No abstract

Machine learning techniques combined with wearable electronics can deliver accurate short-term blood glucose level prediction models. These models can learn personalized glucose–insulin dynamics based on the sensor data collected by monitoring several aspects of the physiological condition and daily activity of an individual. Until now, the prevalent approach for developing data-driven prediction models was to collect as much data as possible to help physicians and patients optimally adjust therapy. The objective of this work was to investigate the minimum data variety, volume, and velocity required to create accurate person-centric short-term prediction models. We developed a series of these models using different machine learning time series forecasting techniques suitable for execution within a wearable processor. We conducted an extensive passive patient monitoring study in real-world conditions to build an appropriate data set. The study involved a subset of type 1 diabetic subjects wearing a flash glucose monitoring system. We comparatively and quantitatively evaluated the performance of the developed data-driven prediction models and the corresponding machine learning techniques. Our results indicate that very accurate short-term prediction can be achieved by only monitoring interstitial glucose data over a very short time period and using a low sampling frequency. The models developed can predict glucose levels within a 15-min horizon with an average error as low as 15.43 mg/dL using only 24 historic values collected within a period of sex hours, and by increasing the sampling frequency to include 72 values, the average error is reduced to 10.15 mg/dL. Our prediction models are suitable for execution within a wearable device, requiring the minimum hardware requirements while at simultaneously achieving very high prediction accuracy.

In this paper, a 4 4 indoor multiple-input multiple-output (MIMO) measurement campaign at a frequency of 2.45 GHz is presented. The main contribution of this work is the analysis of the impact of radio-wave polarization in MIMO systems operating at a typical indoor scenario through the calculation-from the measurements carried out-of a great deal of parameters such as the mean path loss, the cross polarization discrimination (XPD), and the RMS delay spread, which are all essential to estimate the performance of real MIMO systems. In this sense, some path loss models-which have been adjusted according to the measurements-are given, taking into account polarization, attenuation through walls, and the effect of T-junctions existing in the considered indoor scenario. Moreover, additional parameters such as the K-factor and statistical distribution, as well as spatial parameters, are discussed.

No abstract

[1] A new formulation expressed in terms of Uniform Theory of Diffraction (UTD) coefficients for the prediction of the multiple diffraction caused by a series of buildings modeled as wedges, considering spherical-wave incidence, is presented. The solution, which has a certain heuristic nature, is validated with numerical results from technical literature and the particular cases of diffraction by buildings modeled as absorbing knife edges, as well as the one in which the mentioned buildings are replaced by flat-roofed parallel rows of blocks (building rows in cross sections considered to be rectangular in shape) are also analyzed. The computing time is reduced over existing formulations, especially when the number of buildings is large, and the results can be applied in the development of theoretical models, in order to predict a more realistic path loss in urban environments when multiple-building diffraction has to be considered.