检索结果-内蒙古大学图书馆

Metaheuristic Optimization of Time Series Models for Predicting Networks Traffic

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

Differential Privacy Protection Based on Federated Learning in Mobile Crowdsensing

Differential Privacy Protection Based on Federated Learning ...

引用

2023 IEEE International Conference on Dependable, Autonomic and Secure Computing, 2023 International Conference on Pervasive Intelligence and Computing, 2023 International Conference on Cloud and Big Data Computing, 2023 International Conference on Cyber Science and Technology Congress, DASC/PiCom/CBDCom/CyberSciTech 2023

作者： Liu, Qi Wang, Yingjie Zhao, Weitao Qiu, Xuqiang School of Computer and Control Engineering Yantai University Yantai China Yantai Chijiu Clock Co. Ltd. Yantai China

ISBN: (纸本)9798350304602

Mobile Crowdsensing (MCS), as a novel data acquisition paradigm in the Internet of Things (IoT), incentivizes a large number of participants to collaboratively sense data for providing real-time services and accomplishing complex sensing tasks to benefit society. However, a major challenge hindering the further development of MCS is the risk of privacy leakage of participant data. In this paper, an effective integration of Federated Learning (FL) with MCS is proposed. The classic Federated Averaging (FedAvg) algorithm is enhanced, and differential privacy (DP) is introduced to locally preserve the privacy of sensitive user data, referred to as DP-FAG. In DP-FAG, noise is applied to sensitive participant data prior to global model aggregation. Moreover, all sensitive training data is securely stored on participant devices, effectively addressing the trusted third-party issue and ensuring data confidentiality. We conduct extensive experimental analysis on image classification tasks to validate the soundness and effectiveness of our proposed methodology. © 2023 IEEE.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Leak Detection Method via Assembling Twin Attention-based Prediction Models for Natural Gas Gathering Pipelines

An Unsupervised Leak Detection Method via Assembling Twin At...

引用

2024 China Automation Congress, CAC 2024

作者： Zhang, Hao Zuo, Zhonglin Zheng, Li Liang, Shan Lü, Qingguo College of Automation Chongqing University Chongqing China College of Control Science and Engineering Zhejiang University Hangzhou China College of Computer Science Chongqing University Chongqing China

ISBN: (纸本)9798350368604

Accurately detecting leaks in natural gas gathering pipelines cannot only help enterprises and governments timely cope with the safety management problems, but also maintain the reliable operation of pipelines. The data-driven approaches for leak detection have become a preferred solution with the widely installation of sensors in pipeline network. However, these methods face challenges in achieving high identification accuracy due to the lack of labeled leak data and insufficient representation learning. To overcome this difficulty, an unsupervised leak detection method that leverages twin attention-based prediction models is proposed for these gathering pipelines in this article. First, attention-based point and sequence prediction approaches are designed by joint utilization of attention mechanism (AM) and the cascade of one-dimensional convolutional network (1D-CNN) and long short-term memory (LSTM) network, where the sequence one also employs the operation of sequence repetition and flipping for better prediction. Based on the designed attention-based point and sequence prediction approaches, an unsupervised twin attention-based prediction structure is then introduced to jointly establish the normal pipeline models. Specifically, the point prediction model is mainly used to learn the short-term dependency patterns whereas the sequence prediction model for the long-term ones from the multivariate time series. Next, a fusion strategy is presented to fuse the prediction errors generated from the twin attention-based models for the computing of overall leak scores as well as exploiting their complementary detection sensibility. To obtain clear status of pipelines without affected by abnormal points resulting from device anomalies or noises, the minimum covariance determinant (MCD) approach is adopted to attain the reliable leak scores of the fused errors. The experimental results on datasets derived from real-world gathering pipelines validate the effectiveness of

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

The Bayesian CNN-LSTM Mixed Hybrid Algorithm Model of the Photovoltaic Short-term Output Forecasting 3

The Bayesian CNN-LSTM Mixed Hybrid Algorithm Model of the Ph...

