Suppression of noises using fast independent component analysis (FICA) and signal saturation using fuzzy adaptive histogram equalization (FAHE) for intensive care unit false alarms

摘要

In the medical field, fake alarms are classically described as alarms with no clinical or therapeutic effects. A variety of studies exist in the clinical literature regarding the alarms monitoring in Arterial Blood Pressure (ABP) Signal and intensive care medicine. In the proposed work measurement of each one of the ABP, signal values are carried out employing the Fast Independent Component Analysis (FICA), which detects areas affected with high-frequency noise. When the noises in the samples are eliminated, then the signal saturation values are decided with the help of the Fuzzy Wavelet Transform (FWT) technique. Then, the automated feature engineering was carried out utilizing the signal for ABP along with a processed signal, which has the count of the times of every monitored heartbeat acquired from the ABP signal. Subsequently, Kullback-Leibler divergence Kernel -Support Vector Machine (KLDK-SVM), Random Forest (RF), and SVM classifiers were trained so as to generate the classification models. The newly introduced scheme can be used to help the medical professional and specialists, letting them become more useful and are responsive to alarms as quickly as possible. (C) 2019 Elsevier Ltd. All rights reserved.