Back to Search
Start Over
Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis
- Source :
- Sensors, Vol 20, Iss 5, p 1523 (2020), Sensors (Basel, Switzerland), Sensors, Volume 20, Issue 5
- Publication Year :
- 2020
- Publisher :
- MDPI AG, 2020.
-
Abstract
- 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, k-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 &lang<br />3 , 8 &rang<br />and &lang<br />8 , 15 &rang<br />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.
- Subjects :
- Support Vector Machine
Computer science
Computational intelligence
02 engineering and technology
Accelerometer
motion monitoring
lcsh:Chemical technology
Biochemistry
Signal
Analytical Chemistry
Pattern Recognition, Automated
0302 clinical medicine
Heart Rate
Accelerometry
computational intelligence
0202 electrical engineering, electronic engineering, information engineering
lcsh:TP1-1185
Instrumentation
Artificial neural network
Signal Processing, Computer-Assisted
Atomic and Molecular Physics, and Optics
Power (physics)
machine learning
classification
020201 artificial intelligence & image processing
Algorithms
Motion analysis
accelerometers
multimodal signal analysis
Fitness Trackers
Article
03 medical and health sciences
Motion
Heart rate
Humans
Electrical and Electronic Engineering
Exercise
Models, Statistical
business.industry
Reproducibility of Results
Pattern recognition
Bayes Theorem
030229 sport sciences
Bicycling
Mobile phone
Artificial intelligence
Neural Networks, Computer
business
Cell Phone
Software
Subjects
Details
- Language :
- English
- ISSN :
- 14248220
- Volume :
- 20
- Issue :
- 5
- Database :
- OpenAIRE
- Journal :
- Sensors
- Accession number :
- edsair.doi.dedup.....931551e8eb61b4718e489ce86834f4d1