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.
Forecasting geomagnetic indices represents a key point to develop warning systems for the mitigation of possible effects of severe geomagnetic storms on critical ground infrastructures. Here we focus on SYM‐H index, a proxy of the axially symmetric magnetic field disturbance at low and middle latitudes on the Earth's surface. To forecast SYM‐H, we built two artificial neural network (ANN) models and trained both of them on two different sets of input parameters including interplanetary magnetic field components and magnitude and differing for the presence or not of previous SYM‐H values. These ANN models differ in architecture being based on two conceptually different neural networks: the long short‐term memory (LSTM) and the convolutional neural network (CNN). Both networks are trained, validated, and tested on a total of 42 geomagnetic storms among the most intense that occurred between 1998 and 2018. Performance comparison of the two ANN models shows that (1) both are able to well forecast SYM‐H index 1 h in advance, with an accuracy of more than 95% in terms of the coefficient of determination R2; (2) the model based on LSTM is slightly more accurate than that based on CNN when including SYM‐H index at previous steps among the inputs; and (3) the model based on CNN has interesting potentialities being more accurate than that based on LSTM when not including SYM‐H index among the inputs. Predictions made including SYM‐H index among the inputs provide a root mean squared error on average 42% lower than that of predictions made without SYM‐H.
Intimate partner violence (IPV) remains a scourge that compromises the rights of many women around the world, shaping an asymmetry in civil rights. Fighting gender-based violence, especially when it is committed by an intimate partner, is an important responsibility that needs to be addressed from all angles. It is also remarkable that our society is clearly conditioned by information and communication technology (ICT), which involves many aspects of our daily life. Unfortunately, violence that is performed in the real world is also replicated in this ‘virtual’ existence, by offenders in ICT contexts. On the other hand, the same technologies also provide a plethora of opportunities to fight IPV, which are enhanced by the innovative paradigm of the so-called Internet of Things (IoT). In this work, we first present a thorough compilation of ICT proposals already published—based on either hardware or software—aimed at protecting IPV survivors, and which can be applied in real life situations but also within social networks. The challenges that still lie ahead are highlighted and, a complete ICT-based platform for IPV management, within an IoT framework, that overcomes the limitations of previous works is proposed, and then promoting a symmetry between individuals in society.
Health data anonymization is a hot topic, on which both the medical and the computer science communities have made a great effort to provide a safer and trustful way of sharing data among research centers and hospitals.The main challenge in data anonymization is to provide a proper trade off between the utility of the resulting data/models and protecting individual privacy.In this paper we present a real anonymization case, with particular emphasis on choices that have to be made to carry it on, and difficulties experienced using a data set with many dimensions, and not well distinguishable features. We present our approach for evaluating disclosure risks and methods for anonymising high-dimensional medical survey data and measuring the utility of the transformed data.
This work proposes a unified framework to leverage biological information in network propagation-based gene prioritization algorithms. Preliminary results on breast cancer data show significant improvements over state-of-the-art baselines, such as the prioritization of genes that are not identified as potential candidates by interactome-based algorithms, but that appear to be involved in/or potentially related to breast cancer, according to a functional analysis based on recent literature.