Table 3 Comparison of the existing method and the proposed method.

From: Sustainable cyber-physical VANETs with AI-driven anomaly detection and energy-efficient multi-criteria routing using machine learning algorithms

Aspects

Existing method in ratio (%)

Proposed method in ratio (%)

Key features

Detection accuracy

85.90

95.33

High accuracy using Random Forest with feature selection and clustering

False positive rate (FPR)

25.33

15.22

Reduced false positives through optimised classification techniques

Computational efficiency

80.85

94.25

Optimised computational overhead using efficient feature selection

Recall (detection rate)

88.92

96.09

High recall ensures better threat detection with minimal false negatives

Resource Usage Efficiency

75.85

91.45

Lower processing and memory consumption make it suitable for real-time VANET deployment

Back to article page