Management Science and Information Technology

Management Science and Information Technology

Developing Accessible Mobile Tools with AR, ML, and AI for Danger Detection in Children with ASD

Document Type : SI; OMCI 2025

Authors
1 Tunis Business School, University of Tunis, Tunis, Tunisia
2 University of Carthage, ISTEUB, ENAU, LR21ES20, LaRPA, Tunis, Tunisia
Abstract
Objective: Children with autism spectrum disorder (ASD) face challenges in recognizing and responding to potential risks in their environment, which can limit their safety and independence. This study aims to develop and evaluate a mobile application integrating augmented reality (AR), artificial intelligence (AI), and machine learning (ML) to enhance risk awareness and adaptive learning in children with ASD.
Methods: The proposed system employs an artificial intelligence (AI) and machine learning (ML)-based approach using the YOLOv8 model for real-time detection and classification of potentially hazardous objects, providing immediate visual and auditory feedback. The application incorporates augmented reality (AR) to deliver interactive guidance within the user’s environment and follows a user-centered design approach. To evaluate user acceptance and engagement, the Extended Technology Acceptance Model was applied, assessing factors such as perceived usefulness, ease of use, trust, and device compatibility. In addition, an exploratory pilot study involving two children one child with ASD and one neurotypical child was conducted to provide preliminary qualitative insights into interactions with the application.
Results: The model achieved a mean Average Precision (mAP) of 73.7%, with a precision of 79.5% and recall of 70%. The system enabled real-time detection and classification of dangerous objects and users showed improved recognition of potential dangers, with positive caregiver feedback on usability.
Conclusion: The integration of AR, AI, and ML in a user-centered mobile application demonstrates the potential of digital tools to enhance safety and independence for children with autism spectrum disorder. These findings highlight the broader applicability of AI-driven assistive technologies in educational and healthcare contexts, offering guidance for developing adaptive, inclusive and scalable solutions that support child well-being and learning.
Keywords

Acharya, S., & Sharma, K. (2021). Lived experiences of mothers raising children with autism in Chitwan District, Nepal. Autism Research and Treatment, 2021, Article 6614490.
 AlJundi, Z., Alsubaie, S., Faheem, M. H., Almarashi, R. M., Qazi, E., & Kim, J. H. (2024). Dangerous objects detection using deep learning and first responder drone. International Journal of Digital Crime and Forensics, 16(1). https://doi.org/10.4018/IJDCF.367034
 Amin, M. S., & Ahn, H. (2021). Earthquake disaster avoidance learning system using deep learning. Cognitive Systems Research, 66, 221–235. https://doi.org/10.1016/j.cogsys.2020.11.002
Antovski, A., Kostadinovska, S., Simjanoska, M., Eftimov, T., Ackovska, N., & Madevska Bogdanova, A. (2019). Data-driven autism biomarkers selection by using signal processing and machine learning techniques. In Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2019): Volume 3: BIOINFORMATICS (pp. 201–208). SciTePress. https://doi.org/10.5220/0007398902010208
Baird, G., Cass, H., & Slonims, V. (2003). Diagnosis of autism. BMJ, 327(7413), 488–493. https://doi.org/10.1136/bmj.327.7413.488
Bieniarz, A. (2011). Loneliness and silence in autism: Implications for psychotherapy. In V. Eapen (Ed.), Autism—A neurodevelopmental journey from genes to behaviour (pp. 412–424). IntechOpen. https://doi.org/10.5772/17931
Bisong, E. (2019). Building machine learning and deep learning models on Google Cloud Platform: A comprehensive guide for beginners. Apress. https://doi.org/10.1007/978-1-4842-4470-8
Chemnad, K., & Othman, A. (2023). Advancements in Arabic text-to-speech systems: A 22-year literature review. IEEE Access, 11, 1–19. https://doi.org/10.1109/ACCESS.2023.3260844
Cheng, Y., & Bololia, L. (2024). The effects of augmented reality on social skills in children with an autism diagnosis: A preliminary systematic review. Journal of Autism and Developmental Disorders, 54(3), 1317–1331. https://doi.org/10.1007/s10803-022-05878-4
Dixon, D. R., Miyake, C. J., Nohelty, K., Novack, M. N., & Granpeesheh, D. (2020). Evaluation of an immersive virtual reality safety training used to teach pedestrian skills to children with autism spectrum disorder. Behavior Analysis in Practice, 13, 631–640. https://doi.org/10.1007/s40617-019-00401-1
Gunning, M., & Pavlidis, P. (2021). “Guilt by association” is not competitive with genetic association for identifying autism risk genes. Scientific Reports, 11(1), 15950. https://doi.org/10.1038/s41598-021-95488-2
Hirota, T., & King, B. H. (2023). Autism spectrum disorder: A review. JAMA, 329(2), 157–168. https://doi.org/10.1001/jama.2022.24998
Howard, P. L., & Sedgewick, F. (2021). Anything but the phone! Communication mode preferences in the autism community. Autism, 25(8), 2265–2278. https://doi.org/10.1177/13623613211012310
Jones, R. S. P., Zahl, R., & Huws, J. C. (2001). First-hand accounts of emotional experiences in autism: A qualitative analysis. Disability & Society, 16(3), 393–401. https://doi.org/10.1080/09687590120051871
Kenny, L., Hattersley, C., Molins, B., Buckley, C., Povey, C., & Pellicano, E. (2015). Which terms should be used to describe autism? Perspectives from the UK autism community. Autism, 20(4), 442–462. https://doi.org/10.1177/1362361315588200
Instance Nationale de l’Évaluation et de l’Accréditation en Santé (INEAS). (2025). Guide de pratique clinique dans le trouble du spectre de l’autisme chez l’enfant et l’adolescent. Ministère de la Santé, Tunisie. https://portail.ineas.tn/Default/doc/SYRACUSE/1348/le-trouble-du-spectre-de-l-autisme-chez-l-enfant-et-l-adolescent-ineas
Roberts-Yates, C., & Silvera-Tawil, D. (2019). Better education opportunities for students with autism and intellectual disabilities through digital technology. International Journal of Special Education, 34(1), 197–210.
Roboflow. (2023). Roboflow. https://roboflow.com/
Saggers, B., Klug, D., Harper-Hill, K., Ashburner, J., Costley, D., Clark, T., Bruck, S., Trembath, D., Webster, A. A., & Carrington, S. (2016). Australian autism educational needs analysis—What are the needs of schools, parents and students on the autism spectrum? (Full report). Cooperative Research Centre for Living with Autism.
Selcuk, B., & Serif, T. (2023). A comparison of YOLOv5 and YOLOv8 in the context of mobile UI detection. In Mobile Web and Intelligent Information Systems (pp. 161–174). Springer. https://doi.org/10.1007/978-3-031-39764-6_11
Wang, C., Li, H., Deng, X., Liu, Y., Wu, T., Liu, W., & Wang, B. (2024). Improved you only look once v.8 model based on deep learning: Precision detection and recognition of fresh leaves from Yunnan large-leaf tea tree. Agriculture, 14(12), 2324. https://doi.org/10.3390/agriculture14122324
Zeidan, J., Fombonne, E., Scorah, J., Ibrahim, A., Durkin, M. S., Saxena, S., & Elsabbagh, M. (2022). Global prevalence of autism: A systematic review update. Autism Research, 15(5), 778–790. https://doi.org/10.1002/aur.2707