Factor analysis and structural equation modelling of sustainable behaviour in contaminated land remediation

Contaminated land remediation has traditionally been viewed as sustainable practice because it reduces urban sprawl and mitigates risks to human being and the environment. However, in an emerging green and sustainable remediation (GSR) movement, remediation practitioners have increasingly recognized that remediation operations have their own environmental footprint. The GSR calls for sustainable behaviour in the remediation industry, for which a series of white papers and guidance documents have been published by various government agencies and professional organizations. However, the relationship between the adoption of such sustainable behaviour and its underlying driving forces has not been studied. This study aims to contribute to sustainability science by rendering a better understanding of what drives organizational behaviour in adopting sustainable practices. Factor analysis (FA) and structural equation modelling (SEM) were used to investigate the relationship between sustainable practices and key factors driving these behaviour changes in the remediation field. A conceptual model on sustainability in the environmental remediation industry was developed on the basis of stakeholder and institutional theories. The FA classified sustainability considerations, institutional promoting and impeding forces, and stakeholder's influence. Subsequently the SEM showed that institutional promoting forces had significant positive effects on adopting sustainability measures, and institutional impeding forces had significant negative effects. Stakeholder influences were found to have only marginal direct effect on the adoption of sustainability; however, they exert significant influence on institutional promoting forces, thus rendering high total effect (i.e. direct effect plus indirect effect) on the adoption of sustainability. This study suggests that sustainable remediation represents an advanced sustainable practice, which may only be fully endorsed by both internal and external stakeholders after its regulatory, normative and cognitive components are institutionalized. © 2014 Elsevier Ltd. All rights reserved.

Factor analysis based VTS and JUD noise estimation and compensation

Model based compensation schemes are a powerful approach for noise robust speech recognition. Recently there have been a number of investigations into adaptive training, and estimating the noise models used for model adaptation. This paper examines the use of EM-based schemes for both canonical models and noise estimation, including discriminative adaptive training. One issue that arises when estimating the noise model is a mismatch between the noise estimation approximation and final model compensation scheme. This paper proposes FA-style compensation where this mismatch is eliminated, though at the expense of a sensitivity to the initial noise estimates. EM-based discriminative adaptive training is evaluated on in-car and Aurora4 tasks. FA-style compensation is then evaluated in an incremental mode on the in-car task. © 2011 IEEE.

Factor analysis based VTS discriminative adaptive training

Vector Taylor Series (VTS) model based compensation is a powerful approach for noise robust speech recognition. An important extension to this approach is VTS adaptive training (VAT), which allows canonical models to be estimated on diverse noise-degraded training data. These canonical model can be estimated using EM-based approaches, allowing simple extensions to discriminative VAT (DVAT). However to ensure a diagonal corrupted speech covariance matrix the Jacobian (loading matrix) relating the noise and clean speech is diagonalised. In this work an approach for yielding optimal diagonal loading matrices based on minimising the expected KL-divergence between the diagonal loading matrix and "correct" distributions is proposed. The performance of DVAT using the standard and optimal diagonalisation was evaluated on both in-car collected data and the Aurora4 task. © 2012 IEEE.

Healthcare human reliability analysis - By heart

As part of the investigations into a surgical incident involving the accidental retention inside a patient's venous system of a guide wire for central venous catheterisation (CVC), the Human Error Assessment and Reduction Technique (HEART) was used to examine the potential for further occurrences. It was found to be time-efficient and to yield plausible probabilities of human error, although its use in healthcare has challenges, suggesting adaptation would be beneficial.

Healthcare human reliability analysis – by HEART

This book presents the proceedings of the international conference on Contemporary Ergonomics and Human Factors 2013.

Nonparametric Bayesian sparse factor models with application to gene expression modeling

A nonparametric Bayesian extension of Factor Analysis (FA) is proposed where observed data $\mathbf{Y}$ is modeled as a linear superposition, $\mathbf{G}$, of a potentially infinite number of hidden factors, $\mathbf{X}$. The Indian Buffet Process (IBP) is used as a prior on $\mathbf{G}$ to incorporate sparsity and to allow the number of latent features to be inferred. The model's utility for modeling gene expression data is investigated using randomly generated data sets based on a known sparse connectivity matrix for E. Coli, and on three biological data sets of increasing complexity.

