Hybrid Techniques of Facial Feature Image Analysis for Early Detection of Autism Spectrum Disorder Based on Combined CNN Features
Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder characterized by difficulties in social communication and repetitive behaviors. The exact causes of ASD remain elusive and likely involve a combination of genetic, environmental, and neurobiological factors. Doctors often face c...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/18/2948 |
| _version_ | 1797580605782753280 |
|---|---|
| author | Bakri Awaji Ebrahim Mohammed Senan Fekry Olayah Eman A. Alshari Mohammad Alsulami Hamad Ali Abosaq Jarallah Alqahtani Prachi Janrao |
| author_facet | Bakri Awaji Ebrahim Mohammed Senan Fekry Olayah Eman A. Alshari Mohammad Alsulami Hamad Ali Abosaq Jarallah Alqahtani Prachi Janrao |
| author_sort | Bakri Awaji |
| collection | DOAJ |
| description | Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder characterized by difficulties in social communication and repetitive behaviors. The exact causes of ASD remain elusive and likely involve a combination of genetic, environmental, and neurobiological factors. Doctors often face challenges in accurately identifying ASD early due to its complex and diverse presentation. Early detection and intervention are crucial for improving outcomes for individuals with ASD. Early diagnosis allows for timely access to appropriate interventions, leading to better social and communication skills development. Artificial intelligence techniques, particularly facial feature extraction using machine learning algorithms, display promise in aiding the early detection of ASD. By analyzing facial expressions and subtle cues, AI models identify patterns associated with ASD features. This study developed various hybrid systems to diagnose facial feature images for an ASD dataset by combining convolutional neural network (CNN) features. The first approach utilized pre-trained VGG16, ResNet101, and MobileNet models. The second approach employed a hybrid technique that combined CNN models (VGG16, ResNet101, and MobileNet) with XGBoost and RF algorithms. The third strategy involved diagnosing ASD using XGBoost and an RF based on features of VGG-16-ResNet101, ResNet101-MobileNet, and VGG16-MobileNet models. Notably, the hybrid RF algorithm that utilized features from the VGG16-MobileNet models demonstrated superior performance, reached an AUC of 99.25%, an accuracy of 98.8%, a precision of 98.9%, a sensitivity of 99%, and a specificity of 99.1%. |
| first_indexed | 2024-03-10T22:52:07Z |
| format | Article |
| id | doaj.art-663b903309dc45d69fc586fb4e784308 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T22:52:07Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-663b903309dc45d69fc586fb4e7843082023-11-19T10:13:48ZengMDPI AGDiagnostics2075-44182023-09-011318294810.3390/diagnostics13182948Hybrid Techniques of Facial Feature Image Analysis for Early Detection of Autism Spectrum Disorder Based on Combined CNN FeaturesBakri Awaji0Ebrahim Mohammed Senan1Fekry Olayah2Eman A. Alshari3Mohammad Alsulami4Hamad Ali Abosaq5Jarallah Alqahtani6Prachi Janrao7Department of Computer Science, College of Computer Science and Information Systems, Najran University, Najran 6646, Saudi ArabiaDepartment of Artificial Intelligence, Faculty of Computer Science and Information Technology, Alrazi University, Sana’a, YemenDepartment of Information System, College of Computer Science and Information Systems, Najran University, Najran 6646, Saudi ArabiaDepartment of Computer Science and Information Technology, Thamar University, Dhamar 87246, YemenDepartment of Computer Science, College of Computer Science and Information Systems, Najran University, Najran 6646, Saudi ArabiaDepartment of Computer Science, College of Computer Science and Information Systems, Najran University, Najran 6646, Saudi ArabiaDepartment of Computer Science, College of Computer Science and Information Systems, Najran University, Najran 6646, Saudi ArabiaThakur College of Engineering and Technology, Kandivali(E), Mumbai 400101, IndiaAutism spectrum disorder (ASD) is a