MétaCan
Menu
← Back to cohort
Record W4417312180 · doi:10.18280/isi.301007

Hybrid Deep Learning Framework for Autism Detection in Children Using Facial Emotion Recognition

2025· article· W4417312180 on OpenAlexvenueno aff
R. Shekhar, Chetan J. Shelke

Bibliographic record

VenueIngénierie des systèmes d information · 2025
Typearticle
Language
FieldNeuroscience
TopicAutism Spectrum Disorder Research
Canadian institutionsnot available
Fundersnot available
KeywordsDeep learningAutismEmotion recognitionFeature (linguistics)Facial recognition systemFacial expressionFace (sociological concept)

Abstract

fetched live from OpenAlex

Health care providers determine diagnosing autism to be a difficult undertaking because it mostly relies on anomalies in brain activities that could not be evident in the initial stages of a young development autism condition.An alternate and effective method to facilitate the earlier identification of autism involves facial emotion.This is because autistic children typically exhibit unique patterns that make it easier to differentiate from typical kids.some of many significant developments in enhancing the state lifestyle for those having autism is technological assistance.This study proposes a hybrid deep learning approach to detect the autism in children using deep facial features and emotional expressions.The proposed model combines the feature extraction from pre-trained CNN models like EfficientNetB0, ResNet50, and MobileNetV3Small and then classify autism and non-autism using a softvoting ensemble model.The dataset is divided into 80% training and 20% testing.The MobileNetV2 model is used as emotion recognition that integrated on DeepFace model to enhance behavioral interpretation.The proposed model is trained and validated on two datasets: one containing images of autistic and non-autistic children, and another containing six types of emotions.The baseline classifier such as LR obtained the accuracy score of 77.57%, XGBoost of 81.00%, RF of 78.36%, SVM of 79.95%, MLP of 79.68.The proposed model obtained the accuracy score of 84.00% and a ROC-AUC score of 92.29% outperforming as compared to baseline models.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.014
Threshold uncertainty score0.027

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.023
GPT teacher head0.285
Teacher spread0.262 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractno

Explore more

Same venueIngénierie des systèmes d information→Same topicAutism Spectrum Disorder Research→French-language works237,207→