Experimental comparison of functional and multivariate spectral-based supervised classification methods in hyperspectral image

The aim of this article is to assess and compare several statistical methods for hyperspectral image supervised classification only using the spectral dimension. Since hyperspectral profiles may be viewed either as a random vector or a random curve, we propose to confront various multivariate discriminating procedures with functional alternatives. Eight methods representing three important statistical communities (mixture models, machine learning and functional data analysis) have been applied on three hyperspectral datasets following three protocols studying the influence of size and composition of the learning sample, with or without noised labels. Besides this comparative study, this work proposes a functional extension of multinomial logit model as well as a fast computing adaptation of the nonparametric functional discrimination. As a by-product, this work provides a useful comprehensive bibliography and also supplemental material especially oriented towards practitioners.     

Parenting and child experiences in shelter: A qualitative study exploring the effect of homelessness on the parent–child relationship

Depending on the data source, between half a million and 2.48 million children in families experience homelessness each year in the United States. Recent data suggest that approximately half of all homeless children are under the age of 6. A considerable body of quantitative research has documented the occurrence of poor outcomes associated with childhood homelessness in the domains of social–emotional development, physical and behavioral health, academic achievement, and family stability. This qualitative study presents results from 19 interviewers with formerly homeless parents reflecting upon how the experience of being homeless affected their young children and their ability to parent. Findings are contextualized within an attachment perspective. Parental reported effects included confusion, sadness, anxiety or depression, withdrawal, lack of appetite, aggression, and disregard for authority. Parents also talked about the disempowering experience of parenting while in shelter. Unexpectedly, parents of infants said their children were not affected by homelessness, and few parents identified the need for mental health services for their children. The experiences of parents with whom we spoke provide invaluable insight into what shelter staff, social service agencies, philanthropy, policymakers, and researchers can do to support and respect the parent–child relationship in families who are experiencing homelessness.     

A Staged Service Innovation Model*

Drawing from the new product development (NPD) literature, service quality literature (SERVQUAL), and empirically grounded research with 53 service innovation decision makers, we develop a staged service innovation model (SIM) for decision makers. We tested the model using empirical data from 329 firms across five industries. The empirical results show that integrating prelaunch service quality training into new service development process leads to successful service innovation. The model developed in this article can be used as a decision support tool and diagnostic model for assessing service innovation ideas, evaluating performance of ongoing service innovations, allocating resources, and improving success rate of service innovations. Decision makers can use the measures developed in this study as a checklist to identify their strengths in delivering service quality to their own customers as well as areas of improvement. This article extends service innovation research by combining NPD and service quality development into a single study and opens the door to further work that could help improve the success rate of service innovations. The model can serve as a base model for future research extensions in service innovation research. A major takeaway for the academic reader is that the SIM demonstrates the value of using the SERVQUAL literature to understand how best to provide excellent quality that results in more fully satisfied customers and, ultimately, improved service performance.     

Bayesian emulation of complex multi-output and dynamic computer models

Computer models are widely used in scientific research to study and predict the behaviour of complex systems. The run times of computer-intensive simulators are often such that it is impractical to make the thousands of model runs that are conventionally required for sensitivity analysis, uncertainty analysis or calibration. In response to this problem, highly efficient techniques have recently been developed based on a statistical meta-model (the emulator) that is built to approximate the computer model. The approach, however, is less straightforward for dynamic simulators, designed to represent time-evolving systems. Generalisations of the established methodology to allow for dynamic emulation are here proposed and contrasted. Advantages and difficulties are discussed and illustrated with an application to the Sheffield Dynamic Global Vegetation Model, developed within the UK Centre for Terrestrial Carbon Dynamics.     

What's Wrong with Risk Matrices?

Risk matrices—tables mapping "frequency" and "severity" ratings to corresponding risk priority levels—are popular in applications as diverse as terrorism risk analysis, highway construction project management, office building risk analysis, climate change risk management, and enterprise risk management (ERM). National and international standards (e.g., Military Standard 882C and AS/NZS 4360:1999) have stimulated adoption of risk matrices by many organizations and risk consultants. However, little research rigorously validates their performance in actually improving risk management decisions. This article examines some mathematical properties of risk matrices and shows that they have the following limitations. (a) Poor Resolution . Typical risk matrices can correctly and unambiguously compare only a small fraction (e.g., less than 10%) of randomly selected pairs of hazards. They can assign identical ratings to quantitatively very different risks ("range compression"). (b) Errors . Risk matrices can mistakenly assign higher qualitative ratings to quantitatively smaller risks. For risks with negatively correlated frequencies and severities, they can be "worse than useless," leading to worse-than-random decisions. (c) Suboptimal Resource Allocation . Effective allocation of resources to risk-reducing countermeasures cannot be based on the categories provided by risk matrices. (d) Ambiguous Inputs and Outputs . Categorizations of severity cannot be made objectively for uncertain consequences. Inputs to risk matrices (e.g., frequency and severity categorizations) and resulting outputs (i.e., risk ratings) require subjective interpretation, and different users may obtain opposite ratings of the same quantitative risks. These limitations suggest that risk matrices should be used with caution, and only with careful explanations of embedded judgments.     

