Abstract—Analysis of Functional Magnetic Resonance imaging (fMRI) time series plays a vital role in identifying the activation behaviour of neurons in the human brain. However, due to the complexity of the fMRI data, its analysis is challenging. Some studies show that the clustering methods can be beneficial in this respect. We apply a Neutrosophic Set-Based Clustering Algorithm (NEBCA) to fMRI time series datasets by this motivation. For the experimental purpose, we consider fMRI time series related to working memory tasks and resting-state. The clusters with different densities for the two analyzed cases are determined and compared. The identified differences indicate brain regions involved with the processing of the short-memory tasks. The corresponding brain areas are denoted according to Automated Anatomical Labeling (AAL) atlas. The statistical reliability of the findings is verified through various statistical tests. The presented results demonstrate the utility of the neutrosophic set based algorithm in brain neural data analysis.
 

Index Terms—neutrosophic set, entropy, clustering, functional Magnetic Resonance Imaging (fMRI) time series

Cite: Pritpal Singh, Marcin Wątorek, Anna Ceglarek, Magdalena Fąfrowicz, and Paweł Oświęcimka, "Analysis of fMRI Time Series: Neutrosophic-Entropy Based Clustering Algorithm," Journal of Advances in Information Technology, Vol. 13, No. 3, pp. 224-229, June 2022.

Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.