Search

In recent years, advances in sensor technology, connectedness and computational power have come together to produce huge data-sets. The treatment and analysis of these data-sets is known as big data analytics (BDA), and the somewhat related term data mining. Fields allied to human factors/ergonomics (HFE), e.g. statistics, have developed computational methods to derive meaningful, actionable conclusions from these data bases. This paper examines BDA, often characterised by volume, velocity and variety, giving examples of successful BDA use. This examination provides context by considering examples of using BDA on human data, using BDA in HFE studies, and studies of how people perform BDA. Significant issues for HFE are the reliance of BDA on correlation rather than hypotheses and theory, the ethics of BDA and the use of HFE in data visualisation. Practitioner Summary:Human factors/ergonomics practitioners are increasingly likely to work with the large data bases and novel software associated with big data analytics (BDA) and similar fields such as data mining. This paper shows the characteristics of BDA and details methodological and ethical issues that arise in BDA. [ABSTRACT FROM AUTHOR]

In this paper, we develop a new forecasting algorithm for value-at-risk (VaR) based on ARMA-GARCH (autoregressive moving average-generalized autoregressive conditional heteroskedastic) models whose innovations follow a Gaussian mixture distribution. For the parameter estimation, we employ the conditional least squares and quasi-maximum-likelihood estimator (QMLE) for ARMA and GARCH parameters, respectively. In particular, Gaussian mixture parameters are estimated based on the residuals obtained from the QMLE of GARCH parameters. Our algorithm provides a handy methodology, spending much less time in calculation than the existing resampling and bias-correction method developed in Hartz et al. [Accurate value-at-risk forecasting based on the normal-GARCH model, Comput. Stat. Data Anal. 50 (2006), pp. 3032-3052]. Through a simulation study and a real-data analysis, it is shown that our method provides an accurate VaR prediction. [ABSTRACT FROM AUTHOR]

This paper presents a conditional role-involved purpose-based access control (CPAC) model, where users dynamically activate conditional roles in accordance with the context attributes. Based on conditional role, access permissions are assigned that represent what can be accessed for what purpose to roles under certain conditions. On the other hand, conditional purpose is applied along with allowed purpose and prohibited purpose in the model. It allows users using some data for certain purpose with conditions (for instance, Tony agrees that his income information can be used for marketing purposes by removing his name). The structure of a CPAC model is defined and investigated. Access purpose is verified in a dynamic behavior, based on user attributes, context attributes, and authorization policies. Intended purposes are dynamically associated with the requested data object during the access decision. An algorithm is developed to achieve the compliance computation between access purposes and intended purposes and is illustrated with role-based access control (RBAC). Access purpose authorization and authentication in the model are studied with the hierarchical purpose structure. The model separates authorization of access purpose from access decision that improves the flexibility of private data control. [ABSTRACT FROM AUTHOR]

We study the nonparametric maximum likelihood estimate (NPMLE) of the cdf or sub-distribution functions of the failure time for the failure causes in a series system. The study is motivated by a cancer research data (from the Memorial Sloan-Kettering Cancer Center) with interval-censored time and masked failure cause. The NPMLE based on this data set suggests that the existing masking models are not appropriate. We propose a new model called the random partition masking model, which does not rely on the commonly used symmetry assumption (namely, given the failure cause, the probability of observing the masked failure causes is independent of the failure time; see Flehinger et al. Inference about defects in the presence of masking, Technometrics 38 (1996), pp. 247–255). The RPM model is easier to implement in simulation studies than the existing models. We discuss the algorithms for computing the NPMLE and study its asymptotic properties. Our simulation and data analysis indicate that the NPMLE is feasible for a moderate sample size. [ABSTRACT FROM AUTHOR]

We investigate three interval estimators for binomial misclassification rates in a complementary Poisson model where the data are possibly misclassified: a Wald-based interval, a score-based interval, and an interval based on the profile log-likelihood statistic. We investigate the coverage and average width properties of these intervals via a simulation study. For small Poisson counts and small misclassification rates, the intervals can perform poorly in terms of coverage. The profile log-likelihood confidence interval (CI) is often proved to outperform the other intervals with good coverage and width properties. Lastly, we apply the CIs to a real data set involving traffic accident data that contain misclassified counts. [ABSTRACT FROM AUTHOR]

