Intelligent system for identification of wheelchair user's posture using machine learning techniques. Rosero-Montalvo, P., D., Peluffo-Ordonez, D., H., Lopez Batista, V., F., Serrano, J., & Rosero, E., A. IEEE Sensors Journal, 2019.
Intelligent system for identification of wheelchair user's posture using machine learning techniques [link]Website  doi  abstract   bibtex   12 downloads  
This paper presents an intelligent system aimed at detecting a person's posture when sitting in a wheelchair. The main use of the proposed system is to warn an improper posture to prevent major health issues. A network of sensors is used to collect data that are analyzed through a scheme involving the following stages: Selection of prototypes using condensed nearest neighborhood rule (CNN), data balancing with the Kennard-Stone algorithm, and reduction of dimensionality through principal component analysis. In doing so, acquired data can be both stored and processed into a micro controller. Finally, to carry out the posture classification over balanced, pre-processed data, and the K-nearest neighbors algorithm is used. It turns to be an intelligent system reaching a good tradeoff between the necessary amount of data and performance is accomplished. As a remarkable result, the amount of required data for training is significantly reduced while an admissible classification performance is achieved being a suitable trade given the device conditions.
@article{
 title = {Intelligent system for identification of wheelchair user's posture using machine learning techniques},
 type = {article},
 year = {2019},
 keywords = {Embedded system,K-nearest neighbors,Kennard-stone,posture detection,principal component analysis},
 websites = {https://ieeexplore.ieee.org/document/8565996},
 id = {ad6726f2-4cd9-328b-8b88-a644ce0b636c},
 created = {2022-01-26T03:00:55.245Z},
 file_attached = {false},
 profile_id = {aba9653c-d139-3f95-aad8-969c487ed2f3},
 group_id = {b9022d50-068c-31b4-9174-ebfaaf9ee57b},
 last_modified = {2022-01-26T03:00:55.245Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Rosero-Montalvo2019c},
 private_publication = {false},
 abstract = {This paper presents an intelligent system aimed at detecting a person's posture when sitting in a wheelchair. The main use of the proposed system is to warn an improper posture to prevent major health issues. A network of sensors is used to collect data that are analyzed through a scheme involving the following stages: Selection of prototypes using condensed nearest neighborhood rule (CNN), data balancing with the Kennard-Stone algorithm, and reduction of dimensionality through principal component analysis. In doing so, acquired data can be both stored and processed into a micro controller. Finally, to carry out the posture classification over balanced, pre-processed data, and the K-nearest neighbors algorithm is used. It turns to be an intelligent system reaching a good tradeoff between the necessary amount of data and performance is accomplished. As a remarkable result, the amount of required data for training is significantly reduced while an admissible classification performance is achieved being a suitable trade given the device conditions.},
 bibtype = {article},
 author = {Rosero-Montalvo, Paul D. and Peluffo-Ordonez, Diego Hernn and Lopez Batista, Vivian Felix and Serrano, Jorge and Rosero, Edwin A.},
 doi = {10.1109/JSEN.2018.2885323},
 journal = {IEEE Sensors Journal}
}

Downloads: 12