Brain image fMRI data classification and graphical representation of visual object

Abstract

Analyzing neuroimaging data has become a research of interest these days because of their several applications starting from analysis of brain region connectivity to analysis of ventral streams and visual stimuli. In this paper, we propose a model that explains what image a human brain visually perceives based on the neuroimaging information from the ventral temporal cortex (VT) portion. In the model, we used the nilearn library from python repository along with the haxby data set which includes a set of functional MRI from 6 subjects viewing images that contains a grid of black and white pictures of some certain figures. Firstly, the haxby data set was collected and few pre-processing steps such as masking, scaling and smoothing was done in order to reduce the complexity, noise and to standardize the data. Then, the entire data set was cross validated into 80 percent of training example and 20 percent of test example. After the splitting was done, the training examples were passed through a set of learning frameworks such as ‘Nearest Neighbors’, ‘Linear SVM’, ‘RBF SVM’, ‘Gaussian Process’, ‘Decision Tree’, ‘Random Forest’, ‘Neural Net’, ‘AdaBoost’, ‘Naive Bayes’ and ‘QDA’ algorithms. Completing the training, the accuracy of the frameworks was tested and on an average the most accuracy of 95 percent was found with Neural Network and Support Vector Machine (SVM) across all the subjects.