Linear and nonlinear analyses of normal and fatigue heart rate variability signals for miners in high-altitude and cold areas

Classification of exercise fatigue levels by multi-class SVM from ECG and HRV

Among the various physiological signals, electrocardiogram (ECG) is a valid criterion for the classification of various exercise fatigue. In this study, we combine features extracted by deep neural networks with linear features from ECG and heart rate variability (HRV) for exercise fatigue classification. First, the ECG signals are converted into 2-D images by using the short-term Fourier transform (STFT), and image features are extracted by the visual geometry group (VGG) . The extracted image and linear features of ECG and HRV are sent to the different types of classifiers to distinguish distinct exercise fatigue level. To validate performance, the proposed methods are tested on (i) an open-source EPHNOGRAM dataset and (ii) a self-collected dataset (n = 51). The results reveal that the classification based on the concatenated features has the highest accuracy, and the calculation time of the system is also significantly reduced. This demonstrates that the proposed novel hybrid approach can be used to assist in improving the accuracy and timeliness of exercise fatigue classification in a real-time exercise environment. The experimental results show that the proposed method outperforms other recent state-of-the-art methods in terms of accuracy 96.90%, sensitivity 96.90%, F1-score of 0.9687 in EPHNOGRAM and accuracy 92.17%, sensitivity 92.63%, F1-score of 0.9213 in self-collected dataset.

Effects of different extreme cold exposure on heart rate variability

Frequent extreme cold events in recent years have brought serious threats to outdoor workers and rescuers. Changes in ambient temperature are associated with altered cardiac autonomic function. The study aims to investigate heart rate variability (HRV) and its relationship to other physiological parameters under extreme cold exposures. Twelve males underwent a 30-min preconditioning phase in a neutral environment followed by a 30-min cold exposure (-5, -10, -15, and -20 °C). Time-domain indexes(meanRR, SDNN, RMSSD, and pNN50), frequency domain indexes [Log(HF), Log(LF), and low frequency/high frequency (LF/HF)], parasympathetic nervous system (PNS), and sympathetic nervous system (SNS) were analysed. Results showed all HRV indexes of four cold exposures were significant. The decrease in temperature was accompanied by progressive PNS activation with SNS retraction. SDNN was the most sensitive HRV index and had good linear relationships with blood pressure, pulse, and hand temperature. The results are significant for formulating safety protection strategies for workers in extremely cold environments.Practitioner Summary: This study investigated heart rate variability (HRV) in 12 males during a 30-min cold exposure (-5, -10, -15, and -20 °C). Results showed all HRV indexes of four cold exposures were significant. The decrease in temperature was accompanied by progressive PNS activation with SNS retraction. SDNN was the most sensitive HRV index and had good linear relationships with blood pressure, pulse, and hand temperature.

Dose-effect of exercise intervention on heart rate variability of acclimatized young male lowlanders at 3,680 m

This study investigated whether exercise could improve the reduced HRV in an environment of high altitude. A total of 97 young, healthy male lowlanders living at 3,680 m for >1 year were recruited. They were randomized into four groups, of which three performed-low-, moderate-, and high-intensity (LI, MI, HI) aerobic exercise for 4 weeks, respectively. The remaining was the control group (CG) receiving no intervention. For HI, compared to other groups, heart rate (p = 0.002) was significantly decreased, while standard deviation of RR intervals (p < 0.001), SD2 of Poincaré plot (p = 0.046) and the number of successive RR interval pairs that differ by > 50 ms divided by total number of RR (p = 0.032), were significantly increased after intervention. For MI, significantly increase of trigonometric interpolation in NN interval (p = 0.016) was observed after exercise. Further, a decrease in systolic blood pressure (SBP) after high-intensity exercise was found significantly associated with an increase in SD2 (r = - 0.428, p = 0.042). These results indicated that there was a dose effect of different intensities of aerobic exercise on the HRV of acclimatized lowlanders. Moderate and high-intensity aerobic exercise would change the status of the autonomic nervous system (ANS) and decrease the blood pressure of acclimatized lowlanders exposed to high altitude.

