Fatigue Estimation Research Articles

Single-process 3D-printed structures with vibration durability self-awareness

The recent advances in additive manufacturing technology allow the realization of single-process thermoplastic material extrusion (TME) 3D-printed embedded sensors, leading to the easy and inexpensive production of smart structures. While single-process TME dynamic strain sensors have already been researched, vibration durability self-awareness is more than just an additional 3D printed strain sensor and several questions need to be answered. Is the durability self-aware sensors position structure-specific? Is the fatigue life of the sensory element longer than the base structure? Does the fatigue influence the self-awareness capability? Those and several other questions are theoretically and experimentally addressed in this research. Two different fatigue identification methods are researched (i.e. the peak-response and the frequency-drop methods). It was found that the vibration durability self-aware structure printed in a single process is viable and the frequency-drop based method gives reliable fatigue estimation; the fatigue damage was correctly identified even in the case the sensory element was 3D printed in the fatigue zone and already significantly damaged. This research opens up new capabilities for self-aware TME 3D-printed structures. • 3D printed durability self-aware structures are introduced. • Sensing element location and geometry is researched for durability and identification influence. • Two self-awareness identification methods are researched (amplitude and frequency based). • Frequency based self-awareness is reliable even when damage is already relatively high.

Adaptive Cooperative Control for Hybrid FES-Robotic Upper Limb Devices: a Simulation Study.

Robotic systems and Functional Electrical Stimulation (FES) are common technologies exploited in motor rehabilitation. However, they present some limits. To overcome the weaknesses of both approaches, hybrid cooperative devices have been developed, which combine the action of the robot and that of the electrically stimulated muscles on the same joint. In this work, we present a novel adaptive cooperative controller for the rehabilitation of the upper limb. The controller comprises an allocator - which breaks down the reference torque between the motor and the FES a-priori contributions based on muscle fatigue estimation - an FES closed-loop controller, and an impedance control loop on the motor to correct trajectory tracking errors. The controller was tested in simulation environment reproducing elbow flexion/extension movements. Results showed that the controller could reduce motor torque requirements with respect to the motor-only case, at the expense of trajectory tracking performance. Moreover, it could improve fatigue management with respect to the FES-only case. In conclusion, the proposed control strategy provides a good trade-off between motor torque consumption and trajectory tracking performance, while the allocator manages fatigue-related phenomena.Clinical relevance-The use of allocation proves to be effective in both reducing motor torque and FES-induced muscle fatigue and might be an effective solution for hybrid FES-robotic systems.

Activity-Aware Deep Cognitive Fatigue Assessment using Wearables.

Cognitive fatigue is a common problem among workers which has become an increasing global problem. While existing multi-modal wearable sensors-aided automatic cognitive fatigue monitoring tools have focused on physical and physiological sensors (ECG, PPG, Actigraphy) analytic on specific group of people (say gamers, athletes, construction workers), activity-awareness is utmost importance due to its different responses on physiology in different person. In this paper, we propose a novel framework, Activity-Aware Recurrent Neural Network (AcRoNN), that can generalize individual activity recognition and improve cognitive fatigue estimation significantly. We evaluate and compare our proposed method with state-of-art methods using one real-time collected dataset from 5 individuals and another publicly available dataset from 27 individuals achieving max. 19% improvement over the baseline model.

Ultra Low-Cycle Fatigue Behavior Comparison between Additively Manufactured and Rolled 17-4 PH (AISI 630) Stainless Steels

This study investigates the mechanical behavior of additively manufactured (AM) 17-4 PH (AISI 630) stainless steels and compares their behavior to traditionally produced wrought counterparts. The goal of this study is to understand the key parameters influencing AM 17-4 PH steel fatigue life under ULCF conditions and to develop simple predictive models for fatigue-life estimation in AM 17-4 steel components. In this study, both AM and traditionally produced (wrought) material samples are fatigue tested under fully reversed (R = −1) strain controlled (2–4% strain) loading and characterized using micro-hardness, x-ray diffraction, and fractography methods. Results indicate decreased fatigue life for AM specimens as compared to wrought 17-4 PH specimens due to fabrication porosity and un-melted particle defect regions which provide a mechanism for internal fracture initiation. Heat treatment processes performed in this work, to both the AM and wrought specimens, had no observable effect on ULCF behavior. Result comparisons with an existing fatigue prediction model (the Coffin–Manson universal slopes equation) demonstrated consistent over-prediction of fatigue life at applied strain amplitudes greater than 3%, likely due to inherent AM fabrication defects. An alternative empirical ULCF capacity equation is proposed herein to aid future fatigue estimations in AM 17-4 PH stainless steel components.

