Search

The number of published metagenome assemblies is rapidly growing due to advances in sequencing technologies. However, sequencing errors, variable coverage, repetitive genomic regions, and other factors can produce misassemblies, which are challenging to detect for taxonomically novel genomic data. Assembly errors can affect all downstream analyses of the assemblies. Accuracy for the state of the art in reference-free misassembly prediction does not exceed an AUPRC of 0.57, and it is not clear how well these models generalize to real-world data. Here, we present the Residual neural network for Misassembled Contig identification (ResMiCo), a deep learning approach for reference-free identification of misassembled contigs. To develop ResMiCo, we first generated a training dataset of unprecedented size and complexity that can be used for further benchmarking and developments in the field. Through rigorous validation, we show that ResMiCo is substantially more accurate than the state of the art, and the model is robust to novel taxonomic diversity and varying assembly methods. ResMiCo estimated 7% misassembled contigs per metagenome across multiple real-world datasets. We demonstrate how ResMiCo can be used to optimize metagenome assembly hyperparameters to improve accuracy, instead of optimizing solely for contiguity. The accuracy, robustness, and ease-of-use of ResMiCo make the tool suitable for general quality control of metagenome assemblies and assembly methodology optimization. Author summary: Metagenome assembly quality is fundamental to all downstream analyses of such data. The number of metagenome assemblies, especially metagenome-assembled genomes (MAGs), is rapidly increasing, but tools to assess the quality of these assemblies lack the accuracy needed for robust quality control. Moreover, existing models have been trained on datasets lacking complexity and realism, which may limit their generalization to novel data. Due to the limitations of existing models, most studies forgo such approaches and instead rely on CheckM to assess assembly quality, an approach that only utilizes a small portion of all genomic information and does not identify specific misassemblies. We harnessed existing large genomic datasets and high-performance computing to produce a training dataset of unprecedented size and complexity and thereby trained a deep learning model for predicting misassemblies that can robustly generalize to novel taxonomy and varying assembly methodologies. [ABSTRACT FROM AUTHOR]

The paper deals with a robust autonomous path-following functionality, in which the safe velocity and the motion profile of the vehicle with varying tyre-road contact must be guaranteed. The integration of Linear Parameter-Varying (LPV) control and the results of the machine learning-based analysis on the big data of autonomous vehicles is proposed. The integration is achieved in two steps. First, an estimation method on the adhesion coefficient through decision trees is presented. The result of the estimation is incorporated in the robust LPV control through a scheduling variable. During the control design, the error of the machine-learning algorithm is incorporated. Second, an optimisation method of the longitudinal velocity on a predicted horizon is proposed, which is aided with the machine learning-based reachability set approximation of the steering intervention. The effectiveness of the control strategy is illustrated through CarSim simulations. [ABSTRACT FROM AUTHOR]

Energy management and monitoring systems are significant difficulties in applying microgrids to smart homes. Thus, further research is required to address the modeling and operational parts of the system's future results for various applications. This paper proposes a new technique for energy management in a microgrid using a robust control approach and the development of a platform for real-time monitoring. The developed controller is based on a fuzzy logic method used in the energy Internet paradigm with connected distributed generators (DGs) in the microgrid. The developed method regulates the power flow of the microgrid, and frequency/voltage regulation improved the load-management performance and monitoring system using the ThingSpeak platform for real-time data analysis. The MATLAB. simulation results show the feasibility and effectiveness of the proposed strategy and the introduced approach in microgrid control under various operating conditions. Additionally, the results show that the proposed monitoring platform facilitates real-time data analysis. [ABSTRACT FROM AUTHOR]

Consider a one-way or two-way ANOVA design. Typically, groups are compared based on some measure of location. The paper suggests alternative methods where measures of location are replaced by a robust measure of effect size that is based in part on a robust measure of dispersion. The measure of effect size used here does not assume that the groups have a common measure of dispersion. That is, it deals with heteroscedasticity. It is fairly evident that no single method reveals everything of interest regarding how groups differ. Certainly, comparing measures of location provides useful information. But as illustrated, comparing measures of effect size can provide a deeper understanding of how groups compare. [ABSTRACT FROM AUTHOR]

Although the literature on the a priori procedure, designed to help researchers determine the sample sizes they should use in their substantive research, is expanding rapidly, there are two important limitations. First, there is a need to expand to new popular distributions, log-normal and gamma distributions, and the present work provides those expansions. Second, there is a need to test the consequences of wrong distributional assumptions; for example, assuming a log-normal distribution when the population follows a gamma distribution, or the reverse. The present work addresses the limitations with respect to estimating population means, and it includes computer simulations, links to free and user-friendly programs that researchers can utilize for their own research, and two examples involving real data sets for illustrations of our main results. [ABSTRACT FROM AUTHOR]

Three-level clustered data commonly occur in social and behavioral research and are prominently analyzed using multilevel modeling. The influence of the clustering on estimation results is assessed with the intraclass correlation coefficients (ICCs), which indicate the fraction of variance in the outcome located at each higher level. However, ICCs are prone to bias due to high requirements regarding the overall sample size and the sample size at each data level. In Monte Carlo simulations, we investigate how these sample characteristics influence the bias of the ICCs and statistical power of the variance components using robust ML-estimation. Results reveal considerable underestimation on Level-3 and the importance of the Level-3 sample size in combination with the ICC sizes. Based on our results, we derive concise sampling recommendations and discuss limits to our inferences. [ABSTRACT FROM AUTHOR]

Constantly decreasing costs of high-throughput profiling on many molecular levels generate vast amounts of multi-omics data. Studying one biomedical question on two or more omic levels provides deeper insights into underlying molecular processes or disease pathophysiology. For the majority of multi-omics data projects, the data analysis is performed level-wise, followed by a combined interpretation of results. Hence the full potential of integrated data analysis is not leveraged yet, presumably due to the complexity of the data and the lacking toolsets. We propose a versatile approach, to perform a multi-level fully integrated analysis: The Knowledge guIded Multi-Omics Network inference approach, KiMONo (https://github.com/cellmapslab/kimono). KiMONo performs network inference by using statistical models for combining omics measurements coupled to a powerful knowledge-guided strategy exploiting prior information from existing biological sources. Within the resulting multimodal network, nodes represent features of all input types e.g. variants and genes while edges refer to knowledge-supported and statistically derived associations. In a comprehensive evaluation, we show that our method is robust to noise and exemplify the general applicability to the full spectrum of multi-omics data, demonstrating that KiMONo is a powerful approach towards leveraging the full potential of data sets for detecting biomarker candidates. [ABSTRACT FROM AUTHOR]

