ECG Analysis Using Deep CNNs

Introduction

In the recent decade, the deep neural network has been a key enabler for advances in machine learning. One of its sub-branches, the convolutional neural network (CNN), is particularly good at image classification tasks due to its outstanding efficiency and the ability to automatically detect important features without any human supervision.

This project investigates a convolutional neural network model proposed by a group of biomedical researchers in which is used to classify the health states of hearts and specify cardiovascular diseases by analysing the ECG diagram.

Developers will go through a complete research process, including comprehending academic papers, developing CNN models, collecting and training data, comparing with other models and making improvements on the current machine learning frameworks, etc. Experience in using tools such as PyTorch/TensorFlow, pandas, NumPy is an asset, but all the machine learning lovers are welcome!

We are looking for developers with experience in research and/or computer vision to join us. Email iamyan.zhu@mail.utoronto.ca or DM “Yan Zhu” in the UTMIST Discord if you’re interested!

Proposal