Aircrew Actual vs. Prescriptive Sleep Schedules and Resulting Fatigue Estimates.

BACKGROUND: Fatigue is an insidious and costly occurrence in the aviation community, commonly a consequence of insufficient sleep. Some organizations use scheduling tools to generate prescriptive sleep schedules to help aircrew manage their fatigue. It is important to examine whether aircrew follow these prescriptive schedules, especially in very dynamic environments. The current study compares aircrew sleep during missions to prescriptive sleep schedules generated by a mission scheduling tool. METHODS: Participating in the study were 44 volunteers (Mage= 28.23, SDage= 4.23; Proportionmale= 77.27%) from a C-17 mobility squadron providing 25 instances of sleep and mission data (80 flights total). Aircrew wore actigraph watches to measure sleep during missions and prescriptive sleep schedules were collected. Actual and prescriptive sleep was compared with calculated performance effectiveness values per minute across mission flights. RESULTS: Prescriptive schedules generally overestimated effectiveness during missions relative to estimated actual sleep, potentially causing shifts in effectiveness to ranges of increased risk requiring elevated fatigue mitigation efforts. Actual and prescriptive effectiveness estimates tended to increasingly diverge over the course of missions, which magnifies differences on longer missions. DISCUSSION: The current study suggests that aircrew sleep during missions often does not align with prescriptive sleep schedules generated by mission planning software, resulting in effectiveness estimates that are generally lower than predicted. This might discourage aircrew from using mission effectiveness graphs as a fatigue mitigation tool. Additionally, because fatigue estimates factor into overall operational risk management processes, these schedules might underestimate risks to safety, performance, and health. Morris MB, Veksler BZ, Krusmark MA, Gaines AR, Jantscher HL, Gunzelmann G. Aircrew actual vs. prescriptive sleep schedules and resulting fatigue estimates. Aerosp Med Hum Perform. 2021; 92(10):806814.

Assessment of thermal fatigue induced by dryout front oscillation in printed circuit steam generator

A printed circuit steam generator (PCSG) is being considered as the component for pressurized water reactor (PWR) type small modular reactor (SMR) that can further reduce the physical size of the system. Since a steam generator in many PWR-type SMR generates superheated steam, it is expected that dryout front oscillation can potentially cause thermal fatigue failure due to cyclic thermal stresses induced by the transition in boiling regimes between convective evaporation and film boiling. To investigate the fatigue issue of a PCSG, a reference PCSG is designed in this study first using an in-house PCSG design tool. For the stress analysis, a finite element method analysis model is developed to obtain the temperature and stress fields of the designed PCSG. Fatigue estimation is performed based on ASME Boiler and pressure vessel code to identify the major parameters influencing the fatigue life time originating from the dryout front oscillation. As a result of this study, the limit on the temperature difference between the hot side and cold side fluids is obtained. Moreover, it is found that the heat transfer coefficient of convective evaporation and film boiling regimes play an essential role in the fatigue life cycle as well as the temperature difference.

A cross-sectional study exploring overlap in post-stroke fatigue caseness using three fatigue instruments: Fatigue Severity Scale, Fatigue Questionnaire and the Lynch’s Clinical Interview

