Cargando…

Convolutional Neural Network Bootstrapped by Dynamic Segmentation and Stigmergy-Based Encoding for Real-Time Human Activity Recognition in Smart Homes

Recently, deep learning (DL) approaches have been extensively employed to recognize human activities in smart buildings, which greatly broaden the scope of applications in this field. Convolutional neural networks (CNN), well known for feature extraction and activity classification, have been applie...

Descripción completa

Detalles Bibliográficos
Autores principales: Najeh, Houda, Lohr, Christophe, Leduc, Benoit
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9964787/
https://www.ncbi.nlm.nih.gov/pubmed/36850567
http://dx.doi.org/10.3390/s23041969
_version_ 1784896595035160576
author Najeh, Houda
Lohr, Christophe
Leduc, Benoit
author_facet Najeh, Houda
Lohr, Christophe
Leduc, Benoit
author_sort Najeh, Houda
collection PubMed
description Recently, deep learning (DL) approaches have been extensively employed to recognize human activities in smart buildings, which greatly broaden the scope of applications in this field. Convolutional neural networks (CNN), well known for feature extraction and activity classification, have been applied for estimating human activities. However, most CNN-based techniques usually focus on divided sequences associated to activities, since many real-world employments require information about human activities in real time. In this work, an online human activity recognition (HAR) framework on streaming sensor is proposed. The methodology incorporates real-time dynamic segmentation, stigmergy-based encoding, and classification with a CNN2D. Dynamic segmentation decides if two succeeding events belong to the same activity segment or not. Then, because a CNN2D requires a multi-dimensional format in input, stigmergic track encoding is adopted to build encoded features in a multi-dimensional format. It adopts the directed weighted network (DWN) that takes into account the human spatio-temporal tracks with a requirement of overlapping activities. It represents a matrix that describes an activity segment. Once the DWN for each activity segment is determined, a CNN2D with a DWN in input is adopted to classify activities. The proposed approach is applied to a real case study: the “Aruba” dataset from the CASAS database.
format Online
Article
Text
id pubmed-9964787
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-99647872023-02-26 Convolutional Neural Network Bootstrapped by Dynamic Segmentation and Stigmergy-Based Encoding for Real-Time Human Activity Recognition in Smart Homes Najeh, Houda Lohr, Christophe Leduc, Benoit Sensors (Basel) Article Recently, deep learning (DL) approaches have been extensively employed to recognize human activities in smart buildings, which greatly broaden the scope of applications in this field. Convolutional neural networks (CNN), well known for feature extraction and activity classification, have been applied for estimating human activities. However, most CNN-based techniques usually focus on divided sequences associated to activities, since many real-world employments require information about human activities in real time. In this work, an online human activity recognition (HAR) framework on streaming sensor is proposed. The methodology incorporates real-time dynamic segmentation, stigmergy-based encoding, and classification with a CNN2D. Dynamic segmentation decides if two succeeding events belong to the same activity segment or not. Then, because a CNN2D requires a multi-dimensional format in input, stigmergic track encoding is adopted to build encoded features in a multi-dimensional format. It adopts the directed weighted network (DWN) that takes into account the human spatio-temporal tracks with a requirement of overlapping activities. It represents a matrix that describes an activity segment. Once the DWN for each activity segment is determined, a CNN2D with a DWN in input is adopted to classify activities. The proposed approach is applied to a real case study: the “Aruba” dataset from the CASAS database. MDPI 2023-02-09 /pmc/articles/PMC9964787/ /pubmed/36850567 http://dx.doi.org/10.3390/s23041969 Text en © 2023 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
Najeh, Houda
Lohr, Christophe
Leduc, Benoit
Convolutional Neural Network Bootstrapped by Dynamic Segmentation and Stigmergy-Based Encoding for Real-Time Human Activity Recognition in Smart Homes
title Convolutional Neural Network Bootstrapped by Dynamic Segmentation and Stigmergy-Based Encoding for Real-Time Human Activity Recognition in Smart Homes
title_full Convolutional Neural Network Bootstrapped by Dynamic Segmentation and Stigmergy-Based Encoding for Real-Time Human Activity Recognition in Smart Homes
title_fullStr Convolutional Neural Network Bootstrapped by Dynamic Segmentation and Stigmergy-Based Encoding for Real-Time Human Activity Recognition in Smart Homes
title_full_unstemmed Convolutional Neural Network Bootstrapped by Dynamic Segmentation and Stigmergy-Based Encoding for Real-Time Human Activity Recognition in Smart Homes
title_short Convolutional Neural Network Bootstrapped by Dynamic Segmentation and Stigmergy-Based Encoding for Real-Time Human Activity Recognition in Smart Homes
title_sort convolutional neural network bootstrapped by dynamic segmentation and stigmergy-based encoding for real-time human activity recognition in smart homes
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9964787/
https://www.ncbi.nlm.nih.gov/pubmed/36850567
http://dx.doi.org/10.3390/s23041969
work_keys_str_mv AT najehhouda convolutionalneuralnetworkbootstrappedbydynamicsegmentationandstigmergybasedencodingforrealtimehumanactivityrecognitioninsmarthomes
AT lohrchristophe convolutionalneuralnetworkbootstrappedbydynamicsegmentationandstigmergybasedencodingforrealtimehumanactivityrecognitioninsmarthomes
AT leducbenoit convolutionalneuralnetworkbootstrappedbydynamicsegmentationandstigmergybasedencodingforrealtimehumanactivityrecognitioninsmarthomes