Smoking Degree Assessment System based on Upper Limb Resistance Training

Smoking is currently the most common risk factor for chronic obstructive pulmonary disease (COPD). To research the differences in exercise capacity between smokers and healthy subjects, this study proposes a training and assessment method to predict the smoking severity and smoking index of smokers...

Full description

Saved in:
Bibliographic Details
Published in:2022 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) pp. 258 - 262
Main Authors: Zhang, Bochao, Yang, Zhao, Wang, Jiping
Format: Conference Proceeding
Language:English
Published: IEEE 24.06.2022
Subjects:
chronic obstructive pulmonary disease
Conferences
exercise capacity
Lung
Machine learning
Machine learning algorithms
Pulmonary diseases
pulmonary function
Resistance
smoking degree
Support vector machine classification
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Smoking is currently the most common risk factor for chronic obstructive pulmonary disease (COPD). To research the differences in exercise capacity between smokers and healthy subjects, this study proposes a training and assessment method to predict the smoking severity and smoking index of smokers by measuring the changes in pulmonary function parameters before and after exercise in subjects. Subjects are trained to exercise by an upper limb resistance training device, and pulmonary function parameters are collected by a lung function respirometry device, and the optimal model is selected by comparing the characteristics of different machine learning classification and regression algorithms. Experiments were conducted to collect data from 12 subjects. The results show that the accuracy of the support vector machine(SVM) classification algorithm is 0.97, the AUROC is 0.97, and the R 2 of the XGB regression model is 0.99. This study is expected to assist health care professionals in providing personalized rehabilitation advice to patients in future clinical diagnosis.
DOI:10.1109/ICAICA54878.2022.9844465