ObjectivePost stroke fatigue (PSF) is a frequent symptom affecting 25–73% of stroke survivors. The variability in estimates of prevalence found across studies reflects differences in fatigue measures and use of different cut-offs for defining clinically significant fatigue. The main aim of this study is to explore the frequency and overlap in caseness of fatigue using three different fatigue measures in a sample of patients at 3 months post stroke. Furthermore, we wanted to explore the instrument's associations with demographic and clinical characteristics. MethodsThe sample consists of 93 patients with new onset stroke. This cross-sectional study includes three measurements of fatigue, The Fatigue Severity Scale (FSS), The Chalder Fatigue Questionnaire (FQ) and the Lynch Interview. Medical, physical, psychological data and estimates of pre-stroke fatigue were collected 3 months post stroke. ResultsThe FQ using the bimodal scoring yielded about 2.5 more fatigue cases (n = 57) than the FSS with a cut-off mean score of 5 (n = 22). The Lynch interview identified 48 patients as fatigue cases. Conducting multivariate analyses, the three instruments were differently associated with predictor variables such as prestroke fatigue, reduced balance and burden of symptoms reported post stroke. ConclusionThe use of different instruments leads to a large variability in identifying fatigue cases in a sample of stroke patients. Scientifically and clinically a clarification and consensus on how to measure fatigue is warranted. Without correct identification of PSF-cases, knowledge about the causes of fatigue and development of tailored and interdisciplinary interventions are further delayed.

Model-based data augmentation for user-independent fatigue estimation

ObjectiveUser-independent recognition of exercise-induced fatigue from wearable motion data is challenging, due to inter-participant variability. This study aims to develop algorithms that can accurately estimate fatigue during exercise. MethodsA novel approach for wearable sensor data augmentation was used to generate (via OpenSim) a large corpus of simulated wearable human motion data, based on a small corpus of human motion data measured using optical sensors. Simulated data is generated using detailed kinematic modelling with variations based on human anthropometry datasets. Using both the recorded and generated data, we trained three different neural networks (Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), DeepConvLSTM) to perform person-independent fatigue estimation from wearable motion data. ResultsThe estimation performance increased with the amount of simulated training data. Accuracy and correlation values were higher with the proposed data augmentation method as compared to other general time series augmentation methods (e.g, rotation, jettering, magnitude wrapping) with the same amount of training data. An accuracy of 87% and a Pearson correlation coefficient of 90% were achieved on unseen data when the DeepConvLSTM model was trained with the proposed augmented dataset. ConclusionThe enlarged dataset significantly improves the prediction of inter-individual fatigue. Significance: Appropriate augmentation techniques for biomechanical data can improve model accuracy and reduce the need for expensive data collection.

Analysis of turbulence models fitted to site, and their impact on the response of a bottom-fixed wind turbine

This study compares a wind field recommended by the wind turbine design standards to more realistic wind fields based on measurements. The widely used Mann spectral tensor model with inputs recommended by the standard, is compared to FitMann, the Mann model with inputs fitted to measurements and TIMESR; using measured time series combined with the Davenport coherence model. The Mann model produces too low energy levels at the lowest frequencies of the wind spectra, while the wind spectra generated by FitMann approaches the measured values. TIMESR reproduces the measured spectral values at all frequencies. The different models give similar vertical coherence, while the Mann and FitMann models give lower horizontal coherence than TIMESR. Investigating the wind loads on a bottom-fixed 10-MW wind turbine, the spectra for the tower bottom fore-aft and blade root flapwise bending moment follow the shape of the wind spectra closely at low frequencies. The low-frequency range is important for the blade root and in particular the tower bottom bending moment. Thus, the TIMESR model, followed by FitMann, is assumed to give the most accurate fatigue estimates. For the specific situation analysed in this study, the FitMann model gives only 18 and 5 % lower estimates than TIMESR of the tower bottom and blade root damage equivalent bending moments, while the Mann model gives 27 % and 12 % lower estimates. The tower top yaw and fore-aft bending moments depend on the wind coherence. For the specific situation analysed in this study, the FitMann model gives 9 and 5 % higher estimates of the tower top yaw and tower top damage equivalent (bending) moments compared to TIMESR, while the Mann model gives 23 % and 18 % higher estimates. Since only measurements of the vertical coherence are available, it is not clear which model is superior for the tower top moments. However, the importance of a proper coherence model is documented.

Machine Learning Approach for Fatigue Estimation in Sit-to-Stand Exercise.

