Sensor-Based Human Activity Recognition Using Adaptive Class Hierarchy

In sensor-based human activity recognition, many methods based on convolutional neural networks (CNNs) have been proposed. In the typical CNN-based activity recognition model, each class is treated independently of others. However, actual activity classes often have hierarchical relationships. It is...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kazuma Kondo, Tatsuhito Hasegawa
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	human activity recognition class hierarchy deep learning Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/046a63cd506442e79e4b9e3760ba9eab
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:046a63cd506442e79e4b9e3760ba9eab
record_format	dspace
spelling	oai:doaj.org-article:046a63cd506442e79e4b9e3760ba9eab2021-11-25T18:58:57ZSensor-Based Human Activity Recognition Using Adaptive Class Hierarchy10.3390/s212277431424-8220https://doaj.org/article/046a63cd506442e79e4b9e3760ba9eab2021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7743https://doaj.org/toc/1424-8220In sensor-based human activity recognition, many methods based on convolutional neural networks (CNNs) have been proposed. In the typical CNN-based activity recognition model, each class is treated independently of others. However, actual activity classes often have hierarchical relationships. It is important to consider an activity recognition model that uses the hierarchical relationship among classes to improve recognition performance. In image recognition, branch CNNs (B-CNNs) have been proposed for classification using class hierarchies. B-CNNs can easily perform classification using hand-crafted class hierarchies, but it is difficult to manually design an appropriate class hierarchy when the number of classes is large or there is little prior knowledge. Therefore, in our study, we propose a class hierarchy-adaptive B-CNN, which adds a method to the B-CNN for automatically constructing class hierarchies. Our method constructs the class hierarchy from training data automatically to effectively train the B-CNN without prior knowledge. We evaluated our method on several benchmark datasets for activity recognition. As a result, our method outperformed standard CNN models without considering the hierarchical relationship among classes. In addition, we confirmed that our method has performance comparable to a B-CNN model with a class hierarchy based on human prior knowledge.Kazuma KondoTatsuhito HasegawaMDPI AGarticlehuman activity recognitionclass hierarchydeep learningChemical technologyTP1-1185ENSensors, Vol 21, Iss 7743, p 7743 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	human activity recognition class hierarchy deep learning Chemical technology TP1-1185
spellingShingle	human activity recognition class hierarchy deep learning Chemical technology TP1-1185 Kazuma Kondo Tatsuhito Hasegawa Sensor-Based Human Activity Recognition Using Adaptive Class Hierarchy
description	In sensor-based human activity recognition, many methods based on convolutional neural networks (CNNs) have been proposed. In the typical CNN-based activity recognition model, each class is treated independently of others. However, actual activity classes often have hierarchical relationships. It is important to consider an activity recognition model that uses the hierarchical relationship among classes to improve recognition performance. In image recognition, branch CNNs (B-CNNs) have been proposed for classification using class hierarchies. B-CNNs can easily perform classification using hand-crafted class hierarchies, but it is difficult to manually design an appropriate class hierarchy when the number of classes is large or there is little prior knowledge. Therefore, in our study, we propose a class hierarchy-adaptive B-CNN, which adds a method to the B-CNN for automatically constructing class hierarchies. Our method constructs the class hierarchy from training data automatically to effectively train the B-CNN without prior knowledge. We evaluated our method on several benchmark datasets for activity recognition. As a result, our method outperformed standard CNN models without considering the hierarchical relationship among classes. In addition, we confirmed that our method has performance comparable to a B-CNN model with a class hierarchy based on human prior knowledge.
format	article
author	Kazuma Kondo Tatsuhito Hasegawa
author_facet	Kazuma Kondo Tatsuhito Hasegawa
author_sort	Kazuma Kondo
title	Sensor-Based Human Activity Recognition Using Adaptive Class Hierarchy
title_short	Sensor-Based Human Activity Recognition Using Adaptive Class Hierarchy
title_full	Sensor-Based Human Activity Recognition Using Adaptive Class Hierarchy
title_fullStr	Sensor-Based Human Activity Recognition Using Adaptive Class Hierarchy
title_full_unstemmed	Sensor-Based Human Activity Recognition Using Adaptive Class Hierarchy
title_sort	sensor-based human activity recognition using adaptive class hierarchy
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/046a63cd506442e79e4b9e3760ba9eab
work_keys_str_mv	AT kazumakondo sensorbasedhumanactivityrecognitionusingadaptiveclasshierarchy AT tatsuhitohasegawa sensorbasedhumanactivityrecognitionusingadaptiveclasshierarchy
_version_	1718410443900321792

Sensor-Based Human Activity Recognition Using Adaptive Class Hierarchy

Ejemplares similares