학술논문

Novel Analysis of Human Stress Using Adult Blood Pressure and Heart Rate Data Using Random Forest Algorithm
Document Type
Conference
Source
2024 International Conference on Integrated Intelligence and Communication Systems (ICIICS) Integrated Intelligence and Communication Systems (ICIICS), 2024 International Conference on. :1-5 Nov, 2024
Subject
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Fields, Waves and Electromagnetics
Power, Energy and Industry Applications
Radio frequency
Heart rate
Training
Logistic regression
Accuracy
Human factors
Blood pressure
Pressure measurement
Random forests
Stress measurement
novel random forest algorithm
logistic regression
human mental stress
machine learning
kaggle
heart rate
blood pressure
Language
Abstract
Aim: This study uses the Novel Random Forest (RF) algorithm to identify mental stress in adult patients. Heart rate and blood pressure (systolic and diastolic) measurements are utilized to identify mental stress. Materials and Methods: A total of 108402 samples are taken from the Stress Detection of Medical Practitioners dataset, which is hosted on Kaggle. Clincalc, which has two distinct groups, alpha (0.05), power (80 % ), and enrollment ratio, is used to compute the G power for samples. The training dataset (n = 75882) comprises 70% of these samples, whereas the test dataset (n = 32520) comprises 30% of them. To measure how well the RF algorithm performs, accuracy is computed. Results: When it came to the stress detection of medical practitioners and human stress detection datasets, the novel RF method achieved an accuracy of 90.4 % and 88.2%, respectively, whereas logistic regression earned an accuracy of 87.4% and 85.3% (P