Table 9 NasNetMobile ablation study statistical scores for various deep learning models with cohen kappa metric.

From: Pyramidal attention-based T network for brain tumor classification: a comprehensive analysis of transfer learning approaches for clinically reliable and reliable AI hybrid approaches

Model

Mean

Std dev

Skewness

Kurtosis

Median

Variance

NASNET + ANN

0.974384

0.010605

0.074101

 − 1.03949

0.972338

0.000112

NASNET + DNN

0.876937

0.023778

0.073674

0.486557

0.877135

0.000565

NASNET + CNN

0.874238

0.027251

 − 0.20836

 − 1.08754

0.877547

0.000743

NASNET + LSTM

0.962216

0.011607

 − 0.37112

 − 1.06916

0.963173

0.000135

NASNET + CNN + LSTM

0.881426

0.022192

 − 0.03274

 − 0.92671

0.877532

0.000493

NASNET + CHANNEL ATTENTION + CNN

0.968913

0.011396

 − 0.21305

 − 1.02851

0.963249

0.00013

Back to article page