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.
Autism Spectrum Disorder YOLO YOLO v3 v4 CNN Deep learning Machine learning
Autism Spectrum Disorder YOLO YOLO v3 v4 CNN Deep learning Machine learning
Birincil Dil | İngilizce |
---|---|
Konular | Yazılım Mühendisliği |
Bölüm | Derlemeler |
Yazarlar | |
Yayımlanma Tarihi | 27 Şubat 2023 |
Yayımlandığı Sayı | Yıl 2022 Cilt: 2 Sayı: 2 |
Journal of Emerging Computer Technologies
is indexed and abstracted by
Index Copernicus, ROAD, Academia.edu, Google Scholar, Asos Index, Academic Resource Index (Researchbib), OpenAIRE, IAD, Cosmos, EuroPub, Academindex
Publisher
Izmir Academy Association
www.izmirakademi.org