Statistical analysis and Neural Network Modeling of functionally graded porous nanobeams vibration in an elastic medium by considering the surface effects

Cheng, Xiaofei; Al-Khafaji, Sara Hakem; Hashemian, Mohammad; Ahmed, Mariem; Eftekhari, S. Ali; Alanssari, Ali Ihsan; diaa, Nabaa Muhammad; Karim, Manal Morad; Toghraie, Davood; Alawadi, Ahmed Hussien

doi:10.1016/j.engappai.2023.106313

Cited by 11 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the data set is small and very different from the ImageNet image set, then the best strategy for configuring the model is to train it with sequential unfreezing of the convolutional layers of the pre-trained model, starting from the last one, until an acceptable classification accuracy is achieved on the used set of images. If the data set is large enough, but significantly different from ImageNet, then the best strategy would be to train a deep convolutional network model from scratch, but it should still be initialized with weights from ImageNet [13].…”

Section: Transfer Learning Methods In Image Recognitionmentioning

confidence: 99%

Deep Learning Transfer Methods for Biomedical Classification of Images

Al-Janabi

2024

Ijirme

View full text Add to dashboard Cite

Research using computers has been carried out on the effectiveness of applying deep learning transfer methods to solve the problem of identifying human brain tumors using MRI imaging. Various deep learning and fine-tuning methodologies of models have been proposed and implemented. The deep convolution networks MobileNetV2, VGG-16, Xception and ResNet-50, trained on the ImageNet image set, were used as basic models. A deep convolutional neural network 2D-CNN has also been developed and trained. A computer study of the performance indicators revealed that the fine-tuning method was effective On an enlarged data set, the Xception model outperformed other deep learning models in terms of accuracy: the clarity with which brain tumors are classified using MRI images was 94%, precision 97.7%, recall 94.01%, f1 score 96%, AUC 96.90%.

show abstract

Section: Transfer Learning Methods In Image Recognitionmentioning

confidence: 99%