Scientific Reports

Table 2 Results for four classification model architectures on test images.

From: Classifying stages in the gonotrophic cycle of mosquitoes from images using computer vision techniques

Performance metrics	Unfed	Fully fed	Semi-gravid	Gravid	Avg. performance metrics
ResNet50
Precision	100	96.08	100	91.84	96.98
Recall	100	94.23	95.45	100	97.42
F1-score	100	95.15	97.67	95.74	97.14
Accuracy	100	94.23	95.45	100	97.44

MobileNetV2
Precision	95.95	91.84	95.08	80.00	90.71
Recall	100	86.54	87.88	88.89	90.83
F1-score	97.93	89.11	91.34	84.21	90.65
Accuracy	100	86.53	87.88	88.89	91.45

EfficientNet-B0
Precision	97.26	96.00	95.24	83.33	92.96
Recall	100	92.31	90.91	88.89	93.03
F1-score	98.61	94.12	93.02	90.91	92.94
Accuracy	100	92.31	90.91	88.89	93.59

ConvNeXtTiny
Precision	94.20	92.31	89.66	69.09	86.31
Recall	91.55	92.31	78.79	84.44	86.77
F1-score	92.86	92.31	83.87	76.00	86.26
Accuracy	91.55	92.31	78.78	84.44	86.75

Back to article page

Search

Advanced search

Quick links