Sequence-to-Sequence Imputation of Missing Sensor Data
This addresses missing data recovery in sensor applications, but it is incremental as it adapts an existing model to a specific challenge.
The paper tackled the problem of imputing missing sensor data by adapting sequence-to-sequence models to handle three sequences (observed-missing-observed), using forward and backward RNNs with a novel decoder, resulting in 12% more cases with lower errors than the state-of-the-art.
Although the sequence-to-sequence (encoder-decoder) model is considered the state-of-the-art in deep learning sequence models, there is little research into using this model for recovering missing sensor data. The key challenge is that the missing sensor data problem typically comprises three sequences (a sequence of observed samples, followed by a sequence of missing samples, followed by another sequence of observed samples) whereas, the sequence-to-sequence model only considers two sequences (an input sequence and an output sequence). We address this problem by formulating a sequence-to-sequence in a novel way. A forward RNN encodes the data observed before the missing sequence and a backward RNN encodes the data observed after the missing sequence. A decoder decodes the two encoders in a novel way to predict the missing data. We demonstrate that this model produces the lowest errors in 12% more cases than the current state-of-the-art.