Outlier Detection as Instance Selection Method for Feature Selection in Time Series Classification

TL;DR

This paper proposes using outlier detection as an instance filtering method to improve feature selection and classification performance in imbalanced time series datasets, demonstrating significant accuracy gains.

Contribution

It introduces a novel approach of applying outlier detection for instance filtering to enhance feature selection in time series classification tasks.

Findings

Outlier filtering improves classification accuracy in several datasets.

Performance increases up to 16% observed with the proposed method.

Open source code and results are publicly available.

Abstract

In order to allow machine learning algorithms to extract knowledge from raw data, these data must first be cleaned, transformed, and put into machine-appropriate form. These often very time-consuming phase is referred to as preprocessing. An important step in the preprocessing phase is feature selection, which aims at better performance of prediction models by reducing the amount of features of a data set. Within these datasets, instances of different events are often imbalanced, which means that certain normal events are over-represented while other rare events are very limited. Typically, these rare events are of special interest since they have more discriminative power than normal events. The aim of this work was to filter instances provided to feature selection methods for these rare instances, and thus positively influence the feature selection process. In the course of this work, we were able to show that this filtering has a positive effect on the performance of classification models and that outlier detection methods are suitable for this filtering. For some data sets, the resulting increase in performance was only a few percent, but for other datasets, we were able to achieve increases in performance of up to 16 percent. This work should lead to the improvement of the predictive models and the better interpretability of feature selection in the course of the preprocessing phase. In the spirit of open science and to increase transparency within our research field, we have made all our source code and the results of our experiments available in a publicly available repository.