Comparing Time and Frequency Domain Heart Rate Variability for Deep Learning-Based Glucose Detection
Journal
Communications in Computer and Information Science
Date Issued
2022-04-12
Author(s)
Shaqiri, Ervin
DOI
10.1007/978-3-031-04206-5_14
Abstract
International Conference on ICT Innovations
ICT Innovations 2021: ICT Innovations 2021. Digital Transformation pp 188–197Cite as
Comparing Time and Frequency Domain Heart Rate Variability for Deep Learning-Based Glucose Detection
Ervin Shaqiri, Marjan Gusev, Lidija Poposka, Marija Vavlukis & Irfan Ahmeti
Conference paper
First Online: 12 April 2022
165 Accesses
Part of the Communications in Computer and Information Science book series (CCIS,volume 1521)
Abstract
Many researchers have been challenged by the usage of devices related to the Internet of Things in conjunction with machine learning to anticipate and diagnose health issues. Diabetes has always been a problem that society has struggled with. Due to the simplicity with which electrocardiograms can be captured and analysed, deep learning can be used to forecast a patient’s instantaneous glucose levels.
Our solution is based on a unique method for calculating heart rate variability that involves segment identification, averaging, and concatenating the data to reveal better feature engineering results. Immediate plasma glucose levels are detected using short-term heart rate variability and applied a deep learning method based on Autokeras.
In this paper. we address a research question to compare the predictive capability of time and frequency domain features for instantaneous glucose values. The neural architectural search for the time domain approach provided the best results for the 15-min electrocardiogram measurements. Similarly, the Frequency Domain approach showed better results on the same time frame. Regarding the time domain the best results are as follows: RMSE (0.368), MSE (0.193), R2 (0.513), and R2 loss (0.541). The best results for the Frequency Domain approach the best results are as follows: RMSE (0.301), MSE (0.346), R2 (0.45578), and R2 loss (0.482).
ICT Innovations 2021: ICT Innovations 2021. Digital Transformation pp 188–197Cite as
Comparing Time and Frequency Domain Heart Rate Variability for Deep Learning-Based Glucose Detection
Ervin Shaqiri, Marjan Gusev, Lidija Poposka, Marija Vavlukis & Irfan Ahmeti
Conference paper
First Online: 12 April 2022
165 Accesses
Part of the Communications in Computer and Information Science book series (CCIS,volume 1521)
Abstract
Many researchers have been challenged by the usage of devices related to the Internet of Things in conjunction with machine learning to anticipate and diagnose health issues. Diabetes has always been a problem that society has struggled with. Due to the simplicity with which electrocardiograms can be captured and analysed, deep learning can be used to forecast a patient’s instantaneous glucose levels.
Our solution is based on a unique method for calculating heart rate variability that involves segment identification, averaging, and concatenating the data to reveal better feature engineering results. Immediate plasma glucose levels are detected using short-term heart rate variability and applied a deep learning method based on Autokeras.
In this paper. we address a research question to compare the predictive capability of time and frequency domain features for instantaneous glucose values. The neural architectural search for the time domain approach provided the best results for the 15-min electrocardiogram measurements. Similarly, the Frequency Domain approach showed better results on the same time frame. Regarding the time domain the best results are as follows: RMSE (0.368), MSE (0.193), R2 (0.513), and R2 loss (0.541). The best results for the Frequency Domain approach the best results are as follows: RMSE (0.301), MSE (0.346), R2 (0.45578), and R2 loss (0.482).