In recent years, medical image transmission using a multi-cloud system has played a significant role in e-Healthcare infrastructure. It allows medical practitioners to easily store, retrieve, and share patients' medical information across multiple stakeholders. However, multi-cloud image transmission may be vulnerable to multiple security breaches, such as authentication, confidentiality, and security issues. Motivated by these issues, this paper proposes a data-hiding scheme for secure medical image transmission in a multi-cloud environment. The proposed scheme ensures imperceptible robustness and watermark security at a low computational cost. Here, the medical image is divided into a number of shares using Neighbor Mean Interpolation (NMI). To achieve confidentiality, Electronic Patient Healthcare Record (EPHR) is encrypted using Double Scan Pixel Position Shuffling (DSPPS) approach. Then, the encrypted EPHR is divided into shares and embedded in the cover medical image shares. Finally, a minimum of 50% of watermarked image shares are utilized to retrieve the original medical image and encrypted EPHR, consequently reducing multi-cloud latency and computational burden. Experimental results show that the proposed scheme shows high imperceptibility, robustness, and watermark security at a low computational cost. Comparative analysis with some of the recent popular data hiding schemes shows that the proposed scheme has improved imperceptibility and robustness by 10%–15% (approximately) with higher watermark security at a low computational cost. [ABSTRACT FROM AUTHOR]

Considering looming fatality and economic recession, effective policy making based on ongoing COVID-19 pandemic is an urgent and standing issue. Numerous issues for controlling infection have arisen from public discussion led by medical professionals. Yet understanding of these factors has been necessarily qualitative and control measures to correct unfavorable trends specific to an infection area have been lacking. The logical implement for control is a large scale stochastic model with countless parameters lacking robustness and requiring enormous data. This paper presents a remedy for this vexing problem by proposing an alternative approach. Machine learning has come to play a widely circulated role in the study of complex data in recent times. We demonstrate that when machine learning is employed together with the mechanistic framework of a mathematical model, there can be a considerably enhanced understanding of complex systems. A mathematical model describing the viral infection dynamics reveals two transmissibility parameters influenced by the management strategies in the area for the control of the current pandemic. Both parameters readily yield the peak infection rate and means for flattening the curve, which is correlated to different management strategies by employing machine learning, enabling comparison of different strategies and suggesting timely alterations. Treatment of population data with the model shows that restricted non-essential business closure, school closing and strictures on mass gathering influence the spread of infection. While a rational strategy for initiation of an economic reboot would call for a wider perspective of the local economics, the model can speculate on its timing based on the status of the infection as reflected by its potential for an unacceptably renewed viral onslaught. [ABSTRACT FROM AUTHOR]

We provide a publicly available library FarmTest in the R programming system. This library implements a factor-adjusted robust multiple testing principle proposed by Fan et al. (2019) for large-scale simultaneous inference on mean effects. We use a multi-factor model to explicitly capture the dependence among a large pool of variables. Three types of factors are considered: observable, latent, and a mixture of observable and latent factors. The non-factor case, which corresponds to standard multiple mean testing under weak dependence, is also included. The library implements a series of adaptive Huber methods integrated with fast data-driven tuning schemes to estimate model parameters and to construct test statistics that are robust against heavy-tailed and asymmetric error distributions. Extensions to two-sample multiple mean testing problems are also discussed. The results of some simulation experiments and a real data analysis are reported. [ABSTRACT FROM AUTHOR]

In the field of cluster analysis, rough set-based extensions of hard C-means (HCM; k-means) including rough C-means (RCM), rough set C-means (RSCM), and rough membership C-means (RMCM) are promising approaches for dealing with the certainty, possibility, uncertainty of belonging of object to clusters. Since C-means-type methods are strongly affected by noise, noise clustering approaches have been proposed. In noise clustering approaches, noise objects, which are far from any cluster center, are rejected for robust estimation. In this paper, we introduce noise rejection approaches for rough set-based C-means based on probabilistic memberships and propose noise RCM with membership normalization (NRCM-MN), noise RSCM with membership normalization (NRSCM-MN), and noise RMCM (NRMCM). In addition, visualization demonstration of the cluster boundaries on the two-dimensional plane of the proposed methods is carried out to confirm the characteristics of each method. Furthermore, the clustering performance is verified by numerical experiments using real-world datasets. [ABSTRACT FROM AUTHOR]

This article describes fundamentals of controllable electrochemical impedance spectroscopy (cEIS), from circuit design to control and data analysis. In cEIS, a feedback system controls the process of injecting the excitation signal. We design a two degree-of-freedom robust control system, which guarantees tracking and stability of cEIS in the presence of model uncertainties. This article also addresses the concept of persistently exciting signals. cEIS using current driving mode (CDM) and voltage driving mode, and their differences are highlighted. An online cEIS device is designed and built based on the dc–dc buck converter for batteries online applications, where the excitation signal is superimposed on a dc level. The performance of the fabricated cEIS is evaluated through extensive experiments in CDM. The accuracy of the fabricated cEIS is tested, which results in 0.002 Ω root mean square error in the impedance spectra computation of a three-parameter Randles equivalent circuit model (ECM). The performance of the fabricated cEIS is practically verified on a battery cell at different C-rates. First-, second-, and fractional-order Randles ECMs are estimated by using system identification methods, and their impedance spectra are compared with those obtained through the fast Fourier transform. [ABSTRACT FROM AUTHOR]

