[This article belongs to Volume - 55, Issue - 01, 2023]
Gongcheng Kexue Yu Jishu/Advanced Engineering Science
Journal ID : AES-11-01-2023-022

Title : A STUDY ON WEARABLE E-TEXTILES FOR PERSONAL HEALTH MONITORING USING MACHINE LEARNING
Ashish Hooda

Abstract :

In today's world, the rapidly converging fields of electronics textiles make it possible for sensors to be seamlessly and extensively incorporated into textiles, as well as for conductive yarn to be manufactured. A new age in retail may be on the horizon thanks to the possibility of smart textiles, which can interface with smartphones and interpret biological data such as a person's heart rate, temperature, respiration, stress, activity, speed, or even hormone levels. In this work, a study is performed on wearables and garments to create e-textilesusing machine learning techniques such as Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF),Decision Tree (DT) and ensemble classifiers.Some parameters are taken into consideration such as Body Mass Index (BMI), Mental health data, sleep time data as health monitoring data,and race and differ walkingas physical activities to evaluate performance of suggested method.Linear Discrimination Analysis (LDA) is used to dimensionality reductionof health monitoring data and then general health is predicted. Machine learning techniques and ensemble classifiers are applied on physical health activities, to predict physical health. Overall results of the suggested method areestimated in terms of accuracy, recall and F1-measure.Statistical and investigation results shows that the ensemble classifiers obtained the highest accuracy (99.15%), recall (99%) and F1-measure (99.5%) than all other methods.