Uneingeschränkter Zugang

Fusion of RF algorithm and logistic regression model for high-speed illegal toll evasion vehicle inspection

Haiyan Wu

Haiyan Wu

Hebei Expressway Group Limited Qingyin BranchShijiazhuang, China
Suche nach diesem Autor auf
Sciendo|Google Scholar
Wu, Haiyan
  
17. März 2025
Fusion of RF algorithm and logistic regression model for high-speed illegal toll evasion vehicle inspection's Cover Image
Über diesen Artikel
Vorheriger Artikel
Nächster Artikel
Zitieren
COVER HERUNTERLADEN
Online veröffentlicht: 17. März 2025
Eingereicht: 19. Okt. 2024
Akzeptiert: 15. Feb. 2025
DOI: https://doi.org/10.2478/amns-2025-0182
Schlüsselwörter
© 2025 Haiyan Wu, published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

Flowchart of data cleaning
Flowchart of data cleaning

Figure 2.

Architecture diagram of vehicle recognition model for toll evasion
Architecture diagram of vehicle recognition model for toll evasion

Figure 3.

Flowchart of vehicle identification for toll evasion based on RF-logit model
Flowchart of vehicle identification for toll evasion based on RF-logit model

Figure 4.

Details of the construction of the neuron
Details of the construction of the neuron

Figure 5.

BPNN structure
BPNN structure

Figure 6.

Comparison of accuracy and recall
Comparison of accuracy and recall

Figure 7.

Comparison of error fitting curves
Comparison of error fitting curves

Figure 8.

Comparison of ROC curves
Comparison of ROC curves

Data details of various kinds of toll evasion behaviors

Type of fee evasion Fee evasion Data quantity
Imitation category License plate does not match 514
Cheating class U-shape 52
No card Gear shift 64
Change of weight 96
Overtime 152
Defect class Excess weight 78
There is no weight on the weighing table 45
Fight one’s way through a pass 41
Violation category Outlet suspension shaft 32
Inlet suspension shaft 7
Inlet weightless 39
Fee evasion 17

Evaluation Table of inspection effect on TEVs

Models Prediction accuracy Classification accuracy Audit time MSE RMSE Stability
RF-logit 0.88 0.87 0.86 0.89 0.77 0.85
RF-BPNN 0.85 0.84 0.83 0.86 0.84 0.83
RF+SVM 0.87 0.86 0.85 0.88 0.86 0.87
GBM 0.74 0.83 0.82 0.75 0.83 0.84
RF-logit-BPNN 0.92 0.94 0.90 0.92 0.91 0.93
Sprache:
Englisch
Zeitrahmen der Veröffentlichung:
1 Hefte pro Jahr
Fachgebiete der Zeitschrift:
Biologie, Biologie, andere, Mathematik, Angewandte Mathematik, Mathematik, Allgemeines, Physik, Physik, andere
Zeitschrift RSS Feed