A fast permutation entropy for pulse rate variability online analysis with one-sample recursion

Pulse rate variability (PRV) signals are extracted from pulsation signal can be effectively used for cardiovascular disease monitoring in wearable devices. Permutation entropy (PE) algorithm is an effective index for the analysis of PRV signals. However, PE is computationally intensive and impractical for online PRV processing on wearable devices. Therefore, to overcome this challenge, a fast permutation entropy (FPE) algorithm is proposed based on the microprocessor data updating process in this paper, which can analyze PRV signals with single-sample recursive. The simulation data and PRV signals extracted from pulse signals in "Fantasia database" were utilized to verify the performance and accuracy of the improved methods. The results show that the speed of FPE is 211 times faster than PE and maintain the accuracy of algorithm (Root Mean Squared Error = 0) for simulation data with a length of 10,000 samples and embedded dimension m = 5, time delay τ = 5, buffer length Lw = 512. For the RRV signals with 3000∼5000 samples, the result show that the consumption of FPE is less than 0.2 s, which is 175 times faster than PE. This indicates that FPE has better application performance than PE. Furthermore, a low-cost wearable signal detection system is developed to verify the proposed method, the result show that the proposed method can calculate the FPE of PRV signal online with single-sample recursive calculation. Subsequently, entropy-based features are used to explore the performance of decision trees in identifying life-threatening arrhythmias, and the method resulted in a classification accuracy of 85.43%. It can therefore be inferred that the proposed method has great potential in cardiovascular disease.

Machine Learning Based on Event-Related EEG of Sustained Attention Differentiates Adults with Chronic High-Altitude Exposure from Healthy Controls

(1) Objective: The aim of this study was to examine the effect of high altitude on inhibitory control processes that underlie sustained attention in the neural correlates of EEG data, and explore whether the EEG data reflecting inhibitory control contain valuable information to classify high-altitude chronic hypoxia and plain controls. (2) Methods: 35 chronic high-altitude hypoxic adults and 32 matched controls were recruited. They were required to perform the go/no-go sustained attention task (GSAT) using event-related potentials. Three machine learning algorithms, namely a support vector machine (SVM), logistic regression (LR), and a decision tree (DT), were trained based on the related ERP components and neural oscillations to build a dichotomous classification model. (3) Results: Behaviorally, we found that the high altitude (HA) group had lower omission error rates during all observation periods than the low altitude (LA) group. Meanwhile, the ERP results showed that the HA participants had significantly shorter latency than the LAs for sustained potential (SP), indicating vigilance to response-related conflict. Meanwhile, event-related spectral perturbation (ERSP) analysis suggested that lowlander immigrants exposed to high altitudes may have compensatory activated prefrontal cortexes (PFC), as reflected by slow alpha, beta, and theta frequency-band neural oscillations. Finally, the machine learning results showed that the SVM achieved the optimal classification F1 score in the later stage of sustained attention, with an F1 score of 0.93, accuracy of 92.54%, sensitivity of 91.43%, specificity of 93.75%, and area under ROC curve (AUC) of 0.97. The results proved that SVM classification algorithms could be applied to identify chronic high-altitude hypoxia. (4) Conclusions: Compared with other methods, the SVM leads to a good overall performance that increases with the time spent on task, illustrating that the ERPs and neural oscillations may provide neuroelectrophysiological markers for identifying chronic plateau hypoxia.

Applications of wireless sensor networks to improve occupational safety and health in underground mines

INTRODUCTION

The very complex and hazardous environment of underground mines may significantly contribute to occupational fatalities and injuries. Deploying wireless sensor network (WSN) technology has the potential to improve safety and health monitoring of miners and operators. However, the application of WSN in the industry is not fully understood and current research themes in this area are fragmented. Thus, there is a need for a comprehensive review that directly explores the contribution of WSNs to occupational safety and health (OSH) in underground mines.

METHOD

This study aims to conduct a systematic literature review on the existing applications of WSNs for improving OSH in the underground mining industry to pinpoint innovative research themes and their main achievements, reveal gaps and shortcomings in the literature, recommend avenues for future scholarly works, and propose potential safety interventions. The major contribution of this review is to provide researchers and practitioners with a holistic understanding of the integration of WSN applications into underground mine safety and health management.

RESULTS

The review results have been categorized and discussed under three predominant categories including location monitoring and tracking, physiological and body kinematics monitoring, and environmental monitoring. Finally, seven major directions for future research and practical interventions have been identified based on the existing research gaps including: (1) further applications of WSNs for underground mining OSH management; (2) application of WSNs from research to real-world practice; (3) big data analytics and management; (4) deploying multiple WSNs-based monitoring systems; (5) integration of WSNs with other communication systems; (6) adapting WSNs to the Internet of Things (IoT) infrastructure; and (7) autonomous WSNs.

