For people with type 1 diabetes, good blood glucose control is essential to keeping serious disease complications at bay. This entails carefully monitoring blood glucose levels and taking corrective steps whenever they are too high or too low. If blood glucose levels could be accurately predicted, patients could take proactive steps to prevent blood glucose excursions from occurring. However, accurate predictions require complex physiological models of blood glucose behavior. Factors such as insulin boluses, carbohydrate intake, and exercise influence blood glucose in ways that are difficult to capture through manually engineered equations. In this paper, we describe a recursive neural network (RNN) approach that uses long short-term memory (LSTM) units to learn a physiological model of blood glucose. When trained on raw data from real patients, the LSTM networks (LSTMs) obtain results that are competitive with a previous state-of-the-art model based on manually engineered physiological equations. The RNN approach can incorporate arbitrary physiological parameters without the need for sophisticated manual engineering, thus holding the promise of further improvements in prediction accuracy.
This paper proposes the use of Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units for determining whether Mandarin-speaking individuals are afflicted with a form of Dysarthria based on samples of syllable pronunciations. Several LSTM network architectures are evaluated on this binary classification task, using accuracy and Receiver Operating Characteristic (ROC) curves as metrics. The LSTM models are shown to significantly improve upon a baseline fully connected network, reaching over 90% area under the ROC curve on the task of classifying new speakers, when a sufficient number of cepstrum coefficients are used. The results show that the LSTM's ability to leverage temporal information within its input makes for an effective step in the pursuit of accessible Dysarthria diagnoses.
This paper suggests several improvements over the original Time‐expanded Decision Network (TDN; a powerful and generic methodology introduced by Silver and de Weck for designing evolvable complex systems) in order to leverage its ease, flexibility, and scope of use. A more accurate model of the switching process, a simpler network representation, and the ability to address systems with unknown lifetime are some of the improvements. However, the most important added feature is the ability to account for other design requirements within the process, which enables the designers to embed the TDN methodology into their general concept exploration phase. As a result, the enhanced TDN (ETDN) mitigates the need for iterations over several requirement domains and makes achieving the optimal design easier. It is also discussed in the paper that all of the improvements are attained without adding to the original method's complexity and only by a marginal increment of computational costs. As an example, the design of a sports car system is described and all of the new features are applied and the results are thoroughly discussed—although the example's focus is solely on the new improvements and not on the features that are directly inherited from the original method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.