A Novel CNN-Based Framework for Classification of Signal Quality and Sleep Position from a Capacitive ECG Measurement
The further exploration of the capacitive ECG (cECG) is hindered by frequent fluctuations in signal quality from body movement and changes in sleep position. The processing framework must be fundamentally adapted to make full use of this signal. Therefore, we propose a new signal-processing framewor...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/7/1731 |
| _version_ | 1818040889279250432 |
|---|---|
| author | Koshiro Kido Toshiyo Tamura Naoaki Ono MD. Altaf-Ul-Amin Masaki Sekine Shigehiko Kanaya Ming Huang |
| author_facet | Koshiro Kido Toshiyo Tamura Naoaki Ono MD. Altaf-Ul-Amin Masaki Sekine Shigehiko Kanaya Ming Huang |
| author_sort | Koshiro Kido |
| collection | DOAJ |
| description | The further exploration of the capacitive ECG (cECG) is hindered by frequent fluctuations in signal quality from body movement and changes in sleep position. The processing framework must be fundamentally adapted to make full use of this signal. Therefore, we propose a new signal-processing framework that determines the signal quality for short signal segments (2 and 4 seconds) using a multi-class classification model (qua_model) based on a convolutional neural network (CNN). We built another independent deep CNN classifier (pos_model) to classify the sleep position. In the validation, 12 subjects were recruited for a 30-minute experiment, which required the subjects to lie on a bed in different sleeping positions. The short segments, classified as clear (C1 class) by the qua_model, were used to determine sleep positions with the pos_model. In 10-fold cross-validation, the qua_model for signals of 4-second length could recognize the signal of the C1 class at a 0.99 precision and a 0.99 recall; the pos_model could recognize the supine sleep position, the left, and right lateral sleep positions at a 0.99 averaged precision and a 0.99 averaged recall. Given the amount of data accumulated per night and the instability in the signal quality, this fully automatic processing framework is indispensable for a personal healthcare system. Therefore, this study could serve as an important step for cECG technique trying to explore the cECG for unconstrained heart monitoring. |
| first_indexed | 2024-12-10T08:21:42Z |
| format | Article |
| id | doaj.art-d6499a6070d3422e9e767c73173457e6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-12-10T08:21:42Z |
| publishDate | 2019-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d6499a6070d3422e9e767c73173457e62022-12-22T01:56:20ZengMDPI AGSensors1424-82202019-04-01197173110.3390/s19071731s19071731A Novel CNN-Based Framework for Classification of Signal Quality and Sleep Position from a Capacitive ECG MeasurementKoshiro Kido0Toshiyo Tamura1Naoaki Ono2MD. Altaf-Ul-Amin3Masaki Sekine4Shigehiko Kanaya5Ming Huang6Division of Information Science, Nara Institute of Science and Technology, Ikoma 630-0192, JapanFuture Robotics Organization, Waseda University, Tokorozawa 359-1192, JapanDivision of Information Science, Nara Institute of Science and Technology, Ikoma 630-0192, JapanDivision of Information Science, Nara Institute of Science and Technology, Ikoma 630-0192, JapanDepartment of Medical care Technology, Tsukuba International University, Tsuchiura 300-0051, JapanDivision of Information Science, Nara Institute of Science and Technology, Ikoma 630-0192, JapanDivision of Information Science, Nara Institute of Science and Technology, Ikoma 630-0192, JapanThe further exploration of the capacitive ECG (cECG) is hindered by frequent fluctuations in signal quality from body movement and changes in sleep position. The processing framework must be fundamentally adapted to make full use of this signal. Therefore, we propose a new signal-processing framework that determines the signal quality for short signal segments (2 and 4 seconds) using a multi-class classification model (qua_model) based on a convolutional neural network (CNN). We built another independent deep CNN classifier (pos_model) to classify the sleep position. In the validation, 12 subjects were recruited for a 30-minute experiment, which required the subjects to lie on a bed in different sleeping positions. The short segments, classified as clear (C1 class) by the qua_model, were used to determine sleep positions with the pos_model. In 10-fold cross-validation, the qua_model for signals of 4-second length could recognize the signal of the C1 class at a 0.99 precision and a 0.99 recall; the pos_model could recognize the supine sleep position, the left, and right lateral sleep positions at a 0.99 averaged precision and a 0.99 averaged recall. Given the amount of data accumulated per night and the instability in the signal quality, this fully automatic processing framework is indispensable for a personal healthcare system. Therefore, this study could serve as an important step for cECG technique trying to explore the cECG for unconstrained heart monitoring.https://www.mdpi.com/1424-8220/19/7/1731capacitive couplingelectrocardiogramCNNdeep learningsleep positions |
| spellingShingle | Koshiro Kido Toshiyo Tamura Naoaki Ono MD. Altaf-Ul-Amin Masaki Sekine Shigehiko Kanaya Ming Huang A Novel CNN-Based Framework for Classification of Signal Quality and Sleep Position from a Capacitive ECG Measurement Sensors capacitive coupling electrocardiogram CNN deep learning sleep positions |
| title | A Novel CNN-Based Framework for Classification of Signal Quality and Sleep Position from a Capacitive ECG Measurement |
| title_full | A Novel CNN-Based Framework for Classification of Signal Quality and Sleep Position from a Capacitive ECG Measurement |
| title_fullStr | A Novel CNN-Based Framework for Classification of Signal Quality and Sleep Position from a Capacitive ECG Measurement |
| title_full_unstemmed | A Novel CNN-Based Framework for Classification of Signal Quality and Sleep Position from a Capacitive ECG Measurement |
| title_short | A Novel CNN-Based Framework for Classification of Signal Quality and Sleep Position from a Capacitive ECG Measurement |
| title_sort | novel cnn based framework for classification of signal quality and sleep position from a capacitive ecg measurement |
| topic | capacitive coupling electrocardiogram CNN deep learning sleep positions |
| url | https://www.mdpi.com/1424-8220/19/7/1731 |
| work_keys_str_mv | AT koshirokido anovelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement AT toshiyotamura anovelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement AT naoakiono anovelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement AT mdaltafulamin anovelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement AT masakisekine anovelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement AT shigehikokanaya anovelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement AT minghuang anovelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement AT koshirokido novelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement AT toshiyotamura novelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement AT naoakiono novelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement AT mdaltafulamin novelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement AT masakisekine novelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement AT shigehikokanaya novelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement AT minghuang novelcnnbasedframeworkforclassificationofsignalqualityandsleeppositionfromacapacitiveecgmeasurement |