Maps element prediction from raw time-series position data using machine learning techniques

Having geopositional tracking data of users moving in the work space, we would like to detect map elements such as paths, zones of interest and borders and to create abroad map of the working area from this time series raw data. In order to do so, an experiment to generate data was conducted to emulate workers moving around thework-space.Once the data was obtained, further analysis was performed. Visuals ofthe tracking data were produced where one could see the different paths of each userduring the experiment. Once the visuals were analyzed, anomalies which needed removal were detected. For the following, multiple techniques such as local outlier factor were used.With the cleaned up data at hand, density based machine learning algorithms were used to reach our main objective. This lead to the discovery of paths,rooms, buildings and other hot-spots laying around the map. A conclusion was reached that it was possible to discover different elements of a map and to draw out the map regions to a certain degree of accuracy. It was however found that work needs to be done to improve the generated data, the quality of the produced map,the detection of more elements