University of Twente Student Theses
Amplifying the Analyst: Machine Learning Approaches for Buried Utility Characterization
Versloot, C.W.A. (2019) Amplifying the Analyst: Machine Learning Approaches for Buried Utility Characterization.
PDF
3MB |
Abstract: | The Netherlands has a complex underground infrastructure comprising various types of cables and pipelines. Given inadequate registration procedures from the past, large deviations occur between the estimated and actual positions of such utilities. Annually, this results in many utility strikes during excavation work. By consequence, a business model has emerged for utility mapping companies that identify the actual positions of cables and pipelines for their customers. The analyst's job, which is essentially a classification problem with respect to utility material type, is however repetitive and labor-intensive. Fortunately, today, human intellect can be amplified by machines through Machine Learning. In this work, three classes of Convolutional Neural Networks are designed and trained for this purpose harnessing Ground Penetrating Radar data, with promising results. It subsequently presents a prototypical web application that embeds the models, allowing them to be used in practice. Early validation activities confirm its business value. |
Item Type: | Essay (Master) |
Clients: | TerraCarta B.V., Hoogeveen, the Netherlands |
Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
Subject: | 38 earth sciences, 54 computer science, 56 civil engineering |
Programme: | Business Information Technology MSc (60025) |
Link to this item: | https://purl.utwente.nl/essays/79045 |
Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Repository Staff Only: item control page