anish-lakkapragada/Hand-Classification-For-Autism-Diagnosis
[JMIR '22, DataBricks '22] Code for Classification of Abnormal Hand Movement for Aiding in Autism Detection
Combines MediaPipe hand landmark detection with LSTM networks and MobileNet V2 feature extraction to identify hand-flapping behavior from video frames. Uses rigorous 5-fold cross-validation repeated 100 times across randomized dataset splits, achieving 84% F1-score. Includes demo code, trained model checkpoints, and experimental notebooks exploring landmark-based versus CNN-based approaches on the Self-Stimulatory Behavior Dataset.
No commits in the last 6 months.
Stars
23
Forks
6
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/anish-lakkapragada/Hand-Classification-For-Autism-Diagnosis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
eockfen/EyeTism
Early detection of Autism Spectrum Disorder (ASD) is crucial for children's development, yet the...
nicknears/Brain-Disorder-Detection-Through-Eye-Movement
👁️ Analyze eye movements to detect brain disorders, utilizing wearable sensors for better...
Arnav2722/Autism_Prediction
This project builds an end-to-end machine learning pipeline to predict Autism Spectrum Disorder...
Venu22003/Autism-detection-system
AI-powered autism detection using Django and CNN
sainimal1ba-hue/AI-Powered-Sensory-Overload-Prevention-for-Autism
This is is an AI-powered hearing-aid companion app that predicts sensory overload in autistic...