A Hyperdimensional Computing Framework for Analysis of Cardiorespiratory Synchronization During Paced Deep Breathing

Abstract

Autonomic function during deep breathing (DB) is normally scored based on the assumption that the heart rate is synchronized with the breathing. We have observed individuals with subtle arrhythmias during DB, where an autonomic function cannot be evaluated. This paper presents a novel method for analyzing cardiorespiratory synchronization: feature-based analysis of the similarity between heart rate and respiration using the principles of hyperdimensional computing. Heart rate and respiration signals were modeled using Fourier series analysis. Three feature variables were derived and mapped to binary vectors in a high-dimensional space. Using both synthesized data and recordings from patients/healthy subjects, the similarity between the feature vectors was assessed using Hamming distance (high-dimensional space), Euclidean distance (original space), and with a coherence-based index. Methods were evaluated via the classification of the similarity indices into three groups. The distance-based methods achieved good separation of signals into classes with different degrees of cardiorespiratory synchronization, also providing identification of patients with low cardiorespiratory synchronization but high values of conventional DB scores. Moreover, binary high-dimensional vectors allowed an additional analysis of the obtained Hamming distance. Feature-based similarity analysis using hyperdimensional computing is capable of identifying signals with low cardiorespiratory synchronization during DB due to arrhythmias. Vector-based similarity analysis could be applied to other types of feature variables than based on spectral analysis. The proposed methods for robustly assessing cardiorespiratory synchronization during DB facilitate the identification of individuals where the evaluation of the autonomic function is problematic or even impossible, thus increasing the correctness of the conventional DB scores. INDEX TERMS Deep breathing test, deep breathing index, similarity analysis, heart rate variability, hyperdimensional computing.

A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges

“…In [220,221], BSC was applied to biomedical signals: heart rate and respiration. The need for comparing these signals emerged in the scope of a deep breathing test for assessing autonomic function.…”

Vector Symbolic Architectures as a Computing Framework for Nanoscale Hardware

“…Most of these works have been done for classification tasks (see a recent overview in [Ge and Parhi, 2020]). Examples of domains that have benefited from the application of VSA modeling are biomedical signal processing [Rahimi et al, 2019], [Kleyko et al, 2019b], gesture recognition [Rahimi et al, 2016a], , seizure onset detection and localization [Burrello et al, 2020], physical activity recognition [Rasanen and Kakouros, 2014], and fault isolation [Kleyko et al, 2018a] but VSA modeling can be useful for very generic classification tasks , [Diao et al, 2021]. The common feature of these works is a simple training process, which does not require the use of iterative optimization methods, and transparently learns with few training examples.…”

HyperSeed: Unsupervised Learning with Vector Symbolic Architectures

“…VSA [12], [15], [18]- [20] is a computing framework providing methods of representing and manipulating concepts and their meanings in a high-dimensional space. VSA finds its applications in, for example, cognitive architectures [21], natural language processing [22]- [24], biomedical signal processing [1], [25], approximation of conventional data structures [26], [27], and for classification tasks such as gesture recognition [1], [28], cyber threat detection [29], physical activity recognition [30], fault isolation [31], [32]. Examples of efforts on using VSA for other than classification learning tasks are using data HVs for clustering [33]- [35], semi-supervised learning [36], collaborative privacy-preserving learning [37], [38], multi-task learning [39], [40], distributed learning [41], [42].…”

“…The target nodes at each update were pre-selected to be (15,15) -for the first update, (20,20) -for the second update, (10,10) -for the third update, (5,5) -for the fourth update, (25,25) -for the fifth update and (5,25) -for the sixth update. These nodes are marked by red crosses when needed.…”