Analyzing Ground Motion Records with CVI Fuzzy ART

This paper explores using Cluster Validity Indices Fuzzy Adaptative Resonance Theory (CVI Fuzzy ART) to cluster ground motion records (GMRs). Clustering the features extracted from a supervised network trained for predicting the structure damage results in less overfitting from the trained network. Using Cluster Validity Indices (CVIs) to evaluate the clustering gives feedback to how well the data is being classified, allowing further separation of the data.By using CVI Fuzzy ART in combination with features extracted from a trained Convolutional Neural Network (CNN), we were able to form additional clusters in the data. Within the primary clusters, accuracy was improved from our previous best of 82% [1] up to 95% accuracy. Additionally, the ~20% of the data that ended up in secondary clusters was identified as borderline data, highlighting that the result is unstable, and that the more severe class should be considered despite the simulation results.