Introduction: Uncovering safety signals through the collection and assessment of individual case reports remains a core pharmacovigilance activity. Despite the widespread use of disproportionality analysis in signal detection, recommendations are lacking on the minimum size of databases or subsets of databases required to yield robust results.Objective: This study aims to investigate the relationship between database size and robustness of disproportionality analysis, with regards to limiting spurious associations.Methods: Three types of subsets were created from the global database VigiBase: random subsets (500 replicates each of 11 fixed subset sizes between 250 and 100,000 reports), country-specific subsets (all 131 countries available in the original VigiBase extract) and subsets based on the Anatomical Therapeutic Chemical classification. For each subset, a spuriousness rate was computed as the ratio between the number of drug-event combinations highlighted by disproportionality analysis in a permuted version of the subset and the corresponding number in the original subset. In the permuted data, all true reporting associations between drugs and adverse events were broken. Subsets with fewer than five original associations were excluded. Additionally, the set of disproportionately over-reported drug-event combinations in three specific countries at three different time points were clinically assessed for labelledness. These time points corresponded to database sizes of less than 10,000, 5000 and 1000 reports, respectively. All disproportionality analysis was based on the Information Component (IC), implemented as IC025 > 0.Results: Spuriousness rates were below 0.15 for all 110 included countries regardless of subset size, with only seven countries (6%) exceeding the empirical threshold of 0.10 observed for large subsets. All 21 excluded countries had < 500 reports. For random subsets containing 3000-5000 or more reports, the higher end of observed spuriousness rates was close to 0.10. In the clinical assessment, the proportion of labelled or otherwise known drug-event combinations was very high (87-100%) across all countries and time points studied.Conclusions: To mitigate the risk of highlighting spurious associations with disproportionality analysis, a minimum size of 500 reports is recommended for national databases. For databases or subsets that are not country-specific, our recommendation is 5000 reports. This study does not consider sensitivity, which is expected to be poor in smaller databases. [ABSTRACT FROM AUTHOR]

Phenotypic plasticity, the ability of a living organism to respond to the environment, can lead to conclusions from experiments that are idiosyncratic to a particular environment. The level of environmental responsiveness can result in difficulties in reproducing studies from the same institute with the same standardised environment. Here we present a multi-batch approach to in-vivo studies to improve replicability of the results for a defined environment. These multi-batch experiments consist of small independent mini-experiments where the data are combined in an integrated data analysis to appropriately assess the treatment effect after accounting for the structure in the data. We demonstrate the method on two case studies with syngeneic tumour models which are challenging due to high variability both within and between studies. Through simulations and discussions, we explore several data analysis options and the optimum design that balances practical constraints of working with animals versus sensitivity and replicability. Through the increased confidence from the multi-batch design, we reduce the need to replicate the experiment, which can reduce the total number of animals used. [ABSTRACT FROM AUTHOR]

A new evaluation scheme for double exposure three-dimensional particle-tracking velocimetry is proposed. Its main feature, a robust multi-pass matching algorithm, is presented and validated by investigating its performance when applied to a synthetic data set. To evaluate real measurement data, the approach is supplemented by an iterative triangulation scheme, in which the resulting particle positions are validated through the matching algorithm. The comparison with tomographic particle-image velocimetry data shows good agreement. The proposed algorithm allows this approach to be applied to volumetric measurements with seeding densities exceeding standard particle-tracking applications. Therefore, it can serve as a drop-in replacement for tomographic particle-image velocimetry at significantly reduced computational cost. [ABSTRACT FROM AUTHOR]

Machine learning methods have gained increased popularity in biomedical research during the recent years. However, very few of them support the analysis of longitudinal data, where several samples are collected from an individual over time. Additionally, most of the available longitudinal machine learning methods assume that the measurements are aligned in time, which is often not the case in real data. Here, we introduce a robust longitudinal machine learning method, named likelihood contrasts (LC), which supports study designs with unaligned time points. Our LC method is a binary classifier, which uses linear mixed models for modelling and log-likelihood for decision making. To demonstrate the benefits of our approach, we compared it with existing methods in four simulated and three real data sets. In each simulated data set, LC was the most accurate method, while the real data sets further supported the robust performance of the method. LC is also computationally efficient and easy to use. [ABSTRACT FROM AUTHOR]

Count outcomes with excessive zeros are common in behavioral and social studies, and zero-inflated count models such as zero-inflated Poisson (ZIP) and zero-inflated Negative Binomial (ZINB) can be applied when such zero-inflated count data are used as response variable. However, when the zero-inflated count data are used as predictors, ignoring the difference of structural and random zeros can result in biased estimates. In this paper, a generalized estimating equation (GEE)-type mixture model is proposed to jointly model the response of interest and the zero-inflated count predictors. Simulation studies show that the proposed method performs well for practical settings and is more robust for model misspecification than the likelihood-based approach. A case study is also provided for illustration. [ABSTRACT FROM AUTHOR]

Highlights • A magnetic negative stiffness isolator based on Maxwell normal stress is proposed. • A magnetic spring is formed by the Maxwell normal stress to generate negative stiffness. • Active control is integrated into the isolator to realize the active-passive hybrid vibration isolation. • Prototype design and experimental results demonstrate the theoretical analysis. Abstract A new magnetic negative stiffness isolator based on Maxwell normal stress is proposed to improve the low-frequency vibration isolation performance of a system with high static support stiffness. The isolator can provide high negative stiffness maintaining compact size and light weight. The negative stiffness characteristic of the isolator was first modeled through magnetic circuit analysis. Then, the passive vibration isolation performance of the isolator was validated experimentally. Active control was then introduced into the isolation system to improve its ability to adapt to external disturbances and suppress the system's resonance response. The governing equation of the active-passive hybrid vibration isolation system was established. The simulated and experimental results showed that the magnetic negative stiffness isolator with active-passive hybrid control can greatly reduce the isolation initial frequency and significantly suppress the system resonance response in comparison with passive methods. The present work provides a promising way to realize low-frequency broad-band vibration isolation for systems with high static support stiffness. [ABSTRACT FROM AUTHOR]

