Human Interaction Recognition Based on Deep Learning and HMM
This paper proposes a recognition method that combines deep learning with traditional hidden Markov model (HMM) with the aim of improving the recognition accuracy of interaction. First, to construct the classification model, the optimized ALexNet convolutional neural network is used to extract the b...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8892463/ |
id |
doaj-4355596676e546438340b44518eeb931 |
---|---|
record_format |
Article |
spelling |
doaj-4355596676e546438340b44518eeb9312021-03-30T00:37:07ZengIEEEIEEE Access2169-35362019-01-01716112316113010.1109/ACCESS.2019.29519378892463Human Interaction Recognition Based on Deep Learning and HMMAn Gong0Chen Chen1https://orcid.org/0000-0002-7172-6015Mengtang Peng2College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, ChinaCollege of Computer Science and Technology, China University of Petroleum (East China), Qingdao, ChinaCollege of Information Science and Engineering, Central South University, Changsha, ChinaThis paper proposes a recognition method that combines deep learning with traditional hidden Markov model (HMM) with the aim of improving the recognition accuracy of interaction. First, to construct the classification model, the optimized ALexNet convolutional neural network is used to extract the behavior features, followed by the extraction of features that are used to train the long short-term memory (LSTM) network using the Softmax method. Finally, the particle swarm optimization algorithm is used to fuse the classification results with the traditional HMM classification results so that a hybrid classification model is established to obtain the final behavior recognition result. By conducting experiments on the UT-interaction dataset (six types of interaction behavior), the experimental results show that the hybrid model has higher recognition accuracy than other classical methods.https://ieeexplore.ieee.org/document/8892463/Interaction recognitionconvolutional neural networks (CNNs)long short-term memory (LSTM)hidden Markov model (HMM) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
An Gong Chen Chen Mengtang Peng |
spellingShingle |
An Gong Chen Chen Mengtang Peng Human Interaction Recognition Based on Deep Learning and HMM IEEE Access Interaction recognition convolutional neural networks (CNNs) long short-term memory (LSTM) hidden Markov model (HMM) |
author_facet |
An Gong Chen Chen Mengtang Peng |
author_sort |
An Gong |
title |
Human Interaction Recognition Based on Deep Learning and HMM |
title_short |
Human Interaction Recognition Based on Deep Learning and HMM |
title_full |
Human Interaction Recognition Based on Deep Learning and HMM |
title_fullStr |
Human Interaction Recognition Based on Deep Learning and HMM |
title_full_unstemmed |
Human Interaction Recognition Based on Deep Learning and HMM |
title_sort |
human interaction recognition based on deep learning and hmm |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
This paper proposes a recognition method that combines deep learning with traditional hidden Markov model (HMM) with the aim of improving the recognition accuracy of interaction. First, to construct the classification model, the optimized ALexNet convolutional neural network is used to extract the behavior features, followed by the extraction of features that are used to train the long short-term memory (LSTM) network using the Softmax method. Finally, the particle swarm optimization algorithm is used to fuse the classification results with the traditional HMM classification results so that a hybrid classification model is established to obtain the final behavior recognition result. By conducting experiments on the UT-interaction dataset (six types of interaction behavior), the experimental results show that the hybrid model has higher recognition accuracy than other classical methods. |
topic |
Interaction recognition convolutional neural networks (CNNs) long short-term memory (LSTM) hidden Markov model (HMM) |
url |
https://ieeexplore.ieee.org/document/8892463/ |
work_keys_str_mv |
AT angong humaninteractionrecognitionbasedondeeplearningandhmm AT chenchen humaninteractionrecognitionbasedondeeplearningandhmm AT mengtangpeng humaninteractionrecognitionbasedondeeplearningandhmm |
_version_ |
1724188114858016768 |