Physical exercise (PE) has become an essential tool for different rehabilitation programs. High-intensity exercises (HIEs) have been demonstrated to provide better results in general health conditions, compared with low and moderate-intensity exercises. In this context, monitoring of a patients’ condition is essential to avoid extreme fatigue conditions, which may cause physical and physiological complications. Different methods have been proposed for fatigue estimation, such as: monitoring the subject’s physiological parameters and subjective scales. However, there is still a need for practical procedures that provide an objective estimation, especially for HIEs. In this work, considering that the sit-to-stand (STS) exercise is one of the most implemented in physical rehabilitation, a computational model for estimating fatigue during this exercise is proposed. A study with 60 healthy volunteers was carried out to obtain a data set to develop and evaluate the proposed model. According to the literature, this model estimates three fatigue conditions (low, moderate, and high) by monitoring 32 STS kinematic features and the heart rate from a set of ambulatory sensors (Kinect and Zephyr sensors). Results show that a random forest model composed of 60 sub-classifiers presented an accuracy of 82.5% in the classification task. Moreover, results suggest that the movement of the upper body part is the most relevant feature for fatigue estimation. Movements of the lower body and the heart rate also contribute to essential information for identifying the fatigue condition. This work presents a promising tool for physical rehabilitation.

Vibration Fatigue Damage Estimation by New Stress Correction Based on Kurtosis Control of Random Excitation Loadings.

In the pioneer CAE stage, life assessment is the essential part to make the product meet the life requirement. Commonly, the lives of flexible structures are determined by vibration fatigue which accrues at or close to their natural frequencies. However, existing PSD vibration fatigue damage estimation methods have two prerequisites for use: the behavior of the mechanical system must be linear and the probability density function of the response stresses must follow a Gaussian distribution. Under operating conditions, non-Gaussian signals are often recorded as excitation (usually observed through kurtosis), which will result in non-Gaussian response stresses. A new correction is needed to make the PSD approach available for the non-Gaussian vibration to deal with the inevitable extreme value of high kurtosis. This work aims to solve the vibration fatigue estimation under the non-Gaussian vibration; the key is the probability density function of response stress. This work researches the importance of non-Gaussianity numerically and experimentally. The beam specimens with two notches were used in this research. All excitation stays in the frequency range that only affects the second natural frequency, although their kurtosis is different. The results show that the probability density function of response stress under different kurtoses can be obtained by kurtosis correction based on the PSD approach of the frequency domain.

Online Mental Fatigue Monitoring via Indirect Brain Dynamics Evaluation

Driver mental fatigue leads to thousands of traffic accidents. The increasing quality and availability of low-cost electroencephalogram (EEG) systems offer possibilities for practical fatigue monitoring. However, non-data-driven methods, designed for practical, complex situations, usually rely on handcrafted data statistics of EEG signals. To reduce human involvement, we introduce a data-driven methodology for online mental fatigue detection: self-weight ordinal regression (SWORE). Reaction time (RT), referring to the length of time people take to react to an emergency, is widely considered an objective behavioral measure for mental fatigue state. Since regression methods are sensitive to extreme RTs, we propose an indirect RT estimation based on preferences to explore the relationship between EEG and RT, which generalizes to any scenario when an objective fatigue indicator is available. In particular, SWORE evaluates the noisy EEG signals from multiple channels in terms of two states: shaking state and steady state. Modeling the shaking state can discriminate the reliable channels from the uninformative ones, while modeling the steady state can suppress the task-nonrelevant fluctuation within each channel. In addition, an online generalized Bayesian moment matching (online GBMM) algorithm is proposed to online-calibrate SWORE efficiently per participant. Experimental results with 40 participants show that SWORE can maximally achieve consistent with RT, demonstrating the feasibility and adaptability of our proposed framework in practical mental fatigue estimation.

