Learning Decision List from Distributed Data Sources

Learning Decision List from Distributed Data Sources

Bibliographic Details
Main Author: Charllo, Bala Vignesh
Language:English
Published: University of Cincinnati / OhioLINK 2018
Subjects:
Computer Science
Learning Decision List
Distributed Data Mining
Learning by Negotiations
Online Access:http://rave.ohiolink.edu/etdc/view?acc_num=ucin154358126815593
id ndltd-OhioLink-oai-etd.ohiolink.edu-ucin154358126815593
record_format oai_dc
spelling ndltd-OhioLink-oai-etd.ohiolink.edu-ucin1543581268155932021-08-03T07:09:05Z Learning Decision List from Distributed Data Sources Charllo, Bala Vignesh Computer Science Learning Decision List Distributed Data Mining Learning by Negotiations This work offers a simple and robust decision list learning algorithm for a distributed data environment. The standard way of building a decision list in a distributed environment is by aggregating the data which can be computationally complex, communication expensive and involves high infrastructure costs. In this work, a simple communication will be established between distributed locations and the central negotiator. The distributed locations communicate only the model and performance information and never share the raw data between two locations or to the central negotiator. The negotiation process ensures that all the rules in the decision listperform to the maximum by adjusting the boundary walls of decision rules in all possible combinations. This approach allows the model to predict an unknown observation(or instance) by the rule with the highest rank in an ordered decision list which increases the prediction accuracies. This work is a novel and simple approach for decision list generation in a distributed environment with similar accuracies compared to the decision list built using standard centralized approach and this approach is validated using various of datasets. 2018 English text University of Cincinnati / OhioLINK http://rave.ohiolink.edu/etdc/view?acc_num=ucin154358126815593 http://rave.ohiolink.edu/etdc/view?acc_num=ucin154358126815593 unrestricted This thesis or dissertation is protected by copyright: all rights reserved. It may not be copied or redistributed beyond the terms of applicable copyright laws.
collection NDLTD
language English
sources NDLTD
topic Computer Science
Learning Decision List
Distributed Data Mining
Learning by Negotiations
spellingShingle Computer Science
Learning Decision List
Distributed Data Mining
Learning by Negotiations
Charllo, Bala Vignesh
Learning Decision List from Distributed Data Sources
author Charllo, Bala Vignesh
author_facet Charllo, Bala Vignesh
author_sort Charllo, Bala Vignesh
title Learning Decision List from Distributed Data Sources
title_short Learning Decision List from Distributed Data Sources
title_full Learning Decision List from Distributed Data Sources
title_fullStr Learning Decision List from Distributed Data Sources
title_full_unstemmed Learning Decision List from Distributed Data Sources
title_sort learning decision list from distributed data sources
publisher University of Cincinnati / OhioLINK
publishDate 2018
url http://rave.ohiolink.edu/etdc/view?acc_num=ucin154358126815593
work_keys_str_mv AT charllobalavignesh learningdecisionlistfromdistributeddatasources
_version_ 1719455025560813568

Similar Items