Highlights • The method selects the best onset time obtained from different competitive techniques. • Onset times are important features of AE signals to identify source location. • It is not feasible to manually identify AE signals from the noise. • The method can be easily programmed and used in an autonomous way. • The proposed method is extendable to other fields where competing data are available. Abstract Robust identification of the most accurate observed input data among a pool of observations is key in modeling and decision making. A statistically biased observed measurement deteriorates the predictive power of a model and affects decision-making ability based on the prediction of the model. When two competing methods of measurement are available, such as methods which identify arrival times in acoustic emission (AE) signals, a principal question is whether one of the two obtained datasets, or a combination of the two, should be used later on, for example, to localize an AE source. This question becomes more important when collecting not repeatable data such as AE signals created by a propagating crack. This paper considers an inverse source location problem in a concrete block to address the mentioned issue, a proposed methodology which also has wider application in competitive data selection. Elastic energy released by an AE event, such as a propagating crack, is recorded by acoustic emission data acquisition system. The onset time of AE signals is often used to locate the source of the event, and its accuracy directly affects the precision of source identification. This research proposes an innovative approach to select the most probable onset time obtained from two automatic picker methods. The proposed method selects the most probable onset times, which are observed by each picker for each sensor, in a probabilistic fashion. To validate the proposed method, the most accurate onset time observed by each picker is identified by visual inspection and is compared with the one is selected by the proposed method. Finally, the dataset is used for source location identification. Results show that picked onset times determined by the proposed method generate more accurate source identification when compared with coordinates obtained using each dataset individually. [ABSTRACT FROM AUTHOR]

Highlights • A GVM is used to characterize an unknown and complex structural component. • Damage detection based on GVMI approach is developed. • The key parameters on detection resolution are investigated. • Results in honeycomb sandwich structure show the validity of damage detection without any blind area. Abstract This paper presents a novel vibration-based damage detection method using a general vibration model identification (GVMI) approach. A damage index based on the identified general vibration model is constructed for damage detection and localization, with the damage being regarded as a virtual excitation on the structure. The proposed GVMI approach utilizes a general form of high order derivative equation that to be identified and further used to detect changes in the vibration characteristics of the structure. Therefore, the proposed damage detection method requires neither baseline signals nor prior knowledge on the structural parameters, thus offering great application potentials for complex structures with unknown parameters. As a proof-of-concept example, a honeycomb sandwich cantilever beam is investigated for validating the proposed approach. The influences of the key parameters on the detection resolution, such as the measurement interval, the order of the displacement derivative and the selection of the excitation frequency, are investigated. Furthermore, an enhanced version of the GVMI method with an excitation frequency extension is developed by using a data fusion scheme. Taking advantages of the broadband excitations, the blind inspection area can be completely eliminated, whilst improving the effectiveness and the accuracy of the detection. Experimental results with both single and multiple structural damage show the validity and the accuracy of the proposed approach. [ABSTRACT FROM AUTHOR]

Background: The main obstacle encountered in microarray technology is how to mine the valuable information under the profiles and study the genes function.Objective: Maximal information coefficient (MIC) is a novel, non-parametric statistic that has been successfully applied to genome-wide association studies and differentially gene and miRNA expression analysis. However, the data used in these applications are not gold standard but real data.Methods: Therefore, this study attempts to test the feasibility of MIC for differentially expressed gene identification with simulation data.Results: Our experiments indicate that, MIC perfermance is better than Limma always, which is almost the same level of SAM, ROTS or DESeq2. However, the count of AUC < 0.5 of MIC is significantly smaller than the three methods, and MIC does not exhibit an abnormal phenomenon in which the AUC increases as the noise increases.Conclusions: Compared to the existing methods, our experiments show that MIC is not only in the first tier in identifying differentially expressed genes and noise immunity, but also shows better robustness and stronger data/environment adaptability. [ABSTRACT FROM AUTHOR]

Highlights • A new data-dependent method for determining the trimming level in robust clustering. • We monitor the cluster structure as the trimming level changes. • The robust clustering constrains the ratio of eigenvalues of dispersion matrices. • The "car-bike" plot exhibits cluster stability as the eigenvalue constraint varies. • Sizable bibliography relating the work to that in the machine learning and pattern recognition fields. Abstract Monitoring the properties of single sample robust analyses of multivariate data as a function of breakdown point or efficiency leads to the adaptive choice of the best values of these parameters, eliminating arbitrary decisions about their values and so increasing the quality of estimators. Monitoring the trimming proportion in robust cluster analysis likewise leads to improved estimators. We illustrate these procedures on a sample of 424 cows with bovine phlegmon. For clustering we use a method which includes constraints on the eigenvalues of the dispersion matrices, so avoiding thread shaped clusters. The "car-bike" plot reveals the stability of clustering as the trimming level changes. The pattern of clusters and outliers alters appreciably for low levels of trimming. [ABSTRACT FROM AUTHOR]

A two year long experimental dataset in which authors of Radin, et al., 2016 claim to find evidence of mind-matter interaction is independently re-analyzed. In this experiment, participants are asked to periodically shift their attention towards or away from a double-slit optical apparatus. Shifts in fringe visibility of the interference pattern are monitored and tested against the common sense null hypothesis that such shifts should not correlate with the participant’s attention state. We propose a deeper analysis of the dataset, identifying all the necessary arbitrary pre-analysis choices one needs to make, and carefully assessing the results’ robustness regarding these choices. Results are twofold. Firstly, even with a conservative correction for the multiple statistical tests the analysis calls for, we confirm the existence of significant although small anomalies in the direction predicted by the mind-matter interaction hypothesis. On the other hand, and unlike Radin, et al., 2016, we also report significant although even smaller anomalies in the control dataset. This leads us to conclude that this particular dataset does not provide strong evidence of mind-matter interaction, yet certainly contains inexplicable anomalies that should motivate replication attempts in highly controlled environments. [ABSTRACT FROM AUTHOR]

