Attention-based Information Fusion using Multi-Encoder-Decoder Recurrent Neural Networks
This addresses the challenge of improving predictions in sensor networks for applications like monitoring, but it appears incremental as it builds on existing RNN and attention methods.
The paper tackled the problem of predicting future behavior in distributed sensor networks by proposing a new RNN architecture that fuses information from multiple sensor stations using attention-based weighting. It demonstrated effectiveness on three real-world datasets, though no concrete numbers were provided.
With the rising number of interconnected devices and sensors, modeling distributed sensor networks is of increasing interest. Recurrent neural networks (RNN) are considered particularly well suited for modeling sensory and streaming data. When predicting future behavior, incorporating information from neighboring sensor stations is often beneficial. We propose a new RNN based architecture for context specific information fusion across multiple spatially distributed sensor stations. Hereby, latent representations of multiple local models, each modeling one sensor station, are jointed and weighted, according to their importance for the prediction. The particular importance is assessed depending on the current context using a separate attention function. We demonstrate the effectiveness of our model on three different real-world sensor network datasets.