检索结果-内蒙古大学图书馆

Frontiers of computer Science 2025年第4期19卷 43-57页

作者： Xiao MA Shen-Yi ZHAO Zhao-Heng YIN Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing UniversityNanjing 210023China Department of Electrical Engineering and Computer Sciences University of CaliforniaBerkeleyCA 94720-1770USA

Exploration strategy design is a challenging problem in reinforcement learning(RL),especially when the environment contains a large state space or sparse *** exploration,the agent tries to discover unexplored(novel)areas or high reward(quality)*** existing methods perform exploration by only utilizing the novelty of *** novelty and quality in the neighboring area of the current state have not been well utilized to simultaneously guide the agent’s *** address this problem,this paper proposes a novel RL framework,called clustered reinforcement learning(CRL),for efficient exploration in *** adopts clustering to divide the collected states into several clusters,based on which a bonus reward reflecting both novelty and quality in the neighboring area(cluster)of the current state is given to the *** leverages these bonus rewards to guide the agent to perform efficient ***,CRL can be combined with existing exploration strategies to improve their performance,as the bonus rewards employed by these existing exploration strategies solely capture the novelty of *** on four continuous control tasks and six hard-exploration Atari-2600 games show that our method can outperform other state-of-the-art methods to achieve the best performance.

关键词： deep reinforcement learning exploration count-based method clustering K-means

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Chinese Speech Recognition Method Based on the Squeezeformer Model

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2025年第1期52卷 23-31页

作者： Guo, Ying Wang, Li School of Computer Science and software Engineering University of Science and Technology Liaoning Anshan114051 China College of Computer Science and Technology Liaoning Anshan114051 China

End-to-end training has emerged as a prominent trend in speech recognition, with Conformer models effectively integrating Transformer and CNN architectures. However, their complexity and high computational cost pose deployment challenges. To address these issues, we propose a multi-task Chinese speech recognition method based on the Squeezeformer model. We replace the FMCF structure in Conformer with an MF/CF structure, leveraging the convolutional module as a local Multi- Head Attention (MHA) module to enhance efficiency. Multilevel down-sampling and up-sampling using a time-series U-Net further reduce computational costs. By eliminating redundant LayerNorm layers and employing depthwise separable convolutions, we streamline the model, reduce parameters, and lower deployment costs. An Adaptor Layer is integrated into the MHSA module to mitigate the vanishing gradient problem, and a ScaleVar Layer is added to enhance flexibility. Additionally, the RealFormer module is introduced on the decoding side to improve context understanding. Combining Connectionist Temporal Classification (CTC) with attention-based encoding and decoding models for multi-task learning improves performance and accuracy. Experimental results show that the proposed method reduces the parameters on AISHELL-1 dataset by 16% and reduces the character error rate to 5.50%. At the same time, it also shows good performance on AISHELL-2 dataset. © (2025), (International Association of Engineers). All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

A survey on cross-user federated recommendation

引用

Science China(Information Sciences) 2025年第4期68卷 7-32页

作者： Enyue YANG Yudi XIONG Wei YUAN Weike PAN Qiang YANG Zhong MING College of Computer Science and Software Engineering Shenzhen University School of Electrical Engineering and Computer Science The University of Queensland WeBank AI Lab WeBank Department of Computer Science and Engineering Hong Kong University of Science and Technology College of Big Data and Internet Shenzhen Technology University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.

关键词： cross-user federated recommendation federated recommendation federated learning recommender systems user privacy

来源：评论

学校读者我要写书评

暂无评论

A Review of Intelligent Configuration and Its Security for Complex Networks

引用

Chinese Journal of Electronics 2024年第4期33卷 920-947页

作者： Yue ZHAO Bin YANG Fei TENG Xianhua NIU Ning HU Bo TIAN Science and Technology on Communication Security Laboratory School of Computer and Information Engineering Chuzhou University School of Computing and Artificial Intelligence Southwest Jiaotong University School of Computer and Software Engineering Xihua University Cyberspace Institute of Advanced Technology Guangzhou University

Complex networks are becoming more complex because of the use of many components with diverse technologies. In fact, manual configuration that makes each component interoperable has breed latent danger to system security. There is still no comprehensive review of these studies and prospects for further research. According to the complexity of component configuration and difficulty of security assurance in typical complex networks, this paper systematically reviews the abstract models and formal analysis methods required for intelligent configuration of complex networks, specifically analyzes, and compares the current key technologies such as configuration semantic awareness, automatic generation of security configuration, dynamic deployment, and verification evaluation. These technologies can effectively improve the security of complex networks intelligent configuration and reduce the complexity of operation and maintenance. This paper also summarizes the mainstream construction methods of complex networks configuration and its security test environment and detection index system, which lays a theoretical foundation for the formation of the comprehensive effectiveness verification capability of configuration security. The whole lifecycle management system of configuration security process proposed in this paper provides an important technical reference for reducing the complexity of network operation and maintenance and improving network security.

