Developing an Integrated Smart and Stable Driving System Linked Abnormal Data Detection Algorithm

Savar Sharma

Volume 5, Issue 3 2021

Page: 30-35

Abstract

This paper proposes a fog computing-based crowd-sensing detection scheme for abnormal data in the Internet of Vehicles. The traditional cloud computing-based detection scheme has problems such as heavy computing tasks on the central server and too long detection time. To solve this problem and give full play to the computing power of the crowd-sensing terminal, this paper proposes a generalized vehicle following model considering the influence of multiple vehicles ahead based on the intelligent driver model. To improve the stability of traffic flow, considering the speed difference between P vehicles ahead and own vehicle, and adding the influence of the nonlinear weight index, the generalized stability conditions of the new model are obtained through linear stability theoretical analysis.

Back Download



References

  • Xu Ningbin. Research on abnormal data detection algorithm for crowd-sensing car networking [D]. 2018.
  • Yan Mengqiu, Yang Yijun, Zhao Fang. Research on anomaly detection method of intelligent substation data flow based on improved OCSVM [J]. Power System Protection and Control, 2022, 50(6):7.
  • Gong Lei. Research on multi-scale pedestrian detection and tracking method based on integral channel [D]. Jilin University, 2019.
  • Xu Jing. Research on intelligent detection technology of data anomaly based on cloud computing [J]. Automation and Instrumentation, 2020(2):4.
  • Du Huijuan. An abnormal behavior detection system for connected vehicles based on artificial immunity [D]. East China Normal University, 2019.
  • Zheng Zifen. Research on abnormal data detection method of intelligent manufacturing big data [J]. Information Week, 2018(11):1.
  • Sun Yuan, Liao Xiaoping. Anomaly data detection method based on intelligent bat algorithm [J]. Computer and Modernization, 2019(3):6.
  • Hu Jiaojiao. Research on anomaly detection and prediction method of aircraft telemetry time series data based on deep learning [D]. Xi'an University of Technology, 2019.
  • Yang Fan, He Zhengwei, Liu Lirong. Research on real-time detection method of water traffic anomaly data based on Spark and wavelet analysis [J]. Journal of Shaanxi Institute of Technology (Self-Science Edition), 2019(1).
  • Chai Yuan. A preliminary study on the research scheme of abnormal driving behavior recognition system based on MTCNN [J]. 2020.
  • Wang Sisi, Zhang Jinglei, Wang Jianxing, et al. Anomaly detection of aggressive driving behavior based on improved swarm intelligence K-means optimization algorithm [J]. Science Technology and Engineering, 2018, 018(034):208-214 .
  • Shen Shu, Chen Weinan, Li Wenjuan. Dangerous driving behavior detection method and system based on smartphone gait recognition: CN112043280A[P]. 2020.
  • Fan Jiaqi, Li Xin, Huo T ianjiao, et al. Research on cross-domain detection of intelligent vehicles based on single-stage algorithm [J]. Journal of China Highway and Transportation, 2022, 35(3):249-262.
  • Wang Qingjie. An Iterative Data Anomaly Detection Method and Detection System: CN112559803A[P]. 2021.
  • Yang An, Hu Yan, Zhou Liang, et al. Anomaly detection algorithm for industrial control system based on information flow and state flow fusion [J] . Computer Research and Development, 2018, 55(11):11.
  • Xu Baobei. Research on 3D thermal imaging reconstruction technology based on depth camera [D]. Zhejiang University, 2019.
  • Yue Boxuan. Research on fault -tolerant perception and decision-making control methods of intelligent vehicles based on deep learning [D]. Zhejiang University, 2018.
  • Ma Yuchao. Research and application of anomaly detection of time series data based on dynamic baseline performance based on machine learning [J]. China Financial Computer, 2020(6):9.
  • Wang Xiaolong, Zhang Yongfa, Liu Zhong, et al. Research on anomaly detection and analysis method of nuclear power system based on data-driven [J]. Nuclear Power Engineering, 2021, 42(5):7.
  • Huo Guili. Research on automatic driving system optimization based on intelligent control algorithm [J]. Modern Electronic Technology, 2019, 42(20):4.
  • Guo Jiawei. Identification and early warning of abnormal driver behavior based on computer vision [D]. Dalian Maritime University, 2019.
  • Wei Baochang. Research on detection of people and vehicles based on deep learning [D]. Tianjin University of Science and Technology, 2019.
  • Zhang Jun. Research on driving behavior identification and risk assessment method based on Internet of Vehicles data [D]. University of Science and Technology of China, 2020.
  • He Danni. Research on multi-vehicle detection and tracking algorithm based on deep learning [D]. Dalian University of Technology, 2019.
  • Wang Sisi, Zhang Jinglei, Wang Jianxing, et al. Outlier detection of aggressive driving behavior based on improved swarm intelligence K-means optimization algorithm [J]. Science, Technology and Engineering, 2018.
  • Wang Sisi, Zhang Jinglei, Wang Jianxing, et al. Anomaly detection of aggressive driving behavior based on improved swarm intelligence K-means optimization algorithm [J]. Science Technology and Engineering, 2018, 18(34):7.

Looking for Paper Publication??

Come to us.

Submit your Paper