Abstract:

The machine learning algorithms K-nearest neighbours (KNN) and Naive Bayes are used in this research to present a unique method for precisely detecting stress in elderly individuals. The goal of the study was to create a model that could accurately categorise stress levels in elderly people based on physiological information such as heart rate, blood pressure, and oxygen saturation levels. The authors used a dataset consisting of physiological data from elderly patients undergoing medical treatment and applied feature selection techniques to identify the most relevant features for stress detection. They then compared the performance of KNN and Naive Bayes classifiers in accurately predicting stress levels in the dataset. The results showed that both algorithms achieved high accuracy rates in stress detection, with KNN outperforming Naive Bayes in terms of classification accuracy. The proposed approach has potential applications in healthcare settings, where accurate stress detection can facilitate early intervention and improve patient outcomes. The results demonstrate that the proposed approach can accurately classify stress levels in elderly patients, with KNN achieving an accuracy of 93.5% and Naive Bayes achieving an accuracy of 89.6%. These findings suggest that machine learning algorithms can be effectively applied to the detection of stress in elderly patients, offering potential benefits for early detection and intervention in healthcare settings.

Description:

KNN, Naive Bayes, Machine Learning, Kaggle, Heart Rate, Blood Pressure