Time calibration in experiments with networked sensors

Abstract

Physiological sensors are widely used in user studies, often by practitioners with limited expertise in networking. However, large data volumes, and processing times often prevent the use of a single computer to collect the readings in real time. With multiple collection machines appear the problems of data aggregation and, more importantly, synchronisation. This paper describes how the OML reporting library allows solving the aggregation problem at low cost by introducing a lightweight instrumentation reporting to a centralised database. However, with unknown delays in network paths during aggregation and unreliable clocks on acquisition machines, synchronisation is hard to attain. We present a preliminary study of the theoretical feasibility of post hoc synchronisation corrections, supported by an experiment applying correction techniques to artificially impaired clocks and network transmissions. Based on the results of this experiment this paper highlights potential improvements.