Precise Medical Diagnosis For Brain Tumor Detection and Data Sample Imbalance Analysis using Enhanced Kernel Extreme Learning Machine Model with Deep Belief Network Compared to Extreme Machine Learning

To identify the brain tumor according to the categorial identification by using the symptoms. Materials and Methods: To identify brain tumors using Kernel Extreme Learning Machine with improved accuracy over Extreme Machine Learning. The total number of samples that are evaluated on the proposed methodology is 10 in each of 2 groups. Results: The proposed hybrid Kernel Extreme Learning Machine approach gives accuracy 93.31% which is significantly better in classification when compared to Extreme Machine Learning which has less accuracy 81.91% and level of significance is 0.01
$(\mathrm{p} < 0.05)$
. Conclusion: Identifying brain tumor was achieved significantly better by using a novel functional glioma innovation as Kernel Extreme Learning Machine compared to Extreme Machine Learning.