Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Complex defective wafer patterns.

Notes: (a) Edge-ring, (b) Donut, (c) Scratch.

More »

Fig 1 Expand

Fig 2.

Local defective wafer patterns.

More »

Fig 2 Expand

Fig 3.

Methodology of the proposed hybrid system.

More »

Fig 3 Expand

Fig 4.

Distribution of Defect Classes in the Dataset.

More »

Fig 4 Expand

Fig 5.

Defect and non-defect wafer map patterns before histogram equalization.

Notes: (i) Center (ii) Donut (iii) Edge local (iv) Edge ring (v)Local (vi) Near full (vii) Random (viii) Scratch (ix) None.

More »

Fig 5 Expand

Fig 6.

Defect and non-defect wafer map patterns after histogram equalization.

Notes: (i) Center (ii) Donut (iii) Edge local (iv) Edge ring (v)Local (vi) Near full (vii) Random (viii) Scratch (ix) None.

More »

Fig 6 Expand

Fig 7.

Histogram of equalized and un-equalized defective images.

Notes: (a) histogram of unequalized Center defect image; (b) histogram of equalized Center defect image; (c) histogram of unequalized Edge-Local defect image; (d) histogram of equalized Edge-Local defect image; (e) histogram of unequalized Edge-Ring defect image; (f) histogram of equalized Edge-Ring defect image; (g) histogram of the unequalized Local defect image; (h) histogram of equalized Local defect image; (i) histogram of unequalized Scratch defect image; (j) histogram of equalized Scratch defect image.

More »

Fig 7 Expand

Fig 8.

Structure of original MobileNet [28].

More »

Fig 8 Expand

Fig 9.

Graphical representation of ReLU and Swish activation functions.

More »

Fig 9 Expand

Fig 10.

Structure of modifiedMobileNet [28].

More »

Fig 10 Expand

Fig 11.

The multi-head attention mechanism process.

More »

Fig 11 Expand

Fig 12.

The detailed architecture of the proposed hybrid model.

More »

Fig 12 Expand

Fig 13.

The block diagram of the ECOC coding matrix.

More »

Fig 13 Expand

Table 1.

Experimental Settings.

More »

Table 1 Expand

Table 2.

Performance analysis of proposed hybrid model configurations on the imbalanced WM-811k dataset (image size:32 × 32).

More »

Table 2 Expand

Fig 14.

Analysis of the proposed model using several optimizers.

More »

Fig 14 Expand

Fig 15.

Contribution of the Swish activation function to the proposed model.

More »

Fig 15 Expand

Fig 16.

Contribution of the multi-head attention to the proposed model.

More »

Fig 16 Expand

Fig 17.

Contribution of the ECOC-SVM classifier to the proposed model.

More »

Fig 17 Expand

Fig 18.

Impact of histogram equalization on ‘Local’ defect class.

More »

Fig 18 Expand

Fig 19.

Overall performance evaluation of the proposed model based on the histogram equalization process.

More »

Fig 19 Expand

Fig 20.

Confusion matrix of the proposed model.

More »

Fig 20 Expand

Table 3.

Performance analysis of the proposed hybrid model based on different classifiers.

More »

Table 3 Expand

Fig 21.

Comparative analysis based on testing accuracy.

More »

Fig 21 Expand

Fig 22.

Comparative analysis based on MFLOPs.

More »

Fig 22 Expand

Fig 23.

Comparative analysis based on total parameters.

More »

Fig 23 Expand

Table 4.

Comparison of the proposed hybrid approach with other methods based on average values of performance metrics.

More »

Table 4 Expand

Table 5.

Comparison of the proposed hybrid approach with other systems based on the performance metrics.

More »

Table 5 Expand

Table 6.

Comparison of the proposed hybrid model and the base MobileNet model based on dataset balancing.

More »

Table 6 Expand

Table 7.

Comparison of the proposed hybrid approach with other developed methods- based on the classification accuracy of defect classes on the WM-811k dataset.

More »

Table 7 Expand

Fig 24.

Comparison of the proposed hybrid approach with other methods based on accuracy.

More »

Fig 24 Expand