Classification of Silicon (Si) Wafer Material Defects in Semiconductor Choosers using a Deep Learning ShuffleNet-v2-CNN Model

Table 3

Performance analysis of proposed ShuffleNet-v2-CNN model.

Class	Accuracy	Precision	Recall	F1-Score
Center	95.2	93.8	94.9	94.1
Donut	96.5	95.1	96.2	95.8
Edge-Loc	97.6	95.9	96.6	96.2
Edge-Ring	95.8	94.5	95.1	94.7
Local	96.5	93.8	95.8	95.0
Near Full	98.4	97.2	97.7	97.1
Random	97.0	96.1	96.3	95.9
Scratch	98.5	96.8	97.5	97.2
Total Average	96.93	95.4	96.26	95.75