Stress Level Detection Based on the Capacitive Electrocardiogram Signals of Driving Subjects.

The automotive industry and scientific community are making efforts to develop innovative solutions that would increase successful driver performance in preventing crashes caused by drivers' health and concentration. High stress is one of the causes of impaired driver performance. This study investigates the ability to classify different stress levels based on capacitive electrocardiogram (cECG) recorded during driving by unobtrusive acquisition systems with different hardware implementations. The proposed machine-learning model extracted only four features, based on the detection of the R peak, which is the most reliably detected characteristic point even in inferior quality cECG. Another criterion for selecting the features is their low computational complexity, which enables real-time application. The proposed method was validated on three open data sets recorded during driving: electrocardiogram (ECG) recorded by electrodes with direct skin contact (high quality); cECG recorded without direct skin contact through clothes by electrodes built into a portable multi-modal cushion (middle quality); and cECG recorded through the clothes without direct skin contact by electrodes built into a car seat (lowest quality). The proposed model achieved a high accuracy of 100% for high-quality ECG, 96.67% for middle-quality cECG, and 98.08% for the lower-quality cECG.

Reduction of Artifacts in Capacitive Electrocardiogram Signals of Driving Subjects.

The development of smart cars with e-health services allows monitoring of the health condition of the driver. Driver comfort is preserved by the use of capacitive electrodes, but the recorded signal is characterized by large artifacts. This paper proposes a method for reducing artifacts from the ECG signal recorded by capacitive electrodes (cECG) in moving subjects. Two dominant artifact types are coarse and slow-changing artifacts. Slow-changing artifacts removal by classical filtering is not feasible as the spectral bands of artifacts and cECG overlap, mostly in the band from 0.5 to 15 Hz. We developed a method for artifact removal, based on estimating the fluctuation around linear trend, for both artifact types, including a condition for determining the presence of coarse artifacts. The method was validated on cECG recorded while driving, with the artifacts predominantly due to the movements, as well as on cECG recorded while lying, where the movements were performed according to a predefined protocol. The proposed method eliminates 96% to 100% of the coarse artifacts, while the slow-changing artifacts are completely reduced for the recorded cECG signals larger than 0.3 V. The obtained results are in accordance with the opinion of medical experts. The method is intended for reliable extraction of cardiovascular parameters to monitor driver fatigue status.

On Entropy of Probability Integral Transformed Time Series.

The goal of this paper is to investigate the changes of entropy estimates when the amplitude distribution of the time series is equalized using the probability integral transformation. The data we analyzed were with known properties-pseudo-random signals with known distributions, mutually coupled using statistical or deterministic methods that include generators of statistically dependent distributions, linear and non-linear transforms, and deterministic chaos. The signal pairs were coupled using a correlation coefficient ranging from zero to one. The dependence of the signal samples is achieved by moving average filter and non-linear equations. The applied coupling methods are checked using statistical tests for correlation. The changes in signal regularity are checked by a multifractal spectrum. The probability integral transformation is then applied to cardiovascular time series-systolic blood pressure and pulse interval-acquired from the laboratory animals and represented the results of entropy estimations. We derived an expression for the reference value of entropy in the probability integral transformed signals. We also experimentally evaluated the reliability of entropy estimates concerning the matching probabilities.

A Mobile Crowd Sensing Application for Hypertensive Patients.

Mobile crowd sensing (MCS) is an application that collects data from a network of conscientious volunteers and implements it for the common or personal benefit. This contribution proposes an implementation that collects the data from hypertensive patients, thus creating an experimental database using the cloud service Platform as a Service (PaaS). The challenge is to perform the analysis without the main diagnostic feature for hypertension-the blood pressure. The other problems consider the data reliability in an environment full of artifacts and with limited bandwidth and battery resources. In order to motivate the MCS volunteers, a feedback about the patient's current status is created, provided by the means of machine-learning (ML) techniques. Two techniques are investigated and the Random Forest algorithm yielded the best results. The proposed platform, with slight modifications, can be adapted to the patients with other cardiovascular problems.

