Publications by authors named "Muhammad Mahbubur Rashid"
The early diagnosis of autism spectrum disorder (ASD) encounters challenges stemming from domain variations in facial image datasets. This study investigates the potential of active learning, particularly uncertainty-based sampling, for domain adaptation in early ASD diagnosis. Our focus is on improving model performance across diverse data sources.
View Article and Find Full Text PDFArticle Synopsis
- Autism spectrum disorder (ASD) is a neurological condition affecting cognitive, physical, and social skills, with no specific medication available and diagnosis usually based on behavioral assessments.* -
- The study proposes using facial images as biomarkers for early ASD diagnosis and employs deep convolutional neural networks (CNNs) for detection, with various models tested for prediction accuracy.* -
- The modified Xception model achieved the highest accuracy at 95%, outperformed other models, and could assist healthcare professionals in validating their initial screenings for ASD.*