Abstract Data reconciliation has played a significant role in rectifying process data which can meet the conservation laws in industrial processes. Generally, the actual measurements are often easily contaminated by different gross errors. Thus, it is essential to build robust data reconciliation methods to alleviate the impact of gross errors and provide accurate data. In this paper, a novel robust estimator is proposed to improve the robustness of data reconciliation method, which is based on a new robust estimation function. First, the main robust properties are analyzed with its objective and influence functions for the proposed robust estimator. Then, the effectiveness of the new robust data reconciliation method is demonstrated on a linear numerical case and a nonlinear example. Moreover, it is further used to a practical industrial evaporation production process, which also demonstrates that the process data can be better reconciled with the proposed robust estimator. [ABSTRACT FROM AUTHOR]

The E-value was recently introduced on the basis of earlier work as "the minimum strength of association…that an unmeasured confounder would need to have with both the treatment and the outcome to fully explain away a specific treatment-outcome association, conditional on the measured covariates." E-values have been proposed for wide application in observational studies evaluating causality. However, they have limitations and are prone to misinterpretation. E-values have a monotonic, almost linear relationship with effect estimates and thus offer no additional information beyond what effect estimates can convey. Whereas effect estimates are based on real data, E-values may make unrealistic assumptions. No general rule can exist about what is a "small enough" E-value, and users of the biomedical literature are not familiar with how to interpret a range of E-values. Problems arise for any measure dependent on effect estimates and their CIs-for example, bias due to selective reporting and dependence on choice of exposure contrast and level of confidence. The automation of E-values may give an excuse not to think seriously about confounding. Moreover, biases other than confounding may still undermine results. Instead of misused or misinterpreted E-values, the authors recommend judicious use of existing methods for sensitivity analyses with careful assumptions; systematic assessments of whether and how known confounders have been handled, along with consideration of their prevalence and magnitude; thorough discussion of the potential for unknown confounders considering the study design and field of application; and explicit caution in making causal claims from observational studies. [ABSTRACT FROM AUTHOR]

Abstract Manifold based feature extraction has been proved to be an effective technique in dealing with the unsupervised classification tasks. However, most of the existing works cannot guarantee the global optimum of the learned projection, and they are sensitive to different noises. In addition, many methods cannot catch the discriminative information as much as possible since they only exploit the local structure of data while ignoring the global structure. To address the above problems, this paper proposes a novel graph based feature extraction method named low-rank and sparsity preserving embedding (LRSPE) for unsupervised learning. LRSPE attempts to simultaneously learn the graph and projection in a framework so that the global optimal projection can be obtained. Moreover, LRSPE exploits both global and local information of data for projection learning by imposing the low-rank and sparse constraints on the graph, which promotes the method to obtain a better performance. Importantly, LRSPE is more robust to noise by imposing the l 2 , 1 sparsity norm on the reconstruction errors. Experimental results on both clean and noisy datasets prove that the proposed method can significantly improve classification accuracy and it is robust to different noises in comparison with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper aims to modify Shewhart, the weighted variance and skewness correction methods in industrial statistical process control. The robust and asymmetric control limits of range chart are constructed to use in contaminated and skewed distributed process. The way of construction of control limits is simple and corresponds to three methods in which sample range estimator is replaced with the robust interquartile range. These three modified methods are evaluated in terms of their type I risks and average run length by using simulation study. The performance of the proposed range charts is assessed when the Phases I and II data are uncontaminated and contaminated. The Weibull, gamma and lognormal distributions are chosen since they can represent a wide variety of shapes from nearly symmetric to highly skewed. [ABSTRACT FROM AUTHOR]

We introduce flexible robust functional regression models, using various heavy-tailed processes, including a Student t-process. We propose efficient algorithms in estimating parameters for the marginal mean inferences and in predicting conditional means as well as interpolation and extrapolation for the subject-specific inferences. We develop bootstrap prediction intervals (PIs) for conditional mean curves. Numerical studies show that the proposed model provides a robust approach against data contamination or distribution misspecification, and the proposed PIs maintain the nominal confidence levels. A real data application is presented as an illustrative example. [ABSTRACT FROM AUTHOR]

This paper describes the design of an automatic parallelization framework. The kernel supplied at its front end was suggested as an instrument for parallel potential assessment. It was used to measure the maximum achievable speedups in the major set of the CHStone benchmark suite programs. In such framework, we suggested the liberation of parallelism incrementally. We proposed a data dependency heuristic-based transformation method to make true dependences dissociation. We generated an internal representation (IR2), where the Banerjee test conditions are met. Two among three of Banerjee test conditions came to be committed. In shared memory many/multicore platforms, the third condition could be satisfied by privatization. We would be able to choose the safe and the opportune pairwise (mapping-privatization) scheme among a number of threads mapping scenarios that become available in the IR2 structure. Instrumentation on a subset of CHStone benchmark was carried out as a validity proof of our proposal, and the results confirmed that our framework kernel is robust. [ABSTRACT FROM AUTHOR]

Honey bee populations have been declining precipitously over the past decade, and multiple causative factors have been identified. Recent research indicates that these frequently co-occurring stressors interact, often in unpredictable ways, therefore it has become important to develop robust methods to assess their effects both in isolation and in combination. Most such efforts focus on honey bee workers, but the state of a colony also depends on the health and productivity of its queen. However, it is much more difficult to quantify the performance of queens relative to workers in the field, and there are no laboratory assays for queen performance. Here, we present a new system to monitor honey bee queen egg laying under laboratory conditions and report the results of experiments showing the effects of pollen nutrition on egg laying. These findings suggest that queen egg laying and worker physiology can be manipulated in this system through pollen nutrition, which is consistent with findings from field colonies. The results generated using this controlled, laboratory-based system suggest that worker physiology controls queen egg laying behavior. Additionally, the quantitative data generated in these experiments highlight the utility of the system for further use as a risk assessment tool. [ABSTRACT FROM AUTHOR]

