Welcome to CrowdEEG
“CrowdEEG” is a cross-institutional research project out of the David R. Cheriton School of Computer Science at the University of Waterloo, in joint collaboration with Sunnybrook Hospital (University of Toronto) and McGill University.
The overall vision of this project is to combine human and machine intelligence for the scalable and accurate analysis of human clinical EEG data.
A joint venture in machine learning and human health, the CrowdEEG project spans multiple fields and institutions towards the goal of scalable and accurate analysis of medical time series data—utilizing the joint effort of algorithms, experts, and non-experts (students and crowd workers).
Our research is motivated by two key issues: One, time and cost factors are of major importance in the context of analyzing human clinical EEG data because experienced experts like neurologists or EEG technicians are both rare and expensive. Two, highly-trained experts will often disagree about ground truth in multi-channel biosignal time series data, and insight into the source of disagreement among trained experts can inform automated methods of EEG analysis, as well as the education and training of students and crowd workers.
A collaborative annotation tool for medical time series data
The crowdEEG app is a collaborative annotation tool that enables groups of experts or non-expert crowds to perform feature detection or high level classification tasks on medical time series data.