Multiscale Entropy Research Articles

A New Algorithm for Predicting Dam Deformation Using Grey Wolf-Optimized Variational Mode Long Short-Term Neural Network

To solve the problems of difficult-to-model parameter selections, useful-signal extraction and improper-signal decomposition in nonlinear, non-stationary dam displacement time series prediction methods, we propose a new predictive model for grey wolf optimization and variational mode decomposition and long short-term memory (GVLSTM). Firstly, we used the grey wolf optimization (GWO) algorithm to optimize the parameters of variable mode decomposition (VMD), obtaining the optimal parameter combination. Secondly, we used multiscale permutation entropy (MPE) as a standard to select signal screening, determining and recon-structing the effective modal components. Finally, the long short-term memory neural network (LSTM) was used to learn the dam deformation characteristics. The result shows that the GVLSTM model can effectively reduce the estimation deviation of the prediction model. Compared with VMDGRU and VMDANN, the average RMSE and MAE value of each station is increased by 19.11%~28.58% and 27.66%~29.63%, respectively. We used determination (R2) coefficient to judge the performance of the prediction model, and the value of R2 was 0.95~0.97, indicating that our method has good performance in predicting dam deformation. The proposed method has outstanding advantages of high accuracy, reliability, and stability for dam deformation prediction.

Method and Application of Spillway Radial Gate Vibration Signal Denoising on Multiverse Optimization Algorithm-Optimized Variational Mode Decomposition Combined with Wavelet Threshold Denoising

To address the noise issue in the measured vibration signals of spillway radial gate discharge, this paper utilizes the Multiverse Optimization Algorithm (MVO) to optimize the number of decomposition modes (K) and the penalty factor (α) in Variational Mode Decomposition (VMD). This approach ensures improved efficiency of VMD decomposition while maintaining accuracy. Subsequently, the obtained Intrinsic Mode Functions (IMFs) from VMD decomposition are classified based on Multi-scale Permutation Entropy (MPE). IMFs are divided into pure components and noisy components; the noisy components are processed with Wavelet Threshold Denoising (WTD), while the pure components are overlaid and reconstructed to obtain the denoised vibration signal of the gate. Comprehensive comparisons involving artificial signal simulations, gate flow-induced vibration model tests, and numerical simulations lead to the following conclusions: compared to other algorithms, the proposed combined denoising method (MVO-VMD-MPE-WTD) achieves the highest signal-to-noise ratio (SNR) in both the frequency and time domains for artificial signals, while yielding the lowest mean square error (MSE). In the gate flow-induced vibration model tests, the method significantly reduces noise in the vibration signals and effectively preserves characteristic information. The error in preserving characteristic information across model tests and numerical simulations is kept below 1%. Furthermore, compared to other optimization algorithms, the MVO demonstrates higher computational efficiency. The parameter-optimized combined denoising method proposed in this study provides insights into denoising measured vibration signals of hydraulic spillway radial gates and other drainage structures, and it opens possibilities for exploring more efficient optimization algorithms for achieving online monitoring in the future.

Dynamically adjusted normalized multi-scale symbolic dynamic entropy for fault diagnosis of rotating machinery in strong noise

Dynamically adjusted normalized multi-scale symbolic dynamic entropy for fault diagnosis of rotating machinery in strong noise

Bearing fault diagnosis based on novel hierarchical multiscale dispersion entropy in corresponding color block images

Abstract The rolling bearing is a critical component of mechanical equipment, and its failure can lead to serious consequences. In order to effectively extract fault features of rolling bearings and improve fault diagnosis performance, a fault diagnosis framework based on hierarchical multiscale dispersion entropy (HMDE) and improved histogram of oriented gradient (HOG) is proposed by combining entropy method with image recognition method. Firstly, the original vibration signal is subjected to moving average filtering to eliminate sudden noise and outliers. Then, HMDE is used for the extraction of fault features. HMDE can evaluate the complexity of the signal at different levels and scales, thereby extracting more comprehensive information. Based on HMDE, entropy color block (ECB) images are generated and the improved HOG of the images are extracted. Finally, Knearest neighbor (KNN) is used to classify the improved HOG features, completing the recognition of different working states of rolling bearings. The validity and robustness of the proposed fault diagnosis framework are proved by the verification experiments on the public bearing datasets in Case Western Reserve University and Southeast University.

