Insightful Railway Track Evaluation: Leveraging NARX Feature Interpretation

TL;DR

This paper presents a novel interpretable classification method combining NARX models with logistic regression, specifically designed for railway sensor data, enhancing decision-making in safety and maintenance.

Contribution

It introduces a Logistic-NARX Multinomial algorithm and a new NARX-based feature interpretation methodology tailored for railway sector applications.

Findings

Effective multiclass classification with interpretable models

Enhanced feature importance analysis for railway sensor data

Improved decision-making for safety and maintenance

Abstract

The classification of time series is essential for extracting meaningful insights and aiding decision-making in engineering domains. Parametric modeling techniques like NARX are invaluable for comprehending intricate processes, such as environmental time series, owing to their easily interpretable and transparent structures. This article introduces a classification algorithm, Logistic-NARX Multinomial, which merges the NARX methodology with logistic regression. This approach not only produces interpretable models but also effectively tackles challenges associated with multiclass classification. Furthermore, this study introduces an innovative methodology tailored for the railway sector, offering a tool by employing NARX models to interpret the multitude of features derived from onboard sensors. This solution provides profound insights through feature importance analysis, enabling informed decision-making regarding safety and maintenance.