024 Shared Task on Multilingual Coreference Resolution. Our model is based on an end-to-end coreference resolution system. Apart from joined multilingual training, we improved our results with headword mention representation and training large model mT5-xxl through LORA. We provide an analysis of the performance of our model. Our system ended up in 4th place. Moreover, we reached the best performance on three datasets out of 21. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Research and development of an information system for speech recognition based on neural network algorithms metrics 4

Research and development of an information system for speech...

引用

4th IEEE International Conference on Smart information Systems and technologies, SIST 2024

作者： Kanashev, Maksat Mukasheva, Assel Yedilkhan, Didar Rakhmetulaeva, Sabina Gnatyuk, Sergiy Nazym, Mirambayeva Almaty University of Power Engineering and Telecommunications Almaty Kazakhstan The School of Information Technology and Engineering Kazakh-British Technical University Almaty Kazakhstan The Department of Computer Engineering Astana IT University Astana Kazakhstan The Department of Information Systems International University of Information Technologies Almaty Kazakhstan The Faculty of Cybersecurity Computer and Software Engineering National Aviation University National Aviation University Kyiv Ukraine

ISBN: (纸本)9798350374865

This article examines the parameters of speech recognition in audio recordings containing a variety of phrases uttered by different people with different accents and intonations. The aim of the study is to evaluate the recognition speed, the accuracy of audio-to-text conversion and resource consumption when using SpeechRecognition and Levenshtein libraries. During the analysis, the above libraries were used to record and recognize audio files, as well as to calculate the distance between two lines and determine the recognition accuracy. The findings of this study can be useful for improving speech recognition systems and creating more adaptive and efficient solutions for audio data processing. The results of comparing the accuracy of speech recognition models are recorded in JSON format, after which, using the matplotlib library, they are visualized as graphs, comparing the speed and accuracy of recognition. Visualization of data in this way contributes to their improvement and more effective integration into educational systems. In conclusion, the authors emphasize the prospects for further development of speech recognition technologies in different fields. © 2024 IEEE.

关键词： Audio recordings

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Secure Clustering Scheme for Energy Harvesting Wireless Sensor Networks

引用

computer Systems Science & engineering 2023年第4期45卷 497-512页

作者： S.Nithya Roopa P.Anandababu Sibi Amaran Rajesh Verma Department of Computer Science and Engineering Kumaraguru College of TechnologyCoimbatore641049India Department of Computer and Information Science Faculty of ScienceAnnamalai UniversityChidambaram608002India Department of Computing Technologies SRM Institute of Science and TechnologyChennai603203India Department of Electrical Engineering King Khalid UniversityAbha61411Kingdom of Saudi Arabia

Recently,energy harvesting wireless sensor networks(EHWSN)have increased significant attention among research *** harvesting energy from the neighboring environment,the sensors in EHWSN resolve the energy constraint problem and offers lengthened network *** is one of the proficient ways for accomplishing even improved lifetime in *** clustering process intends to appropriately elect the cluster heads(CHs)and construct *** several models are available in the literature,it is still needed to accomplish energy efficiency and security in *** this view,this study develops a novel Chaotic Rider Optimization Based Clustering Protocol for Secure Energy Harvesting Wireless Sensor Networks(CROC-SEHWSN)*** presented CROC-SEHWSN model aims to accomplish energy efficiency by clustering the node in *** CROC-SEHWSN model is based on the integration of chaotic concepts with traditional rider optimization(RO)***,the CROC-SEHWSN model derives a fitness function(FF)involving seven distinct parameters connected to *** accomplish security,trust factor and link quality metrics are considered in the *** design of RO algorithm for secure clustering process shows the novelty of the *** order to demonstrate the enhanced performance of the CROC-SEHWSN approach,a wide range of simulations are carried out and the outcomes are inspected in distinct *** experimental outcome demonstrated the superior performance of the CROC-SEHWSN technique on the recent approaches with maximum network lifetime of 387.40 and 393.30 s under two scenarios.

