Skip to Main Content
A novel hybrid sensor informatics architecture based on discrete wavelet transform (DWT) and multiple fuzzy logic based clustering (m-FCM) is investigated and proposed to estimate sensor drift in a real life oceanic sensor network. DWT is used for sensor pre-processing, data dimension reduction and feature extraction from sensor time series, where as FCM-based approach is used to estimate and correct the cumulative drift in the sensory system. This new drift correction algorithm is tested on a real time estuary sensory platform deployed to monitor the Derwent Estuary in Hobart, Australia, to evaluate the performance. This algorithm outperforms previously reported drift correction paradigms.