Adaptive Confidence-Weighted Feature Fusion for Robust Multimodal Autism Screening in Heterogeneous Pediatric Populations

Article Sidebar

PDF
Published: 2026-02-11
Keywords:
autism spectrum disorder, multimodal fusion, adaptive weighting, behavioral screening, deep learning

Main Article Content

Yaqing Bai
Human Development, University of Rochester, NY, USA

Abstract

Autism Spectrum Disorder early detection encounters significant challenges from heterogeneous manifestations and inconsistent data quality during behavioral assessment. This paper introduces an adaptive confidence-weighted feature fusion algorithm that dynamically adjusts the importance of modalities based on quality metrics and individual characteristics. The framework integrates facial expressions, speech patterns, and eye-tracking through meta-learning-driven weighting strategies. Unlike fixed-weight approaches, the algorithm estimates real-time confidence scores and computes instance-specific weights via cross-modal attention mechanisms. Validation on naturalistic behavioral datasets (video, audio, eye-tracking) from children aged 2-8 years demonstrates 4.9% accuracy improvement over conventional methods, achieving 91.2% accuracy and 88.6% sensitivity. The adaptive mechanism proves particularly effective in scenarios involving low-quality data and diverse age groups.

Article Details

Issue

Vol. 1 No. 1 (2025): 2025 International Conference on Intelligent Computing and Automated Systems (ICAS 2025)

Section

Articles

How to Cite

Adaptive Confidence-Weighted Feature Fusion for Robust Multimodal Autism Screening in Heterogeneous Pediatric Populations. (2026). Journal of Science, Innovation & Social Impact, 1(1), 485-498. https://sagespress.com/index.php/JSISI/article/view/76

References

1. D. L. Robins, K. Casagrande, M. Barton, C. M. A. Chen, T. Dumont-Mathieu, and D. Fein, "Validation of the modified checklist for autism in toddlers, revised with follow-up (M-CHAT-R/F)," Pediatrics, vol. 133, no. 1, pp. 37-45, 2014.

2. S. Mu, M. Cui, and X. Huang, "Multimodal data fusion in learning analytics: A systematic review," Sensors, vol. 20, no. 23, p. 6856, 2020. doi: 10.3390/s20236856

3. J. Gao, P. Li, Z. Chen, and J. Zhang, "A survey on deep learning for multimodal data fusion," Neural Computation, vol. 32, no. 5, pp. 829-864, 2020. doi: 10.1162/neco_a_01273

4. U. Erkan, and D. N. Thanh, "Autism spectrum disorder detection with machine learning methods," Current Psychiatry Research and Reviews, vol. 15, no. 4, pp. 297-308, 2019. doi: 10.2174/2666082215666191111121115

5. M. S. Farooq, R. Tehseen, M. Sabir, and Z. Atal, "Detection of autism spectrum disorder (ASD) in children and adults using machine learning," Scientific Reports, vol. 13, no. 1, p. 9605, 2023. doi: 10.1038/s41598-023-35910-1

6. W. Chango, J. A. Lara, R. Cerezo, and C. Romero, "A review on data fusion in multimodal learning analytics and educational data mining," Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, vol. 12, no. 4, p. e1458, 2022. doi: 10.1002/widm.1458

7. Z. Dong and F. Zhang, “Deep learning-based noise suppression and feature enhancement algorithm for LED medical imaging applications,” J. Sci., Innov. Soc. Impact, vol. 1, no. 1, pp. 9–18, 2025.

8. D. Ramachandram, and G. W. Taylor, "Deep multimodal learning: A survey on recent advances and trends," IEEE Signal Processing Magazine, vol. 34, no. 6, pp. 96-108, 2017. doi: 10.1109/msp.2017.2738401

9. S. L. Oh, V. Jahmunah, N. Arunkumar, E. W. Abdulhay, R. Gururajan, N. Adib, H. M. Ciaccio, K. H. Cheong, and U. R. Acharya, "A novel automated autism spectrum disorder detection system," Complex & Intelligent Systems, vol. 7, no. 5, pp. 2399-2413, 2021.

10. L. Zwaigenbaum, J. A. Brian, and A. Ip, "Early detection for autism spectrum disorder in young children," Paediatrics & Child Health, vol. 24, no. 7, pp. 424-432, 2019. doi: 10.1093/pch/pxz119

11. W. Ali, and S. Malebary, "Particle swarm optimization-based feature weighting for improving intelligent phishing website detection," IEEE Access, vol. 8, pp. 116766-116780, 2020. doi: 10.1109/access.2020.3003569

12. M. Daniels, A. K. Halladay, A. Shih, L. M. Elder, and G. Dawson, "Approaches to enhancing the early detection of autism spectrum disorders: A systematic review of the literature," Journal of the American Academy of Child & Adolescent Psychiatry, vol. 53, no. 2, pp. 141-152, 2014.

13. S. Raj, and S. Masood, "Analysis and detection of autism spectrum disorder using machine learning techniques," Procedia Computer Science, vol. 167, pp. 994-1004, 2020. doi: 10.1016/j.procs.2020.03.399

14. M. Pawłowski, A. Wróblewska, and S. Sysko-Romańczuk, "Effective techniques for multimodal data fusion: A comparative analysis," Sensors, vol. 23, no. 5, p. 2381, 2023. doi: 10.3390/s23052381

15. D. Lahat, T. Adali, and C. Jutten, "Multimodal data fusion: An overview of methods, challenges, and prospects," Proceedings of the IEEE, vol. 103, no. 9, pp. 1449-1477, 2015. doi: 10.1109/jproc.2015.2460697Z. Dong, “AI-driven reliability algorithms for medical LED devices: A research roadmap,” Artif. Intell. Mach. Learn. Rev., vol. 5, no. 2, pp. 54–63, 2024.