EEG glasses for real-time brain electrical activity monitoring
Zanetti, Renato ; Aminifar, Amir LU
and Atienza, David
(2025)
In Scientific Reports
15(1).
- Abstract
Wearable devices are becoming a cornerstone for personalized and long-term health monitoring, enabling early intervention and data-driven medical decisions. In this work, we present e-Glass, a state-of-the-art smart wearable device that enables unobtrusive real-time electroencephalography (EEG) monitoring. Our evaluation shows that e-Glass adheres to the established international guidelines for clinical EEG recordings. Moreover, the acquired data presents a Pearson’s correlation of 0.93 relative to recordings obtained from the Biopac research-grade EEG system. The proposed EEG acquisition device concept is evaluated in two application domains: epileptic seizure detection and cognitive workload monitoring (CWM). First, we present a... (More)
Wearable devices are becoming a cornerstone for personalized and long-term health monitoring, enabling early intervention and data-driven medical decisions. In this work, we present e-Glass, a state-of-the-art smart wearable device that enables unobtrusive real-time electroencephalography (EEG) monitoring. Our evaluation shows that e-Glass adheres to the established international guidelines for clinical EEG recordings. Moreover, the acquired data presents a Pearson’s correlation of 0.93 relative to recordings obtained from the Biopac research-grade EEG system. The proposed EEG acquisition device concept is evaluated in two application domains: epileptic seizure detection and cognitive workload monitoring (CWM). First, we present a lightweight edge machine-learning scheme, designed specifically for e-Glass, achieving overall sensitivity of 64% (100% sensitivity in 11 out of 24 subjects) and 2.35 false-alarms per day, when tested on 982.9 hours of EEG data from the CHB-MIT dataset. Similarly, an CWM strategy with e-Glass reaches an accuracy of 74.5% on unseen data. These results demonstrate that e-Glass is capable of unobtrusive and real-time subject monitoring in outpatient conditions, not only in epileptic seizure detection but also in monitoring the subject’s cognitive state.
(Less)
- author
- Zanetti, Renato
; Aminifar, Amir
LU
and Atienza, David
- organization
-
- NEXTG2COM – a Vinnova Competence Centre in Advanced Digitalisation
- Secure and Networked Systems
- LTH Profile Area: Water
- LTH Profile Area: AI and Digitalization
- LTH Profile Area: Engineering Health
- ELLIIT: the Linköping-Lund initiative on IT and mobile communication
- Department of Electrical and Information Technology
- publishing date
- 2025-12
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Scientific Reports
- volume
- 15
- issue
- 1
- article number
- 43574
- publisher
- Nature Publishing Group
- external identifiers
-
- scopus:105024722962
- pmid:41318658
- ISSN
- 2045-2322
- DOI
- 10.1038/s41598-025-29893-4
- language
- English
- LU publication?
- yes
- id
- 597dc728-fc08-4604-a7ae-99c0a2cede74
- date added to LUP
- 2026-02-13 10:24:30
- date last changed
- 2026-02-14 03:00:08
@article{597dc728-fc08-4604-a7ae-99c0a2cede74,
abstract = {{<p>Wearable devices are becoming a cornerstone for personalized and long-term health monitoring, enabling early intervention and data-driven medical decisions. In this work, we present e-Glass, a state-of-the-art smart wearable device that enables unobtrusive real-time electroencephalography (EEG) monitoring. Our evaluation shows that e-Glass adheres to the established international guidelines for clinical EEG recordings. Moreover, the acquired data presents a Pearson’s correlation of 0.93 relative to recordings obtained from the Biopac research-grade EEG system. The proposed EEG acquisition device concept is evaluated in two application domains: epileptic seizure detection and cognitive workload monitoring (CWM). First, we present a lightweight edge machine-learning scheme, designed specifically for e-Glass, achieving overall sensitivity of 64% (100% sensitivity in 11 out of 24 subjects) and 2.35 false-alarms per day, when tested on 982.9 hours of EEG data from the CHB-MIT dataset. Similarly, an CWM strategy with e-Glass reaches an accuracy of 74.5% on unseen data. These results demonstrate that e-Glass is capable of unobtrusive and real-time subject monitoring in outpatient conditions, not only in epileptic seizure detection but also in monitoring the subject’s cognitive state.</p>}},
author = {{Zanetti, Renato and Aminifar, Amir and Atienza, David}},
issn = {{2045-2322}},
language = {{eng}},
number = {{1}},
publisher = {{Nature Publishing Group}},
series = {{Scientific Reports}},
title = {{EEG glasses for real-time brain electrical activity monitoring}},
url = {{http://dx.doi.org/10.1038/s41598-025-29893-4}},
doi = {{10.1038/s41598-025-29893-4}},
volume = {{15}},
year = {{2025}},
}