Classification of Brain MRIs using Improved Firefly Algorithm Based Ensemble Model
Sarada Prasanna Pati1, Debahuti Mishra2
1Sarada Prasanna Pati, Department of Computer Science & Engineering, Siksha O Anusandhan Deemed to be University, Bhubaneswar (Odisha), India.
2Debahuti Mishra, Department of Computer Science & Engineering, Siksha O Anusandhan Deemed to be University, Bhubaneswar (Odisha), India.
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 599-604 | Volume-8 Issue-5, March 2019 | Retrieval Number: D3252028419/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this work we propose an automated medical image diagnosis system for diagnosing the healthy and diseased brain conditions by analyzing the brain MR images. The system uses a weighted classifier combination basedensemble model for classification of the brain images. In this approach four different base classifiers namely ANN, KNN, SVM and Naïve Bayes are first employed for training. After successful validation of each model the output obtained by each individual model is optimally weighted using animproved Firefly algorithm as well as other established biologically inspired optimization techniques like Particle Swarm Optimization (PSO), Firefly Algorithm (FA) and Genetic Algorithm (GA) based techniques to produce the best possible results. Prior to classification task, the feature extraction for the image datasets are performed using DWT following which, PCA is used for dimensionality reduction. Finally the results obtained are compared with the results obtained by the individual classifiers as well as by the other threeweighted ensemble schemes optimized using PSO, GA and AF. It is in general demonstrated that in all cases the proposed method outperforms other competitive methods.
Keyword: Brain Image Classification, Classifier Ensemble, Discreet Wavelet Transformation, Principal Component Analysis, Firefly Algorithm, Improved Firefly Algorithm.
Scope of the Article: Classification