CONTINUOUS SCORING OF AUTISM SPECTRUM DISORDER PATIENTS BY ANALYZING THEIR EEG SIGNALS

Clinical manifestations and standard psychological tests have been widely used to diagnose autism spectrum disorder (ASD) patients and evaluate their severity level. The gold-standard criterion to diagnose ASD patients is the childhood autism rating scale (CARS), which is a qualitative questionnaire that is filled out through a systematic interview while no physiological test/record is performed to determine this score. To make the diagnosis process quantitative, electroencephalography (EEG) signals have been repeatedly analyzed to differentiate healthy subjects from ASD patients. However, the precise relationship between the abnormal behavior of EEG signals and different ASD severity levels is not well investigated. Here, we use CARS to qualitatively determine the severity level of 14 autistic children, who voluntarily enrolled in our study. We recorded their EEG signals from 19 scalp channels when they were awake in the idle state and elicited three informative features including approximation entropy, multiscale entropy and sample entropy in successive time frames. Among the three measures of entropy, the last one exhibits the highest sensitivity, where its correlation coefficient (CC) exceeds 0.7, on the electrode positions T6 (CC [Formula: see text] 0.74), P4 (CC [Formula: see text] 0.76) and Cz (CC [Formula: see text] 0.75). Results of sample entropy in channels Cz-versus-Pz and P4-versus-FP2 show that a simple K-nearest neighbor classifier can provide 93% classification accuracy among patients with mild, moderate and severe ASD levels. Comparing the proposed method to the conventional ones, we also extracted power spectral density features from the channels but they failed to identify the ASD severity level with an acceptable accuracy.

Multidimensional multiscale complexity analysis of sediment dynamics in the Yanhe Watershed of the loess Plateau, China

The Yanhe Watershed, emblematic of the loess hilly-gully landscape and ecological fragility in China's Loess Plateau, has experienced significant soil erosion and extensive soil-water conservation measures. To elucidate sediment dynamics and identify influencing factors in this region from 1960 to 2020, a novel multidimensional multiscale complexity analysis (MMCA) method was developed, based on entropy and complexity perspectives. This method integrated the refined composite multiscale fuzzy entropy (RCMFE) with multidimensional complexity analysis, offering a nuanced evaluation of sediment complexity and its implications for water resource management and ecological restoration. The findings revealed two distinct stages of sediment complexity variations: 1971–1988 and 2000–present. During the first period, the operation of the Wangyao Reservoir predominantly influenced sediment dynamics, initially reducing sediment complexity through sediment interception but later increasing it during discharge phases, particularly at larger scales. After 2002, extensive vegetation restoration efforts significantly reduced sediment complexity but raised concerns about long-term ecosystem resilience. Over the past decade, urbanization and climate change have exacerbated sediment instability, especially over semi-annual scales. This study advocates for management strategies that prioritize ecosystem sustainability and address the challenges posed by climate change and urbanization, facilitating improved soil and water conservation efforts in the Yanhe Watershed and similar regions in the Loess Plateau.

Observation and analysis of infrasound signals from the 1 January 2024 Japan earthquake

The 1 January 2024 Japan Earthquake occurred off the coast of Noto Peninsula, Japan. Three infrasound arrays s located more than 1400 km away from the epicenter received both local seismic and infrasound signals atmospherically propagating from the epicenter. The back azimuth, elevation angle and other parameters are calculated for the two types of infrasound signals received by the subarray through procedures of Progressive Multi-Channel Correlation (PMCC) and Frequency-Wavenumber (F-K) analysis. Source localization and other processing are also conducted. A recognition feature based on a low-frequency multi-scale entropy algorithm is proposed, and the received seismic signals of this event are correctly identified by using Support Vector Machine (SVM). This paper explores the calculation of earthquake parameters based on local infrasound wave and atmospherically propagated infrasound signals excited by distant earthquake events, and proposes a new method for infrasound signals event identification.

