Physical mechanism-corrected degradation trend prediction network under data missing

Accurate degradation trend prediction (DTP) is crucial for optimizing equipment operation and maintenance, thereby boosting production efficiency. This study introduces a novel Data Repair and Dual-data-stream LSTM (DR-DLSTM) network to tackle the challenge of missing data in equipment DTP. The proposed DR-DLSTM framework employs convex optimization to consider both the trend and periodic variations in the data, incorporating polynomial and trigonometric functions into the implicit feature matrix to construct latent vectors for missing data rectification. The network features a Dual-LSTM block with dual data streams to enhance feature extraction, with two gating update units correlating time series components and redistributing feature weights. The Dual-LSTM enables separate and accurate prediction of trend and periodic components, thereby enhancing the feature extraction capability of the prediction model. Additionally, the integration of physical rule information through Fourier and wavelet transform frequency correction modules allows for dynamic adjustments in prediction outcomes, from global trends to localized details. The DR-DLSTM's effectiveness is demonstrated through comprehensive comparisons with state-of-the-art models across multiple datasets, highlighting its superior performance. The results demonstrate the superiority of the proposed model. These algorithms were implemented in Python using Torch on a 2.9 GHz Intel I7 CPU and TITAN Xp GPU.

Exploring timescale-specific functional brain networks and their associations with aging and cognitive performance in a healthy cohort without dementia

INTRODUCTION

Functional brain networks (FBNs) coordinate brain functions and are studied in fMRI using blood-oxygen-level-dependent (BOLD) signal correlations. Previous research links FBN changes to aging and cognitive decline, but various physiological factors influnce BOLD signals. Few studies have investigated the intrinsic components of the BOLD signal in different timescales using signal decomposition. This study aimed to explore differences between intrinsic FBNs and traditional BOLD-FBN, examining their associations with age and cognitive performance in a healthy cohort without dementia.

MATERIALS AND METHODS

A total of 396 healthy participants without dementia (men = 157; women = 239; age range = 20-85 years) were enrolled in this study. The BOLD signal was decomposed into several intrinsic signals with different timescales using ensemble empirical mode decomposition, and FBNs were constructed based on both the BOLD and intrinsic signals. Subsequently, network features-global efficiency and local efficiency values-were estimated to determine their relationship with age and cognitive performance.

RESULTS

The findings revealed that the global efficiency of traditional BOLD-FBN correlated significantly with age, with specific intrinsic FBNs contributing to these correlations. Moreover, local efficiency analysis demonstrated that intrinsic FBNs were more meaningful than traditional BOLD-FBN in identifying brain regions related to age and cognitive performance.

CONCLUSIONS

These results underscore the importance of exploring timescales of BOLD signals when constructing FBN and highlight the relevance of specific intrinsic FBNs to aging and cognitive performance. Consequently, this decomposition-based FBN-building approach may offer valuable insights for future fMRI studies.

Identification of attention deficit hyperactivity disorder with deep learning model

This article explores the detection of Attention Deficit Hyperactivity Disorder, a neurobehavioral disorder, from electroencephalography signals. Due to the unstable behavior of electroencephalography signals caused by complex neuronal activity in the brain, frequency analysis methods are required to extract the hidden patterns. In this study, the feature extraction was performed with the Multitaper and Multivariate Variational Mode Decomposition methods. Then, these features were analyzed with the neighborhood component analysis and the features that contribute effectively to the classification were selected. The deep learning model including the convolution, pooling, and bidirectional long short term cell and fully connected layer was trained with the selected features. The trained model could effectively classify the subjects with Attention Deficit Hyperactivity Disorder with a deep learning model, support vector machines and linear discriminant analysis. The experiments were validated with an Attention Deficit Hyperactivity Disorder open access dataset ( https://doi.org/10.21227/rzfh-zn36 ). In validation, the deep learning model was able to classify 1210 test samples (600 subjects in the control group as Normal and 610 subjects in the ADHD group as ADHD) in 0.1 s with an accuracy of 95.54%. This accuracy rate is quite high compared to the Linear Discriminant Analysis (76.38%) and Support Vector Machines (81.69%). Experimental results showed that the proposed approach can innovatively classify Attention Deficit Hyperactivity Disorder subjects from the Control group effectively.

