Performance Analysis of Multimodal Emotion Recognition Using ECG and GSR Signals
Implementation Plan:
Step 1: Initially, we will collect, load the YAAD ECG and GSR Signals Dataset and fuse the ECG and GSR and Label Data into a single Dataset.
Step 2: Then, we will preprocess the collected data using bandpass with notch filtering (ECG) and low-pass filtering (GSR) with normalization.
Step 3: Next, we will extract the ECG & GSR features and combine them as a single feature matrix for model training purposes.
Step 4: Next, we will classify the emotion using the Multi-Layer Perceptron ML Algorithm using collected data to predict the emotional state.
Step 5: Finally, we plot performance metrics for the following:
5.1: Number of Epochs vs. Accuracy (%)
5.2: Number of Epochs vs. Precision (%)
5.3: Number of Epochs vs. Recall (%)
5.4: Number of Epochs vs. F1-score (%)
Software Requirements:
1. Development Tool: Python 3.10.x or above version
2. Operating System: Windows-10 (64-bit) or above
Dataset Link:
Link: Young Adult’s Affective Data (YAAD) Using ECG and GSR Signals – Mendeley Data
Note:
1) If the proposed plan does not fully align with your requirements, please provide all necessary details—including steps, parameters, models, and expected outcomes—in advance.
2) Kindly ensure that any missing configurations or specifications are clearly outlined in the plan before confirming.
3) If there’s no built-in solution for what the project needs, we can always turn to reference models, customize our own, different math models or write the code ourselves to fulfil the process.
4) If the plan satisfies your requirement, Please confirm with us.
5) Project based on Simulation only.
