检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yang, Yingnan Zhu, Qingling Chen, Jianyong College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Multivariate time series (MTS) forecasting has been extensively applied across diverse domains, such as weather prediction and energy consumption. However, current studies still rely on the vanilla point-wise self-attention mechanism to capture cross-variable dependencies, which is inadequate in extracting the intricate cross-correlation implied between variables. To fill this gap, we propose Variable Correlation Transformer (VCformer), which utilizes Variable Correlation Attention (VCA) module to mine the correlations among variables. Specifically, based on the stochastic process theory, VCA calculates and integrates the cross-correlation scores corresponding to different lags between queries and keys, thereby enhancing its ability to uncover multivariate relationships. Additionally, inspired by Koopman dynamics theory, we also develop Koopman Temporal Detector (KTD) to better address the non-stationarity in time series. The two key components enable VCformer to extract both multivariate correlations and temporal dependencies. Our extensive experiments on eight real-world datasets demonstrate the effectiveness of VCformer, achieving top-tier performance compared to other state-of-the-art baseline models. Code is available at this repository: https://***/CSyyn/VCformer. Copyright © 2024, The Authors. All rights reserved.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Research on the improved PBFT consensus algorithm based on credit mechanism 3

Research on the improved PBFT consensus algorithm based on c...

引用

3rd International Conference on Artificial Intelligence, Virtual Reality, and Visualization, AIVRV 2023

作者： Wang, Weixing Xu, Guangxia Ye, Liuqin Ma, Chuang School of Artificial Intelligence The Open University of Guangdong China The Cyberspace Institute of Advanced Technology Guangzhou University China Department Economics & Management Beihai Vocational College China School of Software Engineering Chongqing University of Posts and Telecommunications China

ISBN: (纸本)9781510671485

The PBFT consensus algorithm commonly used in the consortium chain has the disadvantages of three-stage consensus process, resulting in high communication costs. This paper proposes an enhanced PBFT algorithm that utilizes a credit mechanism to select master nodes that can improve system availability. The three-stage consensus process of PBFT is optimized, and the master node collects the confirmation messages broadcast by the whole network during the confirmation stage, effectively reducing communication overhead. At the same time, the block height synchronization mechanism is used to ensure the high consistency of consensus node blocks, restore the block height of failed nodes, and achieve fast consensus. Empirical results show that the improved P-PBFT consensus algorithm effectively reduces resource consumption and latency. © 2023 SPIE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Path planning in dynamic environments based on the improved Rapidly-exploring random tree and dynamic window approach

Path planning in dynamic environments based on the improved ...

引用

Chinese Control and Decision Conference, CCDC

作者： Caiqi Wang Yi Xiong Yilong Deng Qi Wu Shiqian Wu School of Information Science and Engineering Wuhan University of Science and Technology Wuhan China School of Software and Internet of Things Engineering Jiangxi University of Finance and Economics Nanchang China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

Path planning in dynamic environments holds paramount significance within the realm of mobile robotics. The Rapidly-Exploring Random Tree (RRT) algorithm stands as one of the most extensively employed path planning algorithms, distinguished by its probabilistic completeness. However, the algorithm suffers from the long time to obtain the initial solution and the blindness of the expansion. To address these shortcomings, an improved RRT algorithm based on dynamic goal-biased sampling method (Dyn-RRT) is proposed to enhance the algorithm’s orientation and reduce the time obtaining the initial solution. To bolster the algorithm’s utility in dynamic settings, Dynamic Window Approach (DWA) is integrated into the Dyn-RRT algorithm to enhance adaptability to the dynamic milieu. In addition, simulation experiments show that proposed dynamic goal-biased sampling method is also applicable to other RRT series algorithms and can greatly reduce the time obtaining the initial solution.

关键词： Heuristic algorithms Blindness Sampling methods Probabilistic logic Path planning Robots Matlab

来源：评论

学校读者我要写书评

暂无评论

Text Recognition for Station Equipment Troubleshooting Based on BERT-BiLSTM-CRF Models

Text Recognition for Station Equipment Troubleshooting Based...

引用

2023 China Automation Congress, CAC 2023

作者： Bai, Wei Wang, Xiaosu Liang, Bo Yang, Guoyuan Zhi, Hanyu Qiao, Yinwei Institute of Computing Technology China Academy of Railway Sciences Co. Ltd. Beijing China Postgraduate Department China Academy of Railway Sciences Beijing China School of Automation and Software Engineering Shanxi University Taiyuan China

ISBN: (纸本)9798350303759

The excessive length and high semantic complexity of station equipment fault handling report texts are addressed to the extent that effective text recognition is difficult to achieve. A station equipment fault handling dataset is formulated and a text recognition system for station fault reports based on the BERT-BiLSTM-CRF model is designed. The method first preprocesses the data using the BERT pre-trained language model to generate word vectors, which are then fed into BiLSTM to obtain the embedded contextual information, which is passed through the CRF model to obtain the global optimal solution, and finally outputs the textual results of the station equipment fault handling. The experimental results show that the model outperforms the other five comparative models by more than 2% in terms of precision, recall, and F1 value (checking accuracy) for intelligent recognition over the five entities predicted by the other five comparative models. This brings a new direction of thinking for the analysis of equipment troubleshooting texts in railway stations. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Fruit and Vegetable Detection with Calorie Estimation Built on Mobilenetv2

Fruit and Vegetable Detection with Calorie Estimation Built ...