complex neurodevelopmental disorder characterized by difficulties in social communication and repetitive behaviors. The exact causes of ASD remain elusive and likely involve a combination of genetic, environmental, and neurobiological factors. Doctors often face challenges in accurately identifying ASD early due to its complex and diverse presentation. Early detection and intervention are crucial for improving outcomes for individuals with ASD. Early diagnosis allows for timely access to appropriate interventions, leading to better social and communication skills development. Artificial intelligence techniques, particularly facial feature extraction using machine learning algorithms, display promise in aiding the early detection of ASD. By analyzing facial expressions and subtle cues, AI models identify patterns associated with ASD features. This study developed various hybrid systems to diagnose facial feature images for an ASD dataset by combining convolutional neural network (CNN) features. The first approach utilized pre-trained VGG16, ResNet101, and MobileNet models. The second approach employed a hybrid technique that combined CNN models (VGG16, ResNet101, and MobileNet) with XGBoost and RF algorithms. The third strategy involved diagnosing ASD using XGBoost and an RF based on features of VGG-16-ResNet101, ResNet101-MobileNet, and VGG16-MobileNet models. Notably, the hybrid RF algorithm that utilized features from the VGG16-MobileNet models demonstrated superior performance, reached an AUC of 99.25%, an accuracy of 98.8%, a precision of 98.9%, a sensitivity of 99%, and a specificity of 99.1%.https://www.mdpi.com/2075-4418/13/18/2948hybrid techniqueCNNXGBoostRFt-SNEcombined features |
| spellingShingle | Bakri Awaji Ebrahim Mohammed Senan Fekry Olayah Eman A. Alshari Mohammad Alsulami Hamad Ali Abosaq Jarallah Alqahtani Prachi Janrao Hybrid Techniques of Facial Feature Image Analysis for Early Detection of Autism Spectrum Disorder Based on Combined CNN Features Diagnostics hybrid technique CNN XGBoost RF t-SNE combined features |
| title | Hybrid Techniques of Facial Feature Image Analysis for Early Detection of Autism Spectrum Disorder Based on Combined CNN Features |
| title_full | Hybrid Techniques of Facial Feature Image Analysis for Early Detection of Autism Spectrum Disorder Based on Combined CNN Features |
| title_fullStr | Hybrid Techniques of Facial Feature Image Analysis for Early Detection of Autism Spectrum Disorder Based on Combined CNN Features |
| title_full_unstemmed | Hybrid Techniques of Facial Feature Image Analysis for Early Detection of Autism Spectrum Disorder Based on Combined CNN Features |
| title_short | Hybrid Techniques of Facial Feature Image Analysis for Early Detection of Autism Spectrum Disorder Based on Combined CNN Features |
| title_sort | hybrid techniques of facial feature image analysis for early detection of autism spectrum disorder based on combined cnn features |
| topic | hybrid technique CNN XGBoost RF t-SNE combined features |
| url | https://www.mdpi.com/2075-4418/13/18/2948 |
| work_keys_str_mv | AT bakriawaji hybridtechniquesoffacialfeatureimageanalysisforearlydetectionofautismspectrumdisorderbasedoncombinedcnnfeatures AT ebrahimmohammedsenan hybridtechniquesoffacialfeatureimageanalysisforearlydetectionofautismspectrumdisorderbasedoncombinedcnnfeatures AT fekryolayah hybridtechniquesoffacialfeatureimageanalysisforearlydetectionofautismspectrumdisorderbasedoncombinedcnnfeatures AT emanaalshari hybridtechniquesoffacialfeatureimageanalysisforearlydetectionofautismspectrumdisorderbasedoncombinedcnnfeatures AT mohammadalsulami hybridtechniquesoffacialfeatureimageanalysisforearlydetectionofautismspectrumdisorderbasedoncombinedcnnfeatures AT hamadaliabosaq hybridtechniquesoffacialfeatureimageanalysisforearlydetectionofautismspectrumdisorderbasedoncombinedcnnfeatures AT jarallahalqahtani hybridtechniquesoffacialfeatureimageanalysisforearlydetectionofautismspectrumdisorderbasedoncombinedcnnfeatures AT prachijanrao hybridtechniquesoffacialfeatureimageanalysisforearlydetectionofautismspectrumdisorderbasedoncombinedcnnfeatures |