Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Machine Learning Approach to the Design of Autonomous Construction Equipment applying Data-Driven Decision Support Tool
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science and Engineering.
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Design engineers working in construction machinery industry face a lot of complexities and uncertainties while taking important decisions during the design of construction equipment. These complexities can be reduced by the implementation of a data-driven decision support tool, which can predict the behaviour of the machine in operational complexity and give some valuable insights to the design engineer. This data-driven decision support tool must be supported by a suitable machine algorithm. The focus of this thesis is to find a suitable machine algorithm, which can predict the behaviour of a machine and can later be involved in the development of such data-driven decision-support tools. In finding such a solution, evaluation of the regression performance of four supervised machine learning regression algorithms, namely SupportVector Machine Regression, Bayesian Ridge Regression, DecisionTree Regression and Random Forest Regression, is done. The evaluation was done on the data-sets personally observed/collected at the site which was extracted from the autonomous construction machine byProduct Development Research Lab (P.D.R.L). An experiment is chosen as a research methodology based on the quantitative format of the data set. The sensor data extracted from the autonomous machine in time series format, which in turn is converted to supervised data with the help of the sliding window method. The four chosen algorithms are then trained on the mentioned data-sets and are evaluated with certain performance metrics (MSE, RMSE, MAE, Training Time). Based on the rigorous data collection, experimentation and analysis, Bayesian Ridge Regressor is found to be the best compared with other algorithms in terms of all performance metrics and is chosen as the optimal algorithm to be used in the development of data-driven decision support tool meant for design engineers working in the construction industry.

Place, publisher, year, edition, pages
2019. , p. 56
Keywords [en]
Machine Learning, Regression, Time Series, Construction Equipment
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:bth-17635OAI: oai:DiVA.org:bth-17635DiVA, id: diva2:1291227
Subject / course
DV2572 Master´s Thesis in Computer Science
Educational program
DVADA Master Qualification Plan in Computer Science
Supervisors
Examiners
Available from: 2019-02-28 Created: 2019-02-22 Last updated: 2019-02-28Bibliographically approved

Open Access in DiVA

BTH2019Goteti(580 kB)241 downloads
File information
File name FULLTEXT02.pdfFile size 580 kBChecksum SHA-512
67a943af0c5f7d451cb8a6869fb484b8f824a144404423d35865a4112e650ee0d3f5f9a6ce79793af3849f199775fc235f4a736d6faba94ace8eed5a4248a7ea
Type fulltextMimetype application/pdf

By organisation
Department of Computer Science and Engineering
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 241 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 1411 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf