Table 9 ANOVA on R2 of various models
From: GrainNet: efficient detection and counting of wheat grains based on an improved YOLOv7 modeling
(a)Input summary | ||||||
|---|---|---|---|---|---|---|
Model | Count | Mean | Std | 95% CI | ||
GrainNet | 5 | 0.92077 | 0.02510 | (0.89877, 0.94277) | ||
YOLOv7 | 5 | 0.82995 | 0.01901 | (0.81328, 0.84661) | ||
YOLOv8 | 5 | 0.89953 | 0.01610 | (0.88541, 0.91364) | ||
FasterRCNN | 5 | 0.36907 | 0.03427 | (0.33903, 0.39910) | ||
YOLOv5 | 5 | 0.91276 | 0.00687 | (0.90674, 0.91878) | ||
(b)ANOVA result | ||||||
|---|---|---|---|---|---|---|
Source of Variation | SS | df | MS | F Stat | P-value | F crit |
Between Groups | 1.11442 | 4 | 0.27860 | 450.78316 | 2.74889E-19 | 2.86608 |
Within Groups | 0.01236 | 20 | 0.00062 | - | - | - |
Total | 1.12678 | 24 | - | - | - | - |
(c)Post Hoc Analysis | Â | |||||
|---|---|---|---|---|---|---|
Model compared with GrainNet | Difference of means | LSD | Lower-bound | Upper-Bound | Â | |
YOLOv7 | 0.09082 | 0.92686 | -0.83603 | 1.01768 | Â | |
YOLOv8 | 0.02125 | 0.92686 | -0.90561 | 0.94810 | Â | |
FasterRCNN | 0.55171 | 0.92686 | -0.37515 | 1.47856 | Â | |
YOLOv5 | 0.00801 | 0.92686 | -0.91885 | 0.93487 | Â | |