Concatenated convolutional neural network model for cuffless blood pressure estimation using fuzzy recurrence properties of photoplethysmogram signals

Abstract

Due to the importance of continuous monitoring of blood pressure (BP) in controlling hypertension, the topic of cuffless BP estimation has been widely studied in recent years. A most important approach is to explore the nonlinear mapping between the recorded peripheral signals and the BP values which is usually conducted by deep neural networks. Because of the sequence-based pseudo periodic nature of peripheral signals such as photoplethysmogram (PPG), a proper estimation model needed to be equipped with the 1-dimensional (1-D) and recurrent layers. This, in turn, limits the usage of 2-dimensional (2-D) layers adopted in convolutional neural networks (CNN) for embedding spatial information in the model. In this study, considering the advantage of chaotic approaches, the recurrence characterization of peripheral signals was taken into account by a visual 2-D representation of PPG in phase space through fuzzy recurrence plot (FRP). FRP not only provides a beneficial framework for capturing the spatial properties of input signals but also creates a reliable approach for embedding the pseudo periodic properties to the neural models without using recurrent layers. Moreover, this study proposes a novel deep neural network architecture that combines the morphological features extracted simultaneously from two upgraded 1-D and 2-D CNNs capturing the temporal and spatial dependencies of PPGs in systolic and diastolic BP estimation. The model has been fed with the 1-D PPG sequences and the corresponding 2-D FRPs from two separate routes. The performance of the proposed framework was examined on the well-known public dataset, namely, multi-parameter intelligent in Intensive Care II. Our scheme is analyzed and compared with the literature in terms of the requirements of the standards set by the British Hypertension Society (BHS) and the Association for the Advancement of Medical Instrumentation (AAMI). The proposed model met the AAMI requirements, and it achieved a grade of A as stated by the BHS standard. In addition, its mean absolute errors and standard deviation for both systolic and diastolic blood pressure estimations were considerably low, 3.05 ± 5.26 mmHg and 1.58 ± 2.6 mmHg, in turn.

Classification of Blood Pressure Levels Based on Photoplethysmogram and Electrocardiogram Signals with a Concatenated Convolutional Neural Network

“…In the feature extraction layer, the computing output map of one layer becomes the input of the subsequent layer during forwarding propagation. This input is then convolved with specific kernels, as shown in Equation (1) [ 50 ]. where is the input of layer , and and stand for the kernel and output of the neuron at layer , respectively.…”

“…The PPG and ECG signal feature maps were concatenated as input to the fully connected classification layer. The formulation of concatenation fusion is shown in Equation (3), which concatenates the two inputs of the extracted feature maps from PPG and ECG signals at the same location, as shown in Equation (4) [ 50 ]. where .…”

An Ultra‐Sensitive Flexible Resistive Sensor with Double Strain Layer and Crack Inspired by the Physical Structure of Human Epidermis: Design, Fabrication, and Cuffless Blood Pressure Monitoring Application

“…[52] Compared with other carbon materials, rGO has good dispersibility in PEDOT:PSS aqueous solution. [53,54] In addition, PEDOT:PSS also has π-π bonds with rGO. In order to verify the above statement, XRD and XPS characterizations were carried out.…”

UTransBPNet: A General Deep Learning Model for Cuffless Blood Pressure Estimation under Activities

“…Therefore, pure CNN is not effective in capturing long-range features from highresolution (>100Hz) physiological signals. So, some efforts were devoted to improving the feature representation of the input physiological signals of CNN models [20,21]. For example, Malayeri et al proposed to transform the physiological signals into phase space and introduced 2D recurrence features by fuzzy recurrence plot as the input attributes together with the 1D signals of the deep models [21].…”