Exploratory Testing of an Artificial Neural Network Classification for Enhancement of the Social Vulnerability Index

Hile, Ryan; Cova, Thomas J.

doi:10.3390/ijgi4041774

Cited by 8 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convergent validation assesses the level of agreement among alternative models measuring the same construct (O'Leary-Kelly and Vokurka 1998;Adcock 2001). Social vulnerability studies have applied statistical and geospatial methods to demonstrate similarity between a new and a widely-accepted model (Cutter et al 2013;Holand and Lujala 2013;Hile and Cova 2015). The prevailing models in the US are the Social Vulnerability Index (SoVI ® ) created at the University of South Carolina (Cutter, Boruff, and Shirley 2003), and the identically named Social Vulnerability Index (SVI) developed at the US Centers for Disease Control (Flanagan et al 2011).…”

Section: Index Validationmentioning

confidence: 99%

How Valid Are Social Vulnerability Models?

Rufat

Tate

Emrich

et al. 2019

Annals of the American Association of Geographers

131

136

View full text Add to dashboard Cite

Social vulnerability models are becoming increasingly important for hazard mitigation and recovery planning, but it remains unclear how well they explain disaster outcomes. Most studies using indicators and indices employ them to either describe vulnerability patterns or compare newly devised measures to existing ones. The focus of this article is construct validation, in which we investigate the empirical validity of a range of models of social vulnerability using outcomes from Hurricane Sandy. Using spatial regression, relative measures of assistance applicants, affected renters, housing damage, and property loss were regressed on four social vulnerability models and their constituent pillars while controlling for flood exposure. The indices best explained housing assistance applicants, while they poorly explained property loss. At the pillar level, themes related to access and functional needs, age, transportation, and housing were the most explanatory. Overall, social vulnerability models with weighted and profile configurations demonstrated higher construct validity than the prevailing social vulnerability indices. The findings highlight the need to expand the number and breadth of empirical validation studies to better understand relationships among social vulnerability models and disaster outcomes.

show abstract

Section: Index Validationmentioning

confidence: 99%

How Valid Are Social Vulnerability Models?

Rufat

Tate

Emrich

et al. 2019

Annals of the American Association of Geographers

131

136

View full text Add to dashboard Cite

show abstract

“…The SoVI is a place-specific assessment of the vulnerability to personal and economic loss of a population because of hazards (Cutter was selected from the American Community Survey (ACS) data for Salt Lake County over the period of 2008-2012 on the basis of the work of Hile and Cova (2015). These variables represent broad characteristics of social vulnerability presented by Cutter et al (2003) and relate to the social-ecological state of the population.…”

Section: Social Vulnerabilitymentioning

confidence: 99%

Vulnerability Assessment to Support Integrated Water Resources Management of Metropolitan Water Supply Systems

Goharian

Burian

Lillywhite³

et al. 2017

J. Water Resour. Plann. Manage.

Self Cite

View full text Add to dashboard Cite

The combined actions of natural and human factors change the timing and availability of water resources and, correspondingly, water demand in metropolitan areas. This leads to an imbalance between supply and demand and, thus, an increase in the vulnerability of water supply systems. Accordingly, methods for systematic analysis and multifactor assessment are needed to estimate the vulnerability of individual components in an integrated water supply system. This paper introduces a new approach to comprehensively assess vulnerability by integrating water resource system characteristics with factors representing exposure, sensitivity, severity, potential severity, social vulnerability, and adaptive capacity. These factors provide a way to consider broader system elements beyond the traditional vulnerability evaluation methods solely on the basis of the magnitude of failure (i.e., severity). In this way, the new vulnerability index gives a more detailed assessment with the potential to recognize critical conditions and components in an integrated system. The effectiveness and advantages of the proposed approach are checked using an investigation of the water supply system of Salt Lake City (SLC), Utah. First, an integrated water resource model was developed using a system simulation software to allocate water from different sources in SLC among designated demand points. The model contains individual simulation modules with representative interconnections among the natural hydroclimate system, built water infrastructure, and institutional decision making. The results of the analysis illustrate that basing vulnerability on a sole factor may lead to insufficient understanding and, hence, inefficient management of the system. For example, ranking of different water sources on the basis of the traditional vulnerability index (i.e., severity) in SLC is not consistent with the ranking on the basis of the proposed integrated vulnerability index. Therefore, during a failure event in the system, such as a water shortage, incomplete understanding of the system's performance may lead to incorrect decisions by managers. The new vulnerability index and assessment approach was able to identify the most vulnerable water sources in the SLC integrated water supply system. In conclusion, use of a more comprehensive approach to simulate the system behavior and estimate vulnerability provides more guidance for decision makers to detect vulnerable components of the system and ameliorate decision making.

show abstract

“…The ANNs can be applied to many fields that involve problems of prediction, classification or control [19]- [23]. In the course of decades of development, a number of scholars and researchers have applied ANNs to various fields, including technology, medicine, economics, and even social sciences, and many of them have achieved remarkable results [24]- [29].…”

Section: Introductionmentioning

confidence: 99%

On Modified Multi-Output Chebyshev-Polynomial Feed-Forward Neural Network for Pattern Classification of Wine Regions

Jin

Huang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Wine, an alcoholic beverage made from fermented grapes, has become an increasingly popular drink. However, wine regions may directly affect the quality and taste of the wine, and misjudgment of the wine regions leads to confusion for dealers and consumers in choosing wine types. In recent decades, different methods in machine learning have been presented and investigated the pattern classification. In this paper, based on the existing results, a modified multi-output Chebyshev-polynomial feed-forward neural network (MOCPFFNN) is presented, analyzed, and applied to the pattern classification of wines regions. According to the orthogonal polynomial theory, the activation functions of the MOCPFFNN are improved to some Chebyshev polynomials. In addition, to have a lower computational complexity, the presented neural network model is automatically determined by the eight-fold cross validation (8FCV) algorithm and the weight direct determination (WDD) algorithm. Finally, comparisons are made among the presented model and other classical methods, e.g., feed-forward back propagation (FFBP), layer recurrent neural network (LRNN), and nonlinear auto regressive with exogenous inputs (NARX), K-nearest neighbors (KNN), random forest, which confirm that the modified MOCPFFNN has the best approximation and generalization performance in the pattern classification of wine regions, with the accuracy rates of the training set and test set reaching 99.17% and 94.83%, respectively. Moreover, the variance of the accuracy of the presented MOCPFFNN method in the experiments is 0, which illustrates its high robustness in pattern classification. INDEX TERMS Eight fold cross validation (8FCV), multi-output Chebyshev-polynomial feed-forward neural network (MOCPFFNN), weight direct determination (WDD), wine region.

show abstract

Exploratory Testing of an Artificial Neural Network Classification for Enhancement of the Social Vulnerability Index

Cited by 8 publications

References 22 publications

How Valid Are Social Vulnerability Models?

How Valid Are Social Vulnerability Models?

Vulnerability Assessment to Support Integrated Water Resources Management of Metropolitan Water Supply Systems

On Modified Multi-Output Chebyshev-Polynomial Feed-Forward Neural Network for Pattern Classification of Wine Regions

Contact Info

Product

Resources

About