Identifying the underlying models in a set of data points that is contaminated by noise and outliers leads to a highly complex multi-model fitting problem. This problem can be posed as a clustering problem by the projection of higher-order affinities between data points into a graph, which can be clustered using spectral clustering. Calculating all possible higher-order affinities is computationally expensive. Hence, in most cases, only a subset is used. In this paper, we propose an effective sampling method for obtaining a highly accurate approximation of the full graph, which is required to solve multi-structural model fitting problems in computer vision. The proposed method is based on the observation that the usefulness of a graph for segmentation improves as the distribution of the hypotheses that are used to build the graph approaches the distribution of the actual parameters for the given data. In this paper, we approximate this actual parameter distribution by using a $k$ th-order statistics-based cost function, and the samples are generated using a greedy algorithm that is coupled with a data sub-sampling strategy. The experimental analysis shows that the proposed method is both accurate and computationally efficient compared with the state-of-the-art robust multi-model fitting techniques. The implementation of the method is publicly available from https://github.com/RuwanT/model-fitting-cbs. [ABSTRACT FROM AUTHOR]

In this paper we introduce OpenEnsembles, a Python toolkit for performing and analyzing ensemble clustering. Ensemble clustering is the process of creating many clustering solutions for a given dataset and utilizing the relationships observed across the ensemble to identify final solutions, which are more robust, stable or better than the individual solutions within the ensemble. The OpenEnsembles library provides a unified interface for applying transformations to data, clustering data, visualizing individual clustering solutions, visualizing and finishing the ensemble, and calculating validation metrics for a clustering solution for any given partitioning of the data. We have documented examples of using OpenEnsembles to create, analyze, and visualize a number of different types of ensemble approaches on toy and example datasets. OpenEnsembles is released under the GNU General Public License version 3, can be installed via Conda or the Python Package Index (pip), and is available at https://github.com/NaegleLab/OpenEnsembles. [ABSTRACT FROM AUTHOR]

This paper presents an effective multiscale energy-based global ternary image (E-GTI) representation for action recognition from depth sequences. The unique property of our representation is that it takes the spatiotemporal discrimination and action speed variations into account, intending to solve the problems of distinguishing similar actions and identifying the actions with different speeds in one goal. The entire method is carried out in two stages. In the first stage, consecutive depth frames are used to generate global ternary image (GTI) features, which implicitly capture both inter-frame motion regions and motion directions. Specifically, each pixel in the GTI represents one of three possible states, namely, positive, negative, and neutral, which indicate the increased, decreased, and same depth values, respectively. To cope with speed variations in actions, energy-based sampling method is utilized, leading to multiscale E-GTI features, where the multiscale scheme can efficiently capture the temporal relationships among frames. In the second stage, all the E-GTI features are transformed by Radon transform (RT) as robust descriptors, which are aggregated by the bag-of-visual-words model as a compact representation. Extensive experiments on benchmark data sets show that our representation outperforms state-of-the-art approaches, since it captures discriminating spatiotemporal information of actions. Due to the merits of energy-based sampling and RT methods, our representation shows robustness to speed variations, depth noise, and partial occlusions. [ABSTRACT FROM AUTHOR]

This paper develops a robust estimator of correlation as a data preprocessing stage to the Prony method that is able to suppress white impulsive noise. The method consists of the following steps. First, the bus voltage magnitudes and phase angles are combined to build a set of complex-valued measurements. Second, the outliers of the complex-valued data samples, which are induced by impulsive noise, are identified and suppressed using the iteratively reweighted phase–phase correlator; the latter is a robust estimator of correlation for complex-valued Gaussian processes, which has been extended here to handle outliers in both magnitude and phase angle of voltage phasor measurements. Finally, the classical Prony method is applied on the robustly estimated voltage phase angles. The good performance of the proposed method is demonstrated through simulations carried out on the two-area four-machine system, on the simplified WECC 179-bus system, as well as on real PMU data. Simulation results show that the method is very fast to compute and is compatible with real-time application requirements. [ABSTRACT FROM AUTHOR]

Pyrheliometer calibration must be done following strict procedures in order to ensure the required robustness and accuracy. These procedures are described in the ISO 9059:1990 and ASTM E 816 – 15 international standards. However, their application requires information that may not always be available or may be subjective, inaccurate or incomplete, as for example, the determination of “percent of cloud coverage” or “the existence of clouds 15° around the Sun”. The irradiance measurements made by the reference and test instruments involved should also be collected over wide periods after, close to and before solar noon, which might not always be the case depending on the weather conditions during calibration. When those data are not available, the standard cannot be applied properly, and the experts have to decide which data can be used for the calibration. In this study, the abovementioned two main standards for pyrheliometer calibration were thoroughly reviewed, and a harmonized protocol is proposed that uses only the main data recorded. Nineteen field pyrheliometers were calibrated to verify the proposed procedure, and the results show its robustness. After calibration, we analyzed the variability in the calibration constant and the influence of some experimental conditions on the calibration results. As in previous references, the results show that variations in solar elevation and wind speed during the day still influenced the calibration constants of most of the test devices. On the contrary, neither the angle between the wind direction and the solar azimuth nor Linke turbidity seemed to influence the calibration constants calculated. The influence of the Linke turbidity is low as the viewing geometry of all involved pyrheliometers is very similar to each other and as low turbidity prevailed. The correlation between the solar elevation and the wind speed was analyzed and calibration constants were found to vary linearly with solar elevation and wind speed, respectively. Pyrheliometer calibration measurement testing was carried out in Summer 2014 at the Plataforma Solar de Almeria (PSA) in the context of the Solar Facilities for the European Research Area 2 Project (SFERA2). [ABSTRACT FROM AUTHOR]

The minimum covariance determinant (MCD) method is a highly robust estimator of multivariate location and scatter, for which a fast algorithm is available. Since estimating the covariance matrix is the cornerstone of many multivariate statistical methods, the MCD is an important building block when developing robust multivariate techniques. It also serves as a convenient and efficient tool for outlier detection. The MCD estimator is reviewed, along with its main properties such as affine equivariance, breakdown value, and influence function. We discuss its computation, and list applications and extensions of the MCD in applied and methodological multivariate statistics. Two recent extensions of the MCD are described. The first one is a fast deterministic algorithm which inherits the robustness of the MCD while being almost affine equivariant. The second is tailored to high‐dimensional data, possibly with more dimensions than cases, and incorporates regularization to prevent singular matrices. This article is categorized under: Statistical and Graphical Methods of Data Analysis > Multivariate Analysis Statistical and Graphical Methods of Data Analysis > Robust Methods Statistical Learning and Exploratory Methods of the Data Sciences > Knowledge Discovery [ABSTRACT FROM AUTHOR]

