Please use this identifier to cite or link to this item: http://ir.juit.ac.in:8080/jspui/jspui/handle/123456789/6064
Full metadata record
DC FieldValueLanguage
dc.contributor.authorAwasthi, Shubham-
dc.contributor.authorBabbar, Sakshi [Guided by]-
dc.date.accessioned2022-09-05T05:44:38Z-
dc.date.available2022-09-05T05:44:38Z-
dc.date.issued2015-
dc.identifier.urihttp://ir.juit.ac.in:8080/jspui/jspui/handle/123456789/6064-
dc.description.abstractThis project aims at predicting real life applications and stresses the importance of data mining in real world. Data mining is an important part of knowledge discovery process that we can analyze an enormous set of data and get hidden and useful knowledge. Keeping the fundamental value of data mining in mind this project concentrates on 2 real world applications. Firstly this project can be used in prediction of cricket world cup 2015 using Bayesian Networks technique. Secondly this project can be used in predicting the quality of river water sample from the given data sets. For the first part using Bayesian model we forecast winners of groupstages, quarterfinals, semifinals and final. Our model predicts Australia to be the new cricket champion of the world. To prove strength of our approach we show predictive results on past world cup 2011. Later in this project we make use of the classification technique of data mining to accomplish predictive task in water quality. Classification technique of data mining is basically the task of assigning objects to one of several predefined categories, is a pervasive problem that encompasses many diverse applications. In this project, we have used naïveBayes classification technique for prediction of water quality in the river Yamuna. To assess the quality of water we have considered 13 parameters some of them are dissolved oxygen (DO), biochemical oxygen demand (BOD) ,pH value etc, that are necessary in order to correctly label the pollution level in the given water sample. Lastly we compare our results with another known classifier decision tree which proves that naïve bayes produces better results than it. In addition to this we have also performed the descriptive task using Association Rule Networks that gives us a clear idea of the role of a specific feature in contributing to a particular class.en_US
dc.language.isoenen_US
dc.publisherJaypee University of Information Technology, Solan, H.P.en_US
dc.subjectData miningen_US
dc.subjectBayesian modelen_US
dc.subjectBiochemical oxygen demanden_US
dc.subjectDissolved oxygenen_US
dc.titlePredictive and Descriptive Analysis using Bayesian Networksen_US
dc.typeProject Reporten_US
Appears in Collections:B.Tech. Project Reports

Files in This Item:
File Description SizeFormat 
Predictive and Descriptive Analysis using Bayesian Networks.pdf2.75 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.