Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis
Motion analysis is an important topic in the monitoring of physical activities and recognition of neurological disorders. The present paper is devoted to motion assessment using accelerometers inside mobile phones located at selected body positions and the records of changes in the heart rate during...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/5/1523 |
| _version_ | 1811187245587103744 |
|---|---|
| author | Hana Charvátová Aleš Procházka Oldřich Vyšata |
| author_facet | Hana Charvátová Aleš Procházka Oldřich Vyšata |
| author_sort | Hana Charvátová |
| collection | DOAJ |
| description | Motion analysis is an important topic in the monitoring of physical activities and recognition of neurological disorders. The present paper is devoted to motion assessment using accelerometers inside mobile phones located at selected body positions and the records of changes in the heart rate during cycling, under different body loads. Acquired data include 1293 signal segments recorded by the mobile phone and the Garmin device for uphill and downhill cycling. The proposed method is based upon digital processing of the heart rate and the mean power in different frequency bands of accelerometric data. The classification of the resulting features was performed by the support vector machine, Bayesian methods, <i>k</i>-nearest neighbor method, and neural networks. The proposed criterion is then used to find the best positions for the sensors with the highest discrimination abilities. The results suggest the sensors be positioned on the spine for the classification of uphill and downhill cycling, yielding an accuracy of 96.5% and a cross-validation error of 0.04 evaluated by a two-layer neural network system for features based on the mean power in the frequency bands <inline-formula> <math display="inline"> <semantics> <mrow> <mo>〈</mo> <mn>3</mn> <mo>,</mo> <mn>8</mn> <mo>〉</mo> </mrow> </semantics> </math> </inline-formula> and <inline-formula> <math display="inline"> <semantics> <mrow> <mo>〈</mo> <mn>8</mn> <mo>,</mo> <mn>15</mn> <mo>〉</mo> </mrow> </semantics> </math> </inline-formula> Hz. This paper shows the possibility of increasing this accuracy to 98.3% by the use of more features and the influence of appropriate sensor positioning for motion monitoring and classification. |
| first_indexed | 2024-04-11T13:58:58Z |
| format | Article |
| id | doaj.art-23ffee0480c54c11aaf5eeaa0edf3e8a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T13:58:58Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-23ffee0480c54c11aaf5eeaa0edf3e8a2022-12-22T04:20:10ZengMDPI AGSensors1424-82202020-03-01205152310.3390/s20051523s20051523Motion Assessment for Accelerometric and Heart Rate Cycling Data AnalysisHana Charvátová0Aleš Procházka1Oldřich Vyšata2Faculty of Applied Informatics, Tomas Bata University in Zlín, 760 01 Zlín, Czech RepublicDepartment of Computing and Control Engineering, University of Chemistry and Technology in Prague, 166 28 Prague 6, Czech RepublicDepartment of Neurology, Faculty of Medicine in Hradec Králové, Charles University, 500 05 Hradec Králové, Czech RepublicMotion analysis is an important topic in the monitoring of physical activities and recognition of neurological disorders. The present paper is devoted to motion assessment using accelerometers inside mobile phones located at selected body positions and the records of changes in the heart rate during cycling, under different body loads. Acquired data include 1293 signal segments recorded by the mobile phone and the Garmin device for uphill and downhill cycling. The proposed method is based upon digital processing of the heart rate and the mean power in different frequency bands of accelerometric data. The classification of the resulting features was performed by the support vector machine, Bayesian methods, <i>k</i>-nearest neighbor method, and neural networks. The proposed criterion is then used to find the best positions for the sensors with the highest discrimination abilities. The results suggest the sensors be positioned on the spine for the classification of uphill and downhill cycling, yielding an accuracy of 96.5% and a cross-validation error of 0.04 evaluated by a two-layer neural network system for features based on the mean power in the frequency bands <inline-formula> <math display="inline"> <semantics> <mrow> <mo>〈</mo> <mn>3</mn> <mo>,</mo> <mn>8</mn> <mo>〉</mo> </mrow> </semantics> </math> </inline-formula> and <inline-formula> <math display="inline"> <semantics> <mrow> <mo>〈</mo> <mn>8</mn> <mo>,</mo> <mn>15</mn> <mo>〉</mo> </mrow> </semantics> </math> </inline-formula> Hz. This paper shows the possibility of increasing this accuracy to 98.3% by the use of more features and the influence of appropriate sensor positioning for motion monitoring and classification.https://www.mdpi.com/1424-8220/20/5/1523multimodal signal analysiscomputational intelligencemachine learningmotion monitoringaccelerometersclassification |
| spellingShingle | Hana Charvátová Aleš Procházka Oldřich Vyšata Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis Sensors multimodal signal analysis computational intelligence machine learning motion monitoring accelerometers classification |
| title | Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis |
| title_full | Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis |
| title_fullStr | Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis |
| title_full_unstemmed | Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis |
| title_short | Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis |
| title_sort | motion assessment for accelerometric and heart rate cycling data analysis |
| topic | multimodal signal analysis computational intelligence machine learning motion monitoring accelerometers classification |
| url | https://www.mdpi.com/1424-8220/20/5/1523 |
| work_keys_str_mv | AT hanacharvatova motionassessmentforaccelerometricandheartratecyclingdataanalysis AT alesprochazka motionassessmentforaccelerometricandheartratecyclingdataanalysis AT oldrichvysata motionassessmentforaccelerometricandheartratecyclingdataanalysis |