Evaluation of heart rate variability by using wavelet transform and a recurrent neural network

Abstract

Abstract-The purpose of this paper is to evaluate the physical and mental stress based on the physiological index, and a new evaluation method of heart rate variability is proposed. This method combines the wavelet transform w^ith a recurrent neural network. The features of the proposed method are as follows: 1. The wavelet transform is utilized for the feature extraction so that the local change of heart rate variability in the time-frequency domain can be extracted. 2. In order to learn and evaluate the different patterns of heart rate variability caused by individual variations, body conditions, circadian rhythms and so on, a new^ recurrent neural netw^ork v^^hich incorporates a hidden Markov Model is used. In the experiments, a mental w^ork-load was given to five subjects, and the subjective rating scores of their mental stress were evaluated using heart rate variability. It w^as confirmed from the experiments that the proposed method could achieve high learning/evaluating performances. Keywords-Heart rate variability, Mental stress. Wavelet transform. Recurrent neural network. Hidden Markov model. I INTRODUCTIONAn electrocardiogram (ECG) is available for a basic physiological index which evaluates the change in patient's body condition and monitors physical and mental stress in his/her daily activities. The heart rate is complicated since it is affected by various factors such as a sinus node for a pacemaker, autononiic nerves, the endocrine system and so on. It is expected that the changes of these factors can be evaluated based on the analysis of Heart Rate Variability (HRV). In this paper, we propose a new evaluation method of HRV.HRV includes many frequency components, and various information can be obtained from them through the frequency domain analysis [1], [2]. In the report of Sayers, which is the pioneer research in this area, three peaks exist on the power spectrum of HRV. The lower frequency component (0.02 -0.06 [Hz]) is influenced by thermoregulation, and the middle frequency component (0.07 -0.14[Hz]) is influenced by blood pressure regulation, and the high frequency component (0.15 -0.5() [Hz]) is influenced by respiration respectively. However, if the power spectrum of HRV is calculated using fast Fourier transform, it expresses rough information in a fixed period of the time series signal, and the dynamic changes of the autononiic nerve activity cannot be expressed. It is difficult to analyze the nonstationary pattern of HRV using this method during the exercise. To overcome this difficulty. The wavelet transform (WT), which extracts local features of HRV in the time-frequency domain, is proposed [3].The changes in the spectrum pattern from physical and mental stress are different among individuals. The subjective feeling of the subjects is also different. These are the problems of the spectrum analysis of HRV. Most previous studies defined specified frequency ranges such as the low frequency component (LF) and the high frequency component (HF) on the power spectrum of HRV, and extracted a...

Workplace Stress Estimation Method Based on Multivariate Analysis of Physiological Indices

“…Typical examples are holter monitors that are routinely used for electrocardiogram (ECG) and electroencephalogram (EEG) monitoring. Recently, with the miniaturization and improved performances of micro-sensors, wearable computing, and wireless communication technologies (Fukuda et al, 2001;Itao, 2007), a new generation of wearable intelligent sensors have been developed (Jovanov et al, 2000). Such devices can significantly decrease the number of hospitalizations and nursing visits (Heidenreich et al, 1999) by acting as a personal quotationvirtual health adviser that can warn the user of a medical emergency or contact a specialized medical response service.…”

“…Studies that evaluate qualitatively and/or quantitatively the stress issued by an external stimulus (Kotlyar et al, 2008;Watanabe et al, 2008) 3. Studies that estimate the occurrence or not of stress based on the observation of changes in physiological indices (Aasa et al, 2006;Fukuda et al, 2001;Itao et al, 2008) Aiming at stress monitoring during daily life activities, our research corresponds to the third category. This category is composed of two groups of methodologies, being methodologies to retrieve stress changes based on the observation of long-term evolution for a single physiological index, and methodologies that build models for stress status output from input of physiological indices, based on multivariate analysis.…”

A mixture of fuzzy filters applied to the analysis of heartbeat intervals

“…However, it is typical that the correlations between signal features and the patients' physiological states are complex and uncertain. Thus, the attempts have been made to approximate these complex and uncertain correlations through the neural/fuzzy models (Fukuda et al 2001;Han et al 2002;Rani et al 2002;Kumar et al 2003a,b;Wilson and Russell 2003a,b;Kumar et al 2004a,b;Engin 2004;Mandryk and Atkins 2007;Kumar et al 2008Kumar et al , 2007bKumar et al , 2009. Adaptive filters are typically used to remove noise and artifacts from the biomedical signals (Philips 1996;Lee and Lee 2005;Plataniotis et al 1999;Mastorocostas et al 2000;Li et al 2008).…”

Heart Rate Variability Dynamics for the Prognosis of Cardiovascular Risk

“…Classical methods of analysis are not absolutely suitable for analysis of HRV [21] , [30] , [31] , [32] . Consequently, some approaches have applied multi-resolution methods to HRV analysis.…”