The exposure analysis of the long-term broadband EMF monitoring in the campus area of the University of Novi Sad.

Due to wide prevalence of electromagnetic field (EMF) sources in human surrounding, EMF-level measurements and corresponding exposure assessment have imposed as an important topic. With an intention to present an approach to the long-term exposure assessment in EMF RATEL network, this paper conveys a high-level statistical analysis of the high-frequency exposure data, acquired during the 5-y time period, for the case study of monitoring sensor installed in the area of the Novi Sad University campus. Time series of exposure values were averaged on a daily, weekly, and monthly basis, and their yearly comparison was performed. Results showed clear differences between the day and night hours, as well between working and weekend days. Regarding exposure values, averaged on the monthly basis, the impact of COVID-19 pandemic in 2020 and 2021 can be noticed. Finally, the highest obtained exposure values (electric field squared) were 22 times below the maximal allowable level, according to the Serbian legislation.

Binarized cross-approximate entropy in crowdsensing environment.

OBJECTIVES: Personalised monitoring in health applications has been recognised as part of the mobile crowdsensing concept, where subjects equipped with sensors extract information and share them for personal or common benefit. Limited transmission resources impose the use of local analyses methodology, but this approach is incompatible with analytical tools that require stationary and artefact-free data. This paper proposes a computationally efficient binarised cross-approximate entropy, referred to as (X)BinEn, for unsupervised cardiovascular signal processing in environments where energy and processor resources are limited. METHODS: The proposed method is a descendant of the cross-approximate entropy ((X)ApEn). It operates on binary, differentially encoded data series split into m-sized vectors. The Hamming distance is used as a distance measure, while a search for similarities is performed on the vector sets. The procedure is tested on rats under shaker and restraint stress, and compared to the existing (X)ApEn results. RESULTS: The number of processing operations is reduced. (X)BinEn captures entropy changes in a similar manner to (X)ApEn. The coding coarseness yields an adverse effect of reduced sensitivity, but it attenuates parameter inconsistency and binary bias. A special case of (X)BinEn is equivalent to Shannon's entropy. A binary conditional entropy for m =1 vectors is embedded into the (X)BinEn procedure. CONCLUSION: (X)BinEn can be applied to a single time series as an auto-entropy method, or to a pair of time series, as a cross-entropy method. Its low processing requirements makes it suitable for mobile, battery operated, self-attached sensing devices, with limited power and processor resources.

Dependency Structures in Differentially Coded Cardiovascular Time Series.

Objectives. This paper analyses temporal dependency in the time series recorded from aging rats, the healthy ones and those with early developed hypertension. The aim is to explore effects of age and hypertension on mutual sample relationship along the time axis. Methods. A copula method is applied to raw and to differentially coded signals. The latter ones were additionally binary encoded for a joint conditional entropy application. The signals were recorded from freely moving male Wistar rats and from spontaneous hypertensive rats, aged 3 months and 12 months. Results. The highest level of comonotonic behavior of pulse interval with respect to systolic blood pressure is observed at time lags τ = 0, 3, and 4, while a strong counter-monotonic behavior occurs at time lags τ = 1 and 2. Conclusion. Dynamic range of aging rats is considerably reduced in hypertensive groups. Conditional entropy of systolic blood pressure signal, compared to unconditional, shows an increased level of discrepancy, except for a time lag 1, where the equality is preserved in spite of the memory of differential coder. The antiparallel streams play an important role at single beat time lag.

Blood pressure and pulse interval coupling: A copula approach.

In this paper a copula approach is applied as a tool for assessing the measure of statistical dependence of parallel cardiovascular time series. Families of Archimedean copulas (Clayton, Frank and Gumbel) are applied to pulse interval, systolic and diastolic blood pressure recorded from male Wistar rats at baseline conditions, and to their isodistributional surrogates with the same marginal, but randomized joint distribution functions. The influence of time offset of the parallel time series is explored. The amount of data required for a stable working point is discussed.