Emotion Classification using EEG signals

Project Title

Emotion Classification using EEG signals

Project Area of Specialization Artificial IntelligenceProject Summary

In this project, human emotions like happiness, sadness, fear, surprise, etc. will be classified through EEG signals using machine learning and deep learning techniques. Human emotions can be recognized from speech, eye blinking, facial expressions, and physiological signals. However, the first three methods are unstable and easily affected by subjectivity. Subjects can deliberately conceal their emotions and leading to recognition errors. Physiological signals such as electrooculogram (EOG), electroencephalogram (EEG), and blood pressure (BVP) are produced spontaneously by the human body. Therefore, physiological signals can more accurately reflect the emotional state of people. Among all these physiological signals, electroencephalogram (EEG) is the overall reflection of the electrophysiological activities of brain nerve cells on the cerebral cortex or scalp surface, which indicates that changes in EEG signals can be used to characterize human emotional changes.

It has been reported that more than 264 million people worldwide suffer from depression, which heavily impacts their quality of life. An accurate diagnosis of MDD (major depressive disorder) is of great importance for early intervention and effective treatment. Traditional diagnosis of MDD (major depressive disorder) mainly depends on subjective evaluation of symptom intensity using interview sessions and psychiatric scales. These methods are useful but time-consuming and sometimes may lead to misdiagnoses due to human and environmental factors. Thus, it is crucial to develop objective approaches to help clinicians diagnose MDD (major depressive disorder) more effectively.

Project Objectives

Objectives and contributions in proposed system are:

• To recognize emotions using efficient techniques.     
• To get the emotions without flaws.                
• To overcome difficulties in previous system.

The emotion can be captured either from face or from verbal communication. In this work we focus on identifying human emotion from EEG signals.  

Project Implementation Method

1. Dataset:

To develop the model for automated classification of human emotions. A standard dataset is needed for this purpose we selected a standard dataset named EEG Brainwave Dataset (Made byPhD Student at Aston University Birmingham, England, United Kingdom).

The data was collected from two people (1 male, 1 female) for 3 minutes per state - positive, neutral, negative. They used a Muse EEG headband which recorded the TP9, AF7, AF8 and TP10 EEG placements via dry electrodes. Six minutes of resting neutral data is also recorded, the stimuli used to evoke the emotions are below

1. Up - Negative (Walt Disney Pictures)
   Opening Death Scene
2. My Girl - Negative (Imagine Entertainment)
   Funeral Scene
3. La La Land - Positive (Summit Entertainment)
   Opening musical number
4. Slow Life - Positive (Bio Quest Studios)
   Nature timelapse
5. Funny Dogs - Positive (Mashup Zone)
   Funny dog clips

2. Preprocessing of EEG Signals:

EEG signals is usually of low amplitude (1-10µV peak) and are contaminated by several noises like high frequency, electrode movement noises etc.

Proper filter will be applied to remove these noises from EEG signals to get a clear EEG signal.

3. Development of the Model:

Several candidate models using classical machine and deep learning algorithm will be analyzed and developed to classify human emotion from EEG signals. The focus will be on developing a model with high accuracy.

Benefits of the Project

EEG-based emotion recognition is broadly used in entertainment, e-learning, and healthcare applications. EEG is utilized for different purposes—for example, instant messaging, online games, assisted therapy, and psychology.

Emotion recognition in Health Care:
An industry that’s taking advantage of this technology is Health Care, with AI-powered recognition software helping to decide when patients necessitate medicine or to help out physicians determine who to see first.

EEG-based Music Player Another application of real-time EEG-based emotion recognition is an EEG based music player website. In this application, the user’s current emotional state is recognized, and then, the corresponding music is played according to the identified emotion. The user’s emotion is detected by the algorithm running behind the scene. Songs are categorized into six emotion types: fear, sadness, frustration, happiness, satisfaction and pleasure.  Information about the current emotional state of the user and the music being played is given on the display of the player. The emotional state is recognized as pleasant, and the music which is categorized as pleasant music is played to the user.

Technical Details of Final Deliverable

As we mentioned before this system is based on EEG signals, and we can also detect and classify human emotions through face and voice recognition. But that is not accurate way, subject can change his/her face expression and voice expression due to which system will be failed to give accurate result.

So, the EEG signals are best for recognizing and classifying human emotions because it is not like we said above.

This system will be Classifying Human Emotions into three types,

1. Positive (Happy, Relax etc)

2. Neutral (Normal)

3. Negative (Sad, Angry, depressed etc)

The system will be traind and according to given dataset, It will detect Emotions of a person. through an EEG signal Detector placed on person's head. 

This system can be used in many places, 

example, Health care etc

Final Deliverable of the Project HW/SW integrated systemCore Industry MedicalOther Industries Education , IT Core Technology Artificial Intelligence(AI)Other Technologies Internet of Things (IoT)Sustainable Development Goals Good Health and Well-Being for People, Peace and Justice Strong InstitutionsRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	64500
Raspberry Pi 3 Board	Equipment	1	25000	25000
Mind Wave Mobile (For EEG Signals)	Equipment	1	25000	25000
LED Monitor Screen	Equipment	1	7000	7000
Connection Cables and Leds	Equipment	5	1000	5000
Stationary	Miscellaneous	5	500	2500