Implementation Plan:
Step 1: Initially,we will collect and load data from the SWELL dataset.
Step 2: Next, we preprocess the data using interpolation techniques to detect and reconstruct these missing values to achieve data reliability.
Step 3: Next, we extract the physiological features using the Joint Modality Features-based framework to detect stress and anxiety disorders based on collected data.
Step 4: Next, we monitor the changes in stress levels using the RF algorithm with Multi-agent Deep Reinforcement Learning (MADRL) methods based on collected data.
Step 5: Next, we train the model using novel Transfer learning integrated into the Quantum Graph Neural Network (TL-QGNN) method to minimize overfitting based on collected data.
Step 6: Next, we classify the various levels of anxiety using identification of pattern distributions and thresholds based on collected data.
Step 7 : Finally, we plot performance for the following metrics:
7.1 : Number of Epochs Vs. Accuracy (%)
7.2 : Number of Epochs Vs. F1-Score (%)
7.3 : Number of Epochs Vs. Precision (%)
7.4 : Number of Epochs Vs. Recall (%)
7.5 : Number of Epochs Vs. Area under curve (AUC)
Software Requirements:
1. Development Tool: Python 3.11.9
2. Operating System: Windows 10 (64-bit) or above
Dataset Link:
Link: https://www.kaggle.com/datasets/qiriro/swell-heart-rate-variability-hrv
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. Kindly ensure that any missing configurations or specifications are clearly outlined in the plan before confirming.
2) 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.
3) If the plan satisfies your requirement, Please confirm with us.
4) Project based on Simulation only.
5) If you have any changes in the dataset ,kindly provide us before we implement it.
We perform with an Existing approach Ref 3 : Title:- A DeepLearning-Based Platform for Workers’ Stress Detection Using Minimally Intrusive Multisensory Devices
