Multi-Phases and Various Feature Extraction and Selection Methodology for Ensemble Gradient Boosting in Estimating Respiratory Rate

Abstract

Estimating the correct respiratory rate (RR) is an essential technique for intensive care units, hospitals, geriatric hospital facilities, and home care services. Capnography is a standard methodology used to monitor carbon dioxide concentrations or partial pressures of respiratory gases to provide the most accurate RR measurements. However, it is inconvenient to use and has been primarily used while administering anesthesia and during intensive care. Many researchers now use electrocardiogram signals to estimate RR. Despite the recent developments, the current hospital environments suffer from inaccurate respiratory monitoring. While various machine learning techniques, including deep learning, have recently been applied to the medical processing sector, only a few studies have been conducted in the field of RR estimation. Therefore, using photoplethysmography, machine-learning techniques such as the ensemble gradient boosting algorithm are being employed in RR estimation. Multi-phases are used based on various feature extraction and selection methodology to improve the performance for RR estimation. In this study, the number of ensembles is increased, and the proposed ensemble methodology is effectively learned to estimate the RR. The proposed ensemble-based gradient boosting algorithm are compared with those of ensemble-based long-short memory network, and ensemble-based supported vector regression techniques, 3.30 breaths per min (bpm), 4.82 bpm and 5.83 bpm based on mean absolute errors. The proposed method shows a more accurate estimate of the respiration rate.

Dual-Sensor Signals Based Exact Gaussian Process-Assisted Hybrid Feature Extraction and Weighted Feature Fusion for Respiratory Rate and Uncertainty Estimations

“…The feature extraction, training, and testing times are computed using MATLAB ® 2022 (The MathWorks Inc., Natick, MA, USA) [ 34 ] based on the dataset as shown in Table 2 . As a result, the proposed power spectral (PS) based on the autocorrelation function requires lower computational times than the multi-phase feature extraction (MF) model [ 13 ] using the BIDMC dataset as given in Table 2 .…”

“…When using the BIDMC dataset, the 230 feature dimensions consisted of 40 AR features, 160 Shannon entropies, 20 fractal estimates using MWL, and 10 wavelet variance estimates as shown in Figure 3 a. Interested readers can refer to [ 13 ].…”

“…Machine learning (ML) is also widely used to estimate response values in the biomedical field. Lee et al [ 13 ] proposed an approach for estimating RR using an ensemble-based gradient boosting algorithm (GBA) based on PPG signals; this approach depends on multiphase features [ 13 ] to improve the RR prediction capability. These features were extracted using several methods such as the autoregressive (AR) method [ 14 ], multifractal wavelet leaders (MWL) [ 15 ], wavelet packet [ 16 ], and maximal overlap discrete wavelet transform (MODWT) [ 17 , 18 ] to compensate for insufficient data.…”

Automatic Features Extraction Integrated With Exact Gaussian Process for Respiratory Rate and Uncertainty Estimations

“…Over the past decade, biomedical engineering has widely VOLUME 4, 2016 used machine learning (ML) to estimate response values. Lee et al [10] proposed PPG signals-based ensemble-gradient boosting algorithm (EGBA) for estimating the RR. Furthermore, an EGBA using multiphase features [10] has been used to enhance the RR estimation performance.…”

State feedback control for human inspiratory system

“…The results were compatible for sensors with environment of magnetic resonance (MR) and the errors of motion of modeling and estimation with sensors were compatible. Lee et al [11] have proposed a technique to estimate the correct respiratory rate in intensive care unit in the services of home care and hospitals. The concentration of carbon dioxide can be monitored by using a capnography or gases of partial pressure of respiratory to supply accurate measurements of respiratory rate.…”