139 Does Extraversion Predict Subjective Ratings of Sleepiness and Performance During Sleep Deprivation?

Abstract Introduction Repeated exposure to total sleep deprivation (TSD) within individuals has demonstrated task-specific, trait-like individual differences in cognitive impairment and subjective sleepiness. Research has suggested that introversion/extraversion may predict individual vulnerability to TSD. While previous analyses have found that extraversion does not reliably predict objective performance impairment on the psychomotor vigilance test (PVT) during TSD, it is not known whether extraversion may predict individuals’ subjective responses to TSD, including subjective ratings of sleepiness, fatigue, mood, performance, and effort. Methods N=21 healthy adults (aged 21-38; 9 women) completed three 4-day/3-night laboratory sessions – each including a baseline night, 36h TSD period, and recovery night –separated by at least 2 weeks each. Two of the sessions were preceded by a week of sleep extension (12h nightly sleep opportunities), while one session was preceded by a week of sleep restriction (6h nightly sleep opportunities), in randomized, counterbalanced order; only the sleep extension sessions are used here. Prior to the experiment, subjects filled out the Eysenck Personality Questionnaire (EPQ), which yielded an extraversion score; one subject did not complete the questionnaire and was excluded from analyses. Every 2h during TSD, subjects completed a 60min neurobehavioral test battery. At the beginning of the test battery, subjects completed the Karolinksa Sleepiness Scale (KSS) and visual analog scales of mood and fatigue (VAS-M and VAS-F). At the end of the test battery, subjects completed self-ratings of their performance (1–7 scale) and effort (1–4 scale). The relationship between extraversion and subjective scores after sleep deprivation (average over last 24h of 36h TSD period) relative to baseline (average over first 12h of TSD period) was analyzed using mixed-effects analysis of covariance, controlling for order, with a random effect over subjects on the intercept. Results No significant relationships were observed between extraversion and subjective estimates of sleepiness (KSS, p=0.45), fatigue (VAS-F, p=0.80), mood (VAS-M, p=0.14), performance (p=0.89), and effort (p=0.93). Conclusion These results indicate that extraversion is not a reliable predictor of trait-like individual differences in subjective vulnerability to 36h TSD. Support (if any) NASA grant NAG9-1161, CDMRP grant W81XWH-20-1-0442

Acute Capsaicin and Exercise Performance in Humans: Potential Neuromuscular Mechanisms

The pungent bioactive ingredient in peppers (Capsaicin; CAP) has been widely investigated for its activation of the transient receptor potential vanilloid 1 (TRPV1) channel on sensory neurons. It has been shown to improve mitochondrial biogenesis, adenosine triphosphate (ATP) production and vascular function. In animal models has been demonstrated that increases exercise performance and decreases fatigue development. However, whether acute oral CAP improves endurance performance and the potential underlying mechanisms remains elusive. This study aimed to evaluate the potential ergogenic and anti-fatigue effects of acute oral CAP supplementation in healthy humans. In a double-blind, placebo-controlled, cross-over design, 10 young healthy males performed constant-load cycling exercise (294±55W; 85% of peak power output) to exhaustion, after acute ingestion of placebo (PL; 1000mg fiber pill) and CAP (780mg pill) capsules. Fatigue was assessed on the dominant quadriceps with the interpolated twitch technique, via changes in supramaximal electrical stimulation pre- vs. post-exercise, during isometric maximal voluntary contractions (MVC) and at rest. Cardiopulmonary parameters (heart rate, cardiac output, oxygen consumption, ventilation) were assessed throughout the exercise. No statistically significant differences were detected in the muscle contractile functions, despite a trend (P=0.07) for a decreased time to exhaustion during CAP (PL: 369±85 vs. CAP: 296±64 sec). All the values (except muscle voluntary activation (%VMA)) significantly decreased from pre- to post-exercise in both conditions. The exercise-induced attenuation of the intrinsic muscle contractile properties (Maximal rate of force development (MRFD) and Maximal relaxation rate (MRR) of the resting twitch force) were mitigated, in part, by CAP. Notably, in the PL condition MRR was seemingly reduced by 47±33%, while only of 29±68% in CAP; contrarily, MRFD decreased similarly of 47±23% and of 40±27% in PL and CAP, respectively. In 9 participants, the resting twitch (estimate of peripheral muscle fatigue) pre- vs. post-exercise decreased less with CAP (PL: 44±17 vs. CAP: 37±13%). CAP did not influence the MVC nor %VMA. The cardiopulmonary responses were similar between the conditions (P>0.05). In contrast to prior work, acute oral capsaicin did not improve endurance performance in the present study. CAP did elicit a tendency for faster relaxation rate, which might suggest an enhanced activation of the sarcoendoplasmic reticulum calcium ATPase (SERCA) pumps, thereby increasing the rate of Ca2+ reuptake and relaxation. However, this altered Ca2+ handling might also increase ATP demand. The tendency for CAP to attenuate the exercise-induced reduction in muscle function, or fatigue, might provide a mechanistic basis for the previously demonstrated beneficial effects of CAP. Further work is needed in larger samples, to further determine the optimal dosing and loading strategies, to better understand the potential ergogenic effects of capsaicin.