引用

International Conference on Advances in Information technology (ICAIT)

作者： Sengottaiayn N Hamsanandhini S Rajesh Sharma R Akey Sungheetha Monika M Ketema Adare Computer Science & Engineering Alliance University Bengaluru India Department of Computer Technology Kongu Engineering College Erode India MSc Software Systems Kongu Engineering College Erode India Department of Computer Science and Engineering Adama Science and Technology University Adama Ethiopia

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

Fruit and Vegetable Recognition with Calorie Estimation based on Mobilenetv2 is a pioneering research endeavor aimed at leveraging deep learning techniques to enhance dietary monitoring and health management. Building upon the success of neural network models in various domains, this study explores the application of Mobilenetv2 and EfficientNet architecture for accurately identifying fruits and vegetables from images and estimating their respective caloric content. The research dataset comprises meticulously curated images of diverse fruits and vegetables, ensuring comprehensive coverage across different categories. Through rigorous experimentation and evaluation, the proposed model demonstrates remarkable accuracy in fruit and vegetable recognition, achieving an impressive accuracy rate of 97.6%. Moreover, the incorporation of calorie estimation adds a novel dimension to dietary analysis, enabling users to make informed decisions regarding their nutritional intake. The findings of this research not only contribute to the advancement of computer vision techniques but also hold significant implications for personalized nutrition tracking and health- conscious applications.

关键词： Deep learning Computer vision Accuracy Architecture Neural networks Buildings Estimation Computer architecture Information technology Monitoring

来源：评论

学校读者我要写书评

暂无评论

Mining Better Samples and Semantic Consistency for Contrast Learning in Forest Semantic Segmentation 41

Mining Better Samples and Semantic Consistency for Contrast ...

引用

第41届中国控制会议

作者： Chongjin Chen Yichao Cao Qingfei Tang Xiaobo Lu School of Software Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing Enbo Technology Co. Ltd.

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Image segmentation has impressive progress in the past several *** good segmentation usually follows pixelwise well-annotated labels which is ***,the robustness would not be guaranteed due to lack-ofdiversity *** work usually focuses on pixels individually and pay less attention to the neighbor *** local context would be scarce and the global context is not utilized following these *** proposal a method,named Forest Semantic Segmentation Network(FSSNet) to address these *** organizes original version and augmented version of images,as two inputs into student branch and teacher branch,and force the two outputs being consistent to strengthen the robustness of our ***,we not only consider pixel itself and also the neighbor pixels because the context of neighbor pixels helps understanding the *** utilizes contrastive loss with memory bank to involve global context in training which will make pixels closer to others in same category and far away from pixels of different categories.A bank filter is suggested to improve the quality of features in the memory *** also proposal a new sample strategy to improve the effect of contrastive loss and reduce the *** method can improve accuracy and strengthen the robustness with affordable extra computation during training process,and no additional computation during inference toward *** to benchmark,the proposed approach can improve the mIoU by 3.1% on our challenging dataset.

关键词： Semantic segmentation Contrastive learning Deep learning

来源：评论

学校读者我要写书评

暂无评论

Towards an Automatic Construction of Simulation Scenarios: A Systematic Review 23

Towards an Automatic Construction of Simulation Scenarios: A...

引用

Proceedings of the Winter Simulation Conference

作者： Christopher W. H. Davis Antonie J. Jetter Philippe J. Giabbanelli Microsoft USA Dept. of Engineering & Technology Management Portland State University USA Dept. of Computer Science & Software Engineering Miami University Oxford USA

ISBN: (纸本)9798350369663

A predictive simulation is built on a conceptual model (e.g., to identify relevant constructs and relationships) and serves to estimate the potential effects of 'what-if' scenarios. Developing the conceptual model and plausible scenarios has long been a time-consuming activity, often involving the manual processes of identifying and engaging with experts, then performing desk research, and finally crafting a compelling narrative about the potential futures captured as scenarios. Automation could speed-up these activities, particularly through text mining. We performed the first review on automation for simulation scenario building. Starting with 420 articles published between 1995 and 2022, we reduced them to 11 relevant works. We examined them through four research questions concerning data collection, extraction of individual elements, connecting elements of insight and (degree of automation of) scenario generation. Our review identifies opportunities to guide this growing research area by emphasizing consistency and transparency in the choice of datasets or methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two novel approaches of adaptive finite-time sliding mode control for a class of single-input multiple-output uncertain nonlinear systems

