An Empirical Evaluation of the t-SNE Algorithm for Data Visualization in Structural Engineering

TL;DR

This paper evaluates the effectiveness of t-SNE combined with SMOTE for visualizing and classifying imbalanced earthquake engineering data, demonstrating improved neural network classifier performance in 2D space.

Contribution

It provides an empirical assessment of t-SNE and SMOTE for visualizing and classifying high-dimensional, imbalanced data in structural engineering applications.

Findings

t-SNE effectively reduces data to 2D for visualization

SMOTE improves classifier performance on imbalanced data

Neural networks perform well with combined t-SNE and SMOTE

Abstract

A fundamental task in machine learning involves visualizing high-dimensional data sets that arise in high-impact application domains. When considering the context of large imbalanced data, this problem becomes much more challenging. In this paper, the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm is used to reduce the dimensions of an earthquake engineering related data set for visualization purposes. Since imbalanced data sets greatly affect the accuracy of classifiers, we employ Synthetic Minority Oversampling Technique (SMOTE) to tackle the imbalanced nature of such data set. We present the result obtained from t-SNE and SMOTE and compare it to the basic approaches with various aspects. Considering four options and six classification algorithms, we show that using t-SNE on the imbalanced data and SMOTE on the training data set, neural network classifiers have promising results without sacrificing accuracy. Hence, we can transform the studied scientific data into a two-dimensional (2D) space, enabling the visualization of the classifier and the resulting decision surface using a 2D plot.