Andere Kunden interessierten sich auch für
![HIV Status Predictive Modeling Using Data Mining Technology]( "HIV Status Predictive Modeling Using Data Mining Technology")
HIV Status Predictive Modeling Using Data Mining Technology44,99 €![Predicting Nutritional Status of Under 5 Children Using Data Mining]( "Predicting Nutritional Status of Under 5 Children Using Data Mining")
Predicting Nutritional Status of Under 5 Children Using Data Mining36,99 €![Predictive Software Measures Based on Formal Z Specifications]( "Predictive Software Measures Based on Formal Z Specifications")
Predictive Software Measures Based on Formal Z Specifications32,99 €![Towards predictive models for e-learning]( "Towards predictive models for e-learning")
Towards predictive models for e-learning30,99 €![Document analysis by means of data mining techniques]( "Document analysis by means of data mining techniques")
Document analysis by means of data mining techniques40,99 €![DATA MINING METHODOLOGY DEVELOPMENT]( "DATA MINING METHODOLOGY DEVELOPMENT")
DATA MINING METHODOLOGY DEVELOPMENT32,99 €![Application of Data Mining to Identify Patterns in VCT Dataset]( "Application of Data Mining to Identify Patterns in VCT Dataset")
Application of Data Mining to Identify Patterns in VCT Dataset23,99 €
Testing for HIV is the key entry point to HIV prevention, treatment, and care and support services. To this end, the objective of this study is to build a predictive modeling for HIV testing and identify its determinants for adults (age14) in Ethiopia. However, traditional statistical methods are not enough to discover a new hidden pattern from these huge amounts of HIV testing data generated by Ethiopian DHS which are too complex and voluminous. Hence, data mining techniques can greatly benefit to analyze these huge data set collected over time. CRISP-DM methodology was used to predict the model for HIV testing. Decision trees (random tree and J48), artificial neural network and logistic regression of predictive models were able to predict whether an individual was being tested or not for HIV given that the selected attributes as an input with an accuracy of 96%, 79%, 78% and 74% respectively. This book, therefore, would be helpful for both health programs and especially for researchers can contribute on how the application of data mining was helpful on predicting HIV testing through different algorithms with efficient prediction power than the traditional statistical methods.