Author
Listed:
- Sujatha Hanumantharayappa
- Manjula R. Bharamagoudra
Abstract
Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by variations in brain function and structure that affect emotion perception, communication, and social interaction. Traditional machine learning (ML) algorithms suffer from bias-variance imbalance and redundant feature representations, leading to inaccurate emotion classification in autistic children due to heterogeneous facial cues and limited annotated data. To address these challenges, this research proposes a Mutual-Information-weighted Shapley Graph (MISG) and Confidence Weighted Aggregation with Ensemble ML (CWAEML) for emotion classification in autistic and non-autistic facial datasets. MISG performs structured graph-based feature refinement by modelling inter-feature dependencies using mutual information and estimating marginal contribution via Shapley theory. Deterministic feature selection removes semantic redundancy while preserving discriminative attributes, thereby improving classifier robustness. The EML integrates multiple base learners, including Multi-Support Vector Machine (MSVM), Naïve Bayes (NB), K-Nearest Neighbour (KNN), Decision Tree (DT), and Random Forest (RF), through confidence-weighted fusion to ensure adaptive learning across emotion domains. The proposed MISG-CWAEML achieves accuracies of 98.75%, 97.95%, and 68.72% on AffectNet, Autistic Children Emotions - Dr. Fatma M. Talaat, and Young AffectNet HQ, respectively, which are superior to conventional SVM and other benchmark models in cross-domain evaluations. The findings demonstrate the effectiveness of graph-based feature selection combined with adaptive ensemble learning in handling complex and imbalanced emotion datasets. The proposed MISG-CWAEML provides practical implications for developing reliable systems, thereby enabling enhanced emotion recognition for children with ASD.
Suggested Citation
Handle:
RePEc:gvu:tcsst0:v:8:y:2026:i:3:id:2340
DOI: 10.36548/jtcsst.2026.3.016
Download full text from publisher
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gvu:tcsst0:v:8:y:2026:i:3:id:2340. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Journal Manager (email available below). General contact details of provider: https://irojournals.com/tcsst .
Please note that corrections may take a couple of weeks to filter through
the various RePEc services.