University of Nevada - Reno
Predictive Modelling of Gas Concentrations in Tunnels Using Machine Learning.
Abstract
dc:description.abstractThis study introduces a machine learning methodology for predicting gas concentrationsat specific location within a tunnel model. The machine learning model is trained using gas concentration data obtained from sensors placed at diverse locations. The procedural sequence commences with the acquisition of data through an experimental protocol designed for training the machine learning model. Subsequently, the K-Nearest Neighbor (KNN) model is employed for predictive computations. The efficacy of the model is assessed through a comprehensive case study. The findings demonstrate that the proposed methodology exhibits a high level of accuracy, affirming its robust performance in predicting gas concentrations within the tunnel model.
Degree
thesis:*- Level thesis:degree_level
- Master's Degree
- Department thesis:degree_department
- Mining Engineering
- Year dc:date.issued
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Battulwar, Kartik
- Advisor dc:contributor.advisor
-
- Sattarvand, Javad Dr.
- Committee members dc:contributor.committeemember
-
- Danko, George
- Feng, Jia
Subjects
dc:subject × 3Identifiers
dc:identifier.*- Handle dc:identifier.uri
- http://hdl.handle.net/11714/10873