HalO [Indoor positioning mobile platorm]

Post-Occupancy Evaluation (POE) as an integrated field between architecture and sociology has created practcal guidelines for evaluatng indoor human behavior within a built environment. This research builds on recent atempts to integrate datafication and machine learning into POE practces that may one day assist Building Information Modeling (BIM) and mult-agent modeling. This research is based on two premises: 1) that the proliferation of Bluetooth Low Energy (BLE) technology allows us to collect a building user's data cost-effectively and 2) that the growing application of machine learning algorithms allows us to process, analyze and synthesize data efficiently. This study illustrates that the mobile platorm HalO can serve as a generic tool for datafication and automation of data analysis of the movement of a building user. In this research, the iOS mobile application HalO, combined with BLE beacons enable building providers (architects, developers, engineers and facility managers etc.) to collect the user's indoor location data. Triangulation was used to pinpoint the user's indoor positions, and k-means clustering was applied to classify users into different gathering groups. Through four research procedures - Design Intention Analysis, Data Collection, Data Storage and Data Analysis - the visualized and classified data helps building providers to beter evaluate building performance, optmize building operations and improve the accuracy of simulations.