A Real-Time Stability Control Method Through sEMG Interface for Lower Extremity Rehabilitation Exoskeletons.

Herein, we propose a real-time stable control gait switching method for the exoskeleton rehabilitation robot. Exoskeleton rehabilitation robots have been extensively developed during the past decade and are able to offer valuable motor ability to paraplegics. However, achieving stable states of the human-exoskeleton system while conserving wearer strength remains challenging. The constant switching of gaits during walking may affect the center of gravity, resulting in imbalance of human–exoskeleton system. In this study, it was determined that forming an equilateral triangle with two crutch-supporting points and a supporting leg has a positive impact on walking stability and ergonomic interaction. First, the gaits planning and stability analysis based on human kinematics model and zero moment point method for the lower limb exoskeleton are demonstrated. Second, a neural interface based on surface electromyography (sEMG), which realizes the intention recognition and muscle fatigue estimation, is constructed. Third, the stability of human–exoskeleton system and ergonomic effects are tested through different gaits with planned and unplanned gait switching strategy on the SIAT lower limb rehabilitation exoskeleton. The intention recognition based on long short-term memory (LSTM) model can achieve an accuracy of nearly 99%. The experimental results verified the feasibility and efficiency of the proposed gait switching method for enhancing stability and ergonomic effects of lower limb rehabilitation exoskeleton.

Characterisation of joint properties through spatial mapping of cracks in fatigue specimens, extracted from the linearly friction welded steel coupon

Linear friction welding (LFW) is widely used for the fabrication of high-value components in the aero-industry. The versatility of use and high integrity of joints produced by LFW, suggest that this technology could contribute greatly to sustainable engineering of the future. For example, in near-net-shape manufacturing, LFW is predicted to offer a substantial reduction in material waste and processing time, in addition to offering the capability of bonding material pairs currently difficult to fusion weld. LFW of steel components is seldom researched in published literature, with little information available on fatigue strength and fracture behaviour of such joints. This may hamper the confidence needed to popularise LFW in wider industry. Thusly, authors conducted a discovery-oriented fatigue study, followed by metallography and micro-hardness tests, conducted on a 100Cr steel LFW coupon and corresponding batch of parent material. The weld coupon was dissected into a set of fatigue specimens, to allow mapping of the joint's internal properties through individual fatigue estimates and fracture morphology of each specimen in the set. A prototype fatigue machine was constructed, designed to deliver independent displacement and force controlled bending or torsional loadings, representing complex real-world conditions more accurately than common, uniaxial tests. The hour-glass shape of fatigue specimens allowed for targeting strictly the weld region, inducing fracture at the weakest material section, which was found to lay far outside the immediate contact interface. Referencing distances from fracture points to the theoretical weld interface plane in each fatigue trial, resulted in discovery of a macroscopic pattern. Interpolated to a crack initiation plane, this pattern is proposed to reflect the heat-affected zone, across the greater LFW coupon. Authors also studied crack paths and suggest a link between fracture direction, residual stresses in joint and angular orientation of the crack initiation plane in respect to the theoretical weld interface.

