NTU Researchers Find Missing Data in an M2M Environment

The proposed Novel imputation method can recover missing data in a wireless sensor network Wireless sensor networks (WSN) are particularly susceptible to interference, battery depletion, hardware failure, and other environmental and communications ailments that lead to data loss. Datasets gathered from sensor networks are often missing a significant fraction of their possible readings. These missing values are problematic for data analysis tools, such as classification engines, time-sequence pattern analysis modules, and other machine learning tasks, which are often ill equipped to deal with missing values