Cardiorespiratory function, resting metabolic rate and heart rate variability in coal miners exposed to hypobaric hypoxia in highland workplace

Background

Owing to intermittent/acute exposure to hypobaric hypoxia, highland miners may often suffer, the physiological characteristics between highland and lowland miners, however, are rarely reported. The objective of this study was to compare the physiological characteristics of coal miners working at disparate altitudes.

Methods

Twenty-three male coal mining workers acclimating to high altitude for 30 ± 6 days in Tibet (highland group; approx. 4500 m above sea level; 628.39 millibar), and 22 male coal mining workers in Hebei (lowland group; less than 100 m above sea level; 1021.82 millibar) were recruited. Tests were conducted to compare ventilatory parameters, circulation parameters, resting metabolic rate (RMR), and heart rate variability (HRV) indices between the two groups in resting state.

Results

Ventilation volume per minute (VE) of the highland group was markedly raised compared to that of the lowland group (11.70 ± 1.57 vs. 8.94 ± 1.97 L/min, p = 0.000). In the meanwhile, O2 intake per heart beat (VO2/HR) was strikingly decreased (3.54 ± 0.54 vs. 4.36 ± 0.69 ml/beat, p = 0.000). Resting metabolic rate relevant to body surface area (RMR/BSA) was found no significant difference between the two groups. Evident reduction in standard deviation of NN intervals (SDNN) and remarkable increase in ratio of low- and high- frequency bands (LF/HF) were manifest in highland miners compared to that of lowland ones (110.82 ± 33.34 vs. 141.44 ± 40.38, p = 0.008 and 858.86 ± 699.24 vs. 371.33 ± 171.46, p = 0.003; respectively).

Conclusions

These results implicate that long-term intermittent exposure to high altitude can lead miners to an intensified respiration, a compromised circulation and a profound sympathetic-parasympathetic imbalance, whereas the RMR in highland miners does not distinctly decline.

Study on the nonfatigue and fatigue states of orchard workers based on electrocardiogram signal analysis

In recent years, fatigue has become an important issue in modern life that cannot be ignored, especially in some special occupations. Agricultural workers are high-risk occupations that, under fatigue conditions over a long period, will cause health problems. In China, since very few studies have focused on the fatigue state of agricultural workers, we were interested in using electrocardiogram (ECG) signals to analyze the fatigue state of agricultural workers. Healthy agricultural workers were randomly recruited from hilly orchards in South China. Through the field experiment, 130 groups of 5-min interval ECG signals were collected, and we analyzed the ECG signal by HRV. The time domain (meanHR, meanRR, SDNN, RMSSD, SDSD, PNN20, PNN50 and CV), frequency domain (VLF percent, LF percent, HF percent, LF norm, HF norm and LF/HF) and nonlinear parameters (SD1, SD2, SD1/SD2 and sample entropy) were calculated and Spearman correlation coefficient analysis and Mann-Whitney U tests were performed on each parameter for further analysis. For all subjects, nine parameters were slightly correlated in nonfatigue and fatigue state. Six parameters were significantly increased and ten HRV parameters were significantly decreased compared the nonfatigue state. As for males, fifteen parameters were significantly different, and for females, eighteen parameters were significantly different. In addition, the probability density functions of SDNN, SDSD, VLF%, HFnorm and LF/HF were significantly different in nonfatigue and fatigue state for different genders, and the nonlinear parameters become more discrete compared the nonfatigue state. Finally, we obtained the most suitable parameters, which reflect the fatigue characteristics of orchard workers under different genders. The results have instructional significance for identifying fatigue in orchard workers and provide a convincing and valid reference for clinical diagnosis.

Empirical study of employee loyalty and satisfaction in the mining industry using structural equation modeling

Mining is a high-risk industry and a crucial economic driver that has a crucial role in the economies of countries worldwide. The implications of the labor market on the sustainability of the mining industry have increased the importance of sustainable human resource management at the strategic level of mining and safety management. In this article, from the perspective of management research in an energy production enterprise, we investigated the relationship between employee loyalty and employee satisfaction through a survey that targets employee loyalty, work quality, and job satisfaction and the relationship between enterprise image and switching costs. Based on service profit chain theory, we established a research model for mining employee loyalty, and 500 miners in a typical extreme mining environment in China were surveyed. The study hypotheses were tested using a structural equation model and an employee loyalty model, followed by empirical testing of the models. Employee loyalty was significantly associated with enterprise image and employee satisfaction, work quality indirectly affected loyalty through satisfaction, and the impact of switching costs on employee loyalty was not significant. We provide strong empirical evidence to help enterprises improve sustainable human resource management and regulatory policies, with important implications for safety production. Our study also provides a useful reference for further studies of sustainable human resource management in mining.

