A Data Filling Methodology for Time Series Based on CNN and (Bi)LSTM Neural Networks

Abstract

During data collection from sensors, several circumstances can affect their continuity and validity, resulting in alterations or loss of data. Although classical statistics methods can reasonably approximate the missing data in a time series, the recent developments in Deep Learning (DL) have given impetus to innovative and much more accurate forecasting techniques. In the present paper, we develop two DL models aimed at filling data gaps in internal temperature time series obtained from monitored apartments located in Bolzano, Italy. These models exploit both pre- and post-gap data, and a correlated time series (the external temperature) in order to predict the internal temperature. The first one consists of two twin networks, each of which is a combination of Convolutional Neural Networks (CNN) and Long Short-Term Memory Neural Networks (LSTM), which are run in opposite directions and then combined. Our second DL model, instead, is a single network containing CNN and Bidirectional LSTM layers (BiLSTM). Both of them capture the fluctuating nature of the data and show good accuracy in reconstructing the target time series. The results they achieve, both in terms of error metrics and of R2-score, are better than those of a simpler DL architecture proposed in the literature for a similar scope, that we take as a baseline. Comparing our two models, the CNN-BiLSTM outperforms the CNN-LSTM, indicating a more effective way of combining past and future information, which is learnt from the data, than the explicit interpolation via a sigmoid function of onward and backwards predictions.