The adoption of sustainable remediation behaviour in the US and UK: a cross country comparison and determinant analysis.

The sustainable remediation concept, aimed at maximizing the net environmental, social, and economic benefits in contaminated site remediation, is being increasingly recognized by industry, governments, and academia. However, there is limited understanding of actual sustainable behaviour being adopted and the determinants of such sustainable behaviour. The present study identified 27 sustainable practices in remediation. An online questionnaire survey was used to rank and compare them in the US (n=112) and the UK (n=54). The study also rated ten promoting factors, nine barriers, and 17 types of stakeholders' influences. Subsequently, factor analysis and general linear models were used to determine the effects of internal characteristics (i.e. country, organizational characteristics, professional role, personal experience and belief) and external forces (i.e. promoting factors, barriers, and stakeholder influences). It was found that US and UK practitioners adopted many sustainable practices to similar extents. Both US and UK practitioners perceived the most effectively adopted sustainable practices to be reducing the risk to site workers, protecting groundwater and surface water, and reducing the risk to the local community. Comparing the two countries, we found that the US adopted innovative in-situ remediation more effectively; while the UK adopted reuse, recycling, and minimizing material usage more effectively. As for the overall determinants of sustainable remediation, the country of origin was found not to be a significant determinant. Instead, organizational policy was found to be the most important internal characteristic. It had a significant positive effect on reducing distant environmental impact, sustainable resource usage, and reducing remediation cost and time (p<0.01). Customer competitive pressure was found to be the most extensively significant external force. In comparison, perceived stakeholder influence, especially that of primary stakeholders (site owner, regulator, and primary consultant), did not appear to have as extensive a correlation with the adoption of sustainability as one would expect.

Psychometric evaluation and experimental validation of the statistics anxiety rating scale.

The Statistics Anxiety Rating Scale (STARS) was adapted into German to examine its psychometric properties (n = 400). Two validation studies (n = 66, n = 96) were conducted to examine its criterion-related validity. The psychometric properties of the questionnaire were very similar to those previously reported for the original English version in various countries and other language versions. Confirmatory factor analysis indicated 2 second-order factors: One was more closely related to anxiety and the other was more closely related to negative attitudes toward statistics. Predictive validity of the STARS was shown both in an experimental exam-like situation in the laboratory and during a real examination situation. Taken together, the findings indicate that statistics anxiety as assessed by the STARS is a useful construct that is more than just an expression of a more general disposition to anxiety.

Linear dimensionality reduction: Survey, insights, and generalizations

© 2015 John P. Cunningham and Zoubin Ghahramani. Linear dimensionality reduction methods are a cornerstone of analyzing high dimensional data, due to their simple geometric interpretations and typically attractive computational properties. These methods capture many data features of interest, such as covariance, dynamical structure, correlation between data sets, input-output relationships, and margin between data classes. Methods have been developed with a variety of names and motivations in many fields, and perhaps as a result the connections between all these methods have not been highlighted. Here we survey methods from this disparate literature as optimization programs over matrix manifolds. We discuss principal component analysis, factor analysis, linear multidimensional scaling, Fisher's linear discriminant analysis, canonical correlations analysis, maximum autocorrelation factors, slow feature analysis, sufficient dimensionality reduction, undercomplete independent component analysis, linear regression, distance metric learning, and more. This optimization framework gives insight to some rarely discussed shortcomings of well-known methods, such as the suboptimality of certain eigenvector solutions. Modern techniques for optimization over matrix manifolds enable a generic linear dimensionality reduction solver, which accepts as input data and an objective to be optimized, and returns, as output, an optimal low-dimensional projection of the data. This simple optimization framework further allows straightforward generalizations and novel variants of classical methods, which we demonstrate here by creating an orthogonal-projection canonical correlations analysis. More broadly, this survey and generic solver suggest that linear dimensionality reduction can move toward becoming a blackbox, objective-agnostic numerical technology.