Inference in Credal Networks Through Integer Programming

A credal network associates a directed acyclic graph with a collection of sets of probability measures; it offers a compact representation for sets of multivariate distributions. In this paper we present a new algorithm for inference in credal networks based on an integer programming reformulation. We are concerned with computation of lower/upper probabilities for a variable in a given credal network. Experiments reported in this paper indicate that this new algorithm has better performance than existing ones for some important classes of networks.

Fault Diagnosis in Internal Combustion Engines Using Nonlinear Multivariate Statistics

This paper presents a statistical-based fault diagnosis scheme for application to internal combustion engines. The scheme relies on an identified model that describes the relationships between a set of recorded engine variables using principal component analysis (PCA). Since combustion cycles are complex in nature and produce nonlinear relationships between the recorded engine variables, the paper proposes the use of nonlinear PCA (NLPCA). The paper further justifies the use of NLPCA by comparing the model accuracy of the NLPCA model with that of a linear PCA model. A new nonlinear variable reconstruction algorithm and bivariate scatter plots are proposed for fault isolation, following the application of NLPCA. The proposed technique allows the diagnosis of different fault types under steady-state operating conditions. More precisely, nonlinear variable reconstruction can remove the fault signature from the recorded engine data, which allows the identification and isolation of the root cause of abnormal engine behaviour. The paper shows that this can lead to (i) an enhanced identification of potential root causes of abnormal events and (ii) the masking of faulty sensor readings. The effectiveness of the enhanced NLPCA based monitoring scheme is illustrated by its application to a sensor fault and a process fault. The sensor fault relates to a drift in the fuel flow reading, whilst the process fault relates to a partial blockage of the intercooler. These faults are introduced to a Volkswagen TDI 1.9 Litre diesel engine mounted on an experimental engine test bench facility.

Molecular Distributions in the Inner Regions of Protostellar Disks

The distributions of molecules in the inner regions of a protostellar disk are presented. These were calculated using an uncoupled chemical/dynamical model, with a numerical integration of the vertical disk structure. A comparison between models with and without the effects of X-ray ionisation is made, and molecules are identified which are good tracers of the ionisation level in this part of the disk, notably CN and C_2H. In the region considered in this paper (r

What motion distributions yield global transparency and spatial segmentation?

We have examined the ability of observers to parse bimodal local-motion distributions into two global motion surfaces, either overlapping (yielding transparent motion) or spatially segregated (yielding a motion boundary). The stimuli were random dot kinematograms in which the direction of motion of each dot was drawn from one of two rectangular probability distributions. A wide range of direction distribution widths and separations was tested. The ability to discriminate the direction of motion of one of the two motion surfaces from the direction of a comparison stimulus was used as an objective test of the perception of two discrete surfaces. Performance for both transparent and spatially segregated motion was remarkably good, being only slightly inferior to that achieved with a single global motion surface. Performance was consistently better for segregated motion than for transparency. Whereas transparent motion was only perceived with direction distributions which were separated by a significant gap, segregated motion could be seen with abutting or even partially overlapping direction distributions. For transparency, the critical gap increased with the range of directions in the distribution. This result does not support models in which transparency depends on detection of a minimum size of gap defining a bimodal direction distribution. We suggest, instead, that the operations which detect bimodality are scaled (in the direction domain) with the overall range of distributions. This yields a flexible, adaptive system that determines whether a gap in the direction distribution serves as a segmentation cue or is smoothed as part of a unitary computation of global motion.

Dynamic Multivariate Statistical Process Control using Subspace Identification

This paper points out a serious flaw in dynamic multivariate statistical process control (MSPC). The principal component analysis of a linear time series model that is employed to capture auto- and cross-correlation in recorded data may produce a considerable number of variables to be analysed. To give a dynamic representation of the data (based on variable correlation) and circumvent the production of a large time-series structure, a linear state space model is used here instead. The paper demonstrates that incorporating a state space model, the number of variables to be analysed dynamically can be considerably reduced, compared to conventional dynamic MSPC techniques.

Statistical Monitoring of Dynamic Multivariate Processes: Part I: Modeling Auto- and Cross-Correlation

The work in this paper is of particular significance since it considers the problem of modelling cross- and auto-correlation in statistical process monitoring. The presence of both types of correlation can lead to fault insensitivity or false alarms, although in published literature to date, only autocorrelation has been broadly considered. The proposed method, which uses a Kalman innovation model, effectively removes both correlations. The paper (and Part 2 [2]) has emerged from work supported by EPSRC grant GR/S84354/01 and is of direct relevance to problems in several application areas including chemical, electrical, and mechanical process monitoring.

Statistical Monitoring of Dynamic Multivariate Processes: Part II: Identifying Fault Magnitude and Signature

This paper builds on work presented in the first paper, Part 1 [1] and is of equal significance. The paper proposes a novel compensation method to preserve the integrity of step-fault signatures prevalent in various processes that can be masked during the removal of both auto- and cross correlation. Using industrial data, the paper demonstrates the benefit of the proposed method, which is applicable to chemical, electrical, and mechanical process monitoring. This paper, (and Part 1 [1]), has led to further work supported by EPSRC grant GR/S84354/01 involving kernel PCA methods.

