Cargando…

An Efficient and Lightweight Deep Learning Model for Human Activity Recognition Using Smartphones

Traditional pattern recognition approaches have gained a lot of popularity. However, these are largely dependent upon manual feature extraction, which makes the generalized model obscure. The sequences of accelerometer data recorded can be classified by specialized smartphones into well known moveme...

Descripción completa

Detalles Bibliográficos
Autores principales: Ankita, Rani, Shalli, Babbar, Himanshi, Coleman, Sonya, Singh, Aman, Aljahdali, Hani Moaiteq
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8199714/
https://www.ncbi.nlm.nih.gov/pubmed/34199559
http://dx.doi.org/10.3390/s21113845
_version_ 1783707442214862848
author Ankita,
Rani, Shalli
Babbar, Himanshi
Coleman, Sonya
Singh, Aman
Aljahdali, Hani Moaiteq
author_facet Ankita,
Rani, Shalli
Babbar, Himanshi
Coleman, Sonya
Singh, Aman
Aljahdali, Hani Moaiteq
author_sort Ankita,
collection PubMed
description Traditional pattern recognition approaches have gained a lot of popularity. However, these are largely dependent upon manual feature extraction, which makes the generalized model obscure. The sequences of accelerometer data recorded can be classified by specialized smartphones into well known movements that can be done with human activity recognition. With the high success and wide adaptation of deep learning approaches for the recognition of human activities, these techniques are widely used in wearable devices and smartphones to recognize the human activities. In this paper, convolutional layers are combined with long short-term memory (LSTM), along with the deep learning neural network for human activities recognition (HAR). The proposed model extracts the features in an automated way and categorizes them with some model attributes. In general, LSTM is alternative form of recurrent neural network (RNN) which is famous for temporal sequences’ processing. In the proposed architecture, a dataset of UCI-HAR for Samsung Galaxy S2 is used for various human activities. The CNN classifier, which should be taken single, and LSTM models should be taken in series and take the feed data. For each input, the CNN model is applied, and each input image’s output is transferred to the LSTM classifier as a time step. The number of filter maps for mapping of the various portions of image is the most important hyperparameter used. Transformation on the basis of observations takes place by using Gaussian standardization. CNN-LSTM, a proposed model, is an efficient and lightweight model that has shown high robustness and better activity detection capability than traditional algorithms by providing the accuracy of 97.89%.
format Online
Article
Text
id pubmed-8199714
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-81997142021-06-14 An Efficient and Lightweight Deep Learning Model for Human Activity Recognition Using Smartphones Ankita, Rani, Shalli Babbar, Himanshi Coleman, Sonya Singh, Aman Aljahdali, Hani Moaiteq Sensors (Basel) Article Traditional pattern recognition approaches have gained a lot of popularity. However, these are largely dependent upon manual feature extraction, which makes the generalized model obscure. The sequences of accelerometer data recorded can be classified by specialized smartphones into well known movements that can be done with human activity recognition. With the high success and wide adaptation of deep learning approaches for the recognition of human activities, these techniques are widely used in wearable devices and smartphones to recognize the human activities. In this paper, convolutional layers are combined with long short-term memory (LSTM), along with the deep learning neural network for human activities recognition (HAR). The proposed model extracts the features in an automated way and categorizes them with some model attributes. In general, LSTM is alternative form of recurrent neural network (RNN) which is famous for temporal sequences’ processing. In the proposed architecture, a dataset of UCI-HAR for Samsung Galaxy S2 is used for various human activities. The CNN classifier, which should be taken single, and LSTM models should be taken in series and take the feed data. For each input, the CNN model is applied, and each input image’s output is transferred to the LSTM classifier as a time step. The number of filter maps for mapping of the various portions of image is the most important hyperparameter used. Transformation on the basis of observations takes place by using Gaussian standardization. CNN-LSTM, a proposed model, is an efficient and lightweight model that has shown high robustness and better activity detection capability than traditional algorithms by providing the accuracy of 97.89%. MDPI 2021-06-02 /pmc/articles/PMC8199714/ /pubmed/34199559 http://dx.doi.org/10.3390/s21113845 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
Ankita,
Rani, Shalli
Babbar, Himanshi
Coleman, Sonya
Singh, Aman
Aljahdali, Hani Moaiteq
An Efficient and Lightweight Deep Learning Model for Human Activity Recognition Using Smartphones
title An Efficient and Lightweight Deep Learning Model for Human Activity Recognition Using Smartphones
title_full An Efficient and Lightweight Deep Learning Model for Human Activity Recognition Using Smartphones
title_fullStr An Efficient and Lightweight Deep Learning Model for Human Activity Recognition Using Smartphones
title_full_unstemmed An Efficient and Lightweight Deep Learning Model for Human Activity Recognition Using Smartphones
title_short An Efficient and Lightweight Deep Learning Model for Human Activity Recognition Using Smartphones
title_sort efficient and lightweight deep learning model for human activity recognition using smartphones
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8199714/
https://www.ncbi.nlm.nih.gov/pubmed/34199559
http://dx.doi.org/10.3390/s21113845
work_keys_str_mv AT ankita anefficientandlightweightdeeplearningmodelforhumanactivityrecognitionusingsmartphones
AT ranishalli anefficientandlightweightdeeplearningmodelforhumanactivityrecognitionusingsmartphones
AT babbarhimanshi anefficientandlightweightdeeplearningmodelforhumanactivityrecognitionusingsmartphones
AT colemansonya anefficientandlightweightdeeplearningmodelforhumanactivityrecognitionusingsmartphones
AT singhaman anefficientandlightweightdeeplearningmodelforhumanactivityrecognitionusingsmartphones
AT aljahdalihanimoaiteq anefficientandlightweightdeeplearningmodelforhumanactivityrecognitionusingsmartphones
AT ankita efficientandlightweightdeeplearningmodelforhumanactivityrecognitionusingsmartphones
AT ranishalli efficientandlightweightdeeplearningmodelforhumanactivityrecognitionusingsmartphones
AT babbarhimanshi efficientandlightweightdeeplearningmodelforhumanactivityrecognitionusingsmartphones
AT colemansonya efficientandlightweightdeeplearningmodelforhumanactivityrecognitionusingsmartphones
AT singhaman efficientandlightweightdeeplearningmodelforhumanactivityrecognitionusingsmartphones
AT aljahdalihanimoaiteq efficientandlightweightdeeplearningmodelforhumanactivityrecognitionusingsmartphones