ePrints

Towards Explainable Sequential Learning

Lookup NU author(s): Dr Giacomo BergamiORCiD, Emma Packer, Dr Kirsty ScottORCiD, Dr Silvia Del DinORCiD

Downloads

• Accepted version [.pdf]

Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).

Abstract

This paper offers a hybridly explainable temporal data processing pipeline, 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 algorithms for multivariate time series classifications {over four dataset considered in the present paper}, thus showcasing the effectiveness of the proposed methodology {premiering the extraction of explainable correlations across Multivariate Time Series dimensions with dataful features}

Publication metadata

Author(s): Bergami G, Packer E, Scott K, Del Din S

Publication type: Article

Publication status: Published

Journal: Computer Science and Information Systems

Year: 2026

Volume: 23

Issue: 1

Pages: 443-473

Online publication date: 01/01/2026

Acceptance date: 16/09/2025

Date deposited: 08/10/2025

ISSN (electronic): 2683-3867

Publisher: National Library of Serbia

URL: https://doi.org/10.2298/CSIS250303077B

DOI: 10.2298/CSIS250303077B

ePrints DOI: 10.57711/gvbv-8010

Altmetrics

Share