no code implementations • 18 Nov 2019 • Ali Oskooei, Sophie Mai Chau, Jonas Weiss, Arvind Sridhar, María Rodríguez Martínez, Bruno Michel
We explore and compare three methods in order to perform unsupervised stress detection: 1) traditional K-Means clustering with engineered time and frequency domain features 2) convolutional autoencoders and 3) long short-term memory (LSTM) autoencoders, both trained on the raw RRI measurements combined with DBSCAN clustering and K-Nearest-Neighbors classification.