A nonlinear optimization methodology for VLSI fixed-outline floorplanning

Floorplanning is a critical step in the physical design of VLSI circuits. The floorplanning optimization problem can be formulated as a global optimization problem minimizing wire length, with the area of each rectangular module fixed while the module’s height and width are allowed to vary subject to aspect ratio constraints. While classical floorplanning seeks to simultaneously minimize the wire length and the area of the floorplan without being constrained by a fixed outline for the floorplan, state-of-the-art technologies such as System-On-Chip require the solution of fixed-outline floorplanning. Fixing the outline of the floorplan makes the problem significantly more difficult. In this paper, we propose a two-stage nonlinear-optimization-based methodology specifically designed to perform fixed-outline floorplanning by minimizing wire length while simultaneously enforcing aspect ratio constraints on soft modules and handling a zero deadspace situation. In the first stage, a convex optimization globally minimizes an approximate measure of wire length. Using the solution of the first stage as a starting point, the second stage minimizes the wire length by sizing the modules subject to the prescribed aspect ratios, and ensuring no overlap. Computational results on standard benchmarks demonstrate that the model is competitive with other floorplanning approaches in the literature. Research supported by a Postgraduate Award, Discovery Grants 312125 and 15296, and RTI Grant 314668 from the Natural Sciences and Engineering Research Council of Canada, by an Ontario Graduate Scholarship, and by a MITACS grant.     

Facilitating Public Participation in Toxic Waste Management Through Engaging ‘The <Emphasis Type="Italic">Object</Emphasis> of Politics’

This paper uses the experience of local community involvement in the disposal of the world’s largest stockpile of toxic hexachlorobenzene waste, at Botany in Sydney, to refine insights regarding strategies for facilitating public participation in such challenging scientific and technological problems. Recent research focussed upon the politics of such issues is used to clarify a critical epistemological role for non-expert community stakeholders building upon an earlier analysis of this case study. This public input can help resolve issues that escape traditional political and/or technical control by enhancing the participatory process and facilitating further attention to the contextual dimensions of planned outcomes. These are then couched in terms of a collectively agreed set of objectives whose integrative character is more conducive to effective outcomes than the traditional, narrower focus upon technical options.     

Comparison of older adult performance during the functional-reach and limits-of-stability tests

Despite widespread use of the functional-reach (FR) and limits-of-stability (LOS) tests, comparisons of postural strategies and postural limits for these tests have not been previously reported. The purpose of this study was to compare postural strategies as determined by cross-correlation analyses of trunk and lower leg angular displacements and postural limits as assessed by maximum center-of-gravity (COG) excursions as older adults at low fall risk completed the FR and LOS tests. Fourteen older adults completed three FR and LOS trials while standing on a Balance Master force platform. Results indicated that despite relatively similar instructions to reach or lean as far as possible without losing balance or altering the base of support, their performance differed with regard to postural strategies employed and maximum COG excursions produced. These findings suggest that because of differences in task constraints, FR and LOS tests should not be used interchangeably.     

Development of a lateral mobility task to identify individuals at risk for mobility disability and functional decline

Lateral mobility is integral to many activities of daily living involving transfer from one position to another. The objective of this study was to develop and evaluate the validity and test-retest reliability of a lateral-mobility (LATMOB) task for older adults. Measurements of lateral mobility, balance, and strength and self-reported and performance-based physical functioning were obtained in 63 women and 77 men > or = 50 years of age. The LATMOB task was significantly correlated with age, knee-extensor strength, grip strength, functional reach, and one-leg-stance time. Test-retest reliability of the task was excellent. The LATMOB task was highly correlated with the car task. Balance was significantly correlated with time to get into and out of a car and performance on the LATMOB task. The LATMOB task was significantly correlated with the Short Physical Performance Battery score. The LATMOB task is valid and reliable, but additional work is needed to assess its sensitivity to change and predictive validity.     

Response distortion in adolescents who smoke: a pilot study

A wide range of data are obtained with self-report. Information obtained from persons using substances is generally reliable and valid, however, many studies show that some proportion of self-reports regarding substance use are inaccurate. This study examines self-reported response distortion in adolescents who received a brief intervention to reduce their smoking. Findings indicate that age and ethnicity of respondent may influence reported response distortion. Factors that appear to influence under- and over-reporting include social desirability and fear of repercussion. Response distortion does not appear to affect rated usefulness of the intervention, nor does intervention type appear to influence whether respondents thought the researcher wanted them to report less use. Results point to the need for further research regarding adolescents and response distortion.