Intelligent Predictor of Energy Expenditure with the Use of Patch-Type Sensor Module
This paper is concerned with an intelligent predictor of energy expenditure (EE) using a developed patch-type sensor module for wireless monitoring of heart rate (HR) and movement index (MI). For this purpose, an intelligent predictor is designed by an advanced linguistic model (LM) with interval pr...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2012-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/12/11/14382 |
id |
doaj-b3b394dd9310404b9cde922797cf2acf |
---|---|
record_format |
Article |
spelling |
doaj-b3b394dd9310404b9cde922797cf2acf2020-11-24T22:25:29ZengMDPI AGSensors1424-82202012-10-011211143821439610.3390/s121114382Intelligent Predictor of Energy Expenditure with the Use of Patch-Type Sensor ModuleMeina LiKeun-Chang KwakYoun-Tae KimThis paper is concerned with an intelligent predictor of energy expenditure (EE) using a developed patch-type sensor module for wireless monitoring of heart rate (HR) and movement index (MI). For this purpose, an intelligent predictor is designed by an advanced linguistic model (LM) with interval prediction based on fuzzy granulation that can be realized by context-based fuzzy c-means (CFCM) clustering. The system components consist of a sensor board, the rubber case, and the communication module with built-in analysis algorithm. This sensor is patched onto the user’s chest to obtain physiological data in indoor and outdoor environments. The prediction performance was demonstrated by root mean square error (RMSE). The prediction performance was obtained as the number of contexts and clusters increased from 2 to 6, respectively. Thirty participants were recruited from Chosun University to take part in this study. The data sets were recorded during normal walking, brisk walking, slow running, and jogging in an outdoor environment and treadmill running in an indoor environment, respectively. We randomly divided the data set into training (60%) and test data set (40%) in the normalized space during 10 iterations. The training data set is used for model construction, while the test set is used for model validation. The experimental results revealed that the prediction error on treadmill running simulation was improved by about 51% and 12% in comparison to conventional LM for training and checking data set, respectively.http://www.mdpi.com/1424-8220/12/11/14382intelligent predictorenergy expenditurepatch-type sensor moduleheart ratemovement indexlinguistic model |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Meina Li Keun-Chang Kwak Youn-Tae Kim |
spellingShingle |
Meina Li Keun-Chang Kwak Youn-Tae Kim Intelligent Predictor of Energy Expenditure with the Use of Patch-Type Sensor Module Sensors intelligent predictor energy expenditure patch-type sensor module heart rate movement index linguistic model |
author_facet |
Meina Li Keun-Chang Kwak Youn-Tae Kim |
author_sort |
Meina Li |
title |
Intelligent Predictor of Energy Expenditure with the Use of Patch-Type Sensor Module |
title_short |
Intelligent Predictor of Energy Expenditure with the Use of Patch-Type Sensor Module |
title_full |
Intelligent Predictor of Energy Expenditure with the Use of Patch-Type Sensor Module |
title_fullStr |
Intelligent Predictor of Energy Expenditure with the Use of Patch-Type Sensor Module |
title_full_unstemmed |
Intelligent Predictor of Energy Expenditure with the Use of Patch-Type Sensor Module |
title_sort |
intelligent predictor of energy expenditure with the use of patch-type sensor module |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2012-10-01 |
description |
This paper is concerned with an intelligent predictor of energy expenditure (EE) using a developed patch-type sensor module for wireless monitoring of heart rate (HR) and movement index (MI). For this purpose, an intelligent predictor is designed by an advanced linguistic model (LM) with interval prediction based on fuzzy granulation that can be realized by context-based fuzzy c-means (CFCM) clustering. The system components consist of a sensor board, the rubber case, and the communication module with built-in analysis algorithm. This sensor is patched onto the user’s chest to obtain physiological data in indoor and outdoor environments. The prediction performance was demonstrated by root mean square error (RMSE). The prediction performance was obtained as the number of contexts and clusters increased from 2 to 6, respectively. Thirty participants were recruited from Chosun University to take part in this study. The data sets were recorded during normal walking, brisk walking, slow running, and jogging in an outdoor environment and treadmill running in an indoor environment, respectively. We randomly divided the data set into training (60%) and test data set (40%) in the normalized space during 10 iterations. The training data set is used for model construction, while the test set is used for model validation. The experimental results revealed that the prediction error on treadmill running simulation was improved by about 51% and 12% in comparison to conventional LM for training and checking data set, respectively. |
topic |
intelligent predictor energy expenditure patch-type sensor module heart rate movement index linguistic model |
url |
http://www.mdpi.com/1424-8220/12/11/14382 |
work_keys_str_mv |
AT meinali intelligentpredictorofenergyexpenditurewiththeuseofpatchtypesensormodule AT keunchangkwak intelligentpredictorofenergyexpenditurewiththeuseofpatchtypesensormodule AT yountaekim intelligentpredictorofenergyexpenditurewiththeuseofpatchtypesensormodule |
_version_ |
1725757442951741440 |