ASD Automatic Detection by Using Yolo V3 and Yolo V4 Method

Abstract

In this paper, we proposed a deep learning model to classify children as healthy or with autism, accurately (MAP = 88%). Autistic children suffer from social skills and repetitive behaviors in communicating with people or the outside world, although autism is often classified as hereditary, autistic patients have facial features, allowing researchers to analyze children's photos to determine whether they have the disease or not. Where the image is translated into words and numbers using YOLO v3, v4. YOLO is one of the modern methods used in detecting things, especially by using convolutional neural networks, which are considered the basis of work especially because of its high speed and accuracy. In this paper, we worked on a data set containing pictures of children with and without autism. This data set contains 2936 number of pictures. After dividing and processing them in terms of intensity of lighting and dimensions, which allows the model to distinguish between images. After training for several times and using the data set, we got good results. were MAP = 88% as an accuracy and current average loss=0.91% and recall=0.85 and F1=0.77.

Keywords

• Autism Spectrum Disorder
• YOLO
• YOLO v3
• v4
• CNN
• Deep learning
• Machine learning

References

1. E. Honey, J. Rodgers, and H. McConachie, “Measurement of restricted and repetitive behaviour in children with autism spectrum disorder: Selecting a questionnaire or interview,” Res. Autism Spectr. Disord., vol. 6, no. 2, pp. 757–776, 2012.
2. M. A. Just, V. L. Cherkassky, A. Buchweitz, T. A. Keller, and T. M. Mitchell, “Identifying autism from neural representations of social interactions: neurocognitive markers of autism,” PLoS One, vol. 9, no. 12, p. e113879, 2014.
3. N. Hasan and M. J. Nene, “An Agent-Based Basic Educational Model for the Children with ASD Using Persuasive Technology,” in 2022 International Conference for Advancement in Technology (ICONAT), 2022, pp. 1–6.
4. J. H. Elder, C. M. Kreider, S. N. Brasher, and M. Ansell, “Clinical impact of early diagnosis of autism on the prognosis and parent–child relationships.,” Psychol. Res. Behav. Manag., 2017.
5. J. Baio et al., “Prevalence of autism spectrum disorder among children aged 8 years—autism and developmental disabilities monitoring network, 11 sites, United States, 2014,” MMWR Surveill. Summ., vol. 67, no. 6, p. 1, 2018.
6. P. Mazumdar, G. Arru, and F. Battisti, “Early detection of children with autism spectrum disorder based on visual exploration of images,” Signal Process. Image Commun., vol. 94, p. 116184, 2021.
7. M. J. Shafiee, B. Chywl, F. Li, and A. Wong, “Fast YOLO: A fast you only look once system for real-time embedded object detection in video,” arXiv Prepr. arXiv1709.05943, 2017.
8. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779–788.

9. M. F. Rabbi, S. M. M. Hasan, A. I. Champa, and M. A. Zaman, “A convolutional neural network model for early-stage detection of autism spectrum disorder,” in 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD), 2021, pp. 110–114.
10. A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “Yolov4: Optimal speed and accuracy of object detection,” arXiv Prepr. arXiv2004.10934, 2020.
11. Z. A. T. Ahmed et al., “Facial Features Detection System To Identify Children With Autism Spectrum Disorder: Deep Learning Models,” Comput. Math. Methods Med., vol. 2022, 2022.
12. L. Guan, Multimedia image and video processing. CRC press, 2017.
13. J. Wu, A. Osuntogun, T. Choudhury, M. Philipose, and J. M. Rehg, “A scalable approach to activity recognition based on object use,” in 2007 IEEE 11th international conference on computer vision, 2007, pp. 1–8.
14. S. Raj and S. Masood, “Analysis and detection of autism spectrum disorder using machine learning techniques,” Procedia Comput. Sci., vol. 167, pp. 994–1004, 2020.
15. J. Du, “Understanding of object detection based on CNN family and YOLO,” in Journal of Physics: Conference Series, 2018, vol. 1004, no. 1, p. 12029.
16. A. Kumar, A. Kalia, and A. Kalia, “ETL-YOLO v4: A face mask detection algorithm in era of COVID-19 pandemic,” Optik (Stuttg)., vol. 259, p. 169051, 2022.
17. S.-C. Huang and T.-H. Le, Principles and Labs for Deep Learning. Academic Press, 2021.
18. J. Yu and W. Zhang, “Face mask wearing detection algorithm based on improved YOLO-v4,” Sensors, vol. 21, no. 9, p. 3263, 2021.
19. A. Alqaraghuli and A. T. A. Oğuz, “Optimized YOLOv4 Algorithm for Car Detection in Traffic Flow,” Turkish J. Sci. Technol., vol. 17, no. 2, pp. 395–403, 2022.
20. N. Kaur, V. KumarSinha, and S. S. Kang, “Early detection of ASD Traits in Children using CNN,” in 2021 2nd Global Conference for Advancement in Technology (GCAT), 2021, pp. 1–7