A Fast and Robust Range Alignment Method for ISAR Imaging Based on a Deep Learning Network and Regional Multi-Scale Minimum Entropy Method

In inverse synthetic aperture radar (ISAR) imaging, range alignment (RA) is crucial for translational compensation. To address the need for rapidity and accuracy in the RA process, a fast and robust range alignment method is proposed based on a deep learning network and minimum entropy (ME) method. The proposed method consists primarily of two components: the CNN-RNN attention mechanism network (CRAN) architecture and the regional multi-scale minimum entropy (RMSME) method. The main distinction of this method from existing approaches lies in its utilization of a deep learning network for rapid coarse alignment, followed by the search for minimum entropy within local regions at multiple scales. The integration strategy effectively addresses the current challenges of poor generalization in deep learning networks and low efficiency in the traditional ME method. The experimental results of simulation data indicate that the proposed method achieves the best range alignment performance compared to RNN, CRAN, and the traditional ME method. The experimental results of the measured data further validate the practicality of the proposed method. This research provides reference significance for the joint application of deep learning and traditional methods in the RA process.

A Novel Fault Feature Selection and Diagnosis Method for Rotating Machinery with SI-IR2CMSE and SSGMM-SR

Abstract In the field of fault diagnosis, machine learning is highly valued for its broad applicability and efficiency. Feature extraction and feature selection are key steps in the application of machine learning, and the performance of fault diagnosis methods relies heavily on the effective execution of these two steps. For this reason, this paper aims to enhance the performance of fault diagnosis methods by improving these two aspects. Firstly, to address the non-linearity and non-stationarity of rotating machinery vibration signals under variable operation conditions, this paper proposes an improved rapid refined composite multiscale sample entropy (IR2CMSE) feature extraction method. In addition, this paper decomposes the vibration signals with improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and extracts the sensitive intrinsic modal functions’ (IMFs') IR2CMSE values (SI-IR2CMSE) as the initial feature vector, which more accurately reveals the intrinsic time-scale characteristics of the vibration signals. Secondly, to address the problem of over-reliance on sample labels in most feature selection methods, this paper proposes a semi-supervised Gaussian mixing model with sparse regularization (SSGMM-SR) feature selection model. The model does not require complete fault labels and can automatically identify important features. Finally, validation with two rotating machinery fault datasets shows that the method proposed in this study exhibits high diagnostic accuracy and stability across multiple classifiers.

Legendre Polynomial Fitting-Based Permutation Entropy Offers New Insights into the Influence of Fatigue on Surface Electromyography (sEMG) Signal Complexity.

In a recently published work, we introduced local Legendre polynomial fitting-based permutation entropy (LPPE) as a new complexity measure for quantifying disorder or randomness in time series. LPPE benefits from the ordinal pattern (OP) concept and incorporates a natural, aliasing-free multiscaling effect by design. The current work extends our previous study by investigating LPPE's capability to assess fatigue levels using both synthetic and real surface electromyography (sEMG) signals. Real sEMG signals were recorded during biceps brachii fatiguing exercise maintained at 70% of maximal voluntary contraction (MVC) until exhaustion and were divided into four consecutive temporal segments reflecting sequential stages of exhaustion. As fatigue levels rise, LPPE values can increase or decrease significantly depending on the selection of embedding dimensions. Our analysis reveals two key insights. First, using LPPE with limited embedding dimensions shows consistency with the literature. Specifically, fatigue induces a decrease in sEMG complexity measures. This observation is supported by a comparison with the existing multiscale permutation entropy (MPE) variant, that is, the refined composite downsampling (rcDPE). Second, given a fixed OP length, higher embedding dimensions increase LPPE's sensitivity to low-frequency components, which are notably present under fatigue conditions. Consequently, specific higher embedding dimensions appear to enhance the discrimination of fatigue levels. Thus, LPPE, as the only MPE variant that allows a practical exploration of higher embedding dimensions, offers a new perspective on fatigue's impact on sEMG complexity, complementing existing MPE approaches.

