IRO Journals
Journal of Trends in Computer Science and Smart Technology

Confidence-Weighted Ensemble Learning and Graph-Based Shapley Theory for Refined Emotion Prediction in Autistic Children

Open Access
Published: 20 July, 2026
Pages: 745-767
  • Sujatha Hanumantharayappa , Sujatha Hanumantharayappa
    School of Electronics and Communication Engineering, REVA University, Bengaluru, India
    School of Electronics and Communication Engineering, REVA University, Bengaluru, India
  • Manjula R. Bharamagoudra Manjula R. Bharamagoudra
    School of Electronics and Communication Engineering, REVA University, Bengaluru, India
    School of Electronics and Communication Engineering, REVA University, Bengaluru, India
view PDF
view PDF

How to Cite

Hanumantharayappa, Sujatha, and Manjula R. Bharamagoudra. 2026. “Confidence-Weighted Ensemble Learning and Graph-Based Shapley Theory for Refined Emotion Prediction in Autistic Children”. Journal of Trends in Computer Science and Smart Technology 8 (3): 745-67. https://doi.org/10.36548/jtcsst.2026.3.016.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Ensemble Machine Learning
Emotion Prediction
Feature Refinement
Shapley Graph Theory
Autism Children

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.

References

  1. Pavez, Rodolfo, Jaime Diaz, Jeferson Arango-Lopez, Danay Ahumada, Carolina Mendez-Sandoval, and Fernando Moreira. "Emo-Mirror: A Proposal to Support Emotion Recognition in Children with Autism Spectrum Disorders." Neural Computing and Applications 35, no. 11 (2023): 7913-7924.
  2. Deveau, Nicholas, Peter Washington, Emilie Leblanc, Arman Husic, Kaitlyn Dunlap, Yordan Penev, Aaron Kline, Onur Cezmi Mutlu, and Dennis P. Wall. "Machine Learning Models Using Mobile Game Play Accurately Classify Children with Autism." Intelligence-Based Medicine 6 (2022): 100057.
  3. Liao, Mengyi, Hengyao Duan, and Guangshuai Wang. "Application of Machine Learning Techniques to Detect the Children with Autism Spectrum Disorder." Journal of Healthcare Engineering 2022, no. 1 (2022): 9340027.
  4. Han, Yu, Donna M. Rizzo, John P. Hanley, Emily L. Coderre, and Patricia A. Prelock. "Identifying Neuroanatomical and Behavioral Features for Autism Spectrum Disorder Diagnosis in Children Using Machine Learning." PLoS One 17, no. 7 (2022): e0269773.
  5. Priyadarshini, Ishaani. "Autism Screening in Toddlers and Adults Using Deep Learning and Fair AI Techniques." Future Internet 15, no. 9 (2023): 292.
  6. Lin, Ping-I., Mohammad Ali Moni, Susan Shur-Fen Gau, and Valsamma Eapen. "Identifying Subgroups of Patients with Autism by Gene Expression Profiles Using Machine Learning Algorithms." Frontiers in Psychiatry 12 (2021): 637022.
  7. Alhakbani, N. “Facial Emotion Recognition-Based Engagement Detection in Autism Spectrum Disorder.” International Journal of Advanced Computer Science and Applications 15, no. 3 (2024): 959–967.
  8. Sundaresan, Avirath, Brian Penchina, Sean Cheong, Victoria Grace, Antoni Valero-Cabré, and Adrien Martel. "Evaluating Deep Learning EEG-Based Mental Stress Classification in Adolescents with Autism for Breathing Entrainment BCI." Brain Informatics 8, no. 1 (2021): 13.
  9. Farooq, Muhammad Shoaib, Rabia Tehseen, Maidah Sabir, and Zabihullah Atal. "Detection of Autism Spectrum Disorder (ASD) in Children and Adults Using Machine Learning." scientific reports 13, no. 1 (2023): 9605.
  10. Vakadkar, Kaushik, Diya Purkayastha, and Deepa Krishnan. "Detection of Autism Spectrum Disorder in Children Using Machine Learning Techniques." SN computer science 2, no. 5 (2021): 386.
  11. Khudhur, Dhuha Dheyaa, and Saja Dheyaa Khudhur. "The Classification of Autism Spectrum Disorder by Machine Learning Methods on Multiple Datasets for Four Age Groups." Measurement: Sensors 27 (2023): 100774.
  12. Aina, Joseph, Oluwatunmise Akinniyi, Md Mahmudur Rahman, Valerie Odero-Marah, and Fahmi Khalifa. "A Hybrid Learning-Architecture for Mental Disorder Detection Using Emotion Recognition." IEEE Access 12 (2024): 91410-91425.
  13. Salhi, Intissar, Mohammed Qbadou, Soukaina Gouraguine, Khalifa Mansouri, Chris Lytridis, and Vassilis Kaburlasos. "RETRACTED: Towards Robot-Assisted Therapy for Children with Autism—The Ontological Knowledge Models and Reinforcement Learning-Based Algorithms." Frontiers in Robotics and AI 9 (2022): 713964.
  14. Bala, Mousumi, Mohammad Hanif Ali, Md Shahriare Satu, Khondokar Fida Hasan, and Mohammad Ali Moni. "Efficient Machine Learning Models for Early Stage Detection of Autism Spectrum Disorder." Algorithms 15, no. 5 (2022): 166.
  15. Song, Chao, Zhong-Quan Jiang, Li-Fei Hu, Wen-Hao Li, Xiao-Lin Liu, Yan-Yan Wang, Wen-Yuan Jin, and Zhi-Wei Zhu. "A Machine Learning-Based Diagnostic Model for Children with Autism Spectrum Disorders Complicated with Intellectual Disability." Frontiers in psychiatry 13 (2022): 993077.
  16. Talaat, Fatma M., Zainab H. Ali, Reham R. Mostafa, and Nora El-Rashidy. "RETRACTED ARTICLE: Real-Time Facial Emotion Recognition Model Based on Kernel Autoencoder and Convolutional Neural Network for Autism Children: Fatma M. Talaat et al." Soft Computing 28, no. 9 (2024): 6695-6708.
  17. Saranya, A., Anandan, R. “Facial Action Coding and Hybrid Deep Learning Architectures for Autism Detection.” Intelligent Automation and Soft Computing 33, no. 2 (2022): 1167-1182.
  18. Savchenko, Andrey V., Lyudmila V. Savchenko, and Ilya Makarov. "Classifying Emotions and Engagement in Online Learning Based on a Single Facial Expression Recognition Neural Network." IEEE transactions on affective computing 13, no. 4 (2022): 2132-2143.
  19. Hosney, Reham, Fatma M. Talaat, Eman M. El-Gendy, and Mahmoud M. Saafan. "AutYOLO-ATT: An Attention-Based YOLOv8 Algorithm for Early Autism Diagnosis Through Facial Expression Recognition." Neural Computing and Applications 36, no. 27 (2024): 17199-17219.
  20. Talaat, Fatma M. "Real-Time Facial Emotion Recognition System Among Children with Autism Based on Deep Learning and IoT." Neural Computing and Applications 35, no. 17 (2023): 12717-12728.
  21. Cheng, Ming, Yingying Zhang, Yixiang Xie, Yueran Pan, Xiao Li, Wenxing Liu, Chengyan Yu et al. "Computer-Aided Autism Spectrum Disorder Diagnosis with Behavior Signal Processing." IEEE Transactions on Affective Computing 14, no. 4 (2023): 2982-3000.
  22. Ciraolo, Davide, Maria Fazio, Rocco Salvatore Calabrò, Massimo Villari, and Antonio Celesti. "Facial Expression Recognition Based on Emotional Artificial Intelligence for Tele-Rehabilitation." Biomedical Signal Processing and Control 92 (2024): 106096.
  23. AffectNet Dataset: https://www.kaggle.com/datasets/mstjebashazida/affectnet (accessed on July 2026).
  24. Autistic Children Emotions - Dr. Fatma M. Talaat dataset: https://www.kaggle.com/datasets/fatmamtalaat/autistic-children-emotions-dr-fatma-m-talaat/data (accessed on July 2026).
  25. Young AffectNet HQ: https://www.kaggle.com/datasets/vfomenko/young-affectnet-hq/data (accessed on July 2026).