EEG(Electroencephalography) EMOTION ANALYSIS.pptx

LKBVFVHJ

1. EEG(Electroencephalography) EMOTION ANALYSIS BY UJWALA BIJEWAR MITU22MCAD0117

2. COMPONENTS Introduction Working Applications of eeg emotion analysis Objectives Proposed solution Exploratory Data Analysis Model evaluation conclusion

3. INTRODUCTION Electroencephalography (EEG) is a method used in EEG emotion detection to assess brain activity and distinguish between various emotional states. EEG is a non-invasive method that records electrical activity along the scalp, providing a high-temporal-resolution view of brain function. By combining EEG data with machine learning and other analytical techniques, researchers can gain valuable insights into how emotions are represented in the brain and how they influence behavior and condition.

4. WORKING How Does EEG Emotion Analysis Work? Participants are exposed to stimuli that evoke specific emotions (e.g., pictures, videos). EEG data is collected while participants experience these emotions. Researchers apply machine learning algorithms to identify patterns in the EEG data associated with different emotions. These patterns can then be used to predict a person's emotional state based on their EEG activity.

5. Applications of EEG emotion analysis Human-computer interaction (HCI): Create interfaces that adapt to a user's emotional state. Neuromarketing: Understand consumer preferences and emotional responses to products/advertisements. Education: Personalize learning experiences based on student engagement and emotional state. Mental health: Develop tools for monitoring and diagnosing a mental health conditions.

6. Objectives Understanding emotional brain activity: Identify and map patterns of brain activity with different emotional states. Study how the brain process and responds to emotional stimuli over the time . Predicting emotional states: Develop models to predict emotional states in real time based on EEG. Classify emotions from EEG signals using machine learning algorithms.

7. Proposed Solution The suggested analysis would gather high-quality EEG data while participants are exposed to a variety of emotional stimuli by using sophisticated data gathering techniques. Data Selection and Loading Data Preprocessing Data Transformation Machine Learning Model / Classification

8. Data Flow Diagram

9. Exploratory Data Analysis

10. Exploratory Data Analysis

11. Model evaluation Process Selection Of Evaluation Metrics: The output of the fit_transform method is a numpy array that contains the encoded labels. The encoded labels are integers that represent the categories in the original labels. For Example, if the original labels were “happy”, “sad”, “angry”, and “fearful”, the encoded labels might be 0, 1, 2, and 3, respectively

12. Model evaluation Process Feature selection:   Defining necessary features for model training :

13. Model evaluation Process Model Performance on Test Dataset:  Algorithm used for training: Random Forest Classifier :   Random forest is a powerful and versatile classifier that combines multiple decision trees to produce accurate and stable predictions. It is widely used in machine learning applications due to its robustness, ease of use, and ability to handle high-dimensional data. By fine-tuning hyperparameters and considering the data and task at hand, random forest can be an effective tool for classification and regression tasks.

14. Model evaluation Process CLASSIFICATION REPORT:    

15. Conclusion The system analyses the user mindset using Eeg signals and makes a prediction based on that. Because these solutions are more affordable for government hospitals and medical experts may prefer to use them for diagnosis. This research looks at a variety of categorical model strategies that helps to get best results. Random Forest Classifier has the highest accuracy 99 percent.

16. THANK YOU!