Multiple Time Series Fusion Based on LSTM An Application to CAP A Phase Classification Using EEG

TL;DR

This paper presents a deep learning approach using LSTM for EEG-based CAP A phase classification, optimized with genetic and particle swarm algorithms, achieving high accuracy and robustness in challenging datasets.

Contribution

It introduces a novel EEG channel fusion method using LSTM combined with optimization algorithms, improving automatic CAP A phase classification performance.

Findings

Achieved an AUC of 0.82 and accuracy of 77-79%.

Selected three EEG channels consistent with CAP protocol.

Demonstrated noise resistance and robustness to channel loss.

Abstract

Biomedical decision making involves multiple signal processing, either from different sensors or from different channels. In both cases, information fusion plays a significant role. A deep learning based electroencephalogram channels' feature level fusion is carried out in this work for the electroencephalogram cyclic alternating pattern A phase classification. Channel selection, fusion, and classification procedures were optimized by two optimization algorithms, namely, Genetic Algorithm and Particle Swarm Optimization. The developed methodologies were evaluated by fusing the information from multiple electroencephalogram channels for patients with nocturnal frontal lobe epilepsy and patients without any neurological disorder, which was significantly more challenging when compared to other state of the art works. Results showed that both optimization algorithms selected a comparable structure with similar feature level fusion, consisting of three electroencephalogram channels, which is in line with the CAP protocol to ensure multiple channels' arousals for CAP detection. Moreover, the two optimized models reached an area under the receiver operating characteristic curve of 0.82, with average accuracy ranging from 77% to 79%, a result which is in the upper range of the specialist agreement. The proposed approach is still in the upper range of the best state of the art works despite a difficult dataset, and has the advantage of providing a fully automatic analysis without requiring any manual procedure. Ultimately, the models revealed to be noise resistant and resilient to multiple channel loss.