A core part of maintenance planning is a monitoring system that provides a good prognosis on health and degradation, often expressed as remaining useful life (RUL). Most of the current data-driven approaches for RUL prediction focus on single-point prediction. These point prediction approaches do not include the probabilistic nature of the failure. The few probabilistic approaches to date either include the aleatoric uncertainty (which originates from the system), or the epistemic uncertainty (which originates from the model parameters), or both simultaneously as a total uncertainty. Here, we propose ensemble neural networks for probabilistic RUL predictions which considers both uncertainties and decouples these two uncertainties. These decoupled uncertainties are vital in knowing and interpreting the confidence of the predictions. This method is tested on NASA's turbofan jet engine CMAPSS data-set. Our results show how these uncertainties can be modeled and how to disentangle the contribution of aleatoric and epistemic uncertainty. Additionally, our approach is evaluated on different metrics and compared against the current state-of-the-art methods.

In this work, we propose a novel ensemble neural network design that is capable of classifying the emotional context of short sentences. Our model consists of three distinct branches, each of which is composed of a combination of recurrent, convolutional, and pooling layers to capture the emotional context of text. Our unique combination of convolutional and recurrent layers enables our network to extract more emotionally salient information from text than formerly possible. Using this network, experiments classifying the emotional context of short sequences of texts from five distinct datasets, were conducted. Results show that the novel method outperforms all historical approaches across all datasets by 8.31 percentage points on average. Additionally, the proposed work produces results that are on average as accurate as state of the art methods, while using two orders of magnitude less training data. The contribution of this paper is a novel ensemble recurrent convolutional neural network capable of detecting and classifying the emotional context of short texts.