Verfahren und System zur Rekonstruktion Neurophysiologischer Signale aus Einkanaligen Gemischten Signalen unter Verwendung Trennbarer Darstellungen

Details

Veröffentlichungs-Nr.

EP4799572

Anmeldetag

19. Dezember 2025

Veröffentlichung

2. September 2026

Rechtsraum

EP

IPC

A61B5/369, A61B5/00

Abstract

The growing use of wearable devices requires accurate and compact representations of high dimensional physiological signals. The present disclosure presents a UNet inspired autoencoder to represent and reconstruct multiple neurophysiological signals from single channel data. The architecture includes single-encoder and multiple decoders to obtain self-attention enabled compact embeddings of mixed ExG (EEG /ECG) signals through decaying encoder-decoder skip connections, for improved representation capability. The embeddings are separable into individual ExG components enabling simultaneous reconstruction of high-fidelity EEG and ECG sources. The pretrained encoder can be used for a complex downstream task with minimum fine-tuning. Using the present disclosure on a large corpus of single-channel mixed ExG generated from overnight Polysomnography (PSG) recordings, it is shown that subject- and class- independent EEG/ECG reconstructions validated by multiple domain-specific metrics can be obtained, and the encoded EEG embeddings can be classified into five sleep stages as a downstream task.

Anmelder

Firma

Tata Consultancy Services Limited

Land

🇮🇳 Indien

Fachgebiete