Table 3 Comparison of different methods.

From: TinyML-enabled fuzzy logic for enhanced road anomaly detection in remote sensing

Method

Accuracy

Precision

Recall

F1-Score

IoU

DCS-TransUperNet31

-

77.9

69.5

73.5

56.7

GOALF63

-

73.2

70.8

72.0

56.2

GCB-Net34

-

-

-

81.5

70.8

DiResNet64

-

78.8

81.5

79.1

66.8

ScRoadExtractor65

-

79.5

71.4

71.3

57.8

TinyML-U-Net-FL (proposed)

73.91

78.2

92.4

84.7

-

  1. This table shows the performance of different models in terms of Accuracy, Precision, Recall, F1-Score, and IoU. The TinyML-U-Net-FL (Proposed) model demonstrates higher Recall and F1-Score than other methods, indicating its effectiveness in road network anomaly detection.
Back to article page