Cargando…
Statistical and Machine Learning Models for Classification of Human Wear and Delivery Days in Accelerometry Data
Accelerometers are increasingly being used in biomedical research, but the analysis of accelerometry data is often complicated by both the massive size of the datasets and the collection of unwanted data from the process of delivery to study participants. Current methods for removing delivery data i...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8069625/ https://www.ncbi.nlm.nih.gov/pubmed/33924388 http://dx.doi.org/10.3390/s21082726 |
_version_ | 1783683281099685888 |
---|---|
author | Moore, Ryan Archer, Kristin R. Choi, Leena |
author_facet | Moore, Ryan Archer, Kristin R. Choi, Leena |
author_sort | Moore, Ryan |
collection | PubMed |
description | Accelerometers are increasingly being used in biomedical research, but the analysis of accelerometry data is often complicated by both the massive size of the datasets and the collection of unwanted data from the process of delivery to study participants. Current methods for removing delivery data involve arduous manual review of dense datasets. We aimed to develop models for the classification of days in accelerometry data as activity from human wear or the delivery process. These models can be used to automate the cleaning of accelerometry datasets that are adulterated with activity from delivery. We developed statistical and machine learning models for the classification of accelerometry data in a supervised learning context using a large human activity and delivery labeled accelerometry dataset. Model performances were assessed and compared using Monte Carlo cross-validation. We found that a hybrid convolutional recurrent neural network performed best in the classification task with an F1 score of 0.960 but simpler models such as logistic regression and random forest also had excellent performance with F1 scores of 0.951 and 0.957, respectively. The best performing models and related data processing techniques are made publicly available in the R package, Physical Activity. |
format | Online Article Text |
id | pubmed-8069625 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-80696252021-04-26 Statistical and Machine Learning Models for Classification of Human Wear and Delivery Days in Accelerometry Data Moore, Ryan Archer, Kristin R. Choi, Leena Sensors (Basel) Article Accelerometers are increasingly being used in biomedical research, but the analysis of accelerometry data is often complicated by both the massive size of the datasets and the collection of unwanted data from the process of delivery to study participants. Current methods for removing delivery data involve arduous manual review of dense datasets. We aimed to develop models for the classification of days in accelerometry data as activity from human wear or the delivery process. These models can be used to automate the cleaning of accelerometry datasets that are adulterated with activity from delivery. We developed statistical and machine learning models for the classification of accelerometry data in a supervised learning context using a large human activity and delivery labeled accelerometry dataset. Model performances were assessed and compared using Monte Carlo cross-validation. We found that a hybrid convolutional recurrent neural network performed best in the classification task with an F1 score of 0.960 but simpler models such as logistic regression and random forest also had excellent performance with F1 scores of 0.951 and 0.957, respectively. The best performing models and related data processing techniques are made publicly available in the R package, Physical Activity. MDPI 2021-04-13 /pmc/articles/PMC8069625/ /pubmed/33924388 http://dx.doi.org/10.3390/s21082726 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Moore, Ryan Archer, Kristin R. Choi, Leena Statistical and Machine Learning Models for Classification of Human Wear and Delivery Days in Accelerometry Data |
title | Statistical and Machine Learning Models for Classification of Human Wear and Delivery Days in Accelerometry Data |
title_full | Statistical and Machine Learning Models for Classification of Human Wear and Delivery Days in Accelerometry Data |
title_fullStr | Statistical and Machine Learning Models for Classification of Human Wear and Delivery Days in Accelerometry Data |
title_full_unstemmed | Statistical and Machine Learning Models for Classification of Human Wear and Delivery Days in Accelerometry Data |
title_short | Statistical and Machine Learning Models for Classification of Human Wear and Delivery Days in Accelerometry Data |
title_sort | statistical and machine learning models for classification of human wear and delivery days in accelerometry data |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8069625/ https://www.ncbi.nlm.nih.gov/pubmed/33924388 http://dx.doi.org/10.3390/s21082726 |
work_keys_str_mv | AT mooreryan statisticalandmachinelearningmodelsforclassificationofhumanwearanddeliverydaysinaccelerometrydata AT archerkristinr statisticalandmachinelearningmodelsforclassificationofhumanwearanddeliverydaysinaccelerometrydata AT choileena statisticalandmachinelearningmodelsforclassificationofhumanwearanddeliverydaysinaccelerometrydata |