检索结果-内蒙古大学图书馆

Natural Language Generation in AI: Developing Human-Like Text Through Deep Learning 1

Natural Language Generation in AI: Developing Human-Like Tex...

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

作者： Arabelli, Rajeshwarrao Gupta, Suneet Prakash, Nilima Ali, Zainab School of Engineering SR University Department of Electronics and Communications Engineerin Warangal India School of Computer Science and Engineering Galgotias University Greater Noida India Northcap University Gurugram India Vivekananda Global University Department of Journalism & Mass Communication Jaipur India

ISBN: (纸本)9798331518578

Natural Language Generation (NLG) is a subset of artificial intelligence that has as its goal to develop techniques to synthesize human language. This paper focuses on the finding of NLG as a field of study as well as how it benefitted from ideas such as deep learning. Next, we consider the development of NLG models, from standard Recurrent Neural Networks to Long Short-Term Memory networks and from Transformers like GPT. Transformer models have proven to be magnificent for the NLG as they remove the drawbacks of previous models and have improved the long-range dependencies and have synthesized appropriate topic-based content. This paper assesses the merits and the demerit of these models and the areas where that they are used such as healthcare, content creation and customer care. Transformer models are particularly good at producing high-quality text, for which it comes with severe difficulties though. The research for this paper aims to consider future developments of NLG with regards to scalability and the potential for change across fields. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Sorted Consecutive Occurrence Queries in Substrings

arXiv

引用

arXiv 2024年

作者： Akram, Waseem Mieno, Takuya Department of Computer Science and Engineering Indian Institute of Technology Kanpur India Department of Computer and Network Engineering University of Electro-Communications Chofu Japan

The string indexing problem is a fundamental computational problem with numerous applications, including information retrieval and bioinformatics. It aims to efficiently solve the pattern matching problem: given a text T of length n for preprocessing and a pattern P of length m as a query, the goal is to report all occurrences of P as substrings of T. Navarro and Thankachan [CPM 2015, Theor. Comput. Sci. 2016] introduced a variant of this problem called the gap-bounded consecutive occurrence query, which reports pairs of consecutive occurrences of P in T such that their gaps (i.e., the distances between them) lie within a query-specified range [g1, g2]. Recently, Bille et al. [FSTTCS 2020, Theor. Comput. Sci. 2022] proposed the top-k close consecutive occurrence query, which reports the k closest consecutive occurrences of P in T, sorted in non-descending order of distance. Both problems are optimally solved in query time with O(n log n)-space data structures. In this paper, we generalize these problems to the range query model, which focuses only on occurrences of P in a specified substring T[a..b] of T. Our contributions are as follows: We propose an O(n log2 n)-space data structure that answers the range top-k consecutive occurrence query in O(|P| + log log n + k) time. We propose an O(n log2+ϵ n)-space data structure that answers the range gap-bounded consecutive occurrence query in O(|P| + log log n + output) time, where ϵ is a positive constant and output denotes the number of outputs. Additionally, as by-products, we present algorithms for geometric problems involving weighted horizontal segments in a 2D plane, which are of independent interest. Copyright © 2024, The Authors. All rights reserved.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Editorial

引用

Computational Geometry: Theory and Applications 2024年 122卷

作者： Bae, Sang Won Okamato, Yoshio Division of Artificial Intelligence and Computer Science Kyonggi University Korea Republic of Department of Computer and Network Engineering Graduate School of Informatics and Engineering The University of Electro-Communications Japan

来源：评论

学校读者我要写书评

暂无评论

Wireless Federated Learning Over Resource-Constrained Networks: Digital Versus Analog Transmissions

引用

IEEE Transactions on Wireless communications 2024年第10期23卷 14020-14036页

作者： Yao, Jiacheng Xu, Wei Yang, Zhaohui You, Xiaohu Bennis, Mehdi Poor, H. Vincent Southeast University Nanjing210096 China Zhejiang Laboratory Hangzhou311121 China The College of Information Science and Electronic Engineering Zhejiang University Zhejiang Hangzhou310027 China The Center for Wireless Communications Oulu University Oulu90014 Finland The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

