Search

Effectively grouping learners in an online environment is a highly useful task. However, datasets used in this task often have large numbers of attributes of disparate types and different scales, which traditional clustering approaches cannot handle effectively. Here, a unique dissimilarity measure based on the random forest, which handles the stated drawbacks of more traditional clustering approaches, is presented. Additionally, a rule-based method is proposed for interpreting the resulting learner segmentations. The approach was implemented on a real dataset of users of the "Career"WISE online educational environment, designed to provide resilience training for women STEM doctoral students, and was shown to find stable and meaningful groups of users.

This paper proposes a new feature selection methodology. The methodology is based on the stepwise variable selection procedure, but, instead of using the traditional discriminant metrics such as Wilks' Lambda, it uses an estimation of the misclassification error as the figure of merit to evaluate the introduction of new features. The expected misclassification error rate (MER) is obtained by using the densities of a constructed function of random variables, which is the stochastic representation of the conditional distribution of the quadratic discriminant function estimate. The application of the proposed methodology results in significant savings of computational time in the estimation of classification error over the traditional simulation and cross-validation methods. One of the main advantages of the proposed method is that it provides a direct estimation of the expected misclassification error at the time of feature selection, which provides an immediate assessment of the benefits of introducing an additional feature into an inspection/classification algorithm. Index Terms--Feature selection, misclassification error rate, quadratic discriminant function.

Process knowledge can be exploited to improve the performance of control charts and it is not unusual to know that a specific variable shifts above or below its mean under an assignable cause. In such a case, a one-sided control chart is common. The available statistical theory for the one-sided tests is used to provide a reasonable compromise for a numerical procedure to design and implement multivariate solutions. Although simulation is used in the analysis, it is not a direct estimate of performance through simulation. Instead, weights are estimated and these are used to easily set a desired on-target average run length. Furthermore, an interesting quadratic programming solution is incorporated into the analysis. Then the statistical results are extended to a partial one-sided case where only some (not all) variables are known to shift in one direction and the numerical procedure is extended to design and implement the charts. A modern method can blend theory and algorithms into a practical solution. We conclude that modern computer software permits an efficient solution to this problem with meaningful performance advantages over traditional multivariate control charts., 1. Introduction Multivariate control charts such as chi-squared, Multivariate Exponentially Weighted Moving Average (MEWMA) and multivariate CUmulative SUM (CUSUM) charts are sensitive to shifts of the process mean vector in [...]

An estimate of cycle time for a product in a factory is critical to semiconductor manufacturers (and in other industries) to assess customer due dates, schedule resources and actions for anticipated job completions, and to monitor the operation. Historical data can be used to learn a predictive model for cycle time based on measured and calculated process metrics (such as work-in-progress at specific operations, lot priority, product type, and so forth). Such a method is relatively easy to develop and maintain. Modern data mining algorithms are used to develop nonlinear predictors applicable to the majority of process lots, and three methods are compared here. They are compared with respect to performance in actual manufacturing data (to predict times for both final and intermediate steps) and for the feasibility to maintain and rebuild the model. Index Terms--Due date, scheduling, statistical models, work-in-progress (WIP).

In the fields of statistics and computer science a wide variety of methodologies exist for solving the traditional classification problem. This study will compare the error rates for various methods under a variety of conditions when the explanatory variables are continuous. The methods under considerations are neural networks, classical discriminant analysis, and two different approaches to decision trees. Training and testing sets are utilized to estimate the error rates of these methods for different numbers of sample sizes, number of explanatory variables, and the number of classes in the dependent variable. These error rates will be used to draw generalized conclusions about the relative efficiencies of the techniques., 1. Introduction The classification of objects into groups or supervised learning is a common decision-making requirement. In general, there are two primary approaches to this process of classification. The traditional [...]

Probe testing following wafer fabrication can produce extremely large amounts of data, which is often used to inspect a final product to determine if the product meets specifications. This data can be further utilized in studying the effects of the wafer fabrication process on the quality or yield of the wafers. Relationships among the parameters may provide valuable process information that can improve future production. This paper compares many methods of using the probe test data to determine the cause of low yield wafers. The methods discussed include two classes of traditional multivariate statistical methods, clustering and principal component methods and regression-based methods. These traditional methods are compared to a classification and regression tree (CART) method. The results for each method are presented. CART adequately fits the data and provides a 'recipe' for avoiding low yield wafers and because CART is distribution-free there are no assumptions about the distributional properties of the data. CART is strongly recommended for analyzing wafer probe data. Index Terms--CART, multivariate statistical methods, tree regression, yield analysis.

