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...
Guardado en:
Autores principales: | , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
MDPI AG
2021
|
Materias: | |
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 |