The first row from the top is showing generated ECG, corresponding to input PPG (second row from the top). The last row is the original ECG.
CardioGAN: Synthesize ECG from PPG
We propose a novel framework called CardioGAN for generating ECG signals from PPG inputs. We utilize attention-based generators and dual time and frequency domain discriminators along with a CycleGAN backbone to obtain realistic ECG signals. To the best of our knowledge, no other studies have attempted to generate ECG from PPG (or in fact any cross-modality signal-to-signal translation in the biosignal domain) using GANs or other deep learning techniques. Moreover, CardioGAN makes it possible monitoring daily life cardiac activity in a continuous manner.
AAAI 2021: https://arxiv.org/pdf/2010.00104.pdf
Self-supervised ECG Representation Learning
We exploit a self-supervised deep multi-task learning framework for electrocardiogram (ECG) -based emotion recognition. To the best of our knowledge, this is the first time self-supervised learning is utilized to perform emotion recognition using ECG.
Classification of Cognitive Load and Expertise for Adaptive Simulation
We propose an end-to-end framework for a trauma simulation that actively classifies a participant’s level of cognitive load and expertise for the development of a dynamically adaptive simulation.
This paper presents a deep learning method for computer-aided differential diagnosis of benign and malignant breast cancer tumors by avoiding potential errors caused by poor feature selection as well as class imbalances in the dataset. (This was done as part of ELEC 879 course project.)
ICMLA 2019: https://ieeexplore.ieee.org/abstract/document/8999310