How a small R&D team achieved great results in the Kaggle competition without using ML algorithms

Written by navigine | Published 2021/06/15
Tech Story Tags: ml | algorithms | navigation | location | microsoft-research | logs | kalman-filter | machine-learning

TLDR A few months ago, Navigine R&D team started participating in the Indoor Location & Navigation competition from XYZ10 and Microsoft Research. Organizers provided the participants with logs from hundreds of shopping centers. It was necessary to predict the floor and the x, y coordinate of the visitor on that floor based on radio signals and inertial sensors. In addition to the logs, participants had metadata in the form of a map, which shows the location of cafes, shops, and other points of interest (POI)via the TL;DR App

no story

Published by HackerNoon on 2021/06/15