International Journal of Advances in Engineering & Scientific Research
Print ISSN : 2349 –4824
Online ISSN : 2349 –3607
Frequency : Continuous
Current Issue : Volume 12 , Issue 1
2025
Mrs.S.Suganya, Abarna K, Abarna S, Keerthiga M
Mrs.S.Suganya, Abarna K, Abarna S, Keerthiga M, Department of Computer Science and Engineering, Kongunadu College of Engineering and Technology, Tamilnadu, India
DOI : https://doi.org/10.5281/zenodo.14924693 Page No : 57-65
Published Online : 2025-02-25
Download Full Article : PDF Check for Updates
Mental well-being is a critical aspect of overall health, and early detection of stress can help prevent severe psychological disorders. This study explores an AI-powered stress prediction model that leverages deep learning techniques in conjunction with the K-Nearest Neighbors (KNN) algorithm to improve the accuracy and efficiency of stress detection. The proposed approach integrates physiological signals, such as heart rate variability, electro dermal activity, and sleep patterns, along with behavioral data, to classify stress levels. Initially, deep learning models, including LSTM and CNN, extract high-level temporal and spatial features from raw input data. These features are then fed into a KNN classifier to enhance interpretability and decision-making by leveraging instance-based learning. Experimental results demonstrate that combining deep learning feature extraction with KNN improves classification performance compared to traditional machine learning methods. The hybrid model achieves high accuracy, precision, and recall in identifying stress patterns, making it suitable for real-time applications in wearable devices and digital health platforms. Furthermore, the model's ability to provide interpretable predictions enhances its applicability in mental health monitoring. This study highlights the potential of AI-driven approaches in personalized stress management and underscores the importance of integrating multiple modalities for robust stress detection. Future work will focus on optimizing feature selection and real-time deployment in mobile health applications to facilitate early intervention and support mental well-being.
Keywords: Stress Prediction, Deep Learning, KNN, Mental Well-Being, Physiological Signals and AI in Healthcare
