Related Experiment Video
Updated: Aug 8, 2025
11:50
EEG Mu Rhythm in Typical and Atypical Development
Published on: April 9, 2014
25.9K
Energy-Efficient EEG-Based Scheme for Autism Spectrum Disorder Detection Using Wearable Sensors
Sarah Alhassan1,2, Adel Soudani1, Manan Almusallam2
1Department of Computer Science, College of Computer and Information Science, King Saud University, Riyadh 11362, Saudi Arabia.
Sensors (Basel, Switzerland)
|February 28, 2023
Summary
This study introduces an energy-efficient method for early autism detection using electroencephalography (EEG) signals. The new approach significantly reduces data transmission, enhancing wearable sensor lifespan for e-health applications.
Area of Science:
- Biomedical Engineering
- Neuroscience
- Computer Science
Background:
- Wearable wireless systems offer e-health solutions for neurological disorder diagnosis.
- Electroencephalography (EEG) is crucial for identifying neural abnormalities in autism spectrum disorders (ASD).
- Transmitting raw EEG data strains wireless sensor lifespan and impacts e-health feasibility.
Purpose of the Study:
- To develop a sensor-based scheme for early-age autism detection.
- To implement an energy-efficient signal transformation method for relevant feature extraction.
- To improve the feasibility of wearable EEG systems for autism diagnosis.
Main Methods:
- Developed a sensor-based scheme for early autism detection.
- Implemented an energy-efficient signal transformation technique.
- Utilized machine learning algorithms for accurate classification of EEG features.
Main Results:
- Achieved 96% accuracy, 100% sensitivity, and 95% F1 score using machine learning models.
- Demonstrated a 97% reduction in energy consumption compared to raw EEG streaming.
- Validated the effectiveness of the proposed energy-efficient scheme.
Conclusions:
- The proposed scheme enables accurate and energy-efficient early autism detection.
- Reduced data transmission conserves sensor energy, extending wireless network lifespan.
- This approach enhances the practicality of wearable EEG for e-health diagnostics.