关键词： Clustering wireless sensor networks network lifetime energy efficiency metaheuristics energy harvesting rider optimization

来源：评论

学校读者我要写书评

暂无评论

Improving long-tail classification via decoupling and regularisation

引用

CAAI Transactions on Intelligence Technology 2025年第1期10卷 62-71页

作者： Shuzheng Gao Chaozheng Wang Cuiyun Gao Wenjian Luo Peiyi Han Qing Liao Guandong Xu School of Computer Science and Technology Harbin Institute of TechnologyShenzhenChina Peng Cheng Laboratory ShenzhenChina Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Harbin Institute of TechnologyShenzhenChina Faculty of Engineering and Information Technology University of Technology SydneySydneyNew South WalesAustralia

Real-world data always exhibit an imbalanced and long-tailed distribution,which leads to poor performance for neural network-based *** methods mainly tackle this problem by reweighting the loss function or rebalancing the ***,one crucial aspect overlooked by previous research studies is the imbalanced feature space problem caused by the imbalanced angle *** this paper,the authors shed light on the significance of the angle distribution in achieving a balanced feature space,which is essential for improving model performance under long-tailed ***,it is challenging to effectively balance both the classifier norms and angle distribution due to problems such as the low feature *** tackle these challenges,the authors first thoroughly analyse the classifier and feature space by decoupling the classification logits into three key components:classifier norm(*** magnitude of the classifier vector),feature norm(*** magnitude of the feature vector),and cosine similarity between the classifier vector and feature *** this way,the authors analyse the change of each component in the training process and reveal three critical problems that should be solved,that is,the imbalanced angle distribution,the lack of feature discrimination,and the low feature *** from this analysis,the authors propose a novel loss function that incorporates hyperspherical uniformity,additive angular margin,and feature norm *** component of the loss function addresses a specific problem and synergistically contributes to achieving a balanced classifier and feature *** authors conduct extensive experiments on three popular benchmark datasets including CIFAR-10/100-LT,ImageNet-LT,and iNaturalist *** experimental results demonstrate that the authors’loss function outperforms several previous state-of-the-art methods in addressing the challenges posed by imbalanced and longtailed datasets,t

关键词： computer vision image classification long-tailed data machine learning

来源：评论

学校读者我要写书评

暂无评论

MQDD: Pre-training of Multimodal Question Duplicity Detection for Software engineering Domain

MQDD: Pre-training of Multimodal Question Duplicity Detectio...

引用

2023 International Conference Recent Advances in Natural Language Processing: Large Language Models for Natural Language Processing, RANLP 2023

作者： Pašek, Jan Sido, Jakub Konopík, Miloslav Pražák, Ondřej NTIS - New Technologies for the Information Society Department of Computer Science and Engineering Faculty of Applied Sciences University of West Bohemia Plzeň Czech Republic

ISBN: (纸本)9789544520922

This work proposes a new pipeline for leveraging data collected on the Stack Overflow website for pre-training a multimodal model for searching duplicates on question answering websites. Our multimodal model is trained on question descriptions and source codes in multiple programming languages. We design two new learning objectives to improve duplicate detection capabilities. The result of this work is a mature, fine-tuned Multimodal Question Duplicity Detection (MQDD) model, ready to be integrated into a Stack Overflow search system, where it can help users find answers for already answered questions. Alongside the MQDD model, we release two datasets related to the software engineering domain. The first Stack Overflow Dataset (SOD) represents a massive corpus of paired questions and answers. The second Stack Overflow Duplicity Dataset (SODD) contains data for training duplicate detection models. © 2023 Incoma Ltd. All rights reserved.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Soliton Solutions for Coupled Nonlinear Generalized Zakharov Equations with Anti-cubic Nonlinearity Using Various Techniques

引用

International Journal of Applied and Computational Mathematics 2024年第1期10卷 1-30页

作者： AlQahtani, Salman A. Alngar, Mohamed E. M. New Emerging Technologies and 5G Network and Beyond Research Chair Department of Computer Engineering College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia Basic Science Department Faculty of Computers and Artificial Intelligence Modern University for Technology and Information Cairo 11585 Egypt

This study introduces novel exact solutions for the coupled nonlinear generalized Zakharov equations with anti-cubic nonlinearity. Utilizing a variety of mathematical approaches, including the extended trial function method, the rational exp (-ψ(ξ))-expansion method, and three well-known auxiliary equation methods, a spectrum of solutions is derived. These solutions encompass dark solitons, bright solitons, singular solitons, Jacobi elliptic functions, periodic waves, and rational solutions. The unique contribution lies in the use of a phase variable θ(ξ) instead of a phase constant, providing fresh insights into wave behavior. A comparative analysis underscores the originality of the derived solutions, setting this work apart from prior studies. These findings advance our understanding of nonlinear dynamics and mathematical modeling, with potential applications in various domains. © 2023, The Author(s), under exclusive licence to Springer Nature India Private Limited.

