Beschreibung
In this book, comparison on performance of artificial neural network and transfer learning is made for classification of breast cancer into malignant and benign. First artificial neural network topology is design using three hidden layers used for feature extraction and after that softmax layer is used for prediction of cancer as malignant and benign. After that deep convolutional neural network transfer learning model is used where VGG19 which is pretrained model is used for feature extraction and after that dense layers are there which are used for final prediction. So the proposed model with transfer learning outperforms the artificial neural network model with overall accuracy of 98.4% and also beat previous convolutional neural network model. In future we can use other transfer learning models like Resnet50, InceptionV3 to increase further accuracy of the model.
Autorenporträt
Dr. Gagan Deep received his Bachelor's degree in Computer Science and Engineering fromPunjab Technical University, Jalandhar, Punjab, India in 2002, M.E. degree in Computer Science and Engineering from PEC University of Technology, Chandigarh, India, in 2005 and Ph.D.degree in Computer Engineering from Panjabi university, Patiala, India, in 2017.
Herstellerkennzeichnung:
OmniScriptum SRL
Str. Armeneasca 28/1, office 1
2012 Chisinau
MD
E-Mail: info@omniscriptum.com
