Empowering Education and Therapy with Data Science
summary
Describes a pipeline that first builds a machine learning emotion classifier that distinguishes six expressions (anger, disgust, fear, happiness, sadness, surprise) using patterned facial features and video feedback, then shifts to EEG-based neurofeedback at Brainhero: multi-electrode recordings, frequency-band thresholds (targeting ~20% above baseline for rewards), and protocols tuned for ASD vs ADHD. Presents a mobile game with operant conditioning that rewards regulated brain patterns in real time, reports symptom alleviation in some children, notes limited data, privacy constraints, and the goal of personalized “braces” for brain activity.
AI-written summary · about
chapters (8)
- 0:00Emotion detection in children
- 1:52Neurofeedback therapy transition
- 3:42Real-time neurofeedback
- 6:06Personalized brain therapy
- 7:53Data sensitivity challenges
- 13:27Quality of life for ASD/ADHD
- 17:30Parental perspectives & future
- 18:59Closing & Q&A
related talks
35mTranslating Brain Electrical Signals into Actions through Models...
03mIdentifying Children Metacognitive Monitoring Performance Through Facial Expressions
49mAffective Computing – Bringing Humans and Machines Closer Through Emotions
19mAI for Autism: Bridging Neuroscience and AI
19mAnger-based BCI Using fNIRS Neurofeedback
31mLearn to control your brain: Brain Computer Interfacing with Python
11mAmbient Intelligence and Emotionally Intelligent Devices
34mEnhancing Customer Experiences with Emotional AI,