Authors :
T. Jagadeeswari; Dr. P. Srinivas; Dr. Y.L. Malathi Latha
Volume/Issue :
Volume 7 - 2022, Issue 8 - August
Google Scholar :
https://bit.ly/3IIfn9N
Scribd :
https://bit.ly/3RiAvZl
DOI :
https://doi.org/10.5281/zenodo.7047257
Abstract :
The Brain Tumors is the one of the leading
disease affects the humans, thus the early detection of
brain tumors prevent millions of deaths. Thus, most of
the researches are focusing on detection of brain tumor
using machine learning based approaches. But, those
approaches are failed to provide the classification
accuracy. To overcome these drawbacks, in this work
Adative Neuron Fuzzy Inference System (ANFIS) based
Deep Learning based Convolution Neural Networks
(DLCNN) classification algorithm has been performing
with the help of effective use of Grey level Co-occurrence
Matrix (GLCM) features. Initially, Probabilistic Kernel
Fuzzy C Means Segmentation (PKFCM) based multi
level segmentation operation has been performed to
detection of accurate tumor region. The simulations are
conducted on various datasets, the results shows that the
proposed work shows the better performance compared
to various conventional approaches with respect to both
quantitative and qualitative evaluation.
Keywords :
Brain Tumor , Detection, Disease, Fuzzy, Machine Learning , Deep Learning , Convolution and Segmentation.
The Brain Tumors is the one of the leading
disease affects the humans, thus the early detection of
brain tumors prevent millions of deaths. Thus, most of
the researches are focusing on detection of brain tumor
using machine learning based approaches. But, those
approaches are failed to provide the classification
accuracy. To overcome these drawbacks, in this work
Adative Neuron Fuzzy Inference System (ANFIS) based
Deep Learning based Convolution Neural Networks
(DLCNN) classification algorithm has been performing
with the help of effective use of Grey level Co-occurrence
Matrix (GLCM) features. Initially, Probabilistic Kernel
Fuzzy C Means Segmentation (PKFCM) based multi
level segmentation operation has been performed to
detection of accurate tumor region. The simulations are
conducted on various datasets, the results shows that the
proposed work shows the better performance compared
to various conventional approaches with respect to both
quantitative and qualitative evaluation.
Keywords :
Brain Tumor , Detection, Disease, Fuzzy, Machine Learning , Deep Learning , Convolution and Segmentation.