Leveraging Wearable Sensors for Human Daily Activity Recognition with Stacked Denoising Autoencoders
Activity recognition has received considerable attention in many research fields, such as industrial and healthcare fields. However, many researches about activity recognition have focused on static activities and dynamic activities in current literature, while, the transitional activities, such as...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/18/5114 |
| _version_ | 1797554304486211584 |
|---|---|
| author | Qin Ni Zhuo Fan Lei Zhang Chris D. Nugent Ian Cleland Yuping Zhang Nan Zhou |
| author_facet | Qin Ni Zhuo Fan Lei Zhang Chris D. Nugent Ian Cleland Yuping Zhang Nan Zhou |
| author_sort | Qin Ni |
| collection | DOAJ |
| description | Activity recognition has received considerable attention in many research fields, such as industrial and healthcare fields. However, many researches about activity recognition have focused on static activities and dynamic activities in current literature, while, the transitional activities, such as stand-to-sit and sit-to-stand, are more difficult to recognize than both of them. Consider that it may be important in real applications. Thus, a novel framework is proposed in this paper to recognize static activities, dynamic activities, and transitional activities by utilizing stacked denoising autoencoders (SDAE), which is able to extract features automatically as a deep learning model rather than utilize manual features extracted by conventional machine learning methods. Moreover, the resampling technique (random oversampling) is used to improve problem of unbalanced samples due to relatively short duration characteristic of transitional activity. The experiment protocol is designed to collect twelve daily activities (three types) by using wearable sensors from 10 adults in smart lab of Ulster University, the experiment results show the significant performance on transitional activity recognition and achieve the overall accuracy of 94.88% on three types of activities. The results obtained by comparing with other methods and performances on other three public datasets verify the feasibility and priority of our framework. This paper also explores the effect of multiple sensors (accelerometer and gyroscope) to determine the optimal combination for activity recognition. |
| first_indexed | 2024-03-10T16:30:06Z |
| format | Article |
| id | doaj.art-deea7ebae4864e109ff880cd00eb8ac6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T16:30:06Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-deea7ebae4864e109ff880cd00eb8ac62023-11-20T12:58:47ZengMDPI AGSensors1424-82202020-09-012018511410.3390/s20185114Leveraging Wearable Sensors for Human Daily Activity Recognition with Stacked Denoising AutoencodersQin Ni0Zhuo Fan1Lei Zhang2Chris D. Nugent3Ian Cleland4Yuping Zhang5Nan Zhou6College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, ChinaCollege of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, ChinaCollege of Information Science and Technology, Donghua University, Shanghai 201620, ChinaSchool of Computing and Mathematics, University of Ulster, Belfast BT370QB, UKSchool of Computing and Mathematics, University of Ulster, Belfast BT370QB, UKCollege of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, ChinaCollege of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, ChinaActivity recognition has received considerable attention in many research fields, such as industrial and healthcare fields. However, many researches about activity recognition have focused on static activities and dynamic activities in current literature, while, the transitional activities, such as stand-to-sit and sit-to-stand, are more difficult to recognize than both of them. Consider that it may be important in real applications. Thus, a novel framework is proposed in this paper to recognize static activities, dynamic activities, and transitional activities by utilizing stacked denoising autoencoders (SDAE), which is able to extract features automatically as a deep learning model rather than utilize manual features extracted by conventional machine learning methods. Moreover, the resampling technique (random oversampling) is used to improve problem of unbalanced samples due to relatively short duration characteristic of transitional activity. The experiment protocol is designed to collect twelve daily activities (three types) by using wearable sensors from 10 adults in smart lab of Ulster University, the experiment results show the significant performance on transitional activity recognition and achieve the overall accuracy of 94.88% on three types of activities. The results obtained by comparing with other methods and performances on other three public datasets verify the feasibility and priority of our framework. This paper also explores the effect of multiple sensors (accelerometer and gyroscope) to determine the optimal combination for activity recognition.https://www.mdpi.com/1424-8220/20/18/5114activity recognitiontransitional activitiesstacked denoising autoencoderswearable sensorsresampling technique |
| spellingShingle | Qin Ni Zhuo Fan Lei Zhang Chris D. Nugent Ian Cleland Yuping Zhang Nan Zhou Leveraging Wearable Sensors for Human Daily Activity Recognition with Stacked Denoising Autoencoders Sensors activity recognition transitional activities stacked denoising autoencoders wearable sensors resampling technique |
| title | Leveraging Wearable Sensors for Human Daily Activity Recognition with Stacked Denoising Autoencoders |
| title_full | Leveraging Wearable Sensors for Human Daily Activity Recognition with Stacked Denoising Autoencoders |
| title_fullStr | Leveraging Wearable Sensors for Human Daily Activity Recognition with Stacked Denoising Autoencoders |
| title_full_unstemmed | Leveraging Wearable Sensors for Human Daily Activity Recognition with Stacked Denoising Autoencoders |
| title_short | Leveraging Wearable Sensors for Human Daily Activity Recognition with Stacked Denoising Autoencoders |
| title_sort | leveraging wearable sensors for human daily activity recognition with stacked denoising autoencoders |
| topic | activity recognition transitional activities stacked denoising autoencoders wearable sensors resampling technique |
| url | https://www.mdpi.com/1424-8220/20/18/5114 |
| work_keys_str_mv | AT qinni leveragingwearablesensorsforhumandailyactivityrecognitionwithstackeddenoisingautoencoders AT zhuofan leveragingwearablesensorsforhumandailyactivityrecognitionwithstackeddenoisingautoencoders AT leizhang leveragingwearablesensorsforhumandailyactivityrecognitionwithstackeddenoisingautoencoders AT chrisdnugent leveragingwearablesensorsforhumandailyactivityrecognitionwithstackeddenoisingautoencoders AT iancleland leveragingwearablesensorsforhumandailyactivityrecognitionwithstackeddenoisingautoencoders AT yupingzhang leveragingwearablesensorsforhumandailyactivityrecognitionwithstackeddenoisingautoencoders AT nanzhou leveragingwearablesensorsforhumandailyactivityrecognitionwithstackeddenoisingautoencoders |