Cargando…

Effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models

Deep learning (DL) models are very useful for human activity recognition (HAR); these methods present better accuracy for HAR when compared to traditional, among other advantages. DL learns from unlabeled data and extracts features from raw data, as for the case of time-series acceleration. Sliding...

Descripción completa

Detalles Bibliográficos
Autores principales: Jaén-Vargas, Milagros, Reyes Leiva, Karla Miriam, Fernandes, Francisco, Barroso Gonçalves, Sérgio, Tavares Silva, Miguel, Lopes, Daniel Simões, Serrano Olmedo, José Javier
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9455026/
https://www.ncbi.nlm.nih.gov/pubmed/36091986
http://dx.doi.org/10.7717/peerj-cs.1052
_version_ 1784785491603750912
author Jaén-Vargas, Milagros
Reyes Leiva, Karla Miriam
Fernandes, Francisco
Barroso Gonçalves, Sérgio
Tavares Silva, Miguel
Lopes, Daniel Simões
Serrano Olmedo, José Javier
author_facet Jaén-Vargas, Milagros
Reyes Leiva, Karla Miriam
Fernandes, Francisco
Barroso Gonçalves, Sérgio
Tavares Silva, Miguel
Lopes, Daniel Simões
Serrano Olmedo, José Javier
author_sort Jaén-Vargas, Milagros
collection PubMed
description Deep learning (DL) models are very useful for human activity recognition (HAR); these methods present better accuracy for HAR when compared to traditional, among other advantages. DL learns from unlabeled data and extracts features from raw data, as for the case of time-series acceleration. Sliding windows is a feature extraction technique. When used for preprocessing time-series data, it provides an improvement in accuracy, latency, and cost of processing. The time and cost of preprocessing can be beneficial especially if the window size is small, but how small can this window be to keep good accuracy? The objective of this research was to analyze the performance of four DL models: a simple deep neural network (DNN); a convolutional neural network (CNN); a long short-term memory network (LSTM); and a hybrid model (CNN-LSTM), when variating the sliding window size using fixed overlapped windows to identify an optimal window size for HAR. We compare the effects in two acceleration sources’: wearable inertial measurement unit sensors (IMU) and motion caption systems (MOCAP). Moreover, short sliding windows of sizes 5, 10, 15, 20, and 25 frames to long ones of sizes 50, 75, 100, and 200 frames were compared. The models were fed using raw acceleration data acquired in experimental conditions for three activities: walking, sit-to-stand, and squatting. Results show that the most optimal window is from 20–25 frames (0.20–0.25s) for both sources, providing an accuracy of 99,07% and F1-score of 87,08% in the (CNN-LSTM) using the wearable sensors data, and accuracy of 98,8% and F1-score of 82,80% using MOCAP data; similar accurate results were obtained with the LSTM model. There is almost no difference in accuracy in larger frames (100, 200). However, smaller windows present a decrease in the F1-score. In regard to inference time, data with a sliding window of 20 frames can be preprocessed around 4x (LSTM) and 2x (CNN-LSTM) times faster than data using 100 frames.
format Online
Article
Text
id pubmed-9455026
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-94550262022-09-09 Effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models Jaén-Vargas, Milagros Reyes Leiva, Karla Miriam Fernandes, Francisco Barroso Gonçalves, Sérgio Tavares Silva, Miguel Lopes, Daniel Simões Serrano Olmedo, José Javier PeerJ Comput Sci Bioinformatics Deep learning (DL) models are very useful for human activity recognition (HAR); these methods present better accuracy for HAR when compared to traditional, among other advantages. DL learns from unlabeled data and extracts features from raw data, as for the case of time-series acceleration. Sliding windows is a feature extraction technique. When used for preprocessing time-series data, it provides an improvement in accuracy, latency, and cost of processing. The time and cost of preprocessing can be beneficial especially if the window size is small, but how small can this window be to keep good accuracy? The objective of this research was to analyze the performance of four DL models: a simple deep neural network (DNN); a convolutional neural network (CNN); a long short-term memory network (LSTM); and a hybrid model (CNN-LSTM), when variating the sliding window size using fixed overlapped windows to identify an optimal window size for HAR. We compare the effects in two acceleration sources’: wearable inertial measurement unit sensors (IMU) and motion caption systems (MOCAP). Moreover, short sliding windows of sizes 5, 10, 15, 20, and 25 frames to long ones of sizes 50, 75, 100, and 200 frames were compared. The models were fed using raw acceleration data acquired in experimental conditions for three activities: walking, sit-to-stand, and squatting. Results show that the most optimal window is from 20–25 frames (0.20–0.25s) for both sources, providing an accuracy of 99,07% and F1-score of 87,08% in the (CNN-LSTM) using the wearable sensors data, and accuracy of 98,8% and F1-score of 82,80% using MOCAP data; similar accurate results were obtained with the LSTM model. There is almost no difference in accuracy in larger frames (100, 200). However, smaller windows present a decrease in the F1-score. In regard to inference time, data with a sliding window of 20 frames can be preprocessed around 4x (LSTM) and 2x (CNN-LSTM) times faster than data using 100 frames. PeerJ Inc. 2022-08-08 /pmc/articles/PMC9455026/ /pubmed/36091986 http://dx.doi.org/10.7717/peerj-cs.1052 Text en ©2022 Jaén-Vargas et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Bioinformatics
Jaén-Vargas, Milagros
Reyes Leiva, Karla Miriam
Fernandes, Francisco
Barroso Gonçalves, Sérgio
Tavares Silva, Miguel
Lopes, Daniel Simões
Serrano Olmedo, José Javier
Effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models
title Effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models
title_full Effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models
title_fullStr Effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models
title_full_unstemmed Effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models
title_short Effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models
title_sort effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models
topic Bioinformatics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9455026/
https://www.ncbi.nlm.nih.gov/pubmed/36091986
http://dx.doi.org/10.7717/peerj-cs.1052
work_keys_str_mv AT jaenvargasmilagros effectsofslidingwindowvariationintheperformanceofaccelerationbasedhumanactivityrecognitionusingdeeplearningmodels
AT reyesleivakarlamiriam effectsofslidingwindowvariationintheperformanceofaccelerationbasedhumanactivityrecognitionusingdeeplearningmodels
AT fernandesfrancisco effectsofslidingwindowvariationintheperformanceofaccelerationbasedhumanactivityrecognitionusingdeeplearningmodels
AT barrosogoncalvessergio effectsofslidingwindowvariationintheperformanceofaccelerationbasedhumanactivityrecognitionusingdeeplearningmodels
AT tavaressilvamiguel effectsofslidingwindowvariationintheperformanceofaccelerationbasedhumanactivityrecognitionusingdeeplearningmodels
AT lopesdanielsimoes effectsofslidingwindowvariationintheperformanceofaccelerationbasedhumanactivityrecognitionusingdeeplearningmodels
AT serranoolmedojosejavier effectsofslidingwindowvariationintheperformanceofaccelerationbasedhumanactivityrecognitionusingdeeplearningmodels