An autonomous medical monitoring system: Validation on arrhythmia detection.

In this paper, we present a generic platform for autonomous medical monitoring and diagnostics. We validated the platform in the context of arrhythmia detection with publicly available databases. The big advantage of this platform is its capacity to deal with various types of physiological signals. Many pre-processing steps are performed to bring the input information into a uniform state that will be explored by a machine learning algorithm. Since this block plays a crucial role in the entire processing pipeline, three different methods were evaluated for detection and classification of anomalies. The results presented in this work are validated on cardiac beats, where the highest accuracy was obtained on the classification of normal beats (94%). On the other hand, atrial fibrillation and premature ventricular contraction beats were classified with an accuracy of 78%.

The use of a neural network to forecast daily grass pollen concentration in a Mediterranean region: the southern part of the Iberian Peninsula.

BACKGROUND: Pollen allergy is a common disease causing hayfever in 15% of the population in Europe. Medical studies report that a prior knowledge of pollen content in the air can be useful in the management of pollen-related diseases. OBJECTIVES: The aim of this work was to forecast daily Poaceae pollen concentrations in the air by using meteorological data and pollen counts from previous days as independent variables. METHODS: Linear regression models and co-evolutive neural network models were used for this study. Pollen was monitored by a Hirst-type spore trap using standard techniques. The data were obtained from the Spanish Aerobiology Network database, University of Cordoba Monitoring Unit. The set of data includes a series of 20 years, from 1982 to 2001. A classification of the years according to their allergenic potential was made using a K-mean cluster analysis with pollen and meteorological parameters. Statistical analysis was applied to all the years of each class with the exception of the most recent year, which was used for model validation. RESULTS: It was observed that cumulative variables and pollen values from previous days are the most important factors in the models. In general, neural network equations produce better results than linear regression equations. CONCLUSION: Co-evolutive neural network models, which obtain the best forecasts (an almost 90% "good" classification), make it possible to predict daily airborne Poaceae pollen concentrations. This new system based on neural network models is a step toward the automation of the pollen forecast process.