LSTM deep learning long-term traffic volume prediction model based on Markov state description

Yang, Dakai; Liang, Qiuhong; Li, Runmei; Wang, Jian; Cai, Bai-Gen

doi:10.1080/02533839.2024.2334209

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article3

Other1

Relationship

Self Cite0

Independent4

Authors

Journals

Cited by 4 publications

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Flow prediction of mountain cities arterial road network for real-time regulation

Cai,

Li,

Dai

et al. 2024

Journal of King Saud University - Computer and Information Scie

View full text Add to dashboard Cite

Flow prediction of mountain cities arterial road network for real-time regulation

Cai,

Li,

Dai

et al. 2024

Journal of King Saud University - Computer and Information Scie

View full text Add to dashboard Cite

Logistics Cargo Volume Prediction Model Based on Combined ARIMA-LSTM Prediction Methods

Luo,

Jiao,

Zhang

et al. 2024

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS)

View full text Add to dashboard Cite

Application of anti-mapping security access technology in network security protection

Ma,

Li,

Liu

et al. 2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

In the current era, characterized by the pervasive Internet of Everything, trillions of data points are exposed to high-level threats, presenting novel challenges to the domain of cyberspace security. This paper introduces a cybersecurity protection framework derived from the PDRR model, enriched with integrated cybersecurity measures. Utilizing a cyberspace mapping architecture that incorporates anti-mapping security access technology, we analyze the robustness of cybersecurity protections. The framework employs penetration testing queue technology to uncover vulnerabilities within cyberspace, the Hidden Markov Model to assess cybersecurity posture, and the QPSO-LightGBM model to evaluate cybersecurity vulnerabilities. To validate the efficacy of the cyberspace mapping architecture in employing anti-mapping security access technology, we have systematically conducted various experimental methodologies, including penetration testing, security posture sensing, and security vulnerability assessment. This integrated approach provides a comprehensive framework for addressing the complex challenges posed by the vast scale of data in today’s interconnected environments. The average send/receive telegram packets of the network I/O graph in the state of SYN flooding attack grows from 60 packets/sec in the normal state to 2.2*104 packets/sec, and the minimum time of security posture perception by the Hidden Markov Model is only 51.28ms. The accuracy of the QPSO-LightGBM model for network security vulnerability assessment reaches 86.58%. Fully utilizing anti-marker security access technology can improve the understanding of the threat situation in network security and enhance the protection ability.

show abstract

LSTM deep learning long-term traffic volume prediction model based on Markov state description

Cited by 4 publications

References 23 publications

Flow prediction of mountain cities arterial road network for real-time regulation

Flow prediction of mountain cities arterial road network for real-time regulation

Logistics Cargo Volume Prediction Model Based on Combined ARIMA-LSTM Prediction Methods

Application of anti-mapping security access technology in network security protection

Contact Info

Product

Resources

About