Mood regulation in euthymic patients with a history of antidepressant-induced mania.

The use of antidepressants in bipolar disorder (BD) remains contentious, in part due to the risk of antidepressant-induced mania (AIM). However, there is no information on the architecture of mood regulation in patients who have experienced AIM. We compared the architecture of mood regulation in euthymic patients with and without a history of AIM. Eighty-four euthymic participants were included. Participants rated their mood, anxiety and energy levels daily using an electronic (e-) visual analog scale, for a mean (SD) of 280.8(151.4) days. We analyzed their multivariate time series by computing each variable's auto-correlation, inter-variable cross-correlation, and composite multiscale entropy of mood, anxiety, and energy. Then, we compared the data features of participants with a history of AIM and those without AIM, using analysis of covariance, controlling for age, sex, and current treatment. Based on 18,103 daily observations, participants with AIM showed significantly stronger day-to-day auto-correlation and cross-correlation for mood, anxiety, and energy than those without AIM. The highest cross-correlation in participants with AIM was between mood and energy within the same day (median (IQR), 0.58 (0.27)). The strongest negative cross-correlation in participants with AIM was between mood and anxiety series within the same day (median (IQR), -0.52 (0.34)). Patients with a history of AIM have a different underlying mood architecture compared to those without AIM. Their mood, anxiety and energy stay the same from day-to-day; and their anxiety is negatively correlated with their mood.

A Sustainable Model for Forecasting Carbon Emission Trading Prices

Carbon trading has garnered considerable attention as a pivotal policy instrument for advancing carbon peaking and carbon neutrality, which are essential components of sustainable development. The capacity to precisely anticipate the cost of carbon trading has significant implications for the optimal deployment of market mechanisms, the economic advancement of technological innovations in corporate emissions reduction, and the facilitation of international energy policy adjustments. To this end, this paper proposes a novel and sustainable trading price prediction tool that employs a four-step process: decomposition, reconstruction, prediction, and integration. This innovative approach first utilizes the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), then reconstructs the decomposition set using multi-scale entropy (MSE), and finally uses the Long Short-Term Memory neural network model (LSTM) enhanced by the Grey Wolf Optimizer (GWO) to predict the carbon emission trading price. The experimental results demonstrate that the tool achieves high accuracy for both the EU carbon price series and the carbon price series of China’s seven major carbon trading markets, with accuracy rates of 99.10% and 99.60% in Hubei and the EU carbon trading markets, respectively. This represents an improvement of approximately 3.1% over the ICEEMDAN-LSTM model and 0.91% over the ICEEMDAN-MSE-LSTM model, thereby contributing to more sustainable and efficient carbon trading practices.

Reduced multiscale complexity of daily behavioral dynamics in autism spectrum disorder.

Autism spectrum disorder (ASD) is difficult to diagnose objectively due to its heterogeneous and complex manifestations. This study aimed to objectively characterize the behavioral phenotypes of ASD children by exploring the multiscale behavioral dynamics. We applied behavioral organization (BO) and multiscale sample entropy (MSE) analyses to physical activity data collected from ASD and typically developing children, using wearable monitors in their daily life. We also examined their correlation with auditory startle response measures and clinical questionnaires, including the Social Responsiveness Scale (SRS) and the Strengths and Difficulties Questionnaire (SDQ). A significant decrease in MSE at timescales longer than 6 min was observed in ASD children, suggesting decreased irregularity or unpredictability, potentially linked to repetitive behaviors or stereotyped patterns commonly observed in ASD. Additionally, an increase in MSE positively correlated with prepulse inhibition levels, indicating its relationship with sensorimotor gating. Moreover, the observed significant negative correlation with the total difficulty score of SDQ substantiates MSE's potential as an objective metric for assessing general mental health problems associated with ASD. Multiscale analysis enhances the understanding of ASD's behavioral dynamics, providing valuable metrics for real-world assessments.