Powder Explosion Inhibitor Prepared from Waste Incinerator Slag: Applied to Explosion Suppression of Oil Shale Dust Explosion

In this paper, a method for waste incineration slag is proposed. An incineration acidification alkalization modification was carried out based on the characteristics of the oxides (SiO2, CaO, Al2O3, Fe2O3, and MgO) of waste incineration slag. With modified slag as the carrier and NaHCO3 as the supporter, a slag-based composite powder explosion inhibitor was prepared with the solvent-crystallization wet coating (WCSC), ball milling dry coating (DCBM), and air impact dry coating (DCAI) methods. The advantages and disadvantages of the three methods were compared and analyzed. Explosion suppression experiments on oil shale dust were carried out, and the explosion suppression mechanism was described. The explosion suppression process of the modified slag–NaHCO3 composite powder explosion inhibitor for oil shale dust was found to involve a synergy of physical and chemical inhibition. This explosion suppression mechanism indicates three requirements for the preparation and application of industrial solid waste-based composite powder explosion inhibitors. The feasibility of preparing composite powder explosion inhibitors from waste incinerator slag was discussed from the experimental point of view and its explosion suppression performance on oil shale dust was studied with the intention of providing a new form of resource utilization for waste incinerator slag.

Longitudinal Changes and Recovery in Heart Rate Variability of Young Healthy Subjects When Exposure to a Hypobaric Hypoxic Environment

Background: The autonomic nervous system (ANS) is crucial for acclimatization. Investigating the responses of acute exposure to a hypoxic environment may provide some knowledge of the cardiopulmonary system’s adjustment mechanism.

Objective: The present study investigates the longitudinal changes and recovery in heart rate variability (HRV) in a young healthy population when exposed to a simulated plateau environment.

Methods: The study followed a strict experimental paradigm in which physiological signals were collected from 33 healthy college students (26 ± 2 years, 171 cm ± 7 cm, 64 ± 11 kg) using a medical-grade wearable device. The subjects were asked to sit in normoxic (approximately 101 kPa) and hypoxic (4,000 m above sea level, about 62 kPa) environments. The whole experimental process was divided into four stable resting measurement segments in chronological order to analyze the longitudinal changes of physical stress and recovery phases. Seventy-six time-domain, frequency-domain, and non-linear indicators characterizing rhythm variability were analyzed in the four groups.

Results: Compared to normobaric normoxia, participants in hypobaric hypoxia had significantly lower HRV time-domain metrics, such as RMSSD, MeanNN, and MedianNN (p &lt; 0.01), substantially higher frequency domain metrics such as LF/HF ratio (p &lt; 0.05), significantly lower Poincaré plot parameters such as SD1/SD2 ratio and other Poincaré plot parameters are reduced considerably (p &lt; 0.01), and Refined Composite Multi-Scale Entropy (RCMSE) curves are reduced significantly (p &lt; 0.01).

Conclusion: The present study shows that elevated heart rates, sympathetic activation, and reduced overall complexity were observed in healthy subjects exposed to a hypobaric and hypoxic environment. Moreover, the results indicated that Multiscale Entropy (MSE) analysis of RR interval series could characterize the degree of minor physiological changes. This novel index of HRV can better explain changes in the human ANS.

Information fusion and multi-classifier system for miner fatigue recognition in plateau environments based on electrocardiography and electromyography signals

BACKGROUND AND OBJECTIVE

Human factors are important contributors to accidents, especially human error induced by fatigue. In this study, field tests and analyses were conducted on physiological indexes extracted from electrocardiography (ECG) and electromyography (EMG) signals in miners working under the extreme conditions of a plateau environment. To provide insights into models for fatigue classification and recognition based on machine learning, multi-modal feature information fusion and miner fatigue identification based on ECG and EMG signals as physiological indicators were studied.

