Shesop Healthcare: Stress and influenza classification using support vector machine kernel

TL;DR

This paper presents a support vector machine-based system for classifying stress and influenza using heart rate data from wearable devices, aiming to provide immediate health status feedback.

Contribution

It introduces a novel approach combining heart rate variance analysis with SVM kernels to classify stress and influenza levels in real-time.

Findings

Effective classification of stress and influenza achieved

Heart rate variance is a key indicator

Real-time health status detection possible

Abstract

Shesop is an integrated system to make human lives more easily and to help people in terms of healthcare. Stress and influenza classification is a part of Shesop's application for a healthcare devices such as smartwatch, polar and fitbit. The main objective of this paper is to classify a new data and inform whether you are stress, depressed, caught by influenza or not. We will use the heart rate data taken for months in Bandung, analyze the data and find the Heart rate variance that constantly related with the stress and flu level. After we found the variable, we will use the variable as an input to the support vector machine learning. We will use the lagrangian and kernel technique to transform 2D data into 3D data so we can use the linear classification in 3D space. In the end, we could use the machine learning's result to classify new data and get the final result immediately: stress or not, influenza or not.