Related Concept Videos
Autism Spectrum Disorder
These core symptoms manifest differently among individuals, ranging from mild to severe. The disorder's complexity extends beyond its clinical presentation, encompassing a diverse range of biological, cognitive, and sociocultural influences.
Modeling in Therapy
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in...
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Anterior Cingulate Cortex Mediates State-Dependent Prioritization of Distressed Conspecifics.
When Robots Learn: Artificial Intelligence and the Next Human-Centered Era of Neurorehabilitation.
Related Experiment Video
Updated: Aug 9, 2025

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
Published on: September 8, 2023
Machine Learning Enabled P300 Classifier for Autism Spectrum Disorder Using Adaptive Signal Decomposition.
Santhosh Peketi1, Sanjay B Dhok1
1Center for VLSI and Nanotechnology, Visvesvaraya National Institute of Technology, Nagpur 440010, India.
This study enhances brain-computer interface (BCI) neurorehabilitation for Autism Spectrum Disorder (ASD) by improving P300 signal detection using variational mode decomposition (VMD). The novel method significantly boosts accuracy in identifying brain signals for better communication training.
More Related Videos
09:47Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
08:17A Semantic Priming Event-related Potential ERP Task to Study Lexico-semantic and Visuo-semantic Processing in Autism Spectrum Disorder
Published on: April 12, 2018
Area of Science:
- Neuroscience
- Biomedical Engineering
- Machine Learning
Background:
- Autism Spectrum Disorder (ASD) is characterized by joint attention deficits impacting communication.
- Brain-computer interfaces (BCIs) using Electroencephalogram (EEG) P300 signals offer neurorehabilitation for ASD.
- P300 signal detection in ASD is challenging due to noise, low amplitude, and high latency.
Purpose of the Study:
- To introduce a novel variational mode decomposition (VMD) application for enhanced P300 signal identification in ASD subjects within a BCI system.
- To improve the accuracy and reliability of P300 signal detection for effective neurorehabilitation in individuals with ASD.
Main Methods:
- EEG signals from ASD subjects were decomposed into five modes using VMD.
- Extracted 30 linear and non-linear time/frequency domain features from each VMD mode.
- Applied Synthetic Minority Oversampling Technique (SMOTE) for data augmentation to address class imbalance.
- Compared three machine learning classifiers for P300 identification.
Main Results:
- The VMD's fifth mode, combined with a Support Vector Machine (SVM) classifier (fine Gaussian kernel), achieved superior performance.
- Achieved high performance metrics: 91.12% accuracy, 91.18% F1-score, and 96.6% Area Under the Curve (AUC).
- Results surpassed other state-of-the-art methods for P300 detection in ASD.
Conclusions:
- The proposed VMD-based BCI approach significantly improves P300 signal identification in individuals with ASD.
- This method offers a promising advancement for neurorehabilitation, enhancing communication training for the ASD population.
- The findings highlight the potential of VMD in overcoming challenges associated with noisy EEG signals in clinical BCI applications.