To enable wireless federated learning (FL) in communication resource-constrained networks, two communication schemes, i.e., digital and analog ones, are effective solutions. In this paper, we quantitatively compare these two techniques, highlighting their essential differences as well as respectively suitable scenarios. We first examine both digital and analog transmission schemes, together with a unified and fair comparison framework under imbalanced device sampling, strict latency targets, and transmit power constraints. A universal convergence analysis under various imperfections is established for evaluating the performance of FL over wireless networks. These analytical results reveal that the fundamental difference between the digital and analog communications lies in whether communication and computation are jointly designed or not. The digital scheme decouples the communication design from FL computing tasks, making it difficult to support uplink transmission from massive devices with limited bandwidth and hence the performance is mainly communication-limited. In contrast, the analog communication allows over-the-air computation (AirComp) and achieves better spectrum utilization. However, the computation-oriented analog transmission reduces power efficiency, and its performance is sensitive to computation errors from imperfect channel state information (CSI). Furthermore, device sampling for both schemes are optimized and differences in sampling optimization are analyzed. Numerical results verify the theoretical analysis and affirm the superior performance of the sampling optimization. © 2002-2012 IEEE.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

A Survey on Trustworthy Edge Intelligence: From Security and Reliability To Transparency and Sustainability

引用

IEEE communications Surveys and Tutorials 2024年第3期27卷 1-1页

作者： Wang, Xiaojie Wang, Beibei Wu, Yu Ning, Zhaolong Guo, Song Yu, Fei Richard School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China School of Cyber Security and Information Law Chongqing University of Posts and Telecommunications Chongqing China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Kowloon Hong Kong China School of Information Technology Carleton University Ottawa ON Canada

Edge Intelligence (EI) integrates Edge Computing (EC) and Artificial Intelligence (AI) to push the capabilities of AI to the network edge for real-time, efficient and secure intelligent decision-making and computation. However, EI faces various challenges due to resource constraints, heterogeneous network environments, and diverse service requirements of different applications, which together affect the trustworthiness of EI in the eyes of stakeholders. This survey comprehensively summarizes the characteristics, architecture, technologies, and solutions of trustworthy EI. Specifically, we first emphasize the need for trustworthy EI in the context of the trend toward large models. We then provide an initial definition of trustworthy EI, explore its key characteristics and give a multi-layered architecture for trustworthy EI. Then, we present enabling technologies for trustworthy EI systems. Subsequently, we summarize several important issues that hinder the achievement of trustworthy EI and provide an in-depth literature review of the state-of-the-art solutions for realizing the trustworthiness of EI. Finally, we discuss the corresponding research challenges and open issues. IEEE

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

RIS as a Network Resource: User Multiplexing and Pricing Algorithms 3

RIS as a Network Resource: User Multiplexing and Pricing Alg...

引用

3rd International Conference on 6G Networking, 6GNet 2024

作者： Papadopoulos, Alexandros Lalas, Antonios Votis, Konstantinos Schmid, Stefan Katsalis, Kostas Liaskos, Christos University of Ioannina Department of Computer Science and Engineering Ioannina Greece Information Technologies Institute CERTH Thessaloniki Greece Aristotle University of Thessaloniki Thessaloniki Greece TU Berlin and Fraunhofer SIT Berlin Germany Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Thessaloniki Greece DOCOMO Communications Laboratory GmbH Munich Germany FORTH Ioannina Greece

ISBN: (纸本)9798350378597

Reconfigurable Intelligent Surfaces (RIS) have the ability to actively control wave propagation through space, enabling the creation of Programmable Wireless Environments (PWEs). This capability allows for the uti-lization and control of previously unexploited resources. However, there is a notable gap in allocating these resources to network users in a way that aligns with the pricing policies of telecommunications stakeholders. This paper considers RIS elements as network resources and describes a pricing policy that links the PWE efficiency of individual users to an optimal method for sharing RIS elements. A specialized policy tailored to this purpose, is designed with a focus on robustness, ensuring its applicability across various RIS functionalities and frequency bands. Its computational efficiency further underscores its viability for deployment in practical scenarios. © 2024 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

MIRA: A Method of Federated MultI-Task Learning for LaRge LAnguage Models

IEEE Networking Letters

引用

IEEE Networking Letters 2025年

作者： Elbakary, Ahmed Ben Issaid, Chaouki Elbatt, Tamer Seddik, Karim Bennis, Mehdi University of Oulu Finland Department of Electronics and Communications Engineering American University in Cairo Egypt Department of Computer Science and Engineering American University in Cairo Egypt Department of Electronics and Communications Engineering Cairo University Egypt

In this paper, we introduce a method for fine-tuning Large Language Models (LLMs), inspired by Multi-Task learning in a federated manner. Our approach leverages the structure of each client's model and enables a learning scheme that considers other clients' tasks and data distribution. To mitigate the extensive computational and communication overhead often associated with LLMs, we utilize a parameter-efficient fine-tuning method, specifically Low-Rank Adaptation (LoRA), to reduce the number of trainable parameters. Experimental results, with different datasets and models, demonstrate the proposed method's effectiveness compared to existing frameworks for federated fine-tuning of LLMs in terms of global and local performances. The proposed scheme outperforms existing baselines by achieving lower local loss for each client, while maintaining comparable global performance. © 2019 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Robust Synergetic Observer based Fault-Tolerant Control for Electric Vehicle Applications 50

