Autism Identification Based on the Intelligent Analysis of Facial Behaviors: An Approach Combining Coarse- and Fine-Grained Analysis
Background: Facial behavior has emerged as a crucial biomarker for autism identification. However, heterogeneity among individuals with autism poses a significant obstacle to traditional feature extraction methods, which often lack the necessary discriminative power. While deep-learning methods hold...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Children |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9067/11/11/1306 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850267705249103872 |
|---|---|
| author | Jingying Chen Chang Chen Ruyi Xu Leyuan Liu |
| author_facet | Jingying Chen Chang Chen Ruyi Xu Leyuan Liu |
| author_sort | Jingying Chen |
| collection | DOAJ |
| description | Background: Facial behavior has emerged as a crucial biomarker for autism identification. However, heterogeneity among individuals with autism poses a significant obstacle to traditional feature extraction methods, which often lack the necessary discriminative power. While deep-learning methods hold promise, they are often criticized for their lack of interpretability. Methods: To address these challenges, we developed an innovative facial behavior characterization model that integrates coarse- and fine-grained analyses for intelligent autism identification. The coarse-grained analysis provides a holistic view by computing statistical measures related to facial behavior characteristics. In contrast, the fine-grained component uncovers subtle temporal fluctuations by employing a long short-term memory (LSTM) model to capture the temporal dynamics of head pose, facial expression intensity, and expression types. To fully harness the strengths of both analyses, we implemented a feature-level attention mechanism. This not only enhances the model’s interpretability but also provides valuable insights by highlighting the most influential features through attention weights. Results: Upon evaluation using three-fold cross-validation on a self-constructed autism dataset, our integrated approach achieved an average recognition accuracy of 88.74%, surpassing the standalone coarse-grained analysis by 8.49%. Conclusions: This experimental result underscores the improved generalizability of facial behavior features and effectively mitigates the complexities stemming from the pronounced intragroup variability of those with autism, thereby contributing to more accurate and interpretable autism identification. |
| format | Article |
| id | doaj-art-53c1919260a04adb826014ecc24c9764 |
| institution | OA Journals |
| issn | 2227-9067 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Children |
| spelling | doaj-art-53c1919260a04adb826014ecc24c97642025-08-20T01:53:41ZengMDPI AGChildren2227-90672024-10-011111130610.3390/children11111306Autism Identification Based on the Intelligent Analysis of Facial Behaviors: An Approach Combining Coarse- and Fine-Grained AnalysisJingying Chen0Chang Chen1Ruyi Xu2Leyuan Liu3Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaFaculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaComputer Science and Artificial Intelligence School, Wuhan University of Technology, Wuhan 430070, ChinaFaculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaBackground: Facial behavior has emerged as a crucial biomarker for autism identification. However, heterogeneity among individuals with autism poses a significant obstacle to traditional feature extraction methods, which often lack the necessary discriminative power. While deep-learning methods hold promise, they are often criticized for their lack of interpretability. Methods: To address these challenges, we developed an innovative facial behavior characterization model that integrates coarse- and fine-grained analyses for intelligent autism identification. The coarse-grained analysis provides a holistic view by computing statistical measures related to facial behavior characteristics. In contrast, the fine-grained component uncovers subtle temporal fluctuations by employing a long short-term memory (LSTM) model to capture the temporal dynamics of head pose, facial expression intensity, and expression types. To fully harness the strengths of both analyses, we implemented a feature-level attention mechanism. This not only enhances the model’s interpretability but also provides valuable insights by highlighting the most influential features through attention weights. Results: Upon evaluation using three-fold cross-validation on a self-constructed autism dataset, our integrated approach achieved an average recognition accuracy of 88.74%, surpassing the standalone coarse-grained analysis by 8.49%. Conclusions: This experimental result underscores the improved generalizability of facial behavior features and effectively mitigates the complexities stemming from the pronounced intragroup variability of those with autism, thereby contributing to more accurate and interpretable autism identification.https://www.mdpi.com/2227-9067/11/11/1306autism identificationhead posefacial expression Intensity and typesLSTMfeature-level attention mechanism |
| spellingShingle | Jingying Chen Chang Chen Ruyi Xu Leyuan Liu Autism Identification Based on the Intelligent Analysis of Facial Behaviors: An Approach Combining Coarse- and Fine-Grained Analysis Children autism identification head pose facial expression Intensity and types LSTM feature-level attention mechanism |
| title | Autism Identification Based on the Intelligent Analysis of Facial Behaviors: An Approach Combining Coarse- and Fine-Grained Analysis |
| title_full | Autism Identification Based on the Intelligent Analysis of Facial Behaviors: An Approach Combining Coarse- and Fine-Grained Analysis |
| title_fullStr | Autism Identification Based on the Intelligent Analysis of Facial Behaviors: An Approach Combining Coarse- and Fine-Grained Analysis |
| title_full_unstemmed | Autism Identification Based on the Intelligent Analysis of Facial Behaviors: An Approach Combining Coarse- and Fine-Grained Analysis |
| title_short | Autism Identification Based on the Intelligent Analysis of Facial Behaviors: An Approach Combining Coarse- and Fine-Grained Analysis |
| title_sort | autism identification based on the intelligent analysis of facial behaviors an approach combining coarse and fine grained analysis |
| topic | autism identification head pose facial expression Intensity and types LSTM feature-level attention mechanism |
| url | https://www.mdpi.com/2227-9067/11/11/1306 |
| work_keys_str_mv | AT jingyingchen autismidentificationbasedontheintelligentanalysisoffacialbehaviorsanapproachcombiningcoarseandfinegrainedanalysis AT changchen autismidentificationbasedontheintelligentanalysisoffacialbehaviorsanapproachcombiningcoarseandfinegrainedanalysis AT ruyixu autismidentificationbasedontheintelligentanalysisoffacialbehaviorsanapproachcombiningcoarseandfinegrainedanalysis AT leyuanliu autismidentificationbasedontheintelligentanalysisoffacialbehaviorsanapproachcombiningcoarseandfinegrainedanalysis |