引用

IET Cyber-Systems and Robotics 2021年第2期3卷 173-183页

作者： Pooyan Alinaghi Hosseinabadi Ali Soltani Sharif Abadi Saad Mekhilef Hemanshu Roy Pota Power Electronics and Renewable Energy Research Laboratory(PEARL) Department of Electrical EngineeringUniversity of MalayaFaculty of EngineeringKuala LumpurMalaysia Department of Electrical Engineering Yazd UniversityFaculty of EngineeringYazdIran School of Software and Electrical Engineering Swinburne University of TechnologyVictoriaAustralia School of Engineering and Information Technology The University of New South WalesCanberraAustralia

Some systems,in spite of having multiple outputs,have only one control input,which makes their control a *** novel controllers are proposed that utilise an adaptive finite-time sliding mode control(AFSMC)scheme for a class of single-input multiple-output(SIMO)nonlinear systems in the presence of unknown mismatched *** alleviate the inherent chattering phenomenon of sliding mode control,new forms of the two designed controllers are suggested by using new sliding *** only can the proposed AFSMC scheme stabilise the system in a finite time,but also it can provide estimated data of the uncertainty upper bound in the *** stability theory is used to obtain finite-time stability analysis of the closed-loop ***,simulation results are carried out in Simulink/MATLAB for a four-dimensional autonomous hyper-chaotic system with mismatched uncertainties as an example of SIMO uncertain nonlinear systems to reveal the effectiveness of the proposed controllers.

关键词： finite nonlinear stability

来源：评论

学校读者我要写书评

暂无评论

Adaptive IoT Decision Making in Uncertain Environments

Adaptive IoT Decision Making in Uncertain Environments

引用

IEEE International Conference on Smart Internet of Things (SmartIoT)

作者： Yan Wang Liwei Zheng Jingjing He Zhanqi Cui Computer School Software Engineering Research Center Beijing Information Science and Technology University Beijing China

The rapid growth of the Internet of Things (IoT) has led to widespread deployment of IoT systems in domains such as smart homes, healthcare, and transportation. However, IoT systems often operate under uncertainty, making it difficult to predict and control their behavior. In this paper, we propose an adaptive decision making approach for IoT systems in uncertain, dynamic environments. We present a framework with perception, decision and execution layers to handle uncertainty in IoT systems. The perception layer senses the environment and system state. The decision layer employs an optimized deep Q-network algorithm (Ad-DQN) specifically designed to handle uncertain environments, enabling it to make informed decisions based on learned experiences. The execution layer implements the actions. We demonstrate the framework on an intelligent air conditioning system as a case study of an IoT system operating under uncertainty. The Ad-DQN based decision layer adapts the air conditioning control policy to maximize comfort while minimizing energy usage. Experiments show our method outperforms traditional DQN method in uncertain environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Medical Cyber-Physical Systems in Society 5.0: Are We Ready?

IEEE Transactions on Technology and Society

引用

IEEE Transactions on technology and Society 2022年第3期3卷 189-198页

作者： Patil, Rajkumar V. Ambritta, Nancy P. Mahalle, Parikshit N. Dey, Nilanjan Vishwakarma Institute of Information Technology Department of Information Technology Pune411048 India Glareal Software Solutions PTE. Ltd. Singapore200809 Singapore Vishwakarma Institute of Information Technology Department of Artificial Intelligence and Data Science Pune411048 India Jis University Department of Computer Science and Engineering Kolkata700109 India

Advancements in cyber-physical systems (CPSs) makes CPSs essential entities in society today, and have made them prominent across all fields. For example, the healthcare industry has evolved technologically and has effectively incorporated CPS into many application areas. While these advancements, involving medical CPSs (MCPS), have been revised according to Society 4.0, there are still issues that need to be considered while we transition from an information-based society (Society 4.0) to a human-centric society (Society 5.0). In this article, we propose an MCPS framework for Society 5.0 in the context of some state-of-the-art technologies. The proposed system focuses on enhancing security aspects of Society 5.0 through introduction of a security layer equipped with protocols, such as open authorization (OAuth), user-managed access (UMA), and self-sovereign identity (SSI). The added security layer is designed to incorporate country-specific security laws. Challenges and design issues in developing a trusted and secure service for MCPS are also discussed using vulnerability assessment and attack modeling. Finally, we discuss ethical aspects that need to be addressed in the transition from Society 4.0 to Society 5.0. © 2020 IEEE.

关键词： Cyber Physical System

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：