Evaluation of a Fatigue Detector Using Eye Closure-Associated Indicators Acquired from Truck Drivers in a Simulator Study.

This paper presents a camera-based prototype sensor for detecting fatigue and drowsiness in drivers, which are common causes of road accidents. The evaluation of the detector operation involved eight professional truck drivers, who drove the truck simulator twice-i.e., when they were rested and drowsy. The Fatigue Symptoms Scales (FSS) questionnaire was used to assess subjectively perceived levels of fatigue, whereas the percentage of eye closure time (PERCLOS), eye closure duration (ECD), and frequency of eye closure (FEC) were selected as eye closure-associated fatigue indicators, determined from the images of drivers' faces captured by the sensor. Three alternative models for subjective fatigue were used to analyse the relationship between the raw score of the FSS questionnaire, and the eye closure-associated indicators were estimated. The results revealed that, in relation to the subjective assessment of fatigue, PERCLOS is a significant predictor of the changes observed in individual subjects during the performance of tasks, while ECD reflects the individual differences in subjective fatigue occurred both between drivers and in individual drivers between the 'rested' and 'drowsy' experimental conditions well. No relationship between the FEC index and the FSS state scale was found.

Deep learning-based method for the continuous detection of heart rate in signals from a multi-fiber Bragg grating sensor compatible with magnetic resonance imaging.

A method for the continuous detection of heart rate (HR) in signals acquired from patients using a sensor mat comprising a nine-element array of fiber Bragg gratings during routine magnetic resonance imaging (MRI) procedures is proposed. The method is based on a deep learning neural network model, which learned from signals acquired from 153 MRI patients. In addition, signals from 343 MRI patients were used for result verification. The proposed method provides automatic continuous extraction of HR with the root mean square error of 2.67 bpm, and the limits of agreement were -4.98-5.45 bpm relative to the reference HR.

Development of a new method for assessing the heart rate increase during tests in human carrying centrifuge.

Exposition to head to foot accelerations (+Gz) on human carrying centrifuge are associated with increase in heart rate (HR). Sometimes, especially with extremely high HR values it is almost impossible to distinguish between fast sinus rhythm and supraventricular tachycardia which is essential for the safety of the subject and therefore the decision regarding break the centrifuge examination earlier. AIM: The aim of the work was to answer the question: what is the maximum physiological rise of the sinus heart rate, recorded beat to beat, during tests in the overload centrifuge, which should lead to the suspicion of paroxysmal supraventricular tachycardia? MATERIALS AND METHODS: The material tested was an electrocardiogram (ECG) digital records of 150 pilots, achieved during both GOR and ROR tests, carried out in the human centrifuge. The HR, increase of HR (ΔHR) and their changes accompanying the + Gz acceleration ware analysed. RESULTS: Mean values of the parameters determined from all centrifuge exposures were: HR - 105.8 beats per minutes (bpm,) ΔHR 2.5, + Gz 4.06. There was no relationship between ΔHR and + Gz increase The values of ΔHR, meeting the eligibility criteria for the possible PT, were in the range 2.41 to 11.19 bpm on average 2.5 bpm. CONCLUSIONS: Rapid/unexpected HR beat to beat acceleration (ΔHR) during a GOR or ROR centrifugal test, exceeding 11 beats/min, in relation to the HR rate immediately preceding it and persisting for at least 4 consecutive heart evolutions, requires the attention of the examining doctor, and ECG should be examined for paroxysmal tachycardia.

Detection of respiratory rate using a classifier of waves in the signal from a FBG-based vital signs sensor.