关键词： Coupled nonlinear generalized Zakharov equations Extended trial function method Rational exp(- ψ(ξ))-expansion method Soliton solutions Three famous auxiliary equation methods

来源：评论

学校读者我要写书评

暂无评论

Threats Detection and Analysis Based on SYSMON Tool 13

Threats Detection and Analysis Based on SYSMON Tool

引用

13th International Conference on Dependable Systems, Services and technologies, DESSERT 2023

作者： Bahniuk, Nataliia Oleksandr, Linchuk Kateryna, Bortnyk Inna, Kondius Kateryna, Melnyk Kondius, Kostiantyn Lutsk National Technical University Department of Computer Engineering and Cyber Security Lutsk Ukraine Lutsk National Technical University Dean of the Faculty of Computer and Information Technologies Lutsk Ukraine

ISBN: (纸本)9798350396119

In this work, an nalysis for the study of threats in a real environment with the possibility of conducting a full-fledged analysis of threats, as well as their simulationhas been developed for research purposes. Designed laboratory was built for the threats research, specification of deploying and configuring Sysmon, imitation of an attack in laboratory conditions and its investigation by implicit signs, the processesing of threat analysis using the Sysmon tool. We present a system based on the analysis of continuous input chan-nels of Sysmon logs. The system is based on the Cyber Threat Analysis Ontology and analyzes SYSMON logs to classify software according to different threat levels and enhance cyber defense capabilities with situational awareness, prediction and auto-mated actions. The developed laboratory improves the effectiveness of threat analysis using the Sysmon tool, makes study of threats, deploying and configuring Sysmon, imitation of an attack in laboratory conditions and its investigation by implicit signs. It can be applied for the study of threats in a real environment with the possibility of conducting a full-fledged analysis of threats, as well as their simulation for research purposes. © 2023 IEEE.

关键词： Laboratories

来源：评论

学校读者我要写书评

暂无评论

Ferroelectrically gated two-dimensional bismuth oxyselenides for strain-invariant flexible synaptic thin-film transistors

引用

Science China(information Sciences) 2025年第5期68卷 396-403页

作者： Jie WEN Fei XIAO Zheng-Dong LUO Dongxin TAN Xuetao GAN Dawei ZHANG Zhufei CHU Yinshui XIA Yan LIU Genquan HAN Hangzhou Institute of Technology Xidian University State Key Discipline Laboratory of Wide Band Gap Semiconductor Technology School of MicroelectronicsXidian University Key Laboratory of Light Field Manipulation and Information Acquisition Ministry of Industry and Information Technology Shaanxi Key Laboratory of Optical Information Technology School of Physical Science and Technology Northwestern Polytechnical University School of Materials Science and Engineering The University of New South Wales ARC Centre of Excellence in Future Low-Energy Electronics Technologies (FLEET) The University of New South Wales Faculty of Electrical Engineering Computer Science Ningbo University

Two-dimensional van der Waals（2D vdW） semiconductors have proven to be of great importance for flexible thinfilm transistors（TFTs） owing to their intrinsic mechanical flexibility and superior electronic *** particular,bismuth oxyselenide（Bi2O2Se）,featuring ultrahigh electron mobility along with facile scalable thin-film growth methods,could offer a new option to deliver massively enhanced potential for flexible ***,it has remained a challenge to achieve nonvolatile flexible memory devices based on Bi2O2Se TFTs,thereby hindering the extension of Bi2O2Se TFTs to storage and emerging neuromorphic computing ***,a flexible synaptic TFT is demonstrated through the creation of a Bi2O2Se-based ferroelectric field-effect transistor（FeFET） structure on the flexible mica *** proposed device exhibits excellent nonvolatile memory characteristics,including a large memory window,excellent current modulation ratio,great retention,and strong ***,the Bi2O2Se-based FeFET can be operated as a synaptic device with analog conductance-modulating *** to the superior mechanical flexibility of the component materials and the mica substrate,the Bi2O2Se-based FeFETs can retain their performance against various bending states,showing a straininvariant electrical *** study marks the advancement of Bi2O2Se-based TFTs toward flexible nonvolatile memories and synaptic devices.

