Can we predict music genres based on fMRI connectivity patterns alone? This project explores a single-subject decoding approach using ROI-to-ROI correlation matrices and machine learning classifiers on OpenNeuro dataset ds003720.
This project applies machine learning to decode perceived emotions from fMRI data using ROI-based features. Data from the ds003548 OpenNeuro dataset are analyzed, with task labels extracted from events files. ROI time series are extracted using the MIST 64-ROI atlas, and mean signals during emotion blocks are classified using linear SVM. The goal is to distinguish between six conditions (happy, sad, angry, neutral, blank, scrambled), demonstrating key concepts and challenges in neuroimaging-based classification.
The project focused on extracting activities from functional images in a previous study about neural representation of melody-transposition. Using parcellated brain atlas as a mask, the BOLD signals underwent univariate analysis to look for effects in error detection or music-like stimulus-related brain regions/
An attempt to replicate the study by Soler-Vidal et al. (2022), using the study’s dataset available on OpenNeuro. Attempted preprocessing of the first participant, sub-01, using FSL (FEAT files in ‘sub-01’ folder) and fMRIPrep (material found in ‘code’ and ‘derivatives’ folders). Attempted creation of timing files, found in ‘Ideal_Time_Series’ folder.
This project trains machine learning classification models to make predictions of adhd diagnosis from brain fRMI connectivity measures which are obtained from a resting state ADHD dataset . The main goals of this project are to get more practice with machine learning tools and to learn how work with brain data more precisely fMRI data.
This project utilizes fMRI data and machine learning to predict sleep states, aiming to enhance understanding of sleep patterns and disorders. By analyzing brain activity during different sleep stages, it seeks to improve diagnostics and develop personalized treatments for sleep disorders. The primary goal is to determine whether a participant is asleep or awake using resting-state fMRI data.
Brain Decoding is the reconstruction of the sensory and other stimuli form the information that has already been encoded and represented in the brain. For example, image genration, and task classification, from brain activity signals could be covered under this topic. In this project, a graph neural netwrok appriach is used to learn the representation of the brain regions activities, and do image classification for the end-user (patient).
We used the ADHD-200 Sample dataset to implement various machine learning classification models, aimed at diagnosing ADHD through resting-state fMRI signals.
Language consists of many thousands of words which differ in meaning and syntactic category. Some words may refer to reletevely touchable, hence concrete aspects of the world while others are abstract in meaning which do not have physical references. But which brain areas are associated with tactile word processing? This project aims to investigate brain activation of participants when listening to tactile vs non-tactile word stimuli. The preliminary result shows that large areas of parietal lobe is particularly activated to tactile words compared to non-tactile words
This project investigates the neural correlates of athletic performance using fMRI, dMRI, and FSLVBM to compare grey matter volume and white matter connectivity between athletes and non-athletes. The study aims to identify brain regions associated with athletic performance, explore white matter connectivity differences, and examine the relationship between brain structure and specific athletic skills. The dataset included nine Indiana University football players and nine controls.
Copyright (c) 2026, BrainHack School; all rights reserved.
Template by Bootstrapious. Ported to Hugo by DevCows.