METHODS

Fifty-five miners were randomly selected as field test subjects, and characteristic signals were extracted from 110 groups of ECG and EMG signals as the basic signals for fatigue analysis. We conducted principal component analysis (PCA) and grey relational analysis (GRA) on the measurement indicators. Support vector machine (SVM), random forest (RF) and extreme gradient boosting (XG-Boost) machine learning models were used for fatigue classification based on multi-modal information fusion. The area under the receiver operating characteristic (ROC) curve and the confusion matrix were used to evaluate the performance of the recognition models.

RESULTS

The ECG and EMG signals showed obvious changes with fatigue. The results of fatigue model identification showed that PCA feature fusion was superior to GRA feature fusion for all three machine learning approaches, and XG-Boost achieved the best performance, with a recognition accuracy of 89.47%, a sensitivity and specificity of 100%, and an AUC of 0.90. The SVM model also showed good recognition performance (89.47% accuracy, AUC=0.89). The worst performance was that of the RF model, with a recognition accuracy of only 78.95%.

CONCLUSIONS

This study shows that the physiological indexes of ECG and EMG exhibit obvious, regular changes with fatigue and that it is feasible to use SVM, RF and XG-Boost models for miner fatigue identification. The PCA fusion technique can improve the identification accuracy more than the GRA method. XG-Boost classification yields the best accuracy and robustness. This study can serve as a reference for clinical research on the identification of human fatigue at high altitudes and for the clinical study of acute mountain sickness and human acclimatization to high altitudes.

Non-Invasive Physiological Monitoring for Physical Exertion and Fatigue Assessment in Military Personnel: A Systematic Review

During operational activities, military personnel face extremely demanding circumstances, which when combined lead to severe fatigue, influencing both their well-being and performance. Physical exertion is the main condition leading to fatigue, and its continuous tracking would help prevent its effects. This review aimed to investigate the up-to-date progress on non-invasive physiological monitoring to evaluate situations of physical exertion as a pre-condition to fatigue in military populations, and determine the potential associations between physiological responses and fatigue, which can later result in decision-making indicators to prevent health-related consequences. Adhering to the PRISMA Statement, four databases (Scopus, Science Direct, Web of Science and PubMed) were used for a literature search based on combinations of keywords. The eligibility criteria focused on studies monitoring physiological variables through non-invasive objective measurements, with these measurements being developed in military field, combat, or training conditions. The review process led to the inclusion of 20 studies. The findings established the importance of multivariable assessments in a real-life context to accurately characterise the effects of military practices. A tendency for examining heart rate variables, thermal responses, and actigraphy measurements was also identified. The objectives and experimental protocols were diverse, but the effectiveness of non-invasive measurements in identifying the most fatigue-inducing periods was demonstrated. Nevertheless, no assessment system for standardised application was presented. Future work may include the development of assessment methods to translate physiological recordings into actionable information in real-time and mitigate the effects of fatigue on soldiers’ performance accurately.

Psychophysiological data-driven multi-feature information fusion and recognition of miner fatigue in high-altitude and cold areas

Fatigue-induced human error is a leading cause of accidents. The purpose of this exploratory study in China was to perform field tests to measure fatigue psychophysiological parameters, such as electrocardiography (ECG), electromyography (EMG), pulse, blood pressure, reaction time and vital capacity (VC), in miners in high-altitude and cold areas and to perform multi-feature information fusion and fatigue identification. Forty-five miners were randomly selected as subjects for a field test, and feature signals were extracted from 90 psychophysiological features as basic signals for fatigue analysis. Fatigue sensitivity indices were obtained by Pearson correlation analysis, t-test and receiver operating characteristic (ROC) curve performance evaluation. The ECG time-domain, ECG frequency-domain, EMG, VC, systolic blood pressure (SBP), and pulse were significantly different after miner fatigue. The support vector machine (SVM) and random forest (RF) techniques were used to classify and identify fatigue by information fusion and factor combination. The optimal fatigue classification factors were ECG-FD (CV Accuracy = 85.0%) and EMG (CV Accuracy = 90.0%). The optimal combination of factors was ECG-TD + ECG-FD + EMG (CV accuracy = 80.0%). Furthermore, SVM machine learning had a good recognition effect. This study shows that SVM and RF can effectively identify miner fatigue based on fatigue-related factor combinations. ECG-FD and EMG are the best indicators of fatigue, and the best performance and robustness are obtained with three-factor combination classification. This study on miner fatigue identification provides a reference for research on clinical medicine and the identification of human fatigue under high-altitude, cold and low-oxygen conditions.