Correlation between insulin-like growth factor and complexity of glucose time series index in patients with newly diagnosed acromegaly: a PILOT study.

Acromegaly has a high risk of abnormal glucose metabolism. The complexity of the glucose time series index (CGI) is calculated from refined composite multi-scale entropy analysis of the continuous glucose monitoring (CGM) data. CGI is a new indicator of glucose imbalance based on ambulatory glucose monitoring technology, which allows for earlier response to glucose metabolism imbalance and correlates with patient prognosis. To compare the differences in glucose metabolic profile and CGI between acromegaly with normal glucose tolerance (NGT) and healthy subjects. Eight newly diagnosed patients with acromegaly (GH group) and eight age- and gender-matched healthy subjects (Control group) were included in this study. All participants underwent oral glucose tolerance test (OGTT) and 72-h CGM. A refined composite multi-scale entropy analysis was performed on the CGM data to calculate the CGI and we compare the differences in glycemic profiles and CGI between the two groups. After OGTT, compared with the control group, patients in the GH group had higher 2 h blood glucose (BG) (mmol/L) [GH vs control, 6.7 (6.1, 7.0) vs 5.2 (3.8, 6.3), P = 0.012], 3 h BG [5.1 (3.8, 6.5) vs 4.0 (3.4, 4.2), P = 0.046], mean BG [6.3 (6.1, 6.5) vs 5.5 (5.1, 5.9), P = 0.002], 2 h insulin (mU/L) [112.9 (46.8, 175.5) vs 34.1 (17.1, 55.6), P = 0.009], and 3 h insulin [26.8 (17.1, 55.4) vs 10.4 (4.2, 17.8), P = 0.016]. CGI was lower in the GH group [2.77 (1.92, 3.15) vs 4.2 (3.3, 4.8), P = 0.008]. Spearman's correlation analysis showed insulin-like growth factor (IGF) (r = -0.897, P < 0.001) and mean glucose (r = -0.717, P = 0.003) were significantly negatively correlated with CGI. Multiple linear stepwise regression showed that IGF-1 (r = -0.652, P = 0.028) was independent factor associated with CGI in acromegaly. IGF-1 was significantly associated with CGI, and CGI may serve as a novel marker to evaluate glucose homeostasis in acromegaly with normal glucose tolerance.

Evaluating cortical excitatory and inhibitory activity through interictal intracranial electroencephalography in mesial temporal lobe epilepsy.

Gamma oscillation regularity (GOR) indicates the synchronization of inhibitory interneurons, while the reactivity of cortico-cortical evoked potentials (CCEPs) is supposed to reflect local cortical excitability. Under the assumption that the early response of CCEP near the stimulation site also indicates excitatory activity primarily mediated by pyramidal cells, we aimed to visualize the cortical inhibitory and excitatory activities using GOR and CCEP in combination and to use them to predict the epileptogenic zone (EZ) in mesial temporal lobe epilepsy (MTLE). In five patients who underwent intracranial electrode implantation, GOR and CCEP reactivity in the vicinity of the stimulation site was quantified. The interictal GOR was calculated using multiscale entropy (MSE), the decrease of which was related to the enhanced GOR. These parameters were compared on an electrode-and-electrode basis, and spatially visualized on the brain surface. As a result, elevated GOR and CCEP reactivities, indicative of enhanced inhibitory and excitatory activities, were observed in the epileptogenic regions. Elevated CCEP reactivity was found to be localized to a restricted area centered on the seizure onset region, whereas GOR elevation was observed in a broader region surrounding it. Although these parameters independently predicted the EZ with high specificity, we combined the two to introduce a novel parameter, the excitatory and inhibitory (EI) index. The EI index predicted EZ with increased specificity compared with GOR or CCEP reactivity alone. Our results demonstrate that GOR and CCEP reactivity provided a quantitative visualization of the distribution of cortical inhibitory and excitatory activities and highlighted the relationship between the two parameters. The combination of GOR and CCEP reactivities are expected to serve as biomarkers for localizing the epileptogenic zone in MTLE from interictal intracranial electroencephalograms.

