MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

Linear Regression Analysis

Survival Analysis: Techniques for Censored and Truncated Data

The book reviews section generally accepts for review only those books whose content and level reflect the general editorial policy of Technometrics. Publishers are invited to send books for review to Eric R. Ziegel, Amoco Research Center, Mail Station F-l/C& P.O. Box 3011, Naperville, Illinois 60566-7011. Please include the price of the book. The opinions expressed in this section are those of the reviewers and do not necessarily reflect those of the editorial staff or the sponsoring societies. Listed prices were provided by the publisher when the books were received by Technometrics and may not be current.

Adventures in Stochastic Processes

Fault diagnosis and prognosis are some of the most crucial functionalities in complex and safety-critical engineering systems, and particularly fault diagnosis, has been a subject of intensive research in the past four decades. Such capabilities allow for detection and isolation of early developing faults as well as prediction of fault propagation, which can allow for preventive maintenance, or even serve as a countermeasure to the possibility of catastrophic incidence as a result of a failure. Following a short preliminary overview and definitions, this article provides a survey of recent research on fault prognosis. Additionally, we report on some of the significant application domains where prognosis techniques are employed. Finally, some potential directions for future research are outlined.

Failure Prognosis and Applications—A Survey of Recent Literature

B-splines are commonly used to fit complicated functions in Computer Aided Design and signal processing because they are simple yet flexible However, how to place the knots appropriately in B-spline curve fitting remains a difficult problems This article discusses a two-stage knot placement method to place knots adapting to the curvature structures of unknown function In the first stage, a subset of basis functions is selected from the pre-specified multi-resolution basis set using a statistical variable selection method: Lasso In the second stage, a vector space that is spanned by the selected basis functions is constructed and a concise knot vector is identified that is sufficient to characterize the vector space to fit the unknown function The effectiveness of the proposed method is demonstrated using numerical studies on multiple representative functions

Adaptive B-spline knot selection using multi-resolution basis set

Remaining useful life prediction plays an important role in ensuring the safety, availability, and efficiency of various engineering systems. In this paper, we propose a flexible Bayesian multiple-phase modeling approach to characterize degradation signals for prognosis. The priors are specified with a novel stochastic process and the multiple-phase model is formulated to a novel state-space model to facilitate online monitoring and prediction. A particle filtering algorithm with stratified sampling and partial Gibbs resample-move strategy is developed for online model updating and residual life prediction. The advantages of the proposed method are demonstrated through extensive numerical studies and real case studies.

Multiple-Phase Modeling of Degradation Signal for Condition Monitoring and Remaining Useful Life Prediction

Event logs, commonly available in modern mechatronic systems, contain rich information on the operating status and working conditions of the system. This article proposes a method to build a statistical model using event logs for system failure prediction. To achieve the best prediction performance, prescreening and statistical variable selection are adopted to select the best set of predictor events, coded as covariates in the statistical model. In-depth discussion of the prediction power of the model in terms of false alarm and misdetection probability is presented. Using a real-world example, the effectiveness of the proposed method is further confirmed.

Event log modeling and analysis for system failure prediction

This article develops a series of statistical approaches that can be used to infer size distribution, volume number density, and volume fraction of three-dimensional (3D) ellipsoidal particles based on two-dimensional (2D) cross-sectional images. Specifically, this article first establishes an explicit linkage between the size of the ellipsoidal particles and the size of cross-sectional elliptical contours. Then an efficient Quasi-Monte Carlo EM algorithm is developed to overcome the challenge of 3D size distribution estimation based on the established complex linkage. The relationship between the 3D and 2D particle number densities is also identified to estimate the volume number density and volume fraction. The effectiveness of the proposed method is demonstrated through simulation and case studies.

Inferring 3D Ellipsoids Based on Cross-Sectional Images With Applications to Porosity Control of Additive Manufacturing

Quantile regression as an alternative to conditional mean regression (i.e., least-square regression) is widely used in many areas. It can be used to study the covariate effects on the entire response distribution by fitting quantile regression models at multiple different quantiles or even fitting the entire regression quantile process. However, estimating the regression quantile process is inherently difficult because the induced conditional quantile function needs to be monotone at all covariate values. In this article, we proposed a regression quantile process estimation method based on monotone B-splines. The proposed method can easily ensure the validity of the regression quantile process and offers a concise framework for variable selection and adaptive complexity control. We thoroughly investigated the properties of the proposed procedure, both theoretically and numerically. We also used a case study on wind power generation to demonstrate its use and effectiveness in real problems. Supplem...

Yuan Yuan

Papers

Adaptive B-spline knot selection using multi-resolution basis set

Multiple-Phase Modeling of Degradation Signal for Condition Monitoring and Remaining Useful Life Prediction

Event log modeling and analysis for system failure prediction

Inferring 3D Ellipsoids Based on Cross-Sectional Images With Applications to Porosity Control of Additive Manufacturing

Modeling Regression Quantile Process Using Monotone B-Splines