Angular distributions of electrons in photoionization of 3s subshell of atomic chlorine

R-matrix calculated photoelectron angular distribution asymmetry parameters, beta for Cl+ 3s3p(5) P-3(o) and 3s(2)3p(3) (D-2(o))3d P-1(o) final ionic states in photoionization of the ground state of atomic Cl are presented in the photon energy range from threshold to 80 eV. The results, characterized by prominent autoionization structures which are sensitive to multielectron correlations, are compared with those recently measured by Whitfield et al (Whitfield S B, Kehoe K, Krause M 0 and Caldwell C D 2000 Phys. Rev. Lett. 84 4818). Contrary to experiment and previous theoretical calculations, our detailed CIV3 structure calculation (Deb N C, Crothers D S F, Felfli Z and Msezane A Z 2002 J. Phys. B: At. Mol. Opt. Phys. submitted) has identified the lowest P-1(o) level of Cl+ as 3S(2)3p(3)(D-2(o))3d P-1(o) rather than 3s3p(5) P-1(o). The implications and consequences of the measured data for the 3s P-1(o) level are also discussed in the context of our calculated energies for Cl+ and beta for 3d P-1(o).

The effects of dispersal mode on the spatial distribution patterns of intertidal molluscs.

1. As many species of marine benthic invertebrates have a limited capacity for movement as adults, dispersal mode is often considered as a determinant of geographical ranges, genetic structure and evolutionary history. Species that reproduce without a larval stage can only disperse by floating or rafting. It is proposed that the colonization processes associated with such direct developing species result in spatial distributions that show relatively greater fine scale patchiness than the distributions of species with a larval dispersal stage. This hypothesis was tested by collecting molluscs at different spatial scales in the Isle of Man. 2. Spatial distribution patterns supported the predictions based on dispersal mode. Estimated variance components for species with larval dispersal suggested that the majority of the spatial variation was associated with variation between shores. In comparison, there was relatively more variability within shores for abundance counts of species with direct development. 3. Multivariate analyses reflected the univariate results. An assemblage of direct developers provided a better discrimination between sites (100 m separation) but the group of species with larval dispersal gave a clearer separation of shores (separated by several km). 4. The fine scale spatial structure of direct developing species was reflected in higher average species diversity within quadrats. Species richness also reflected dispersal mode, with a higher fraction of the regional species pool present for direct developers in comparison to species with larval dispersal. This may reflect the improved local persistence of taxa that avoid the larval dispersal stage.

Multivariate prediction of clarified butter composition using Raman spectroscopy

Raman spectroscopy has been used to predict the abundance of the FA in clarified butterfat that was obtained from dairy cows fed a range of levels of rapeseed oil in their diet. Partial least squares regression of the Raman spectra against FA compositions obtained by GC showed good prediction for the five major (abundance >5%) FA with R-2=0.74-0.92 and a root mean SE of prediction (RMSEP) that was 5-7% of the mean. In general, the prediction accuracy fell with decreasing abundance in the sample, but the RMSEP was 1.25%. The Raman method has the best prediction ability for unsaturated FA (R-2=0.85-0.92), and in particular trans unsaturated FA (best-predicted FA was 18:1 tDelta9). This enhancement was attributed to the isolation of the unsaturated modes from the saturated modes and the significantly higher spectral response of unsaturated bonds compared with saturated bonds. Raman spectra of the melted butter samples could also be used to predict bulk parameters calculated from standard analyzes, such as iodine value (R-2=0.80) and solid fat content at low temperature (R-2=0.87). For solid fat contents determined at higher temperatures, the prediction ability was significantly reduced (R-2=0.42), and this decrease in performance was attributed to the smaller range of values in solid fat content at the higher temperatures. Finally, although the prediction errors for the abundances of each of the FA in a given sample are much larger with Raman than with full GC analysis, the accuracy is acceptably high for quality control applications. This, combined with the fact that Raman spectra can be obtained with no sample preparation and with 60-s data collection times, means that high-throughput, on-line Raman analysis of butter samples should be possible.

Spatially Correlated Multiple-Ananna Channel Capacity Distributions

In this paper, we investigate the capacity of multiple-input multiple-output (MIMO) wireless communication systems over spatially correlated Rayleigh distributed flat fading channels with complex Gaussian additive noise. Specifically, we derive the probability density function of the mutual information between transmitted and received complex signals of MIMO systems. Using this density we derive the closed-form ergodic capacity (mean), delay-limited capacity, capacity variance and outage capacity formulas for spatially correlated channels and then evaluate these formulas numerically. Numerical results show how the channel correlation degrades the capacity of MIMO communication systems. We also show that the density of mutual information of correlated/uncorrelated MIMO systems can be approximated by a Gaussian density with derived mean and variance, even for a finite number of inputs and outputs.