Proposing a Fuzzy Soft‐max‐based classifier in a hybrid deep learning architecture for human activity recognition
Abstract Human Activity Recognition (HAR) is the process of identifying and analysing activities performed by a person (or persons). This paper proposes an efficient HAR system based on wearable sensors that uses deep learning techniques. The proposed HAR takes the advantage of staking Convolutional...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi-IET
2022-03-01
|
| Series: | IET Biometrics |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/bme2.12066 |
| _version_ | 1797430542602338304 |
|---|---|
| author | Reza Shakerian Meisam Yadollahzadeh‐Tabari Seyed Yaser Bozorgi Rad |
| author_facet | Reza Shakerian Meisam Yadollahzadeh‐Tabari Seyed Yaser Bozorgi Rad |
| author_sort | Reza Shakerian |
| collection | DOAJ |
| description | Abstract Human Activity Recognition (HAR) is the process of identifying and analysing activities performed by a person (or persons). This paper proposes an efficient HAR system based on wearable sensors that uses deep learning techniques. The proposed HAR takes the advantage of staking Convolutional Neural Network and Long Short‐Term (LSTM), for extracting the high‐level features of the sensors data and for learning the time‐series behaviour of the abstracted data, respectively. This paper proposed a Fuzzy Soft‐max classifier for the dense layer which classifies the output of LSTM Blocks to the associated activity classes. The authors’ decision for proposing this classifier was because sensor data related to the resembling human activities, such as walking and running or opening door and closing door, are often very similar to each other. For this reason, the authors expect that adding fuzzy inference power to the standard Soft‐max classifier will increase its accuracy for distinguishing between similar activities. The authors were also interested in considering a post‐processing module that considers activity classification over a longer period. Using the proposed Fuzzy Soft‐max classifier and by the post‐processing technique, the authors were able to reach the 97.03 and 85.1 rates of accuracy for the PAMAP2 and Opportunity dataset, respectively. |
| first_indexed | 2024-03-09T09:30:09Z |
| format | Article |
| id | doaj.art-8cfa814ff1c04c678bc5ab7e68cb727a |
| institution | Directory Open Access Journal |
| issn | 2047-4938 2047-4946 |
| language | English |
| last_indexed | 2024-03-09T09:30:09Z |
| publishDate | 2022-03-01 |
| publisher | Hindawi-IET |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj.art-8cfa814ff1c04c678bc5ab7e68cb727a2023-12-02T04:30:56ZengHindawi-IETIET Biometrics2047-49382047-49462022-03-0111217118610.1049/bme2.12066Proposing a Fuzzy Soft‐max‐based classifier in a hybrid deep learning architecture for human activity recognitionReza Shakerian0Meisam Yadollahzadeh‐Tabari1Seyed Yaser Bozorgi Rad2Department of Computer Engineering Islamic Azad University, Babol Branch Babol IranDepartment of Computer Engineering Islamic Azad University, Babol Branch Babol IranDepartment of Computer Engineering Islamic Azad University, Babol Branch Babol IranAbstract Human Activity Recognition (HAR) is the process of identifying and analysing activities performed by a person (or persons). This paper proposes an efficient HAR system based on wearable sensors that uses deep learning techniques. The proposed HAR takes the advantage of staking Convolutional Neural Network and Long Short‐Term (LSTM), for extracting the high‐level features of the sensors data and for learning the time‐series behaviour of the abstracted data, respectively. This paper proposed a Fuzzy Soft‐max classifier for the dense layer which classifies the output of LSTM Blocks to the associated activity classes. The authors’ decision for proposing this classifier was because sensor data related to the resembling human activities, such as walking and running or opening door and closing door, are often very similar to each other. For this reason, the authors expect that adding fuzzy inference power to the standard Soft‐max classifier will increase its accuracy for distinguishing between similar activities. The authors were also interested in considering a post‐processing module that considers activity classification over a longer period. Using the proposed Fuzzy Soft‐max classifier and by the post‐processing technique, the authors were able to reach the 97.03 and 85.1 rates of accuracy for the PAMAP2 and Opportunity dataset, respectively.https://doi.org/10.1049/bme2.12066deep learningFuzzyHuman Activity Recognition (HAR)soft‐max classifier |
| spellingShingle | Reza Shakerian Meisam Yadollahzadeh‐Tabari Seyed Yaser Bozorgi Rad Proposing a Fuzzy Soft‐max‐based classifier in a hybrid deep learning architecture for human activity recognition IET Biometrics deep learning Fuzzy Human Activity Recognition (HAR) soft‐max classifier |
| title | Proposing a Fuzzy Soft‐max‐based classifier in a hybrid deep learning architecture for human activity recognition |
| title_full | Proposing a Fuzzy Soft‐max‐based classifier in a hybrid deep learning architecture for human activity recognition |
| title_fullStr | Proposing a Fuzzy Soft‐max‐based classifier in a hybrid deep learning architecture for human activity recognition |
| title_full_unstemmed | Proposing a Fuzzy Soft‐max‐based classifier in a hybrid deep learning architecture for human activity recognition |
| title_short | Proposing a Fuzzy Soft‐max‐based classifier in a hybrid deep learning architecture for human activity recognition |
| title_sort | proposing a fuzzy soft max based classifier in a hybrid deep learning architecture for human activity recognition |
| topic | deep learning Fuzzy Human Activity Recognition (HAR) soft‐max classifier |
| url | https://doi.org/10.1049/bme2.12066 |
| work_keys_str_mv | AT rezashakerian proposingafuzzysoftmaxbasedclassifierinahybriddeeplearningarchitectureforhumanactivityrecognition AT meisamyadollahzadehtabari proposingafuzzysoftmaxbasedclassifierinahybriddeeplearningarchitectureforhumanactivityrecognition AT seyedyaserbozorgirad proposingafuzzysoftmaxbasedclassifierinahybriddeeplearningarchitectureforhumanactivityrecognition |