COPELABS DSpace Repository

An MBR Classification Model for Pervasive Wireless Systems

Show simple item record

dc.contributor.author Dattagupta, Samrat
dc.contributor.author Sofia, Rute C.
dc.contributor.author Mendes, Paulo
dc.date.accessioned 2018-07-21T00:03:44Z
dc.date.available 2018-07-21T00:03:44Z
dc.date.issued 2018-05
dc.identifier.uri http://hdl.handle.net/20.500.11933/767
dc.description.abstract This MBR classification model is intended to evaluate the performance of MBR against other approaches in the context of pervasive wireless networks, where smart data is collected from multiple sources. Validation of the model is provided based on a realistic data set. In the analysis carried out, the following models were used for comparison: Decision Tree (DT) with 3 branches and depth of 4; Neural Network (NN) using Multi-layer perceptron architecture and 3 hidden units; Logistic Regression (LR) using a Probit Link function; Memory Based Reasoning (MBR) with 16 nearest neighbors.
dc.publisher COPELABS, University Lusofona en_US
dc.title An MBR Classification Model for Pervasive Wireless Systems en_US
dc.type Other en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account