Show simple item record

dc.contributor.advisorWhite, Carl
dc.contributor.authorEmanuel, William Gilbert
dc.contributor.departmentElectrical and Computer Engineeringen_US
dc.contributor.programDoctor of Engineeringen_US
dc.date.accessioned2018-04-27T15:04:17Z
dc.date.available2018-04-27T15:04:17Z
dc.date.issued2015
dc.description.abstractA Decision Support System (DSS) with a weighting system for individual components to interpret the sports turf playing condition infrastructure (TPCI) is currently not available to sports turf professionals [1]. To fill this gap, this study developed a DSS with a weighting system for individual components of the Sports Turf Managers Association's (STMA) Playing Conditions Index (PCI). Applying objective computer applications in statistics, data mining and machine learning technologies resulted in the valid classification of the STMA PCI variables using computer algorithms: Decision Tree, Bayesian, Sequential Minimal Optimization (SMO), Regression, and Neural Networks. Experts in this field also recognized the need to focus on the key parameters and reduce the number of parameters currently used in the testing of turf conditions. Therefore, this research further led to the development of a gold standard analytical model to refine the current number of parameters by removing the least significant variables and applied a systems engineering methodology to the STMA PCI data. Data collection and sports turf testing are critical components in the overall maintenance and operation of sports facilities. Sports surfaces are tested for a variety of reasons and the purpose of testing sports surfaces can be split into broad categories: 1) determine compliance with minimum standards, 2) assessment of surface quality across different tiers of sport, 3) inform management, operations and maintenance intervention, 4) for research into surface design, function or injury risk [1]. An additional purpose may be 5) to identify below average turf playing conditions in communities and schools, i.e. environmental disparities. Urban built environments appear to have limited access to turf sports facilities because of disparities found in their turf playing conditions. Such built environment disparities seem to be more evident in urban environments compared to other affluent communities and schools [2]. A first step in addressing these disparities is to enable stakeholders in sports facility management, planning, operations and maintenance to better understand their TPCI. Therefore, a gold standard analytical model which objectively and accurately assesses turf playing conditions is one way to classify built environment disparities.
dc.genredissertations
dc.identifierdoi:10.13016/M2D50G097
dc.identifier.urihttp://hdl.handle.net/11603/9927
dc.language.isoen
dc.relation.isAvailableAtMorgan State University
dc.rightsThis item is made available by Morgan State University for personal, educational, and research purposes in accordance with Title 17 of the U.S. Copyright Law. Other uses may require permission from the copyright owner.
dc.subjectData miningen_US
dc.subjectEnvironmental justiceen_US
dc.subjectCity planningen_US
dc.subjectEnvironmental justiceen_US
dc.subjectDecision Support Systems (DSS)en_US
dc.subjectNeural networks (Computer science)en_US
dc.subjectComputer engineeringen_US
dc.titleA Decision Support System (DSS) Assessment Model For Turf Playing Condition Infrastructure (TPCI) As An Early Indicator Of Compliance With Performance Quality Standards
dc.typeText


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record