BACKGROUND AND OBJECTIVE: Monitoring of changes in respiratory rate provides information on a patient's psychophysical state. This paper presents a respiratory rate detection method based on analysis of signals from a fiber Bragg grating (FBG)-based sensor. METHODS: The detection method is based on a system of software blocks that identify notches in the signal waveforms, determine their parameters, and then transmit them to the classifier, which decides which of them are the characteristic waves of the respiratory cycle. The classifier of respiratory waves was developed by means of machine learning methods and using the training data obtained from 10 volunteers (7 males, 3 females, age: 41.1 ±â€¯8.28 years, weight: 73.6 ±â€¯15.25 kg, height 173.5 ±â€¯6.43 cm), who were lying in the tube of a 3-Tesla magnetic resonance imaging (MRI) scanner. RESULTS: In the verification study, aimed at assessing the performance of the method for detecting respiratory rate, 15 subjects (14 males, 1 female, age: 20.2 ±â€¯3.00 years, weight: 75.47 ± 10.58 kg, height 179.13 ± 6.27 cm) were involved. Clinically satisfactory results of respiratory rate detection were obtained: root mean square error of 1.48 rpm and the limits of agreement at -2.73 rpm and 3.04 rpm. The results indicate a high efficiency of the classifier, i.e., sensitivity: 96.50 ± 3.44%, precision: 95.42 ± 2.84%, and accuracy: 92.99 ± 3.37%. CONCLUSION: The all-dielectric sensor acquires the respiration curve and the proposed scheme of computation enables for extracting respiratory rate automatically and continuously. This scheme based on machine learning procedures will be integrated into a system to facilitate non-invasive continuous monitoring of MRI patients.

A study of the relationship between the level of anxiety declared by MRI patients in the STAI questionnaire and their respiratory rate acquired by a fibre-optic sensor system.

Magnetic resonance imaging (MRI) patients often experience anxiety-related respiratory disorders, including hyperventilation, but their respiratory indicators are not routinely monitored during scanning. Free from metal parts and immune to electromagnetic radiation, fibre-optic sensors have the potential to better control the patient's condition by providing continuous non-invasive monitoring of the respiratory rate (RR). The study was purposed to assess the relationship between anxiety in MRI patients and their RR acquired by a fibre-optic sensor system. Forty-four subjects were involved in the study. The mean RR values recorded for 2 minutes immediately after the beginning and immediately before the end of the scanning were assessed relative to the State-Trait Anxiety Inventory (STAI) X-1 scores obtained immediately before and immediately after the scanning, respectively. A growth mixture model analysis was performed to statistically differentiate two groups of subjects according to the trends in repeated measures of RR. A significant lowering of the anxiety state was observed in the group characterised by a decrease in RR, whereas essentially no change in anxiety level was observed in the group with a stable RR. The t-test showed significant differences in changes in anxiety between these groups (t(39) = -2.349, p = 0.012, Cohen's d = 2.13).

Development and evaluation of a novel system for inducing orthostatic challenge by tilt tests and lower body negative pressure.

Lower body negative pressure (LBNP) is a method derived from space medicine, which in recent years has been increasingly used by clinicians to assess the efficiency of the cardiovascular regulatory mechanisms. LBNP with combined tilt testing is considered as an effective form of training to prevent orthostatic intolerance. We have developed a prototype system comprising a tilt table and LBNP chamber, and tested it in the context of the feasibility of the device for assessing the pilots' efficiency. The table allows for controlled tilting in the range from -45 to +80° at the maximum change rate of 45°/s. The LBNP value can smoothly be adjusted down to -100 mmHg at up to 20 mmHg/s. 17 subjects took part in the pilot study. A 24-minute scenario included -100 mmHg supine LBNP, head up tilt (HUT) and -60 mmHg LBNP associated with HUT, separated by resting phases. The most noticeable changes were observed in stroke volume (SV). During supine LBNP, HUT and the combined stimulus, a decrease of the SV value by 20%, 40% and below 50%, respectively, were detected. The proposed system can map any pre-programed tilt and LBNP profiles, and the pilot study confirmed the efficiency of performing experimental procedures.

Preliminary Results of the LF/HF Ratio as an Indicator for Estimating Difficulty Level of Flight Tasks.

