Related Experiment Video
Updated: Jan 12, 2026

13:32
Recording Human Electrocorticographic ECoG Signals for Neuroscientific Research and Real-time Functional Cortical Mapping
Published on: June 26, 2012
26.7K
An Active Dry-Contact Continuous EEG Monitoring System for Seizure Detection Applications in Clinical Neurophysiology
IEEE Transactions on Bio-Medical Engineering
|November 6, 2025
Summary
This study introduces a low-cost EEG headset and AI for early seizure detection in infants. The system demonstrates high accuracy and comparable performance to commercial devices, improving infant neurological care.
Area of Science:
- Biomedical Engineering
- Neuroscience
- Artificial Intelligence
Background:
- Neonatal seizures pose significant risks for long-term neurological damage.
- Current continuous electroencephalography (cEEG) monitoring is expensive and requires specialized personnel.
- There is a need for accessible and accurate seizure detection methods for vulnerable infants.
Purpose of the Study:
- To develop a low-cost, adjustable electroencephalography (EEG) headset using active dry-contact electrodes.
- To integrate an explainable deep learning model for real-time seizure detection from reduced-montage EEG.
- To implement a multimodal artifact removal algorithm for enhanced signal quality.
Main Methods:
- Acquisition of EEG signals using active electrodes and a custom analog front end.
- Fabrication of a 3D-printed, adjustable headset for diverse head sizes.
- Training a deep learning model for neonatal seizure detection and applying artifact removal algorithms.
- Clinical evaluation against a commercial wet-electrode cEEG system.
Main Results:
- The proposed system achieved a correlation coefficient > 0.8 with commercial devices.
- Noise mitigation performance was comparable to commercial systems.
- The deep learning model showed significant accuracy and recall improvements over existing methods.
- Artifact removal effectively preserved seizure-relevant EEG features.
Conclusions:
- The developed EEG system offers a promising low-cost solution for early seizure detection in infants.
- The combination of dry electrodes, deep learning, and artifact removal enhances diagnostic capabilities.
- This technology has the potential to improve neurological outcomes for high-risk newborns.