In this paper, we introduce the concept of fine-tuned learning which relies on the notion of data approximation followed by sequential data refinement. We seek to determine whether fine-tuned learning is a viable approach to use when trying to solve combinatorial optimization problems. In particular, we conduct an extensive computational experiment to study the performance of fine-tuned-learning-based heuristics for the traveling salesman problem (TSP). We provide important insight that reveals how fine-tuned learning works and why it works well, and conclude that it is a meritorious concept that deserves serious consideration by researchers solving difficult problems.

Modern statistical process control must often cope with large quantities of highly autocorrelated data. Alwan and Radson (1992) proposed the monitoring of autocorrelated processes by plotting the averages of small batches of data separated by skipping observations. Using results for the AR(1) process, we show that generally better performance can be achieved with no skipping and much larger batch sizes. The resulting batch-means charts derive from methods used in simulation output analysis and can be implemented easily with common digital control systems., 1. Introduction Increased use of online automated data acquisition systems is producing unprecedented volumes of data with high autocorrelation (Hahn, 1989). This trend is most pronounced in the chemical and [...]

Adaptive sampling is an enhancement to a classical statistical process control scheme in which the time between samples from the process is varied based on the available information. Unlike the classical Shewhart control schemes, the performance of an adaptive sampling scheme for detecting a process which is off-target before the first observation is selected can differ from the steady-state performance, which is the performance of the scheme for detecting a process shift after the control scheme has been operating for some time. Often steady-state performance is the more important criterion for evaluating statistical process control schemes. Previous work has considered initial performance and steady-state performance, but the charts examined were optimized for initial performance. The development of charts optimized for steady-state performance and a comparison to previously developed schemes are the topics of this paper. Tables providing performance information on adaptive schemes are included.

Gradient boosting method has been successfully used for single target prediction problems. In real world applications, however, problems involving the prediction of multiple target attributes are often of interest. In this paper, a multi-target boosting method for regression problems, named as MTBR, is proposed. Although MTBR builds one model for each target attribute separately, all the target attributes are utilized when building each model. In each boosting iteration, the base learner, the regression tree in particular, is learned by selecting the best models from all the target attributes. We also introduce a novel knowledge transfer approach. That is, the tree structure learned from one target attribute, representing a way to partition the feature space, is used to predict another target attribute. Experiments with six data sets compare MTBR to other ensemble regression methods, and prove the effectiveness of MTBR in leveraging the knowledge of multiple target attributes and improving the model accuracy. [ABSTRACT FROM AUTHOR]

Motivation Matched case–control analysis is widely used in biomedical studies to identify exposure variables associated with health conditions. The matching is used to improve the efficiency. Existing variable selection methods for matched case–control studies are challenged in high-dimensional settings where interactions among variables are also important. We describe a quite different method for high-dimensional matched case–control data, based on the potential outcome model, which is not only flexible regarding the number of matching and exposure variables but also able to detect interaction effects. Results We present Matched Forest (MF), an algorithm for variable selection in matched case–control data. The method preserves the case and control values in each instance but transforms the matched case–control data with added counterfactuals. A modified variable importance score from a supervised learner is used to detect important variables. The method is conceptually simple and can be applied with widely available software tools. Simulation studies show the effectiveness of MF in identifying important variables. MF is also applied to data from the biomedical domain and its performance is compared with alternative approaches. Availability and implementation R code for implementing MF is available at https://github.com/NooshinSh/Matched%5fForest. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

The detection of changes in the distribution of process variables is referred to as the change-point problem. Existing methods focus on detecting a single (or few) change point in a univariate (or low-dimensional) process. We consider the important high-dimensional multivariate case with multiple change points and without an assumed distribution. In this work the problem is transformed into a supervised learning problem with time as the output response and the process variables as inputs. Our focus is to identify the subset of variables that change. This important, practical scenario is analysed through a supervised learner with a variable importance measure that is used to identify the variables that change among hundreds of variables. Simulated cases are discussed in the paper to verify the proposed method. Moreover, the same data sets are compared with a multivariate exponentially weighted moving average control chart and the advantages of the supervised learner are illustrated. [ABSTRACT FROM AUTHOR]

The 2N problem is defined by the function h, which maps N to N on the set of positive integers, h(N) = (2N), where N is a 2-digit positive integer. A 2-digit positive integer is chosen at random from 10-99 and multiplied by 2. The last two digits of the resulting product are then isolated and multiplied by 2, and the process is repeated until the starting integer is obtained. For even integers, this process results in either of three outcomes, a repetitive loop without returning to the starting integer, or 4 or 20 repetitions to return to the starting integer.