INTRODUCTION: The main aim of this study was to differentiate the magnitude of a pilot's heart rate variability (HRV) when performing assisted and unassisted flights, as well as simple and complex flight tasks. METHODS: Cardiac monitoring in flights was carried out using a compact, mobile ECG recorder. A frequency analysis of the heart rate (HR) signal was performed to determine the ratio of low-frequency spectral power (LF) to high-frequency spectral power (HF). RESULTS: The LF/HF ratio observed in the zone (M=1.047, SD=0.059) was significantly different than the LF/HF calculated preflight (M=0.877, SD=0.043) and postflight (M=0.793, SD=0.037). There was no main effect of the flight type (unassisted zone flight vs. zone flight with an instructor) on the LF/HF parameter. However, greater psychophysiological load of a pilot was observed in the training zone flights when compared to simple circle flights (main effect of the flight type). CONCLUSIONS: As the LF/HF ratio turned out to be significantly higher in the zone than pre- and postflight, this parameter can be useful for predicting the risk of excessive stress and arousal of pilots during flights. Based on the LF/HF ratio we can also estimate difficulty level of flight tasks, because our research has shown higher values of this parameter in the training zone flights than in simple circle flights.

A method of detecting heartbeat locations in the ballistocardiographic signal from the fiber-optic vital signs sensor.

We present a flexible, easy-to-expand digital signal processing method for detecting heart rate (HR) for cardiac vibration signals of fiber Bragg grating (FBG) sensor. The FBG-based method of measuring HR is possible to use during the magnetic resonance imaging procedure, which is its unique advantage. Our goal was to design a detection method with plurality of parameters and to subject these parameters to genetic algorithm optimization technique. In effect, we arrived at a method that is well able to deal with much distorted signals with low SNR. We proved that the method we developed allows automatic adjustment to the shape of the waves of signal carrying useful information about the moments of heartbeat. Thus, we can easily adapt our technique to the analysis of signals, which contains information on HR, from sensors employing different techniques of strain detection. The proposed method has the capabilities of analyzing signals in semi-real-time (online) with beat-to-beat resolution, significantly low delay, and negligible computational power requirements. We verified our method on recordings in a group of seven subjects. Verification included over 6000 heartbeats (82 min 47 s of recordings). The root-mean-square error of our method does not exceed 6.0 bpm.

Fiber Bragg grating-based sensor for monitoring respiration and heart activity during magnetic resonance imaging examinations.

We present a fiber-optic sensor for monitoring respiration and heart activity designed to operate in the magnetic resonance imaging (MRI) environment. The sensor employs a Plexiglas springboard, which converts movements of the patient's body lying on the board (i.e., lung- and heart-induced vibrations) to strain, where a fiber Bragg grating attached to the board is used to measure this strain. Experimental studies are carried out during thoracic spine MRI examinations. The presence of the metal-free sensor construction in the MRI environment does not pose a threat to the patient and has no influence over the quality of imaging, and the signal is identical to that obtained without any electromagnetic interference. The results show that the sensor is able to accurately reflect the ballistocardiographic signal, enabling determinations of the respiration rate (RR) and heart rate (HR). The data delivered by the sensor are normally distributed on the Bland-Altman plot for the characteristic point determination and exhibit clear dependence on the RR and HR values for the RR and HR determinations, respectively. Measurement accuracies are better than 7% of the average values, and thus, with further development, the sensor will be implemented in routine MRI examinations.

Monitoring respiration and cardiac activity using fiber Bragg grating-based sensor.

This paper shows the design of a fiber-based sensor for living activities in human body and the results of a laboratory evaluation carried out on it. The authors have developed a device that allows for monitoring the vibrations of human body evoked by living activities--breathing and cardiac rhythm. The device consists of a Bragg grating inscribed into a single mode optical fiber and operating on a wavelength of around 1550 nm. The fiber Bragg grating (FBG) is mounted inside a pneumatic cushion to be placed between the backrest of the seat and the back of the monitored person. Deformations of the cushion, involving deformations of the FBG, are proportional to the vibrations of the body leaning on the cushion. Laboratory studies have shown that the sensor allows for obtaining dynamic strains on the sensing FBG in the range of 50-124 µ strain caused by breathing and approximately 8.3 µstrain induced by heartbeat, which are fully measurable by today's FBG interrogation systems. The maximum relative measurement error of the presented sensor is 12%. The sensor's simple design enables it to be easily implemented in pilot's and driver's seats for monitoring the physiological condition of pilots and drivers.