An ensemble multi-stream classifier for infant needs detection.

In this paper, we propose a novel multi-stream video classifier for infant needs detection. The proposed system is an ensemble-based system that combines several machine learning to improve the overall result of the state-of-the-art algorithms. It is a multi-stream in the sense that it combines the output predictions of both audio and images of infants from every single classifier employed in the system for a unified result. This produces better performance and results compared to the previous other research techniques, which relied on only one of these modalities. For training and testing the proposed system, from the Dunstan Baby Language video collection, we built three separate datasets for videos, images, and sounds encompassing the five primary infant needs that require predicting. These are: hunger, have wind, uncomfortable (require diaper change), wants to burp or tired, with a total of 3348 samples. We used four different ensemble algorithms for the best reachable performance. The proposed algorithm improves the overall accuracies of each single classifier from a low of 51% to a high of 99%. The proposed method also improves the accuracy of the classification process by about 9% compared to the state-of-the-art approaches, which was 90%.

Prediction of patient's response to OnabotulinumtoxinA treatment for migraine.

Migraine affects the daily life of millions of people around the world. The most well-known disabling symptom associated with this illness is the intense headache. Nowadays, there are treatments that can diminish the level of pain. OnabotulinumtoxinA (BoNT-A) has become a very popular medication for treating migraine headaches in those cases in which other medication is not working, typically in chronic migraines. Currently, the positive response to Botox treatment is not clearly understood, yet understanding the mechanisms that determine the effectiveness of the treatment could help with the development of more effective treatments. To solve this problem, this paper sets up a realistic scenario of electronic medical records of migraineurs under BoNT-A treatment where some clinical features from real patients are labeled by doctors. Medical registers have been preprocessed. A label encoding method based on simulated annealing has been proposed. Two methodologies for predicting the results of the first and the second infiltration of the BoNT-A based treatment are contempled. Firstly, a strategy based on the medical HIT6 metric is described, which achieves an accuracy over 91%. Secondly, when this value is not available, several classifiers and clustering methods have been performed in order to predict the reduction and adverse effects, obtaining an accuracy of 85%. Some clinical features as Greater occipital nerves (GON), chronic migraine time evolution and others have been detected as relevant features when examining the prediction models. The GON and the retroocular component have also been described as important features according to doctors.

Support System to Improve Reading Activity in Parkinson's Disease and Essential Tremor Patients.

The use of information and communication technologies (ICTs) to improve the quality of life of people with chronic and degenerative diseases is a topic receiving much attention nowadays. We can observe that new technologies have driven numerous scientific projects in e-Health, encompassing Smart and Mobile Health, in order to address all the matters related to data processing and health. Our work focuses on helping to improve the quality of life of people with Parkinson's Disease (PD) and Essential Tremor (ET) by means of a low-cost platform that enables them to read books in an easy manner. Our system is composed of two robotic arms and a graphical interface developed for Android platforms. After several tests, our proposal has achieved a 96.5% accuracy for A4 80 gr non-glossy paper. Moreover, our system has outperformed the state-of-the-art platforms considering different types of paper and inclined surfaces. The feedback from ET and PD patients was collected at "La Princesa" University Hospital in Madrid and was used to study the user experience. Several features such as ease of use, speed, correct behavior or confidence were measured via patient feedback, and a high level of satisfaction was awarded to most of them. According to the patients, our system is a promising tool for facilitating the activity of reading.