A procedure for monitoring multiple discrete counts is proposed. This procedure is based on the likelihood ratio statistic for Poisson counts when input variables are measurable. This statistic is the deviance residual resulting from a generalized linear model. The likelihood ratio statistic is derived and shown to be more effective than using a C chart on the raw counts. [ABSTRACT FROM AUTHOR]

A particle count data stream is examined. The data are shown to consist of two mixed process distributions, a base Poisson count process and an outlier process. A model is developed that describes the mixed data stream. A smoothing and filtering method, using an exponentially weighted moving average (EWMA) and Poisson probabilities, is developed that separates the two process distributions into a base process and an outlier process. By separating the two distributions, statistical monitoring schemes can be applied to each. A Bernoulli EWMA is introduced for monitoring the outlier process. Average run length (ARL) evaluation is performed using Markov chain methodology, and suggestions for implementation are provided. [ABSTRACT FROM AUTHOR]

A comprehensive performance study and comparison of several adaptive statistical process control procedures is presented. These adaptive control chart procedures are modifications to standard Shewhart control charts that include changing the sampling interval, the sample size or both according to rules based on the value of the sample statistic. Adaptive control techniques are known to improve the performance of the standard Shewhart control charts. In this paper we develop a four-state adaptive sample size control chart and several variations of a three-state combined adaptive sample size and sampling interval control chart. We then compare these new schemes with the previously developed schemes, the two-state adaptive sampling interval, the two-state adaptive sample size and two-state combined adaptive sample size and sampling interval control chart, three-state adaptive sample size control chart and non-adaptive Shewhart control charts. These results show that the addition of the third and fourth states on the adaptive control chart schemes improve the control chart performance; however, the improvement is relatively modest. [ABSTRACT FROM AUTHOR]

A computationally efficient and flexible method for mapping categorical variables to numeric scores in heterogeneous (mixed-type) data is discussed. A novel scoring objective attempts to preserve the mutual information between all the variables using a nontraditional clustering approach for mixed data.

Optical dimensional metrology (ODM) technology that produces spatially dense surface measurement data is increasingly employed for quality-control purposes in discrete parts manufacturing. Such data contain a wealth of information on the surface dimensional characteristics of individual parts and on the nature of part-to-part variation. The large body of prior quality-control work on analyzing dimensional metrology data has focused heavily on fitting parametric geometric features such as circles or planes to the data for individual parts and checking whether the features are within specifications; and subsequent analysis of part-to-part variation is restricted to those specific features. In this article, we present an approach for identifying and visualizing the nature of part-to-part variation in a more general manner that is not restricted to a prespecified set of parametric features. The basis for the approach is manifold learning applied to the collective ODM data for a set of measured parts. Particular emphasis is on handling the extremely high dimensionality of ODM data. [ABSTRACT FROM AUTHOR]

Clustering is an important aspect of data mining, while clustering high-dimensional mixed-attribute data in a scalable fashion still remains a challenging problem. In this paper, we propose a tree-ensemble clustering algorithm for static datasets, CRAFTER, to tackle this problem. CRAFTER is able to handle categorical and numeric attributes simultaneously, and scales well with the dimensionality and the size of datasets. CRAFTER leverages the advantages of a tree-ensemble to handle mixed attributes and high dimensionality. The concept of the class probability estimates is utilized to identify the representative data points for clustering. Through a series of experiments on both synthetic and real datasets, we have demonstrated that CRAFTER is superior than Random Forest Clustering (RFC), an existing tree-based clustering method, in terms of both the clustering quality and the computational cost. [ABSTRACT FROM AUTHOR]

Douglas M. HAWKINS and David H. OLWELL. New York: Springer-Verlag, 1998. ISBN 0-387-98365-1. xii + 247 pp. $54.95. A book devoted to this topic is an excellent contribution. Over the [...]

