RMS PROP: 2 – CLASS CNN ACCURACY MODEL FOR CERVİCAL CANCER PREDİCTİON AND CLASSİFİCATİON İN DEEP LEARNİNG

  • ^S. Selvaraj, D.Deepa, A. Affiya, G. Aiswarya, G. Brindha

Abstract

Cervical cancer is the major increasing sicknesses among women in India and also around the
world. In existing approach, Machine Learning (ML) systems were used to predict the cancer cells in
human beings. In previous work, two popular ML techniques like Voting Classifier and Deep Neural
Network (DNN) Classifier are used to predict cervical growth. The cervical cancer datasets from
Unique Client Identifier (UCI) store was taken to predict the cancer cells. But this approach failed to
provide better accuracy. This paper proposed of cervical cancer cell prediction and classification
system based on deep learning. Convolutional Neural Network (CNN) model is used for prediction
and classification. CNN model has 3 layers. To extract deep-learned features, the cell images were
fed into a Convolutional layer (1st layer). To reduce the dimensionality, the input images were fed into
pooling layer (2nd layer). Finally, the fully connected layer has been introduced. After the process, the
class label has derived from the CNN model for given input image. CNN provide better accuracy in
prediction and classification of cervical cells. The experiment was done by collecting the cervical
cancer dataset from Pap smear Herlev database. The main objective of the project is to predict and
classify the cervical cancer images with high accuracy. The proposed CNN based system achieved
high accuracy in the prediction problem (2-class) and classification problem (2-class).

Published
2020-04-13
How to Cite
^S. Selvaraj, D.Deepa, A. Affiya, G. Aiswarya, G. Brindha. (2020). RMS PROP: 2 – CLASS CNN ACCURACY MODEL FOR CERVİCAL CANCER PREDİCTİON AND CLASSİFİCATİON İN DEEP LEARNİNG. International Journal of Advanced Science and Technology, 29(6s), 2762 -. Retrieved from http://sersc.org/journals/index.php/IJAST/article/view/12197