Conditional variational autoencoders for probabilistic wind turbine blade fatigue estimation using Supervisory, Control, and Data Acquisition data

AbstractWind turbine fatigue estimation is based on time‐consuming Monte Carlo simulations for various wind conditions, followed by cycle‐counting procedures and the application of engineering damage models. The outputs of the fatigue simulations are large in volume and of high dimensionality, as they typically consist of estimates on finite‐element computational meshes. The strain and stress tensor time series, which are the primary quantities of interest when considering the problem of fatigue estimation, are dictated by complex vibration characteristics due to the coupled effect of aerodynamics, structural dynamics, geometrically non‐linear mechanics, and control. A Variational Auto‐Encoder (VAE) is trained in order to model the probability distribution of the accumulated fatigue on the root cross‐section of a simulated wind turbine blade. The VAE is conditioned on historical data that correspond to coarse wind‐field measurement statistics, such as mean hub‐height wind speed, standard deviation of hub‐height wind speed and shear exponent. In the absence of direct measurements of structural loads, the proposed technique finds applications in making long‐term probabilistic deterioration predictions from historical Supervisory, Control, and Data Acquisition (SCADA) data, while capturing the inherent aleatoric uncertainty due to the incomplete information on strain time series of the wind turbine structure, when only SCADA data statistics are available.

Random processes imitation in the problem of fatigue under variable loading

There is strong evidence, that the extrema and their sequence play a major role in metal fatigue. Due to this random testing with extrema control might be preferable, compared with the testing with generating by the spectral densities. The method is proposed allowing to generate random processes with the stable integral characteristics of cumulative distributions, and at the same time, being random by their nature. The algorithm consists of two steps. The first one is creating the random sequence of extrema, basing on the target Markov matrix, filled up on the base of the loading process, recorded during exploitation. The next step is the creation of the random process with its continuous first derivate. The special concatenation procedure was proposed and had been proved to create the continuous function reconstruction out of the point-wise specification (local maximums and minimums sequence). To judge the frequency content a regression analysis of two random variables was performed. The obtained continuous process might be undergone by the spectral analysis to get the spectral density function, which might be required in applying some methods for random fatigue estimation. The main trait of the proposed method is the coincidence of the rain-flow cycle counting characteristics of the initial and the resulting processes.

발목 PPG 신호 처리 개선을 위한 Zero Phase Filter 설계 및 시스템 연구

One of the areas of steady interest in modern society is health. In addition, in order to keep the individual’s health at its best, the healthcare device market is undergoing many trials and developments. The latest threat to COVID-19 is a major threat to heart disease patients, and it is time for continuous monitoring technology to be needed to prevent it. In particular, PPG sensor technology is relatively commercialized amid various attempts to analyze cardiovascular conditions. In general, we prefer to measure signals from fingers and wrists, which have a stable advantage in obtaining signals. However, there are cases where it is not suitable for the user’s lifestyle, which creates inconvenience. In this study, signal is measured from the ankles to minimize the inconvenience that users may experience when wearing them. And IIR Filter is applied for stable signal acquisition and analysis. Phase Delay, one of the disadvantages of this, is an unnecessary factor in real-time analysis. Zero Phase Filter is designed and applied to the system for further signal analysis. The results of the study compared three types of raw data, IIR Filter data, and Zero Phase Filter data acquired from PPG sensors, and were able to confirm the tendency of Zero Phase Filter data to match the peak points of raw data relative to IIR Filter data. The above results indicate the tendency for in-depth analysis of signals free from Phase Delay in the real-time acquisition of ankle PPG signals. Through peak-to-peak analysis and deep development of algorithms, various applications are expected to be possible by designing stress estimation and fatigue estimation systems that do not constrain users’ upper bodies.

Convolutional neural networks in medical image understanding: a survey

Imaging techniques are used to capture anomalies of the human body. The captured images must be understood for diagnosis, prognosis and treatment planning of the anomalies. Medical image understanding is generally performed by skilled medical professionals. However, the scarce availability of human experts and the fatigue and rough estimate procedures involved with them limit the effectiveness of image understanding performed by skilled medical professionals. Convolutional neural networks (CNNs) are effective tools for image understanding. They have outperformed human experts in many image understanding tasks. This article aims to provide a comprehensive survey of applications of CNNs in medical image understanding. The underlying objective is to motivate medical image understanding researchers to extensively apply CNNs in their research and diagnosis. A brief introduction to CNNs has been presented. A discussion on CNN and its various award-winning frameworks have been presented. The major medical image understanding tasks, namely image classification, segmentation, localization and detection have been introduced. Applications of CNN in medical image understanding of the ailments of brain, breast, lung and other organs have been surveyed critically and comprehensively. A critical discussion on some of the challenges is also presented.