关键词： Bi$_{2}$O$_{2}$Se FeFET nonvolatile memory flexible device synaptic transistor

来源：评论

学校读者我要写书评

暂无评论

Exploring Post-Quantum Cryptographic Algorithms for Secure Data Transmission 3

Exploring Post-Quantum Cryptographic Algorithms for Secure D...

引用

3rd IEEE International Conference on Problems of Informatics, Electronics and Radio engineering, PIERE 2024

作者： Gulomov, Sherzod R. Khudayberganov, Temur R. Ravshanova, Maftuna X. Turdiev, Temur T. Atabayev, Sultonbek S. Tashkent University of Information Technologies named after Muhammad al-Khwarizmi Dean of the Faculty of Cyber Security Urgench Uzbekistan Urgench branch of Tashkent University of Information Technologies named after Muhammad al-Khwarizmi Dept. Information security Urgench Uzbekistan Urgench Branch of Tashkent University of Information Technologies named after Muhammad al-Khwarizmi Dept. Computer engineering Urgench Uzbekistan Urgench branch of Tashkent University of Information Technologies named after Muhammad al-Khwarizmi Dept. Information technology Urgench Uzbekistan Urgench Branch of Tashkent University of Information Technologies named after Muhammad al-Khwarizmi Dept. Computer engineering Urgench Uzbekistan

ISBN: (纸本)9798331516321

The rapid advancement of quantum computing introduces a critical threat to established cryptographic systems, such as RSA and ECC, by enabling quantum attacks those classical systems cannot withstand. This evolving threat creates a necessity for post-quantum cryptographic (PQC) algorithms to ensure secure data transmission in the quantum era. PQC encompasses diverse approaches, including lattice-based, hash-based, code-based, and multivariate polynomial cryptography. Each category offers distinct advantages and challenges: lattice-based algorithms provide robust security but may require substantial computational resources, while hash-based approaches are easier to implement but limited in flexibility. Code-based algorithms deliver strong security with significant computational demand, and multivariate polynomial approaches boast efficiency, though they face scrutiny over quantum resilience. This paper evaluates these PQC algorithms in terms of their security, performance, and feasibility, identifying optimal methods to secure data transmission in a future where quantum threats are prevalent. © 2024 IEEE.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Ensemble Learning Methods for Turkish Text Categorization

A Comparative Study of Ensemble Learning Methods for Turkish...

引用

International Artificial Intelligence and Data Processing Symposium (IDAP)

作者： Ezgi Zorarpaci Department of Computer Engineering Faculty of Computer and Information Technologies Istanbul University Istanbul Turkey

ISBN: (数字)9798331531492

ISBN: (纸本)9798331531508

Text categorization (TC) is a natural language processing (NLP) task commonly used in text mining. It is defined as the automatic assignment of text to a set of given categories. Ensemble-based methods that unify multiple models effectively improve the prediction performance and result in higher accuracies than a standalone classifier in general. Motivated by this idea, it is proposed to evaluate the performances of the different ensemble classifiers on Turkish TC dataset (i.e., TTC-3600) in this paper. Firstly, OneR attribute evaluator algorithm diminishes the high dimensionality of Turkish text training data. Different combinations of the base classification algorithms are then compared using this reduced data to assess the impact of ensemble learning on Turkish text data. Bayesian network (BN), extra tree (ET), random forest (RF), and multinomial naive bayes (MNB) classification algorithms are used for the base classifiers. bagging, adaBoost, and voting mechanisms are employed to unify these base classifiers in ensemble learning. According to the experimental results, the proposed model achieves a competitive classification accuracy ($93.83 \%$) to the state-of-the-art (SOTA) methods. Moreover, the proposed method has a pretty low runtime that is only 125.8 seconds for TC task.

关键词： Accuracy Runtime Text categorization Training data Natural language processing Classification algorithms Bayes methods Ensemble learning Random forests Classification tree analysis

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：