Robust Synergetic Observer based Fault-Tolerant Control for ...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Boumegouas, Mohammed Kabir Billa Kouzi, Katia Trabelsi, Mohamed Iqbal, Atif Birame, Mhamed Shadmand, Mohammad B. Laboratory of Semiconductors and Functional Materials Amar Telidji University of Laghouat Algeria Electronics and Communications Engineering Department Kuwait College of Science and Technology Kuwait Department of Electrical Engineering Qatar University Doha Qatar Department of Electrical & Computer Engineering University of Illinois ChicagoIL United States

ISBN: (纸本)9781665464543

Speed sensor faults are very common in electric vehicle (EV) applications, often disrupting system performance due to the reliance on speed sensor data by the electric drives. Consequently, fault-tolerant control approaches require robust observer structures capable of functioning effectively during faults, swiftly identifying and reconfiguring failures. Thus, this paper presents a novel fault-tolerant control design leveraging a synergetic observer (SO) to substitute the speed sensor in the event of fault. Comparative analysis with a super-twisting sliding mode observer (ST-SMO) highlights the proposed observer's superior performance in terms of tracking accuracy and ripple reduction. The presented simulation results demonstrate promising performance of the proposed observer for fault-tolerant control in EV applications. © 2024 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Solution of Robust Stochastic Discrete Filtering Problem Based on Minimax Functional Criterion

Solution of Robust Stochastic Discrete Filtering Problem Bas...

引用

2024 International Russian Automation Conference, RusAutoCon 2024

作者： Reshetnikova, Irina V. Marshakov, Daniil V. Sokolov, Sergey V. Moscow Technical University of Communications and Informatics North Caucasus branch Research Department Rostov-on-Don Russia Moscow Technical University of Communications and Informatics North Caucasus branch Department of Information Security Rostov-on-Don Russia Moscow Technical University of Communications and Informatics North Caucasus branch Department of Informatics and Computer Engineering Rostov-on-Don Russia

Currently, the solution to the vast majority of problems of assessing the state of discrete stochastic systems operating in stochastic environments is carried out using algorithms developed on the basis of the discrete Kalman filter. The main disadvantage of such estimation schemes is the need for an accurate a priori description of the probabilistic characteristics of the noise of the object and the interference of its observer, the absence of which leads to divergence of the filtering process. All known modifications of the Kalman filtering scheme ensure the stability of the estimation process only for some special cases, leaving the problem of an a priori description of the operating conditions of real systems as a whole unresolved. In this regard, the paper considers an alternative approach to the synthesis of a stable (robust) stochastic estimation scheme based on the choice of a matrix filtering coefficient from the optimization condition of a minimax functional criterion determined by the most unfavorable class of probabilistic distributions noise of the object and its observer. An advantageous feature of the proposed filter, in addition to its robust properties, is a significantly smaller dimension compared to the Kalman scheme, equal to the dimension of the object, which sharply reduces the amount of computational costs in the practical implementation of the filter. The results of a numerical experiment illustrating the effectiveness of the considered approach are presented. © 2024 IEEE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Multi-Representation Spatial-Temporal Graph Convolutional Networks for Network Traffic Prediction

引用

IEEE Internet of Things Journal 2025年

作者： Yang, Yang He, Yechen Zhao, Binnan Wu, Celimuge Gao, Zhipeng Rui, Lanlan Beijing University of Posts and Telecommunications School of Computer Science Beijing100876 China University of Electro-Communications Department of Computer and Network Engineering Tokyo1828585 Japan

With the rapid proliferation of the Internet of Things, network traffic prediction has become crucial for intelligent network management, enabling more reliable and flexible services for a vast array of IoT devices and applications. The heterogeneous and dynamic nature of IoT networks introduces complex spatial relations and underlying periodic dependencies in spatial-temporal graphs that existing methods struggle to model effectively. In this paper, we propose Multi-Representation Spatial-Temporal Graph Convolutional Networks (MRSTGCN), a novel unified framework specifically designed to address these challenges. MRSTGCN integrates a Multi-Representation Graph Convolutional Network (MRGCN) module to model node heterogeneity and complex traffic propagation, and two complementary embedding modules - Historical Embedding and Temporal Embedding - to capture and fuse periodic dependencies across different fine-grained temporal cycles. Extensive experiments are conducted on two network traffic datasets, and the results demonstrate that MRSTGCN achieves state-of-the-art performance with obvious improvements in MAE, RMSE and MAPE on three prediction horizons. © 2025 IEEE.

关键词： Convolutional neural networks

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：