Towards Explainable Sequential Learning

TL;DR

This paper introduces a hybrid explainable AI pipeline for temporal data that combines numerical and event-based analysis, providing human-understandable results and outperforming existing methods.

Contribution

It presents a novel explainable pipeline that integrates numerical and event-based approaches for multivariate time series classification, extending specification mining algorithms.

Findings

Outperforms state-of-the-art multivariate time series classifiers

Enables human-explainable results through a hybrid approach

Extends event-based literature with new specification mining algorithms

Abstract

This paper offers a hybrid explainable temporal data processing pipeline, DataFul Explainable MultivariatE coRrelatIonal Temporal Artificial inTElligence (EMeriTAte+DF), bridging numerical-driven temporal data classification with an event-based one through verified artificial intelligence principles, enabling human-explainable results. This was possible through a preliminary a posteriori explainable phase describing the numerical input data in terms of concurrent constituents with numerical payloads. This further required extending the event-based literature to design specification mining algorithms supporting concurrent constituents. Our previous and current solutions outperform state-of-the-art solutions for multivariate time series classifications, thus showcasing the effectiveness of the proposed methodology.