Automated Hypertension Detection Using ConvMixer and Spectrogram Techniques with Ballistocardiograph Signals
Blood pressure is the pressure exerted by the blood in the veins against the walls of the veins. If this value is above normal levels, it is known as high blood pressure (HBP) or hypertension (HPT). This health problem which often referred to as the “silent killer” reduces the quality of life and ca...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/2/182 |
| _version_ | 1827626881024786432 |
|---|---|
| author | Salih T. A. Ozcelik Hakan Uyanık Erkan Deniz Abdulkadir Sengur |
| author_facet | Salih T. A. Ozcelik Hakan Uyanık Erkan Deniz Abdulkadir Sengur |
| author_sort | Salih T. A. Ozcelik |
| collection | DOAJ |
| description | Blood pressure is the pressure exerted by the blood in the veins against the walls of the veins. If this value is above normal levels, it is known as high blood pressure (HBP) or hypertension (HPT). This health problem which often referred to as the “silent killer” reduces the quality of life and causes severe damage to many body parts in various ways. Besides, its mortality rate is very high. Hence, rapid and effective diagnosis of this health problem is crucial. In this study, an automatic diagnosis of HPT has been proposed using ballistocardiography (BCG) signals. The BCG signals were transformed to the time-frequency domain using the spectrogram method. While creating the spectrogram images, parameters such as window type, window length, overlapping rate, and fast Fourier transform size were adjusted. Then, these images were classified using ConvMixer architecture, similar to vision transformers (ViT) and multi-layer perceptron (MLP)-mixer structures, which have attracted a lot of attention. Its performance was compared with classical architectures such as ResNet18 and ResNet50. The results obtained showed that the ConvMixer structure gave very successful results and a very short operation time. Our proposed model has obtained an accuracy of 98.14%, 98.79%, and 97.69% for the ResNet18, ResNet50, and ConvMixer architectures, respectively. In addition, it has been observed that the processing time of the ConvMixer architecture is relatively short compared to these two architectures. |
| first_indexed | 2024-03-09T13:03:45Z |
| format | Article |
| id | doaj.art-62140de084e54812893e39af94e28eee |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T13:03:45Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-62140de084e54812893e39af94e28eee2023-11-30T21:50:44ZengMDPI AGDiagnostics2075-44182023-01-0113218210.3390/diagnostics13020182Automated Hypertension Detection Using ConvMixer and Spectrogram Techniques with Ballistocardiograph SignalsSalih T. A. Ozcelik0Hakan Uyanık1Erkan Deniz2Abdulkadir Sengur3Electrical-Electronics Engineering Department, Engineering Faculty, Bingol University, Bingol 12000, TurkeyElectrical-Electronics Engineering Department, Engineering Faculty, Munzur University, Tunceli 62000, TurkeyElectrical-Electronics Engineering Department, Technology Faculty, Firat University, Elazig 23119, TurkeyElectrical-Electronics Engineering Department, Technology Faculty, Firat University, Elazig 23119, TurkeyBlood pressure is the pressure exerted by the blood in the veins against the walls of the veins. If this value is above normal levels, it is known as high blood pressure (HBP) or hypertension (HPT). This health problem which often referred to as the “silent killer” reduces the quality of life and causes severe damage to many body parts in various ways. Besides, its mortality rate is very high. Hence, rapid and effective diagnosis of this health problem is crucial. In this study, an automatic diagnosis of HPT has been proposed using ballistocardiography (BCG) signals. The BCG signals were transformed to the time-frequency domain using the spectrogram method. While creating the spectrogram images, parameters such as window type, window length, overlapping rate, and fast Fourier transform size were adjusted. Then, these images were classified using ConvMixer architecture, similar to vision transformers (ViT) and multi-layer perceptron (MLP)-mixer structures, which have attracted a lot of attention. Its performance was compared with classical architectures such as ResNet18 and ResNet50. The results obtained showed that the ConvMixer structure gave very successful results and a very short operation time. Our proposed model has obtained an accuracy of 98.14%, 98.79%, and 97.69% for the ResNet18, ResNet50, and ConvMixer architectures, respectively. In addition, it has been observed that the processing time of the ConvMixer architecture is relatively short compared to these two architectures.https://www.mdpi.com/2075-4418/13/2/182hypertensionhigh blood pressureBCG signalspectrogramconvolutional mixer |
| spellingShingle | Salih T. A. Ozcelik Hakan Uyanık Erkan Deniz Abdulkadir Sengur Automated Hypertension Detection Using ConvMixer and Spectrogram Techniques with Ballistocardiograph Signals Diagnostics hypertension high blood pressure BCG signal spectrogram convolutional mixer |
| title | Automated Hypertension Detection Using ConvMixer and Spectrogram Techniques with Ballistocardiograph Signals |
| title_full | Automated Hypertension Detection Using ConvMixer and Spectrogram Techniques with Ballistocardiograph Signals |
| title_fullStr | Automated Hypertension Detection Using ConvMixer and Spectrogram Techniques with Ballistocardiograph Signals |
| title_full_unstemmed | Automated Hypertension Detection Using ConvMixer and Spectrogram Techniques with Ballistocardiograph Signals |
| title_short | Automated Hypertension Detection Using ConvMixer and Spectrogram Techniques with Ballistocardiograph Signals |
| title_sort | automated hypertension detection using convmixer and spectrogram techniques with ballistocardiograph signals |
| topic | hypertension high blood pressure BCG signal spectrogram convolutional mixer |
| url | https://www.mdpi.com/2075-4418/13/2/182 |
| work_keys_str_mv | AT salihtaozcelik automatedhypertensiondetectionusingconvmixerandspectrogramtechniqueswithballistocardiographsignals AT hakanuyanık automatedhypertensiondetectionusingconvmixerandspectrogramtechniqueswithballistocardiographsignals AT erkandeniz automatedhypertensiondetectionusingconvmixerandspectrogramtechniqueswithballistocardiographsignals AT abdulkadirsengur automatedhypertensiondetectionusingconvmixerandspectrogramtechniqueswithballistocardiographsignals |