Nonlinear vibration feature extraction based on power spectrum envelope adaptive empirical Fourier decomposition

Analyzing the vibration features of a shipboard stabilized platform (SSP) is significant to the design or vibration compensation of a marine gravimetric survey vibration isolation system. Empirical Fourier decomposition (EFD) is a recently developed method for nonlinear and non-stationary signal decomposition. However, the spectral segmentation boundary needs to be set in advance according to sophisticated experience, and it is easy to be disturbed by noise, and the decomposition result is inaccurate. In order to accurately extract the nonlinear vibration characteristics of SSP, this paper proposes a new method called power spectrum envelope adaptive empirical Fourier decomposition (PSEEFD). Firstly, the number of selected modal decomposition is determined based on the mutual information to realize adaptive segmentation. Then, the improved power spectrum envelope segmentation method is adopted to effectively diminish the interference of noise since the segmentation boundary is formed by the minimum of the adjacent extreme points enveloped by the maximum value of the power spectrum. The spectrum segments obtained from segmentation contain less interference. Finally, the component signal in each frequency band is reconstructed by inverse fast Fourier transform, and the instantaneous frequency signal component with physical significance is obtained. Through the analysis of vibration simulation signals and measured data of SSP, the proposed method is compared with EMD, AFVMD, EWT and EFD. The results show that PSEEFD has a well suppression of noise interference and can effectively extract the characteristics of nonlinear vibration signals.

Implementation of hybrid wind speed prediction model based on different data mining and signal processing approaches

Accurate estimation of wind speed (WS) data, which greatly influences meteorological parameters, plays a vital role in the safe operation and optimization of the power system and water resource management. The study's main aim is to combine artificial intelligence and signal decomposition techniques to improve WS prediction accuracy. Feed-forward back propagation neural network (FFBNN), support vector machine (SVM) and Gaussian processes regression (GPR) models, discrete wavelet transform (DWT), and empirical mode decomposition (EMD) were used to forecast the WS values ​​1 month ahead in Burdur meteorology station. Statistical criteria such as Willmott's index of agreement, mean bias error, mean squared error, determination coefficient, Taylor diagram and regression analysis, and graphical indicators were used to evaluate the prediction success of the models. As a result of the study, it was determined that both wavelet transform and EMD signal processing increased the WS prediction performance of the stand-alone ML model. The best performance was obtained with the hybrid EMD-Matern 5/2 kernel GPR with test (R²:0.802) and validation (R²:0.606). The most successful model structure was obtained using input variables with a delay of up to 3 months. The study's results contribute to wind energy-related institutions in terms of practical use, planning, and management of wind energy.

Improving the accuracy of air relative humidity prediction using hybrid machine learning based on empirical mode decomposition: a comparative study

This paper proposes a hybrid air relative humidity prediction based on preprocessing signal decomposition. New modelling strategy was introduced based on the use of the empirical mode decomposition, variational mode decomposition, and the empirical wavelet transform, combined with standalone machine learning to increase their numerical performances. First, standalone models, i.e., extreme learning machine, multilayer perceptron neural network, and random forest regression, were used for predicting daily air relative humidity using various daily meteorological variables, i.e., maximal and minimal air temperatures, precipitation, solar radiation, and wind speed, measured at two meteorological stations located in Algeria. Second, meteorological variables are decomposed into several intrinsic mode functions and presented as new input variables to the hybrid models. The comparison between the models was achieved based on numerical and graphical indices, and obtained results demonstrate the superiority of the proposed hybrid models compared to the standalone models. Further analysis revealed that using standalone models, the best performances are obtained using the multilayer perceptron neural network with Pearson correlation coefficient, Nash-Sutcliffe efficiency, root-mean-square error, and mean absolute error of approximately ≈0.939, ≈0.882, ≈7.44, and ≈5.62 at Constantine station, and ≈0.943, ≈0.887, ≈7.72, and ≈5.93 at Sétif station, respectively. The hybrid models based on the empirical wavelet transform decomposition exhibited high performances with Pearson correlation coefficient, Nash-Sutcliffe efficiency, root-mean-square error, and mean absolute error of approximately ≈0.950, ≈0.902, ≈6.79, and ≈5.24, at Constantine station, and ≈0.955, ≈0.912, ≈6.82, and ≈5.29, at Sétif station. Finally, we show that the new hybrid approaches delivered high predictive accuracies of air relative humidity, and it was concluded that the contribution of the signal decomposition was demonstrated and justified.

Conditional empirical wavelet transform with modified ratio of cyclic content for bearing fault diagnosis

Empirical wavelet transform (EWT) is usually employed to segment Fourier spectrum for fault diagnosis. However, the original empirical segmentation approach may be easily affected by noise. In this paper, several conditions and a modified ratio of cyclic content are then proposed to help establish proper spectrum segments and to improve fault diagnosis. The proposed conditions include a pre-whitening process to reduce discrete frequency noise, a threshold to avoid white frequency noise, an additional boundary for the last considered maximum, distance requirement for consecutive local maxima, as well as one iteration of finding local extremums. Finally, the proposed method is compared with EWT and fast kurtogram methods in three case studies. The results indicate that the proposed method can provide more favorable diagnosis results.

