Paper detail

SeismoFlow -- Data augmentation for the class imbalance problem

In several application areas, such as medical diagnosis, spam filtering, fraud detection, and seismic data analysis, it is very usual to find relevant classification tasks where some class occurrences are rare. This is the so called class imbalance problem, which is a challenge in machine learning. In this work, we propose the SeismoFlow a flow-based generative model to create synthetic samples, aiming to address the class imbalance. Inspired by the Glow model, it uses interpolation on the learned latent space to produce synthetic samples for one rare class. We apply our approach to the development of a seismogram signal quality classifier. We introduce a dataset composed of5.223seismograms that are distributed between the good, medium, and bad classes and with their respective frequencies of 66.68%,31.54%, and 1.76%. Our methodology is evaluated on a stratified 10-fold cross-validation setting, using the Miniceptionmodel as a baseline, and assessing the effects of adding the generated samples on the training set of each iteration. In our experiments, we achieve an improvement of 13.9% on the rare class F1-score, while not hurting the metric value for the other classes and thus observing the overall accuracy improvement. Our empirical findings indicate that our method can generate high-quality synthetic seismograms with realistic looking and sufficient plurality to help the Miniception model to overcome the class imbalance problem. We believe that our results are a step forward in solving both the task of seismogram signal quality classification and class imbalance.