On-the-fly mathematical formulation for estimating people flow from elevator load data in smart building virtual sensing platforms

Koichi Kondo, Ryosuke Ohori, Kiyotaka Matsue, Hiroyuki Aizu

Abstract: Highlights•People flow estimation from elevator trip records and load data is considered.•Parameters are estimated by optimization using equation-based models.•Features in obtained sensor data are formulated as equations.•The model for optimization is derived by modifying the base equations on-the-fly.•The modified or added equations improve the accuracy for under-defined cases.