High-Resolution Structural Analysis of Dyneins by Cryo-electron Microscopy

Cryo-electron microscopy (cryo-EM) has become the mainstream technique for studying macromolecular structures. Determining the structures of protein complexes is more accessible to structural biologists than ever before. Nevertheless, obtaining high-resolution structures of molecular motors like dynein is still an extremely challenging goal due to their troublesome behaviors in ice, their exceedingly flexible conformations, and their intricate architectures. Dynein is a large molecular machine that drives the movement of many essential cellular cargos and is also the key force generator that powers ciliary motility. High-resolution structural information of dyneins in different states is critical for the in-depth mechanistic understanding of their roles in cells. Here, we summarize the cryo-EM approaches that we have used to study the structures of outer-arm dynein arrays bound to microtubule doublets. Our approaches can be applied to other similar structures and further optimized to deal with even more complicated targets.

Digital Filtering and Signal Decomposition: A Priori and Adaptive Approaches in Body Area Sensing

Elimination of undesired signals from a mixture of captured signals in body area sensing systems is studied in this paper. A series of filtering techniques including a priori and adaptive approaches are explored in detail and applied involving decomposition of signals along a new system's axis to separate the desired signals from other sources in the original data. Within the context of a case study in body area systems, a motion capture scenario is designed and the introduced signal decomposition techniques are critically evaluated and a new one is proposed. Applying the studied filtering and signal decomposition techniques demonstrates that the functional based approach outperforms the rest in reducing the effect of undesired changes in collected motion data which are due to random changes in sensors positioning. The results showed that the proposed technique reduces variations in the data for average of 94% outperforming the rest of the techniques in the case study although it will add computational complexity. Such technique helps wider adaptation of motion capture systems with less sensitivity to accurate sensor positioning; therefore, more portable body area sensing system.

Multi-curve fitting and tubulin-lattice signal removal for structure determination of large microtubule-based motors

Revealing high-resolution structures of microtubule-associated proteins (MAPs) is critical for understanding their fundamental roles in various cellular activities, such as cell motility and intracellular cargo transport. Nevertheless, large flexible molecular motors that dynamically bind and release microtubule networks are challenging for cryo-electron microscopy (cryo-EM). Traditional structure determination of MAPs bound to microtubules needs alignment information from the reconstruction of microtubules, which cannot be readily applied to large MAPs without a fixed binding pattern. Here, we developed a comprehensive approach to estimate the microtubule networks (multi-curve fitting), model the tubulin-lattice signals, and remove them (tubulin-lattice subtraction) from the raw cryo-EM micrographs. The approach does not require an ordered binding pattern of MAPs on microtubules, nor does it need a reconstruction of the microtubules. We demonstrated the capability of our approach using the reconstituted outer-arm dynein (OAD) bound to microtubule doublets. The tubulin-lattice subtraction improves the OAD alignment, thus leading to high-resolution reconstructions. In addition, the multi-curve fitting approach provides an accurate automatic alternative method to pick or segment filaments in 2D images and potentially in 3D tomograms. The accuracy of our approach has been demonstrated by using several other biological filaments. Our work provides a new tool to determine high-resolution structures of large MAPs bound to curved microtubule networks.

Voice for Health: The Use of Vocal Biomarkers from Research to Clinical Practice

Diseases can affect organs such as the heart, lungs, brain, muscles, or vocal folds, which can then alter an individual's voice. Therefore, voice analysis using artificial intelligence opens new opportunities for healthcare. From using vocal biomarkers for diagnosis, risk prediction, and remote monitoring of various clinical outcomes and symptoms, we offer in this review an overview of the various applications of voice for health-related purposes. We discuss the potential of this rapidly evolving environment from a research, patient, and clinical perspective. We also discuss the key challenges to overcome in the near future for a substantial and efficient use of voice in healthcare.

Predictive modeling of drug effects on electrocardiograms

Whole electrocardiogram (ECG) waveform analysis is a technique for evaluating aggregate arrhythmic risks of drugs. In this paper, we propose methods for exploring changes to ECG morphology due to drug effects using Gaussian model parameters, and predict patient specific post-drug ECG based on pre-drug ECG. We evaluate the proposed methods using clinical ECG recordings from subjects under the effect of anti-arrhythmic drugs Dofetilide, Quinidine, Ranolazine, and Verapamil, from the ECGRVDQ database on PhysioNet. Paired-sample t-test p-values (>0.05) suggest the proposed method can achieve similar results when compared to expert annotated J to T_peak and T_peak to T_end intervals for all four drug states. We employed a leave-one-out cross validation strategy to train the prediction model and produce the results. Mean Pearson correlations between all predicted and recorded post-drug waveform morphologies for all drug states across both the vector magnitude lead and Lead II is 0.94±0.05, with p-values <0.01 for all predictions; indicating significant predictions. Parameters from ECG models with Gaussian basis can be used to calculate clinically useful information and to capture or predict changes in cardiac signals due to drug effects.