Impact of wearable device data and multi-scale entropy analysis on improving hospital readmission prediction.

Unplanned readmissions following a hospitalization remain common despite significant efforts to curtail these. Wearable devices may offer help identify patients at high risk for an unplanned readmission. We conducted a multi-center retrospective cohort study using data from the All of Us data repository. We included subjects with wearable data and developed a baseline Feedforward Neural Network (FNN) model and a Long Short-Term Memory (LSTM) time-series deep learning model to predict daily, unplanned rehospitalizations up to 90 days from discharge. In addition to demographic and laboratory data from subjects, post-discharge data input features include wearable data and multiscale entropy features based on intraday wearable time series. The most significant features in the LSTM model were determined by permutation feature importance testing. In sum, 612 patients met inclusion criteria. The complete LSTM model had a higher area under the receiver operating characteristic curve than the FNN model (0.83 vs 0.795). The 5 most important input features included variables from multiscale entropy (steps) and number of active steps per day. Data available from wearable devices can improve ability to predict readmissions. Prior work has focused on predictors available up to discharge or on additional data abstracted from wearable devices. Our results from 35 institutions highlight how multiscale entropy can improve readmission prediction and may impact future work in this domain. Wearable data and multiscale entropy can improve prediction of a deep-learning model to predict unplanned 90-day readmissions. Prospective studies are needed to validate these findings.

'Knock down the brain': a nonlinear analysis of electroencephalography to study the effects of sub-concussion in boxers.

Boxing is associated with a high risk of head injuries and increases the likelihood of chronic traumatic encephalopathy. This study explores the effects of sub-concussive impacts on boxers by applying both linear and nonlinear analysis methods to electroencephalogram (EEG) data. Twenty-one boxers were selected (mean ± SD, age 28.38 ± 5.5 years; weight 67.55 ± 8.90 kg; years of activity 6.76 ± 5.45; education 14.19 ± 3.08 years) and divided into 'beginner' and 'advanced' groups. The Montreal Cognitive Assessment and the Frontal Assessment Battery were administered; EEG data were collected in both eyes-open (EO) and eyes-closed (EC) conditions during resting states. Analyses of EEG data included normalized power spectral density (nPSD), power law exponent (PLE), detrended fluctuation analysis and multiscale entropy. Statistical analyses were used to compare the groups. Significant differences in nPSD and PLE were observed between the beginner and advanced boxers, with advanced boxers showing decreased mean nPSD and PLE (nPSD 4-7 Hz, p = 0.013; 8-13 Hz, p = 0.003; PLE frontal lobe F3 EC, p = 0.010). Multiscale entropy analysis indicated increased entropy at lower frequencies and decreased entropy at higher frequencies in advanced boxers (F3 EC, p = 0.024; occipital lobe O1 EO, p = 0.029; occipital lobe O2 EO, p = 0.036). These changes are similar to those seen in Alzheimer's disease. Nonlinear analysis of EEG data shows potential as a neurophysiological biomarker for detecting the asymptomatic phase of chronic traumatic encephalopathy in boxers. This methodology could help monitor athletes' health and reduce the risk of future neurological injuries in sports.

