Real Time Emotion Detection using EEG
Transcript of Real Time Emotion Detection using EEG
![Page 1: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/1.jpg)
Real Time Emotion Detection using EEGMina MikhailSupervisor:
Dr. Khaled El-Ayat Dr. Rana El Kaliouby
![Page 2: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/2.jpg)
Emotions
• Emotion is a mental and a physiological state
• Emotion is very subjective
• There are more than 90 definitions of “emotion”
![Page 3: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/3.jpg)
Models of Emotion Representation
• Two models for emotion representation
– Darwin’s Model
– Multi-dimensional View
![Page 4: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/4.jpg)
Models of Emotion Representation
• The muti-dimensional view is often used
– Simplicity
– Universality
![Page 5: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/5.jpg)
Motivation
• Lots of applications
– Quantifying customers’ experience for product evaluation
– Assistive Technology– Software Adaptation– Monitoring safety critical systems
![Page 6: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/6.jpg)
Emotion Detection Channels
• Machine vision
• Voice detection
![Page 7: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/7.jpg)
Physiological Channels
• They cannot be faked• Produced from involuntary secretion
glands• Peripheral nervous system
– Skin conductance– Skin temperature variations– Blood pressure– Heart Beat
![Page 8: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/8.jpg)
Why EEG?
• Based on the cognitive theory of emotion, the brain is the center of every human action
• Physiological signals, facial expressions, voice are all generated as a result of brain signals
![Page 9: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/9.jpg)
EEG Primer
• Whenever a neuron is active, its voltage changes
• Million of neurons fire together• Each mental state produces a distinct
pattern of electrical activity
![Page 10: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/10.jpg)
Brain Regions
•• Frontal Lobe Frontal Lobe – Primary motor cortex, Frontal Eye,– information processing,
•• ParietalParietal– Sensory information, taste, pressure, sound,
temp..•• OccipitalOccipital
– Visual processing center•• TemporalTemporal
– Auditory processing
Frontal lobe
Parietal
OccipitalTemporal
![Page 11: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/11.jpg)
Rhythmic ActivityRhythm Frequency Range Location Reason
Delta (0-4) Hz Frontal lobe Deep sleep
Theta (4-7) Hz Midline, temporal Drowsiness and
meditation
Alpha (8-13) Hz Frontal, Occipital Relaxing, closed eyes
Mu (8-12) Hz Central Contralateral Motor
acts
Beta (13-30) Hz Frontal, central Concentration and
thinking
Gamma (30- 100+) Hz Cognitive functions
![Page 12: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/12.jpg)
EEG and Emotions• Emotions are most obvious in the alpha band
• The right hemisphere is responsible for negative emotions (disgust, fear, stress)
• The left hemisphere is responsible for positive emotions (Happiness, joy)
• EEG power decreases during sadness and increases during happiness (frontal lobe)
![Page 13: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/13.jpg)
EEG and Emotion
![Page 14: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/14.jpg)
General Approach
![Page 15: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/15.jpg)
Questions?
• Can we detect four different emotions, happiness, fear, disgust and neutral with reasonable accuracy?
• What is the minimum number of electrodes that can be used to detect the four emotions with a reasonable accuracy?
• What are the best features to extract?
![Page 16: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/16.jpg)
Experiments
![Page 17: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/17.jpg)
EEG Montage
• 10-20 internationalsystem
![Page 18: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/18.jpg)
Signal Preprocessing
• Notch filter (to remove line noise)• Independent Component Analysis
![Page 19: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/19.jpg)
Feature Extraction
![Page 20: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/20.jpg)
Classification
• Support Vector Machines (SVMs)
• Artificial Neural Networks
• Bayesian Networks
![Page 21: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/21.jpg)
Tools
• G.Mobilab– 8 channels– Active electrodes
• BCI2000• EEGLAB• IAPS
![Page 22: Real Time Emotion Detection using EEG](https://reader031.fdocuments.in/reader031/viewer/2022012101/6169f38511a7b741a34d2db1/html5/thumbnails/22.jpg)
Plan
• Classify the signals into positive, negative and neutral states and classify between these signals
• Try to divide the negative states into disgust and fear
• Explore emotion detection accuracy Vs. number of channels