Given a classification task, an approach to improve accuracy relies on the use of abstaining classifiers. These classifiers are trained to reject observations for which predicted values are not reliable enough: these rejected observations belong to an abstaining area in the feature space. Two equivalent methods exist to theoretically compute the optimal abstaining area for a given classification problem. The first one is based on the posterior probability computed by the model and the other is based on the derivative of the ROC function of the model. Although the second method has proved to give the best results, in small-sample settings such as the one found in omics data, the estimation of posterior probabilities and derivative of ROC curve are both lacking of precision leading to far from optimal abstaining areas. As a consequence none of the two methods bring the expected improvements in accuracy. We propose five alternative algorithms to compute the abstaining area adapted to small-sample problems. The idea of these algorithms is to compute an accurate and robust estimation of the ROC curve and its derivatives. These estimation are mainly based on the assumption that the distribution of the output of the classifier for each class is normal or mixture of normal distributions. These distributions are estimated by a kernel density estimator or Bayesian semiparametric estimator. Another method works on the approximation of the convex hull of the ROC curve. Once the derivative of the ROC curve are estimated, the optimal abstaining area can be directly computed. The performance of our algorithms are directly related to their capacity to compute an accurate estimation of the ROC curve. A sensitivity analysis of our methods to the dataset size and rejection cost has been done on a set of experiments. We show that our methods improve the performances of the abstaining classifiers on several real datasets and for different learning algorithms. [ABSTRACT FROM AUTHOR]

In the era of big data, it is increasingly common that large amount of data is generated across multiple distributed sites and cannot be gathered into a centralized site for further analysis, which invalidates the assumption of traditional clustering techniques based on centralized models. The major challenge is that these distributed datasets cannot be trivially merged due to issues such as privacy concerns, limited network bandwidth among sites and limited computational capacity of a single site. To tackle this challenge, we propose an efficient distributed clustering scheme using boundary information (DCUBI), which features good flexibility and scalability. The main procedure of DCUBI consists of three steps: local-global-local. Firstly, each local site extracts the boundary points from its own local data and applies traditional clustering on boundary points only. Secondly, labeled boundary points from each site are sent to the central site as local representatives where boundary and cluster fusion is conducted to form the global clustering model. Finally, the global boundary and cluster information is sent back to each local site for refined local clustering. To demonstrate the effectiveness of DCUBI, we plug the well-known DBSCAN algorithm into DCUBI and comprehensive experiments are conducted using datasets with different properties. Experiment results clearly verify the quality of clustering by DCUBI as well as its superior time efficiency when the volume of data in each site is large. Furthermore, other popular clustering techniques especially those with high time complexity such as spectral clustering and affinity propagation clustering are also plugged into DCUBI to demonstrate the flexibility of the proposed scheme. [ABSTRACT FROM AUTHOR]

A novel methodology based deep belief networks and multiple models (DBNs-MMs) is presented to accomplish fault detection for complex systems. And firstly, historical datasets are collected and processed to train the DBNs, so that DBNs can be constructed to learn the nonlinear dynamic characteristics of complex system, and so a model with a specific architecture and some initial intelligence will be built up. Secondly, the operation condition and real-time measurement data are employed in DBNs-MMs to get a series of network outputs. Finally, the residuals can be obtained by comparing the measurement output and each DBN output. Then, the fault detection can be achieved by employing a properly adaptive threshold for each residual. Some faulty cases of the complex cryogenic propellant loading system have been used to demonstrate the effectiveness of the proposed fault detection methodology, and the result has shown its excellent performance. [ABSTRACT FROM AUTHOR]

Three-phase induction motors are extensively used in the industry due to their robustness characteristics, low cost and easy maintenance. Usually, it is necessary to implement drive and control systems for such motors, which requires the knowledge of their mechanical and electrical parameters. However, in some cases, these data are not immediately available, or the values of the parameters may change due to the wear of motor components. Such problems can be circumvented if an efficient parameter estimation technique is available. In order to automatically estimate the parameters efficiently, the present work proposes a method, based on the differential evolution algorithm, aimed at the estimation of the electrical and mechanical parameters of three-phase induction motors. Such algorithm is capable of estimating the parameters of the equivalent electrical circuit, such as stator and rotor resistances and leakage inductances, the magnetizing inductance, and also mechanical parameters, such as moment of inertia and the friction coefficient. The performance of the proposed parameter estimation technique is evaluated for three different input signals: (i) current signal of a phase associated with the speed measured from a tachogenerator, (ii) current signal of a phase associated with the speed acquired from a torquemeter, and (iii) only the current signal of one phase. Finally, a series of simulated and experimental results are presented to validate the proposed technique, and the results show the good performance of the proposed strategies. [ABSTRACT FROM AUTHOR]

This paper presents a self-learning decision making procedure for robust real-time train rescheduling in case of disturbances. The procedure is applicable to aperiodic timetables of mixed-tracked networks and it consists of three steps. The first two are executed in real-time and provide the rescheduled timetable, while the third one is executed offline and guarantees the self-learning part of the method. In particular, in the first step, a robust timetable is determined, which is valid for a finite time horizon . This robust timetable is obtained solving a mixed integer linear programming problem aimed at finding the optimal compromise between two objectives: the minimization of the delays of the trains and the maximization of the robustness of the timetable. In the second step, a merging procedure is first used to join the obtained timetable with the nominal one. Then, a heuristics is applied to identify and solve all conflicts eventually arising after the merging procedure. Finally, in the third step an offline cross-efficiency fuzzy Data Envelopment Analysis technique is applied to evaluate the efficiency of the rescheduled timetable in terms of delays minimization and robustness maximization when different relevance weights (defining the compromise between the two optimization objectives) are used in the first step. The procedure is thus able to determine appropriate relevance weights to employ when disturbances of the same type affect again the network. The railway service provider can take advantage of this procedure to automate, optimize, and expedite the rescheduling process. Moreover, thanks to the self-learning capability of the procedure, the quality of the rescheduling is improved at each reapplication of the method. The technique is applied to a real data set related to a regional railway network in Southern Italy to test its effectiveness. [ABSTRACT FROM AUTHOR]