引用

3rd International Conference on New Energy and Power engineering, ICNEPE 2023

作者： Dong, Enchong Guo, Yuxi North China Electric Power University School of Control and Computer Engineering Beijing China Shenzhen College of International Education Shenzhen China

ISBN: (纸本)9798350393224

Due to the volatility, randomness, and intermittency of photovoltaic power generation, it is difficult to accurately forecast its output. This paper proposes a Bayesian-optimized CNN-LSTM mixed neural model for a short-term photovoltaic output prediction model. First of all, the Xinjiang photovoltaic power station dataset is selected and preprocessed in this study. Secondly, the CNN method is applied for data feature extraction. And then the Bayesian optimization algorithm is used to analyze the LSTM super parameter optimization. Finally, the data, after undergoing feature extraction, are input into the Bayes theorem-LSTM model for forecast generation. The results show that the proposed algorithm has realized the accurate prediction of photovoltaic power, getting better than most other single benchmark models. These findings not only highlight the improved efficacy of the proposed algorithm but also affirm its potential applicability and value for practical implementation. © 2023 IEEE.

关键词： Bayesian algorithm Convolutional Neural Network algorithm Long Short-Term Memory algorithm Photovoltaic power output prediction

来源：评论

学校读者我要写书评

暂无评论

3D pulmonary vessel segmentation based on improved residual attention u-net

引用

Medicine in Novel Technology and Devices 2023年第4期20卷 64-75页

作者： Jiachen Han Naixin He Qiang Zheng Lin Li Chaoqing Ma School of Computer and Control Engineering Yantai UniversityYantai264005ShandongChina Yantaishan Hospital Affiliated Binzhou Medical UniversityYantai264003ShandongChina

Automatic segmentation of pulmonary vessels is a fundamental and essential task for the diagnosis of various pulmonary vessels *** accuracy of segmentation is suffering from the complex vascular *** this paper,an Improved Residual Attention U-Net(IRAU-Net)aiming to segment pulmonary vessel in 3D is *** extract more vessel structure information,the Squeeze and Excitation(SE)block is embedded in the down sampling *** in the up sampling stage,the global attention module(GAM)is used to capture target features in both high and low *** two stages are connected by Atrous Spatial Pyramid Pooling(ASPP)which can sample in various receptive fields with a low computational *** the evaluation experiment,the better performance of IRAU-Net on the segmentation of terminal vessel is *** is expected to provide robust support for clinical diagnosis and treatment.

关键词： Pulmonary vessel segmentation RAU-Net Squeeze and excitation Atrous spatial pyramid pooling Deep learning

来源：评论

学校读者我要写书评

暂无评论

Parallel control Strategy for Flexible Operation of Ultra-supercritical Units Under Digital Twin Theory 2

Parallel Control Strategy for Flexible Operation of Ultra-su...

引用

2nd IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2022

作者： Huang, Ting Hou, Guolian School of Control and Computer Engineering North China Electric Power University Beijing China

ISBN: (纸本)9781665492270

With the rapid development of big data and cloud technology, the coordinate control of thermal power plants is fast changing to a flexible and adaptive intelligent control model. In order to improve the operational flexibility of ultra supercritical (USC) units, a parallel control scheme based on ACP method is constructed in this paper. Firstly, an artificial control system that can reflect the operational conditions of units in real-time is constructed by the digital twin technology. Then, the precise model and active disturbance rejection control method are chosen for artificial system to guide the operation of USC units using computation experiments. Afterwards, the operational stability is ensured by the parallel execution of the artificial control system and actual USC units. Finally, the remarkable control performance of USC units based on the proposed parallel control scheme is successfully confirmed on a 1000MW units. © 2022 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Energy-independent solution using a medium-power wind turbine to ensure the irrigation deficit in an isolated agricultural areal 24

Energy-independent solution using a medium-power wind turbin...

