The impact of machine learning on fiber network engineering

Fabion Kauker, 3-GIS Product Architect, presents the results of his research in a paper awarded at the 2018 Human Computer Interaction International conference as the best paper of the Human Interface and the Management of Information thematic area. The research looks at the trade-offs between three approaches that can be developed for fiber network planning to interpret satellite imagery and determine the location of residences or businesses.

Machine learning has gained momentum in network planning and design as information models have transformed into geocentric databases. As the telecom industry seeks new methods to reduce costs, expand service areas, and deliver new applications, participants are looking to the promise of artificial intelligence (AI), machine learning (ML), and human-in-the-loop (HitL) methods that will be possible with network data.

While AI and ML hold the promise of or iterative computation for reliable and repeatable results, research like Fabion’s is needed to determine where it will unlock the value of network data for enacting decisions. You can read and download the paper, An Exploration of Crowdwork, Machine Learning and Experts for Extracting Information from Data, here.