Purpose: To provide a mathematical calculation scheme for customized intraocular lens (IOL) design based on high resolution anterior segment optical coherence tomography (AS-OCT) of anterior eye segment and axial length data. Material and Methods: We use the corneal and anterior segment data from the high resolution AS-OCT and the axial length data from the IOLMaster to create a pseudophakic eye model. An inverse calculation algorithm for the IOL back surface optimization is introduced. We employ free form surface representation (bi-cubic spline) for the corneal and IOL surface. The merit of this strategy is demonstrated by comparing with a standard spherical model and quadratic function. Four models are calculated: (1) quadratic cornea ++ quadratic IOL; (2) spline cornea ++ quadratic IOL; (3) spline cornea ++ spline IOL; and (4) spherical cornea ++ spherical IOL. The IOL optimization process for the pseudophakic eye is performed by numerical ray-tracing method within a 6-mm zone. The spot diagram on the fovea (forward ray-tracing) and wavefront at the spectacle plane (backward ray-tracing) are compared for different models respectively. Results: The models with quadratic (1) or spline (3) surface representation showed superior image performance than the spherical model 4. The residual wavefront errors (peak to valley) of models 1, 2, and 3 are below one micron scale. Model 4 showed max wavefront error of about 15 µµm peak to valley. However, the combination of quadratic best fit IOL with the free form cornea (model 2) showed one magnitude smaller wavefront error than the spherical representation of both surfaces (model 3). This results from higher order terms in cornea height profile. Conclusions: A four-surface eye model using a numerical ray-tracing method is proposed for customized IOL calculation. High resolution OCT data can be used as a sufficient base for a customized IOL characterization. [ABSTRACT FROM AUTHOR]

In the parametric regression model, the covariate missing problem under missing at random is considered. It is often desirable to use flexible parametric or semiparametric models for the covariate distribution, which can reduce a potential misspecification problem. Recently, a completely nonparametric approach was developed by [H.Y. Chen, Nonparametric and semiparametric models for missing covariates in parameter regression, J. Amer. Statist. Assoc. 99 (2004), pp. 1176-1189; Z. Zhang and H.E. Rockette, On maximum likelihood estimation in parametric regression with missing covariates, J. Statist. Plann. Inference 47 (2005), pp. 206-223]. Although it does not require a model for the covariate distribution or the missing data mechanism, the proposed method assumes that the covariate distribution is supported only by observed values. Consequently, their estimator is a restricted maximum likelihood estimator (MLE) rather than the global MLE. In this article, we show the restricted semiparametric MLE could be very misleading in some cases. We discuss why this problem occurs and suggest an algorithm to obtain the global MLE. Then, we assess the performance of the proposed method via some simulation experiments. [ABSTRACT FROM AUTHOR]

Although there has been significant research on modelling and learning user preferences for various types of objects, there has been relatively little work on the problem of representing and learning preferences over sets of objects. We introduce a representation language, DD-PREF, that balances preferences for particular objects with preferences about the properties of the set. Specifically, we focus on the depth of objects (i.e. preferences for specific attribute values over others) and on the diversity of sets (i.e. preferences for broad vs. narrow distributions of attribute values). The DD-PREF framework is general and can incorporate additional object- and set-based preferences. We describe a greedy algorithm, DD-Select, for selecting satisfying sets from a collection of new objects, given a preference in this language. We show how preferences represented in DD-PREF can be learned from training data. Experimental results are given for three domains: a blocks world domain with several different task-based preferences, a real-world music playlist collection, and rover image data gathered in desert training exercises. [ABSTRACT FROM AUTHOR]

A new method for detecting the parameter changes in generalized autoregressive heteroskedasticity GARCH (1,1) model is proposed. In the proposed method, time series observations are divided into several segments and a GARCH (1,1) model is fitted to each segment. The goodness-of-fit of the global model composed of these local GARCH (1,1) models is evaluated using the corresponding information criterion (IC). The division that minimizes IC defines the best model. Furthermore, since the simultaneous estimation of all possible models requires huge computational time, a new time-saving algorithm is proposed. Simulation results and empirical results both indicate that the proposed method is useful in analysing financial data. [ABSTRACT FROM AUTHOR]

We consider regression experiments involving a response variable Y and a large number of predictor variables X1,…, Xd, many of which may be irrelevant for the prediction of Y and thus must be removed before Y can be predicted from the X's. We consider two procedures that select variables by using importance scores that measure the strength of the relationship between predictor variables and a response and keep those variables whose importance scores exceed a threshold. In the first of these procedures, scores are obtained by randomly drawing subregions (tubes) of the predictor space that constrain all but one predictor and in each subregion computing a signal-to-noise ratio (efficacy) based on a nonparametric univariate regression of Y On the unconstrained variable. The subregions are adapted to boost weak variables iteratively by searching (hunting) for the subregions in which the efficacy is maximized. The efficacy can be viewed as an approximation to a one-to-one function of the probability of identifying features. By using importance scores based on averages of maximized efficacies, we develop a variable selection algorithm called EARTH (efficacy adaptive regression tube hunting) based on examining the conditional expectation of the response given all but one of the predictor variables for a collection of randomly, adaptively and iteratively selected regions. The second importance score method (RFVS) is based on using random forest importance values to select variable. Computer simulations show that EARTH and RFVS are successful variable selection methods compared with other procedures in nonparametric situations with a large number of irrelevant predictor variables, and that when each is combined with the model selection and prediction procedure MARS, the tree-based prediction procedure GUIDE, and the random forest method, the combinations lead to improved prediction accuracy for certain models with many irrelevant variables. We give conditions under which a version of the EARTH algorithm selects the correct model with probability tending to 1 as the sample size n tends to infinity even if d → ∞ n → ∞. We include the analysis of a real data set in which we show how a training set can be used to find a threshold for the EARTH importance scores. [ABSTRACT FROM AUTHOR]