Time series with seasonal variability is widely used to describe processes in variousfields, such as trade, analysis of financial markets, forecasting passenger air transportation,and description climatic changes. Recently, this approach has been describetechnological well. In regard, applying predictive models control systems ofcomplex technical objects become possible. Machine learning method...

Missing values are a common problem of time series such as sensor-generated data due to issues collection, transmission, and storage. To deal with this problem, various imputation methods have been proposed. Among these methods, variants recurrent neural networks (RNNs) attracted lot attention they provide natural representation temporal dynamics. Though shown achieve higher accuracy, mostly fo...