SSIM—A Deep Learning Approach for Recovering Missing Time Series Sensor Data

Abstract

Missing data are unavoidable in wireless sensor networks, due to issues such as network communication outage, sensor maintenance or failure, etc. Although a plethora of methods have been proposed for imputing sensor data, limitations still exist. First, most methods give poor estimates when a consecutive number of data are missing. Second, some methods reconstruct missing data based on other parameters monitored simultaneously. When all the data are missing, these methods are no longer effective. Third, the performance of deep learning methods relies highly on a massive number of training data. Moreover in many scenarios, it is difficult to obtain large volumes of data from wireless sensor networks. Hence, we propose a new sequence-to-sequence imputation model (SSIM) for recovering missing data in wireless sensor networks. The SSIM uses the state-of-the-art sequence-to-sequence deep learning architecture, and the long short-term memory network is chosen to utilize both past and future information for a given time. Moreover, a variable-length sliding window algorithm is developed to generate a large number of training samples so the SSIM can be trained with small data sets. We evaluate the SSIM by using real-world time series data from a water quality monitoring network. Compared to methods like ARIMA, seasonal ARIMA, matrix factorization, multivariate imputation by chained equations, and expectation–maximization, the proposed SSIM achieves up to 69.2%, 70.3%, 98.3%, and 76% improvements in terms of the root mean square error, mean absolute error, mean absolute percentage error (MAPE), and symmetric MAPE, respectively, when recovering missing data sequences of three different lengths. The SSIM is therefore a promising approach for data quality control in wireless sensor networks.