Detecting weak position fluctuations from encoder signal using singular spectrum analysis

Mechanical fault or defect will cause some weak fluctuations to the position signal. Detection of such fluctuations via encoders can help determine the health condition and performance of the machine, and offer a promising alternative to the vibration-based monitoring scheme. However, besides the interested fluctuations, encoder signal also contains a large trend and some measurement noise. In applications, the trend is normally several orders larger than the concerned fluctuations in magnitude, which makes it difficult to detect the weak fluctuations without signal distortion. In addition, the fluctuations can be complicated and amplitude modulated under non-stationary working condition. To overcome this issue, singular spectrum analysis (SSA) is proposed for detecting weak position fluctuations from encoder signal in this paper. It enables complicated encode signal to be reduced into several interpretable components including a trend, a set of periodic fluctuations and noise. A numerical simulation is given to demonstrate the performance of the method, it shows that SSA outperforms empirical mode decomposition (EMD) in terms of capability and accuracy. Moreover, linear encoder signals from a CNC machine tool are analyzed to determine the magnitudes and sources of fluctuations during feed motion. The proposed method is proven to be feasible and reliable for machinery condition monitoring.

Assessing Global Water Storage Variability from GRACE: Trends, Seasonal Cycle, Subseasonal Anomalies and Extremes

Throughout the past decade, the Gravity Recovery and Climate Experiment (GRACE) has given an unprecedented view on global variations in terrestrial water storage. While an increasing number of case studies have provided a rich overview on regional analyses, a global assessment on the dominant features of GRACE variability is still lacking. To address this, we survey key features of temporal variability in the GRACE record by decomposing gridded time series of monthly equivalent water height into linear trends, inter-annual, seasonal, and subseasonal (intra-annual) components. We provide an overview of the relative importance and spatial distribution of these components globally. A correlation analysis with precipitation and temperature reveals that both the inter-annual and subseasonal anomalies are tightly related to fluctuations in the atmospheric forcing. As a novelty, we show that for large regions of the world high-frequency anomalies in the monthly GRACE signal, which have been partly interpreted as noise, can be statistically reconstructed from daily precipitation once an adequate averaging filter is applied. This filter integrates the temporally decaying contribution of precipitation to the storage changes in any given month, including earlier precipitation. Finally, we also survey extreme dry anomalies in the GRACE record and relate them to documented drought events. This global assessment sets regional studies in a broader context and reveals phenomena that had not been documented so far.

Streaming visualisation of quantitative mass spectrometry data based on a novel raw signal decomposition method

As data rates rise, there is a danger that informatics for high-throughput LC-MS becomes more opaque and inaccessible to practitioners. It is therefore critical that efficient visualisation tools are available to facilitate quality control, verification, validation, interpretation, and sharing of raw MS data and the results of MS analyses. Currently, MS data is stored as contiguous spectra. Recall of individual spectra is quick but panoramas, zooming and panning across whole datasets necessitates processing/memory overheads impractical for interactive use. Moreover, visualisation is challenging if significant quantification data is missing due to data-dependent acquisition of MS/MS spectra. In order to tackle these issues, we leverage our seaMass technique for novel signal decomposition. LC-MS data is modelled as a 2D surface through selection of a sparse set of weighted B-spline basis functions from an over-complete dictionary. By ordering and spatially partitioning the weights with an R-tree data model, efficient streaming visualisations are achieved. In this paper, we describe the core MS1 visualisation engine and overlay of MS/MS annotations. This enables the mass spectrometrist to quickly inspect whole runs for ionisation/chromatographic issues, MS/MS precursors for coverage problems, or putative biomarkers for interferences, for example. The open-source software is available from http://seamass.net/viz/.

Morphological modeling of cardiac signals based on signal decomposition

In this paper a general framework is presented for morphological modeling of cardiac signals from a signal decomposition perspective. General properties of a desired morphological model are presented and special cases of the model are studied in detail. The presented approach is studied for modeling the morphology of electrocardiogram (ECG) signals. Specifically, three types of ECG modeling techniques, including polynomial spline models, sinusoidal model and a model previously presented by McSharry et al., are studied within this framework. The proposed method is applied to datasets from the PhysioNet ECG database for compression and modeling of normal and abnormal ECG signals. Quantitative and qualitative results of these applications are also presented and discussed.