Deep clustering of traffic signals using a single seismic station

In this study, we present an unsupervised deep clustering framework based on Deep Embedded Clustering (DEC) to automatically identify traffic-induced signal segments from high-frequency seismic noise recorded by a single seismic station. The presented dataset is part of our study on using DEC to analyze seismic signals at urban scales. 1. The Synthetic Data folder contains simulated traffic-induced seismic signals.2. The Field Data folder includes raw seismic recordings collected from three different sites.3. The Input for DEC folder provides the preprocessed dataset used for model training.