Search Results for « Non-parametric framework »

We develop a Bayesian non-parametric quantile panel regression model. Within each quantile, the response function is a convex combination of a linear model and a non-linear function, which we approximate using Bayesian Additive Regression Trees (BART). Cross-sectional information at the pth quantile is captured through a conditionally heteroscedastic latent factor. The non-parametric feature of our model enhances flexibility, while the panel feature, by exploiting cross-country information, increases the number of observations in the tails. We develop Bayesian Markov chain Monte Carlo (MCMC) methods for estimation and forecasting with our quantile factor BART model (QF-BART), and apply them to study growth at risk dynamics in a panel of 11 advanced economies.

Despite its great potential in studying brain anatomy and structure, diffusion magnetic resonance imaging (dMRI) is marred by artefacts more than any other commonly used MRI technique. In this paper we present a non-parametric framework for detecting and correcting dMRI outliers (signal loss) caused by subject motion. Signal loss (dropout) affecting a whole slice, or a large connected region of a slice, is frequently observed in diffusion weighted images, leading to a set of unusable measurements. This is caused by bulk (subject or physiological) motion during the diffusion encoding part of the imaging sequence. We suggest a method to detect slices affected by signal loss and replace them by a non-parametric prediction, in order to minimise their impact on subsequent analysis. The outlier detection and replacement, as well as correction of other dMRI distortions (susceptibility-induced distortions, eddy currents (EC) and subject motion) are performed within a single framework, allowing the use of an integrated approach for distortion correction. Highly realistic simulations have been used to evaluate the method with respect to its ability to detect outliers (types 1 and 2 errors), the impact of outliers on retrospective correction of movement and distortion and the impact on estimation of commonly used diffusion tensor metrics, such as fractional anisotropy (FA) and mean diffusivity (MD). Data from a large imaging project studying older adults (the Whitehall Imaging sub-study) was used to demonstrate the utility of the method when applied to datasets with severe subject movement. The results indicate high sensitivity and specificity for detecting outliers and that their deleterious effects on FA and MD can be almost completely corrected.

We examine Cosmic Microwave Background (CMB) temperature power spectra from the BOOMERANG, MAXIMA, and DASI experiments. We non-parametrically estimate the true power spectrum with no model assumptions. This is a significant departure from previous research which used either cosmological models or some other parameterized form (e.g. parabolic fits). Our non-parametric estimate is practically indistinguishable from the best fit cosmological model, thus lending independent support to the underlying physics that governs these models. We also generate a confidence set for the non-parametric fit and extract confidence intervals for the numbers, locations, and heights of peaks and the successive peak-to-peak height ratios. At the 95%, 68%, and 40% confidence levels, we find functions that fit the data with one, two, and three peaks respectively (0 <= l <= 1100). Therefore, the current data prefer two peaks at the 1 sigma level. However, we also rule out a constant temperature function at the >8 sigma level. If we assume that there are three peaks in the data, we find their locations to be within l_1 = (118,300), l_2 = (377,650), and l_3 = (597,900). We find the ratio of the first peak-height to the second (Delta T_1)/(Delta T_2)^2= (1.06, 4.27) and the second to the third (Delta T_2)/(Delta T_3)^2= (0.41, 2.5). All measurements are for 95% confidence. If the standard errors on the temperature measurements were reduced to a third of what they are currently, as we expect to be achieved by the MAP and Planck CMB experiments, we could eliminate two-peak models at the 95% confidence limit. The non-parametric methodology discussed in this paper has many astrophysical applications.

Abstract Drought has a complex climatic and spatio‐temporal feature. Therefore, its accurate monitoring is a great challenge for hydrological research. Recently, the use of standardized drought indices (SDIs) for drought monitoring is common in practice. However, because of the subjective choices of probability distribution, the uncertainty related to extreme events always exists in SDIs‐based drought‐monitoring tools. The present research extends the generalized non‐parametric framework for drought monitoring. The application of the proposed framework is based on seven meteorological stations in Pakistan. The preliminary analysis considered the standardized precipitation temperature index (SPTI) at different time scales. The significance of the proposed framework is to address extreme values with more accuracy under a non‐parametric framework. It is concluded that the suitable choice of probability‐plotting‐position formulas allows greater accuracy when capturing the probability of extreme drought events.

Imperceptible adversarial attacks aim to fool DNNs by adding imperceptible perturbation to the input data. Previous methods typically improve the imperceptibility of attacks by integrating common attack paradigms with specifically designed perception-based losses or the capabilities of generative models. In this paper, we propose Adversarial Attacks in Diffusion (AdvAD), a novel modeling framework distinct from existing attack paradigms. AdvAD innovatively conceptualizes attacking as a non-parametric diffusion process by theoretically exploring basic modeling approach rather than using the denoising or generation abilities of regular diffusion models requiring neural networks. At each step, much subtler yet effective adversarial guidance is crafted using only the attacked model without any additional network, which gradually leads the end of diffusion process from the original image to a desired imperceptible adversarial example. Grounded in a solid theoretical foundation of the proposed non-parametric diffusion process, AdvAD achieves high attack efficacy and imperceptibility with intrinsically lower overall perturbation strength. Additionally, an enhanced version AdvAD-X is proposed to evaluate the extreme of our novel framework under an ideal scenario. Extensive experiments demonstrate the effectiveness of the proposed AdvAD and AdvAD-X. Compared with state-of-the-art imperceptible attacks, AdvAD achieves an average of 99.9$\%$ (+17.3$\%$) ASR with 1.34 (-0.97) $l_2$ distance, 49.74 (+4.76) PSNR and 0.9971 (+0.0043) SSIM against four prevalent DNNs with three different architectures on the ImageNet-compatible dataset. Code is available at https://github.com/XianguiKang/AdvAD.

