A Teenager Physical Fitness Evaluation Model Based on 1D-CNN with LSTM and Wearable Running PPG Recordings
People attach greater importance to the physical health of teenagers because adolescence is a critical period for the healthy development of the human body. With the progress of biosensing technologies and artificial intelligence, it is feasible to apply wearable devices to continuously record teena...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Biosensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-6374/12/4/202 |
| _version_ | 1797436668037300224 |
|---|---|
| author | Junqi Guo Boxin Wan Siyu Zheng Aohua Song Wenshan Huang |
| author_facet | Junqi Guo Boxin Wan Siyu Zheng Aohua Song Wenshan Huang |
| author_sort | Junqi Guo |
| collection | DOAJ |
| description | People attach greater importance to the physical health of teenagers because adolescence is a critical period for the healthy development of the human body. With the progress of biosensing technologies and artificial intelligence, it is feasible to apply wearable devices to continuously record teenagers’ physiological signals and make analyses based on modern advanced methods. To solve the challenge that traditional methods of monitoring teenagers’ physical fitness lack accurate computational models and in-depth data analyses, we propose a novel evaluation model for predicting the physical fitness of teenagers. First, we collected 1024 teenagers’ PPGs under the guidance of the proposed three-stage running paradigm. Next, we applied the median filter and wavelet transform to denoise the original signals and obtain HR and SpO<sub>2</sub>. Then, we used the Pearson correlation coefficient method to finalize the feature set, based on the extracted nine physical features. Finally, we built a 1D-CNN with LSTM model to classify teenagers’ physical fitness condition into four levels: excellent, good, medium, and poor, with an accuracy of 98.27% for boys’ physical fitness prediction, and 99.26% for girls’ physical fitness prediction. The experimental results provide evidence supporting the feasibility of predicting teenagers’ physical fitness levels by their running PPG recordings. |
| first_indexed | 2024-03-09T11:05:54Z |
| format | Article |
| id | doaj.art-2568a92bb58d4de1b8480ad2cd7adba0 |
| institution | Directory Open Access Journal |
| issn | 2079-6374 |
| language | English |
| last_indexed | 2024-03-09T11:05:54Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biosensors |
| spelling | doaj.art-2568a92bb58d4de1b8480ad2cd7adba02023-12-01T00:57:47ZengMDPI AGBiosensors2079-63742022-03-0112420210.3390/bios12040202A Teenager Physical Fitness Evaluation Model Based on 1D-CNN with LSTM and Wearable Running PPG RecordingsJunqi Guo0Boxin Wan1Siyu Zheng2Aohua Song3Wenshan Huang4School of Artificial Intelligence, Beijing Normal University, Beijing 100875, ChinaSchool of Artificial Intelligence, Beijing Normal University, Beijing 100875, ChinaSchool of Electronic Information and Automation, Tianjin University of Science and Technology, Tianjin 300222, ChinaSchool of Artificial Intelligence, Beijing Normal University, Beijing 100875, ChinaSchool of Artificial Intelligence, Beijing Normal University, Beijing 100875, ChinaPeople attach greater importance to the physical health of teenagers because adolescence is a critical period for the healthy development of the human body. With the progress of biosensing technologies and artificial intelligence, it is feasible to apply wearable devices to continuously record teenagers’ physiological signals and make analyses based on modern advanced methods. To solve the challenge that traditional methods of monitoring teenagers’ physical fitness lack accurate computational models and in-depth data analyses, we propose a novel evaluation model for predicting the physical fitness of teenagers. First, we collected 1024 teenagers’ PPGs under the guidance of the proposed three-stage running paradigm. Next, we applied the median filter and wavelet transform to denoise the original signals and obtain HR and SpO<sub>2</sub>. Then, we used the Pearson correlation coefficient method to finalize the feature set, based on the extracted nine physical features. Finally, we built a 1D-CNN with LSTM model to classify teenagers’ physical fitness condition into four levels: excellent, good, medium, and poor, with an accuracy of 98.27% for boys’ physical fitness prediction, and 99.26% for girls’ physical fitness prediction. The experimental results provide evidence supporting the feasibility of predicting teenagers’ physical fitness levels by their running PPG recordings.https://www.mdpi.com/2079-6374/12/4/202teenager physical fitness monitoringwearable braceletsnoninvasive biosensorswireless biosensorsPhotoplethysmography (PPG)Pearson correlation coefficient (PCC) |
| spellingShingle | Junqi Guo Boxin Wan Siyu Zheng Aohua Song Wenshan Huang A Teenager Physical Fitness Evaluation Model Based on 1D-CNN with LSTM and Wearable Running PPG Recordings Biosensors teenager physical fitness monitoring wearable bracelets noninvasive biosensors wireless biosensors Photoplethysmography (PPG) Pearson correlation coefficient (PCC) |
| title | A Teenager Physical Fitness Evaluation Model Based on 1D-CNN with LSTM and Wearable Running PPG Recordings |
| title_full | A Teenager Physical Fitness Evaluation Model Based on 1D-CNN with LSTM and Wearable Running PPG Recordings |
| title_fullStr | A Teenager Physical Fitness Evaluation Model Based on 1D-CNN with LSTM and Wearable Running PPG Recordings |
| title_full_unstemmed | A Teenager Physical Fitness Evaluation Model Based on 1D-CNN with LSTM and Wearable Running PPG Recordings |
| title_short | A Teenager Physical Fitness Evaluation Model Based on 1D-CNN with LSTM and Wearable Running PPG Recordings |
| title_sort | teenager physical fitness evaluation model based on 1d cnn with lstm and wearable running ppg recordings |
| topic | teenager physical fitness monitoring wearable bracelets noninvasive biosensors wireless biosensors Photoplethysmography (PPG) Pearson correlation coefficient (PCC) |
| url | https://www.mdpi.com/2079-6374/12/4/202 |
| work_keys_str_mv | AT junqiguo ateenagerphysicalfitnessevaluationmodelbasedon1dcnnwithlstmandwearablerunningppgrecordings AT boxinwan ateenagerphysicalfitnessevaluationmodelbasedon1dcnnwithlstmandwearablerunningppgrecordings AT siyuzheng ateenagerphysicalfitnessevaluationmodelbasedon1dcnnwithlstmandwearablerunningppgrecordings AT aohuasong ateenagerphysicalfitnessevaluationmodelbasedon1dcnnwithlstmandwearablerunningppgrecordings AT wenshanhuang ateenagerphysicalfitnessevaluationmodelbasedon1dcnnwithlstmandwearablerunningppgrecordings AT junqiguo teenagerphysicalfitnessevaluationmodelbasedon1dcnnwithlstmandwearablerunningppgrecordings AT boxinwan teenagerphysicalfitnessevaluationmodelbasedon1dcnnwithlstmandwearablerunningppgrecordings AT siyuzheng teenagerphysicalfitnessevaluationmodelbasedon1dcnnwithlstmandwearablerunningppgrecordings AT aohuasong teenagerphysicalfitnessevaluationmodelbasedon1dcnnwithlstmandwearablerunningppgrecordings AT wenshanhuang teenagerphysicalfitnessevaluationmodelbasedon1dcnnwithlstmandwearablerunningppgrecordings |