analog-vs-digital-communication (concept of analog and digital).pptx
Emotion recognition-from-multichannel-eeg-signal-using-2 d
1. Emotion recognition from multichannel EEG signal using 2D data
Augmentation and Convolutional Neural Network (CNN)
Al-Arraf Uzzaman(201826003)
Nymphia Nourin (201826007)
Pratik Das(201826014)
Dewan Imran Ahmed(201826017)
Paromita Kundu(201826037)
Syeda Umme Ayman(201826040)
2. Objective
• Generating topographic image with augmented DEAP dataset
• Classification of topographic images into Valence-Arousal model
• Training and validating Deep Learning algorithm using CNN
3. Workflow
Collecting Raw EEG
signals for different
Emotions
Noise Cancellation
Data Augmentation
and generation of 2D
Topographic Images
Feature Extraction
And Classification by
CNN
4. Data Augmentaion
Generation of 9X9
matrix taking the
average of the
nearest points
Red dots-original
electrode points
Gray dots-
Augmented data
points
5. Image generation and Classification
Topographic image generation
LVHA HVHA
HVLA
LVLA
Valence-arousal model
11. Reference:
• 1) Emotion Recognition from EEG-based on Power Spectral Topography using Convolutional Neural
Network.
• https://doi.org/10.1016/j.array.2021.100072
• 2) Employing PCA and t-statistical approach for feature extraction and
• classification of emotion from multichannel EEG signal
• https://doi.org/10.1016/j.eij.2019.10.002
• 3) Human Emotion Recognition with Electroencephalographic Multidimensional Features by Hybrid
Deep Neural Networks
• https://www.researchgate.net/publication/320392126_Human_Emotion_Recognition_with_Electroenc
ephalographic_Multidimensional_Features_by_Hybrid_Deep_Neural_Networks
• 4. Mueller SC. The influence of emotion on cognitive control: relevance for development and
adolescent psychopathology. Front Psychol 2011;2:327.
• https:// doi.org/10.3389/fpsyg.2011.00327.
• 5. Tyng CM, Amin HU, Saad MNM, Malik AS. The influences of emotion on learning and memory. Front
Psychol August 2017;8(1454):24.
• https://doi.org/10.3389/ fpsyg.2017.01454.