Gas-rigid-flexible compound blade coupling enhanced experimental study on chaotic mixing of multiphase flow

Efficient fluid mixing is essential for process intensification. This study proposes a new method in which gas-rigid-flexible composite blades are coupled to enhance chaotic mixing in multiphase flow systems. The rigidity and flexibility of the blades were adjusted by intermittent gas injection, which increased the effectiveness of mixing of the liquid-liquid two-phase fluid. This study investigates the influence of different process parameters on the mixing efficiency and quantifies the chaotic characteristics of fluid mixing through pressure-time series analysis of multiscale entropy and the 0–1 test. A high-speed camera recorded the bubble movement in the flow field, while particle image velocimetry (PIV) revealed the enhancement of the properties of the flow field in the system due to the suspended motion of the particles. Using suitable process parameters, gas-rigid-flexible composite blade coupling significantly enhanced the mixing effect, where the mixing time of the G-RFCP system was reduced by 1.42 times compared to that of the CP system. Bubble motion, deformation, and rupture enhanced the mechanical agitation, increasing the intensity of the turbulence and chaotic behaviour. Flow-field analysis indicated a three-fold increase in the vorticity and a 1.04-fold increase in the velocity difference for the G-RFCP system compared with those of the CP system. This study provides theoretical and experimental foundations for understanding chaotic mixing in liquid-liquid two-phase fluids.

A hybrid method for fault diagnosis of rolling bearings

Abstract Traditional diagnostic methods often have insufficient accuracy and noise reduction, which leads to diagnostic errors. To address these issues, this paper proposes an advanced fault diagnosis model that combines the variational mode decomposition (VMD) improved by a Variable-Objective Search Whale Optimization Algorithm (VSWOA) with a Pelican Optimization (PO)-boosted Kernel Extreme Learning Machine (KELM) algorithm. The application of the method is shown here in the fault diagnosis of rolling bearings. The proposed VSWOA enhances the performance of VMD by incorporating a Sobol sequence, nonlinear time-varying factors, a multi-objective initial search strategy, and an elite Cauchy chaos mutation strategy, significantly improving noise reduction in vibration signals. Fault information is precisely extracted using waveform factors, sample entropy, and advanced composite multiscale fuzzy entropy, which enables effective feature screening and dimensionality reduction. The POA fine-tunes the KELM parameters, increasing the classification accuracy. The effectiveness of the model is verified through experimental evaluations using bearing data with injected Gaussian noise (from Case Western Reserve University) and the SpectraQuest datasets, where significant improvements in noise reduction and fault detection accuracy are achieved.

Physiological complexity of body sway during dual-task gait in faller older adults

Background: The impact of simultaneous cognitive demand on gait’s physiological complexity in community-dwelling older adults with and without self-reported falls is yet unknown. Objective: To analyze whether the physiological complexity of body sway during dual-task and single gait is worse in once-only fallers than in non-faller older adults. Methods: A total of 58 community-dwelling older adults aged 60 to 80 participated in this study, of whom 21 had self-reported a single fall in the previous 12 months (fallers) and 37 matched participants with no fall self-reported (non-fallers). An inertial sensor (Physilog® 5, Gait Up, Switzerland) was used to acquire the time series of the body center of mass (CoM) sway in the anteroposterior (AP), mediolateral (ML) and vertical (V) directions during single gait (ST) and the gait under dual task (DT). The composite refined multiscale fuzzy entropy method was used to calculate the physiological complexity index (CI) in a MATLAB environment. SPSS (IBM; v.25.0) was used to analyze the effects of group (Fallers vs. Non-fallers), condition (ST vs. DT), and interaction (group vs. condition), using generalized linear mixed models, with an alpha of 5%. Results: No interaction or group effect was observed for the CI. However, when comparing DT with ST, a main effect of the condition was observed for the AP direction (F = 62.394; p &lt; .001) with a reduction of 0.53 (95% CI: -0.66 to -0.39), ML (F = 4.724; p = .034) with an increase of 0.22 (95% CI: 0.17 to 0.42), and V (F = 6.457; p = .014) with a decrease of 0.17. Conclusion: Just one fall in the previous 12 months does not deleteriously influence the body’s physiological complexity during gait under concurrent cognitive demand (dual task). On the other hand, DT significantly affects the gait physiological complexity in community-dwelling older adults.