BACKGROUND: To estimate a threshold limit value for a compound known to have harmful health effects, an 'elbow' threshold model is usually applied. We are interested on non-parametric flexible alternatives. METHODS: We describe how a step function model fitted by isotonic regression can be used to estimate threshold limit values. This method returns a set of candidate locations, and we discuss two algorithms to select the threshold among them: the reduced isotonic regression and an algorithm considering the closed family of hypotheses. We assess the performance of these two alternative approaches under different scenarios in a simulation study. We illustrate the framework by analysing the data from a study conducted by the German Research Foundation aiming to set a threshold limit value in the exposure to total dust at workplace, as a causal agent for developing chronic bronchitis. RESULTS: In the paper we demonstrate the use and the properties of the proposed methodology along with the results from an application. The method appears to detect the threshold with satisfactory success. However, its performance can be compromised by the low power to reject the constant risk assumption when the true dose-response relationship is weak. CONCLUSION: The estimation of thresholds based on isotonic framework is conceptually simple and sufficiently powerful. Given that in threshold value estimation context there is not a gold standard method, the proposed model provides a useful non-parametric alternative to the standard approaches and can corroborate or challenge their findings.

Software Visualization encompasses the development and evaluation of methods for graphically representing different aspects of methods of software, including its structure, execution and evolution. Creating visualizations helps the user to better understand complex phenomena. It is also found by the software engineering community that visualization is essential and important. In order to visualize the evolution of the models in Model-Driven Software Evolution, authors have proposed a framework which consists of 7 key areas (views) and 22 key features for the assessment of Model Driven Software Evolution process and addresses a number of stakeholder concerns. The framework is derived by the application of the Goal Question Metric Paradigm. This paper aims to describe an application of the framework by considering different visualization tools/CASE tools which are used to visualize the models in different views and to capture the information of models during their evolution. Comparison of such tools is also possible by using the framework.

Summary We propose a non‐parametric framework for analysing data defined over products of metric spaces, a versatile class encountered in various fields. This framework accommodates non‐stationarity and seasonality and is applicable to both local and global domains, such as the Earth's surface, as well as domains evolving over linear time or time embedded in more complex geometries. Our focus is on defining random correlation functions over these spaces, which we achieve through the introduction of a symplectic double random sequence, developed using a novel constructive approach termed compositional stick‐breaking. We explore the distributional properties of the resulting random correlation functions, particularly when used as non‐parametric priors for unknown correlation structures in a Bayesian framework. Because this modelling strategy relies on infinite orthogonal expansions, and truncations are used to ensure computational feasibility, we analyse the impact of these truncations by deriving probabilistic upper bounds for the approximations they introduce. Finally, we demonstrate the method's performance through applications to synthetic data and real wind speed data on the hypertorus.

The increased availability and usage of modern medical imaging induced a strong need for automatic medical image segmentation. Still, current image segmentation platforms do not provide the required functionalities for plain setup of medical image segmentation pipelines. Already implemented pipelines are commonly standalone software, optimized on a specific public data set. Therefore, this paper introduces the open-source Python library MIScnn. The aim of MIScnn is to provide an intuitive API allowing fast building of medical image segmentation pipelines including data I/O, preprocessing, data augmentation, patch-wise analysis, metrics, a library with state-of-the-art deep learning models and model utilization like training, prediction, as well as fully automatic evaluation (e.g. cross-validation). Similarly, high configurability and multiple open interfaces allow full pipeline customization. Running a cross-validation with MIScnn on the Kidney Tumor Segmentation Challenge 2019 data set (multi-class semantic segmentation with 300 CT scans) resulted into a powerful predictor based on the standard 3D U-Net model. With this experiment, we could show that the MIScnn framework enables researchers to rapidly set up a complete medical image segmentation pipeline by using just a few lines of code. The source code for MIScnn is available in the Git repository: https://github.com/frankkramer-lab/MIScnn.

The recently evolved family of coronaviruses known as the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) or COVID-19 has spread across the world at a critically alarming rate, thereby causing a global health emergency.Several nations have been adversely affected in terms of both social and economic aspects.Hence there is an utmost need to control the transmission rate of the virus by incorporating stringent control measures.In this article, a non-parametric framework for characterizing the epidemiological behaviour of COVID-19 is suggested.Several statistical analysis tests have been conducted on the time series data acquired for four countries to derive a relationship between the three considered cases, viz. the new incidence of COVID-19, new deaths, and new sample testing facilities.Further, considering the dynamical behaviour of the sample data, a smoothing spline approach is implemented to obtain a better analysis of the observations.Subsequently, autocorrelation function is used to study the degree of correlation for each considered case for specific time lags.Finally, the nonparametric kernel density estimate is adopted for obtaining a robust characterization of the underlying distributions pertaining to each case considered in this study.Hence these observations lead to the development of an efficient prediction framework that can be implemented for analysing the epidemiological behaviour of the COVID-19 pandemic.