PANFIS++: A Generalized Approach to Evolving Learning

TL;DR

PANFIS++ is a novel evolving learning algorithm designed for data stream mining that effectively handles data uncertainty, temporal dynamics, and redundant streams, achieving high accuracy with low complexity.

Contribution

It introduces a generalized evolving learning algorithm with active learning, uncertainty tolerance, and recurrent architecture for dynamic data streams.

Findings

Achieves highest predictive accuracy in case studies.

Reduces complexity while maintaining performance.

Effectively handles data uncertainty and temporal dynamics.

Abstract

The concept of evolving intelligent system (EIS) provides an effective avenue for data stream mining because it is capable of coping with two prominent issues: online learning and rapidly changing environments. We note at least three uncharted territories of existing EISs: data uncertainty, temporal system dynamic, redundant data streams. This book chapter aims at delivering a concrete solution of this problem with the algorithmic development of a novel learning algorithm, namely PANFIS++. PANFIS++ is a generalized version of the PANFIS by putting forward three important components: 1) An online active learning scenario is developed to overcome redundant data streams. This module allows to actively select data streams for the training process, thereby expediting execution time and enhancing generalization performance, 2) PANFIS++ is built upon an interval type-2 fuzzy system environment, which incorporates the so-called footprint of uncertainty. This component provides a degree of tolerance for data uncertainty. 3) PANFIS++ is structured under a recurrent network architecture with a self-feedback loop. This is meant to tackle the temporal system dynamic. The efficacy of the PANFIS++ has been numerically validated through numerous real-world and synthetic case studies, where it delivers the highest predictive accuracy while retaining the lowest complexity.