Extracellular neural recordings have become an essential technique for studying and monitoring neural activity, which is of vital importance in understanding brain functions. However, how to accurately and effectively detect spikes from the extracellular recording signals is still a major related challenge. The existing methods for spike detection have achieved much progress while they are vulnerable to the background noise. In this paper, we develop an object-dependent sparse representation framework for high accuracy and robust extracellular spike detection. Specifically, by exploiting the structural similarities of spikes, we construct an object-dependent dictionary to achieve a sparse and comprehensive representation of the recorded signals. Thus, the problem of spike detection can be formulated as a convex sparse optimization problem. Through systematically analyzing the optimal solution, the number and locations of spikes in the recorded signal are finally determined. In addition, singular value decomposition (SVD) is introduced to further improve the flexibility and robustness of the proposed method. Experimental results on both synthesized extracellular neural recordings and real data show that the proposed method outperforms the existing methods. [ABSTRACT FROM AUTHOR]

Mixture of experts (MoE) is a popular framework in the fields of statistics and machine learning for modeling heterogeneity in data for regression, classification and clustering. MoE for continuous data are usually based on the normal distribution. However, it is known that for data with asymmetric behavior, heavy tails and atypical observations, the use of the normal distribution is unsuitable. We introduce a new robust non-normal mixture of experts modeling using the skew t distribution. The proposed skew t mixture of experts, named STMoE, handles these issues of the normal mixtures experts regarding possibly skewed, heavy-tailed and noisy data. We develop a dedicated expectation conditional maximization (ECM) algorithm to estimate the model parameters by monotonically maximizing the observed data log-likelihood. We describe how the presented model can be used in prediction and in model-based clustering of regression data. Numerical experiments carried out on simulated data show the effectiveness and the robustness of the proposed model in fitting non-linear regression functions as well as in model-based clustering. Then, the proposed model is applied to the real-world data of tone perception for musical data analysis, and the one of temperature anomalies for the analysis of climate change data. The obtained results confirm the usefulness of the model for practical data analysis applications. [ABSTRACT FROM AUTHOR]

In this paper, an innovative robust prediction algorithm for performance degradation of proton exchange membrane fuel cell (PEMFC) is proposed based on a combination of model-based and data-driven prognostic method. A novel approach using the moving window method is applied, in order to 1) train the developed models; 2) update the weight factors of each method and 3) further fuse the predicted results iteratively. In the proposed approach, both model-based and data-driven methods are simultaneously used to achieve a better accuracy. During the prediction process, each dataset in the proposed moving window are divided into three sections respectively: training, evaluation and prediction. The training data are used first to identify the models parameters. The evaluation data are then used to measure the weight of each method, which represents the degree of confidence of each method in the actual state. Based on these dynamically adjusting weight factors, the prediction results from different methods are then fused using weighted average methodology to calculate the final prediction results. In order to verify the proposed method, three experimental validations with different aging testing profiles have been performed. The results demonstrate that the proposed hybrid prognostic approach can achieve a higher accuracy than conventional prediction methods. In addition, in order to find the satisfactory trade-off between the prediction accuracy and forecast time for optimizing on-line prognostic, the performance variation of proposed approach with different moving window length is further showed and discussed. [ABSTRACT FROM AUTHOR]

This paper presented a new data-driven robust control scheme for unknown nonlinear systems in the presence of input saturation and external disturbances. According to the input and output data of the nonlinear system, a recurrent neural network (RNN) data-driven model is established to reconstruct the dynamics of the nonlinear system. An adaptive output-feedback controller is developed to approximate the unknown disturbances and a novel input saturation compensation method is used to attenuate the effect of the input saturation. Under the proposed adaptive control scheme, the uniformly ultimately bounded convergence of all the signals of the closed-loop nonlinear system is guaranteed via Lyapunov analysis. The simulation results are given to show the effectiveness of the proposed data-driven robust controller. [ABSTRACT FROM AUTHOR]

In many epidemiology studies, family data with survival endpoints are collected to investigate the association between risk factors and disease incidence. Sometimes the risk of the disease may change when a certain risk factor exceeds a certain threshold. Finding this threshold value could be important for disease risk prediction and diseases prevention. In this work, we propose a change-point proportional hazards model for clustered event data. The model incorporates the unknown threshold of a continuous variable as a change point in the regression. The marginal pseudo-partial likelihood functions are maximized for estimating the regression coefficients and the unknown change point. We develop a supremum test based on robust score statistics to test the existence of the change point. The inference for the change point is based on the m out of n bootstrap. We establish the consistency and asymptotic distributions of the proposed estimators. The finite-sample performance of the proposed method is demonstrated via extensive simulation studies. Finally, the Strong Heart Family Study dataset is analyzed to illustrate the methods. [ABSTRACT FROM AUTHOR]

Multidimensional scaling (MDS) is an efficient technique for data analysis, and has been successfully applied in data visualization, object retrieval, data clustering, and so on. However, its use in image hashing is rarely discussed yet. In this study, we investigate the use of MDS in image hashing and propose an MDS-based hashing algorithm resistant to any-angle rotation. The proposed algorithm extracts a rotation-invariant feature matrix with log-polar transform and discrete Fourier transform from the normalized image, and learns a compact and discriminative representation from the feature matrix by MDS. Experiments with 3845 images are carried out and the results demonstrate that the proposed algorithm is robust to many content-preserving operations, including any-angle rotation, and reaches good discrimination. Receiver operating characteristics (ROC) curve comparisons illustrate that the proposed algorithm outperforms some state-of-the-art algorithms in classification with respect to robustness and discrimination. [ABSTRACT FROM AUTHOR]