引用

24th International Conference on control Systems and computer Science, CSCS 2023

作者： Fudulu, Cosmin-Florin Fagarasan, Ioana Boicu, Mihaela Gabriela Vasluianu, Mihaela Dobrea, Marius - Alexandru Neculoiu, Giorgian University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Romania Technical University of Civil Engineering of Bucharest Faculty of Hidrotechnics Romania

ISBN: (纸本)9798350313390

Smart agricultural systems require irrigation systems powered by renewable energy sources that are also adaptable for isolated areas without connection possibility to the electricity network or the water network. For such situations, in this paper, a solution is proposed using a wind turbine and a submersible pump to feed a water basin, subsequently irrigation is done by free fall. The developed solution is designed and simulated using a model of a medium-power wind turbine, and a battery storage element with the aim of providing the necessary electricity for irrigation of an agricultural area in Buzau, where there is a water deficit. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Event Recommendation Based on Heterogeneous Social Network Information and Time Information 4

Event Recommendation Based on Heterogeneous Social Network I...

引用

4th International Conference on Advanced Information Science and System, AISS 2022

作者： Zhao, Xiaofan Ma, Wenming School of Computer and Control Engineering Yantai University Shandong Province Yantai City China

ISBN: (纸本)9781450397933

In recent years, event-based social networks have developed rapidly, and event recommendation has attracted more and more attention. At present, for event recommendation, it is centered on the event, and aims to help users get the events which they are interested in from a large number of events. However, compared with traditional recommendation problems, event recommendation has many challenges. First of all, there is no obvious explicit rating of users' response to events, but implicit feedback. Secondly, the recommendation of events has heterogeneous social network relations. At the same time, most users participate in few events, which leads to a very serious data sparsity problem. In order to address these challenges and improve the effectiveness of event recommendation, this paper proposes an event recommendation model that integrates users' online and offline heterogeneous social network information and time information. The model uses Bayesian personalized ranking as the framework to process the implicit feedback information of users and events, and simultaneously combines online and offline social network information and time information to model together to improve the accuracy of recommendation. Experimental results based on real data sets show that the performance of the proposed model is better than other methods. © 2022 ACM.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Research on the Flux-weakening Capability of the Reverse-salient Permanent Magnet Synchronous Motor 26

Research on the Flux-weakening Capability of the Reverse-sal...

引用

26th International Conference on Electrical Machines and Systems, ICEMS 2023

作者： Zhao, Xiaokun Zhang, Cheng Wang, Weinan Kou, Baoquan Zhu, Liangkuan Northeast Forestry University College of Computer and Control Engineering Harbin China Harbin Institute of Technology Department of Electrical and Automation Harbin China

ISBN: (纸本)9798350317589

Permanent magnet synchronous motors (PMSMs) offer the benefits of high torque density and a superior power factor. Nevertheless, the challenge lies in the inherent difficulty of adjusting the permanent magnet flux. To address this issue, this paper analyzes the influence of electromagnetic parameters on the constant-power speed range (CPSR). First, the analysis focuses on the influence of d-axis inductance and saliency ratio, aiming to establish a design method for achieving a wide CPSP in PMSMs. Second, based on the electromagnetic parameter requirements, a reverse-salient PMSM is proposed and its working principle is explained. Finally, the electromagnetic characteristics, including torque and the CPSP, are determined through the application of the finite element method (FEM). The obtained results confirm that the reverse-salient PMSM achieves a CPSP of 7:1, thus validating the accuracy of the theoretical analysis. © 2023 IEEE.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

On Mikhailov Stability Conditions for a Class of Integer-and Commensurate Fractional-Order Discrete-Time Systems 21st

On Mikhailov Stability Conditions for a Class of Integer-and...

引用

21st Polish control Conference, PCC 2023

作者： Stanislawski, Rafal Rydel, Marek Department of Electrical Control and Computer Engineering Opole University of Technology ul. Pŕoszkowska 76 Opole45-758 Poland

ISBN: (纸本)9783031351693

The Mikhailov stability condition is a classical stability test for continuous-time systems, similar to the well-known Nyquist method. However, in contrast to the Nyquist criterion, the Mikhailov stability tests do not reach considerable research attention. This paper introduces an extension of Mikhailov stability condition for two classes of a discretetime system in terms of linear time-invariant system, and fractional-order one based on ‘forward-shifted’ Gr¨unwald-Letnikov difference. Simulation experiments confirm the usefulness of the Mikhailov methods for stability analysis of discrete-time systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Continuous time systems

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：