关键词： Complex networks Intelligent configuration Configuration security software defined network Lifecycle management

来源：评论

学校读者我要写书评

暂无评论

Security experimental framework of trajectory planning for autonomous vehicles

引用

International Journal of Intelligent Networks 2024年第1期5卷 315-324页

作者： Al-sheyab, Sujoud Al-shara, Zakarea Al-khaleel, Osama Department of Computer Engineering Jordan University of Science and Technology Irbid Jordan Department of Software Engineering Jordan University of Science and Technology Irbid Jordan

In the contemporary landscape, autonomous vehicles (AVs) have emerged as a prominent technological advancement globally. Despite their widespread adoption, significant hurdles remain, with security standing out as a critical concern. The potential for attacks within AV networks, exemplified by the Trajectory Privacy Attack on Autonomous Driving (T-PAAD), underscores the urgency for robust security measures. Unfortunately, existing simulations for preemptively assessing the T-PAAD attack's impact are scarce. This paper introduces the Security Experimental Framework for Autonomous Vehicles (SEFAV), designed to address this gap by providing a versatile platform for simulating security scenarios in AV environments. SEFAV is cross-platform and compatible with different operating systems such as Windows and Linux, enhancing accessibility for researchers and practitioners. Our primary focus lies in showcasing the T-PAAD attack within our framework, highlighting its efficacy in evaluating and fortifying AV security. © 2024 The Authors

关键词： Vehicle routing

来源：评论

学校读者我要写书评

暂无评论

A Generative Model-Based Network Framework for Ecological Data Reconstruction

引用

computers, Materials & Continua 2025年第1期82卷 929-948页

作者： Shuqiao Liu Zhao Zhang Hongyan Zhou Xuebo Chen School of Electronic and Information Engineering University of Science and Technology LiaoningAnshan114051China School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan114051China

This study examines the effectiveness of artificial intelligence techniques in generating high-quality environmental data for species introductory site selection *** Strengths,Weaknesses,Opportunities,Threats(SWOT)analysis data with Variation Autoencoder(VAE)and Generative AdversarialNetwork(GAN)the network framework model(SAE-GAN),is proposed for environmental data *** model combines two popular generative models,GAN and VAE,to generate features conditional on categorical data embedding after SWOT *** model is capable of generating features that resemble real feature distributions and adding sample factors to more accurately track individual sample *** data is used to retain more semantic information to generate *** model was applied to species in Southern California,USA,citing SWOT analysis data to train the *** show that the model is capable of integrating data from more comprehensive analyses than traditional methods and generating high-quality reconstructed data from them,effectively solving the problem of insufficient data collection in development *** model is further validated by the Technique for Order Preference by Similarity to an Ideal Solution(TOPSIS)classification assessment commonly used in the environmental data *** study provides a reliable and rich source of training data for species introduction site selection systems and makes a significant contribution to ecological and sustainable development.

关键词： Convolutional Neural Network(CNN) VAE GAN TOPSIS data reconstruction

来源：评论

学校读者我要写书评

暂无评论

Advancing Smart Sensor Networks and Carbon-Based Biosensors through Artificial Intelligence: A Deep Learning Approach to Optoelectronic Device Innovation

引用

IEEE Access 2025年 13卷 86083-86109页

作者： Luo, Keliang Putra University of Malaysia Software Engineering Faculty of Computer Science and Information Technology Kuala Lumpur43400 Malaysia

This research proposes a novel artificial decision-marking framework suitable for modern smart sensor networks and carbon-based biosensor systems which deals with uncertainty and the peculiarity of the data. To achieve the goals, the approach relies on the optoelectronic properties of carbon nanomaterials and already combines AI and deep learning. This raises the level of sensing, real-time data fusion, and adaptive decision-making within the environment to unprecedented levels. To enhance sensor evaluation in sensor manufacturing, we take a step further and implement Dombi Interval Valued Intuitionistic Fuzzy Sets (D-IVIFs) and work with Dombi Interval Valued Intuitionistic Fuzzy Dombi Bonferroni Mean (D-IVIFDBM) for hierarchical decision-making. Moreover, two Multi-Attribute Group Decision Making (MAGDM) methods IVIFWDBM and IVIFWDGBM are developed for expert evaluation aggregation in selection tasks of different criteria to enhance selection accuracy. These experiments did demonstrate improvements in decision accuracy as well as better overall performance than conventional models of comparison. The numerical experiments showed that these methods are more effective than traditional MAGDM models. Introducing such an advanced decision framework in deep learning systems enables improved adaptability, security, and resilience in next-generation sensor networks and biosensor devices. The new paradigm enables real-time signal interpretation and adaptive learning and provides effective solutions in harsh environments where severe fluctuations are common. This study assists in addressing the discrepancy between conceptual decision models and actual physical achievements in smart sensing, which will foster the development of more sophisticated and efficient optoelectronic devices. © 2013 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Real-time all-frequency global llumination with radiance caching

