Publication Date

2016

Document Type

Dissertation/Thesis

First Advisor

Gupta, Abhijit

Degree Name

M.S. (Master of Science)

Department

Department of Mechanical Engineering

LCSH

Big data||Automobiles--Electronic equipment||Automobiles--Performance

Abstract

Many companies have invested a lot over the past decade just to collect the data and store them in a cloud. However collection of such large amount of data will be justified only when there are some useful insights drawn from them. There is a lot of data collected from vehicles. The volume, velocity, variability and complexity of the data from various sensors are massive. Access to this type of data is only going to increase with time, so industries need appropriate methods to transform this raw data into insights and knowledge. Extraction of insights which were previously unknown or potentially useful patterns or knowledge from this kind of these massive amounts of data can only be achieved by using Big Data analytics. Conventional software cannot handle the robustness of these, so modern tools such as Hadoop and Knime were used in this thesis to analyze the data. Raw high resolution data was used and a model was developed to understand vehicle/customer behaviors and then compared and contrasted. This thesis involves found a proper method for identifying and calculating the principal attributes that accurately and efficiently characterize a vehicle's operation. Predicting the power of new vehicles and finding the similarities between new vehicles and old vehicles was the main goal of this thesis.

Comments

Advisors: Abhijit Gupta.||Committee members: Pradip Majumdar; Ji-Chul Ryu.||Includes bibliographical references.||Includes illustrations.

Extent

v, 20 pages

Language

eng

Publisher

Northern Illinois University

Rights Statement

In Copyright

Rights Statement 2

NIU theses are protected by copyright. They may be viewed from Huskie Commons for any purpose, but reproduction or distribution in any format is prohibited without the written permission of the authors.

Media Type

Text

Share

COinS