SmartImpute
Soma Bandyopadhyay, Krithi Ramamritham · 2016
One of the major concerns of sensor signal analytics is missing or incomplete samples. Data misses occur mainly because of delays or faults in data capturing infrastructure. We propose a novel mechanism for missing data imputation. The novelty of our mechanism arises from its exploitation of the semantics of different features of the sensor signal to estimate the missing samples. Our methods are based on statistical learning and analysis. We demonstrate the efficacy of the proposed method using real data from smart-energy meters.