A framework is presented to simulate and analyze the effect of multiple business scenarios on the adoption behavior of a group of technology products. Diffusion is viewed as an emergent phenomenon that results from the interaction of consumers. An agent-based model is used in which potential adopters of technology product are allowed to be influenced by their local interactions within the social network. Along with social influence, the effect of product features is important and we ascribe feature sensing attributes to the consumer agents along with sensitivities to social influence. The model encompasses utility theory and discrete choice models in the decision-making process for the consumers. We use expressive machine learning algorithms that can handle complex, nonlinear, and interactive effects to identify important inputs that contribute to the model and to graphically summarize their effects. We present a realistic case study that demonstrates the ability of this framework to model changes in market shares for a group of products in response to business scenarios such as new product introduction and product discontinuation under different pricing strategies. The models and other tools developed here are envisioned to be a part of a recommender system that provides insights into the effects of various business scenarios on shaping market shares of different product groups. [ABSTRACT FROM AUTHOR]

A process-oriented basis representation can be used to express multivariate quality vectors as linear combinations of fault patterns, plus a residual. Monitoring the estimated coefficients of the linear relationship is especially useful when the quality vector contains measurements of the same unit at different locations on a part or other types of profile data. To use process-oriented methods for monitoring changes in the mean of the quality vector, one needs to identify whether the effects occur only as special causes or also as common causes of variation. The calculation of process-oriented model coefficients is shown for each case. In general, the coefficients must be computed by weighted least squares, but we show that, in some circumstances, the ordinary least squares estimates are equivalent. In such cases, charting the proposed U² statistic is equivalent to charting a T² statistic computed from the process-oriented coefficients, making the process-oriented statistical process control (SPC) statistic optimal in the sense of being most powerful for detecting mean shifts in the process-oriented space. When there are fewer cause-related patterns than the number of elements in the quality vector, the process-oriented basis is incomplete. In this case, the SPC methods are applied in a subspace of the original quality vector space. For some practical examples, it is shown that: the process-oriented basis representation approach yields substantially better average run-length performance compared with the usual T² chart applied to the original quality vectors. [ABSTRACT FROM AUTHOR]

Automated visual inspection (AVI) systems these days are considered essential in the assembly of surface-mounted devices (SMDs) in the electronics industry. This industry has faced the problem of rapid introduction and retirement of SMD-based products with the consequent obsolescence of the inspection systems already in the assembly lines. The constant introduction of new products has caused AVI systems to become rapidly obsolete. The general goal of this research centers on developing self-training AVI systems for the inspection of SMD components. The premise is that these systems would be less prone to obsolescence. In this paper, the authors describe the methodology being used for automatically selecting the features to inspect new components. In particular, this paper explores the use of multi- variate stepwise discriminant analysis techniques, such as Wilks' Lambda, in order to automate the feature selection process. All of these techniques are applied to a case study of the inspection of SMD components. [ABSTRACT FROM AUTHOR]

In previous simple cases generalized linear model (GLM)-based control charts have been shown to be very effective in detecting shifts in multivariate counts when input variables are measurable. This paper studies the effectiveness of GLM-based control charts on more complicated data sets with multiple inputs and outputs whose relationships are varied. Results show that the GLM-based charts were most effective in detecting changes in the means of overdispersed counts (when compared with counts with normal dispersion). The GLM-based charts were more effective than multiple C charts in detecting changes in the means of counts when multiple complicated relationships exist. Copyright © 2004 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

There are several multivariate extensions to the venerable cumulative sum (CUSUM) chart. This work provides a comparison of the advantages and disadvantages of each, as well as performance evaluations and a description of their interrelationships. A new derivation is also provided. Extensive simulation results that include initial and steady-state conditions are presented. Geometric descriptions are used, and names are proposed based on these geometric characteristics. As several of the key steps in the development of a multivariate extension to a CUSUM also appear in the construction of a two-sided CUSUM, some approaches to a two-sided CUSUM are also summarized. Copyright © 2004 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