引用

Computational Visual Media 2024年第5期10卷 923-936页

作者： Youxin Xing Gaole Pan Xiang Chen Ji Wu Lu Wang Beibei Wang School of Software Shandong UniversityJinan 250101China School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China

Global illumination(GI)plays a crucial role in rendering realistic results for virtual exhibitions,such as virtual car *** scenarios usually include all-frequency bidirectional reflectance distribution functions(BRDFs),although their geometries and light configurations may be *** allfrequency BRDFs in real time remains challenging due to the complex light *** approaches,including precomputed radiance transfer,light probes,and the most recent path-tracing-based approaches(ReSTIR PT),cannot satisfy both quality and performance requirements ***,we propose a practical hybrid global illumination approach that combines ray tracing and cached GI by caching the incoming radiance with *** approach can produce results close to those of ofline renderers at the cost of only approximately 17 ms at runtime and is robust over all-frequency *** approach is designed for applications involving static lighting and geometries,such as virtual exhibitions.

关键词： real-time global illumination all-frequency BRDFs Haar wavelets radiance caching

来源：评论

学校读者我要写书评

暂无评论

A multi-mode real-time system verification model using efficient event-driven dataset

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第2期15卷 1187-1200页

作者： Islam, Nayreet Azim, Akramul Department of Electrical Computer and Software Engineering University of Ontario Institute of Technology Oshawa Canada

Real-time systems experience many safety and performance issues at run time due to different uncertainties in the environment. Systems are now becoming highly interactive and must be able to execute in a changing environment without experiencing any failure. A real-time system can have multiple modes of operation such as safety and performance. The system can satisfy its safety and performance requirements by switching between the modes at run time. It is essential for the designers to ensure that a multi-mode real-time system operates in the expected mode at run time. In this paper, we present a verification model that identifies the expected mode at run time and checks whether the multi-mode real-time system is operating in the correct mode or not. To determine the expected mode, we present a monitoring module that checks the environment of the system, identifies different real-world occurrences as events, determines their properties and creates an event-driven dataset for failure analysis. The dataset consumes less memory in comparison to the raw input data obtained from the monitored environment. The event-driven dataset also facilitates onboard decision-making because the dataset allows the system to perform a safety analysis by determining the probability of failure in each environmental situations. We use the probability of failure of the system to determine the safety mode in different environmental situations. To demonstrate the applicability of our proposed scheme, we design and implement a real-time traffic monitoring system that has two modes: safety, and performance. The experimental analysis of our work shows that the verification model can identify the expected operating mode at run time based on the safety (probability of failure) and performance (usage) requirements of the system as well as allows the system to operate in performance mode (in 3295 out of 3421 time intervals) and safety mode (in 126 out of 3421 time intervals). The experimental resul

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Application of data twinning based on deep time series model in smart city traffic flow prediction

引用

Discover Internet of Things 2025年第1期5卷 1-21页

作者： Gao, Li Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huai’an223003 China

This paper introduces an intelligent traffic flow prediction system that combines data twinning and deep learning, aiming to improve the prediction accuracy and model adaptability by integrating grey prediction model (GM(1,1)), long-short-term memory network (LSTM) and particle swarm optimization (PSO). The system construction starts from physical layer data acquisition, deals with missing data through smoothing and interpolation, and applies the GM(1,1) model to construct a digital twin layer for preliminary prediction. The information fusion mechanism combines real-time data and forecast data to optimize the model inputs, and the PSO algorithm is used to optimize the model parameters. The LSTM model is used as a deep time-series model, and combined with the output of the data twin prediction to make a comprehensive prediction, and at the same time, feature engineering is utilized to enhance the model performance. The system implements dynamic feedback adjustment to optimize the model in real time according to the prediction error. Empirical analysis shows that the LSTM model with integrated data twin (LSTM + DT) outperforms the traditional model in prediction accuracy, stability, and generalization ability, especially in peak hours, holidays, and emergency response, and provides a reliable solution for intelligent traffic management despite the long training time. © The Author(s) 2025.

关键词： Deep learning

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：