A model-based scheme is proposed for monitoring multiple gamma-distributed variables. The procedure is based on the deviance residual, which is a likelihood ratio statistic for detecting a mean shift when the shape parameter is assumed to be unchanged and the input and output variables are related in a certain manner. We discuss the distribution of this statistic and the proposed monitoring scheme. An example involving the advance rate of a drill is used to illustrate the implementation of the deviance residual monitoring scheme. Finally, a simulation study is performed to compare the average run length (ARL) performance of the proposed method to the standard Shewhart control chart for individuals. Copyright © 2003 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

It is commonly assumed that an assignable cause may shift a process mean persistently to an unknown but constant value. However, there are situations such that a mean change is not persistently constant but time varying, which is known as the signature of a fault. Different forms of fault signatures may arise, especially when a residuals control chart is used to monitor an autocorrelated or closed-loop controlled process. Incorporating a priori knowledge of a fault signature, fault-sensitized control charts may be developed. In this paper, we investigate two control charts of this kind: generalized likelihood ratio (GLR) and cumulative score (Cuscore) charts. A sine wave representing a bounded signal and a linear trend representing an unbounded signal are used as fault signatures for investigation purposes. Two different cases are analyzed, a known fault signature and parameter and a known fault signature but unknown parameter. Both the initial performances and steady-state performances of these charts are analyzed. The former case is somewhat artificial since it is synchronizing the control statistic and the fault signature; the latter one is more realistic since time of the occurrence of a fault is unknown. Simulation results show that GLR charts are robust to unknown signal start times and perform better than the alternatives for the cases compared. Copyright © 2003 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Extends the dynamic time warping technique to forecast process measurements using process data to define a template. Discussion on time warping in process data; Explanation on dynamic time warping; Conclusions.

In this paper, the robustness of the multivariate exponentially weighted moving average (MEWMA) control chart to non-normal data is examined. Two non-normal distributions of interest are the multivariate $t$ distribution and the multivariate gamma distribution. Recommendations for constructing MEWMA control charts when the normality assumption may be violated are provided. Copyright © 2002 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Focuses on the development of guidelines for selecting an approach in the use of control charts in industrial processes. Effect of the characteristics of industrial processes on the design and analysis of control charts; Use of a physically realistic disturbance model; Effectivity of control charts on statistical process control.

Variable sampling interval (VSI) control charts vary the sampling rate adaptively as a function of the data coming from the process in order to reduce the detection delay of process changes. Zero-time performance refers to the detection delay of a process change that is present during the onset of the chart at time zero. Steady-state performance refers to the detection delay of a process change that occurs after the chart has been operating for some time. The zero-time performance of a VSI control chart can differ considerably from the chart's steady-state performance, which is generally more important than the zero-time performance. We develop an efficient quadratic-programming algorithm for the construction and investigation of steady-state-optimal sampling policies for various VSI charts. We show that a steady-state-optimal VSI scheme is fundamentally different from the respective zero-time-optimal VSI scheme, and recommend VSI policies based on two sampling intervals for the various types of control charts considered. [ABSTRACT FROM AUTHOR]

Evaluates the plan performance of military air operations containing a number of sequential or parallel tasks. Involvement of several activities in the military air operations; Tools use in planning and scheduling air operation plans; Use of probability distribution in characterizing the task duration.

In this paper we demonstrate the use of control charts based on orthogonal contrasts for a semiconductor manufacturing process. The statistical performance of individuals control charts based on these contrasts and their exponentially weighted moving average counterparts is compared to that of the traditional approach. Contrast-based charts have superior detection capabilities than the traditional approach when targeted at specific process disturbances. Copyright © 2001 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

This paper shows that economic statistical design can provide for better statistical properties without significantly increasing optimal total costs. Cost comparisons between optimal economic statistical designs and optimal economic designs show no significant cost increases. The average run length (ARL) constraints added by economic statistical design significantly improve the statistical properties of the control chart scheme. False alarm frequency is limited while keeping good shift detection characteristics. In addition, the Multivariate Exponentially Weighted Moving Average (MEWMA) control schemes performed better from the cost standpoint than the benchmark pure statistical design—the Hotelling T2 control chart. This improvement held for unconstrained and constrained designs. Finally, cost comparisons at small values of n showed significant advantage for the MEWMA schemes. Copyright © 2001 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Presents information on a study which developed an alternative jump disturbance model. Description of the integrated moving average model; Simulation of the disturbance process; Discussion; Conclusions.