Victor Gonzalez

Photosensitivity is a neurological condition in which the brain produces epileptic reactions known as Photoparoxysmal Responses (PPR) to certain visual stimuli, which may trigger epileptic seizures in the worst cases. This pathology is diagnosed through a standardized protocol called Intermittent Photic Stimulation consisting of stimulating the patient with a flashing light while recording the brain activity by Electroencephalogram (EEG) until a PPR is triggered. Due to the nature of the stimulation process and the photosensitivity’s low prevalence, the automatic detection of PPR becomes a highly unbalanced problem where PPR activity can be considered as anomalous activity surrounded by large portions of normal brain activity. This research proposes the use of a Variational Autoencoder (VAE) to extract features from the EEG segments by reducing them into the latent space to train several Anomaly Detection models proposed by the literature and compare their PPR detection performance. Results show that no AD model could detect any PPR activity correctly while the VAE model, also used for this task in our previous research, reached Accuracy, Sensitivity, and Specificity values of around 85%.

In recent research, the prime and irreducible elements of strong finite factorization domains were studied. It was shown that strongly computable strong finite factorization domains (SCSFFD) have necessarily computable irreducible elements and a computable division algorithm. However, the question of how to best classify this class of structures is left unanswered. This work provides a classification for SCSFFDs by showing the existence of a computable norm where norm-form equations can be solved computably. This classification provides the intuition to extend further the notion of strong computability to finite factorization domains in general.

It is always possible to construct a real function f, given random quantities X and Y with continuous distribution functions F and G, respectively, in such a way that f(X) and f(Y), also random quantities, have both the same distribution function, say H. This result of De Finetti introduces an alternative way to somehow describe the `opinion' of a group of experts about a continuous random quantity by the construction of Fields of coincidence of opinions (FCO). A Field of coincidence of opinions is a finite union of intervals where the opinions of the experts coincide with respect to that quantity of interest. We speculate on (dis)advantages of Fields of Opinion compared to usual `probability' measures of a group and on their relation with a continuous version of the well-known Allais' paradox

There are many real-world applications like healthcare systems, job monitoring, well-being and personal fitness tracking, monitoring of elderly and frail people, assessment of rehabilitation and follow-up treatments, affording Fall Detection (FD) and ADL (Activity of Daily Living) identification, separately or even at a time. However, the two main drawbacks of these solutions are that most of the times, the devices deployed are obtrusive (devices worn on not quite common parts of the body like neck, waist and ankle) and the poor battery life. Thus, this work proposes a low-power classification algorithm based on an Ensemble of KNN and K-Means algorithms (EKMeans) to identify Falls and High-Intensity ADL events such as running, jogging and climbing up stairs. The input of EKMeans are triaxial accelerometer data gathered from wrist-wearable devices. The proposal will be validated on the Fall&ADL publicly available datasets UMAFall, UCIFall and FallAllD, considering two kinds of activity labelling: Two-Class and Multi-Class. An exhaustive comparative study between our proposal, and the baseline algorithms KNN and a feed-forward Neural Network (NN) is deployed, where EKMeans outperformed clearly the Specificity (ADL classification) of the KNN and NN for the three datasets. Finally, a comparative battery consumption study has been included deploying the analyzed algorithms in a WearOS smartwatch, where EKMeans drains the battery from 100% to 0% in 27.45 hours, saving 5% and 21% concerning KNN and NN, respectively. Keywords: Human Activity Recognition, ADL Identification, Fall Detection TS Clustering, TS Classification, Wearable Devices, Low-Power HAR.

Bullying of people with Special Educational Needs with or without disabilities is a reality, being one of the most affected groups. This study presents the data obtained in a European Erasmus+ project in which 96 young people and adults with SEN/D from four countries participated: Ireland, Spain, Italy, and Portugal. Firstly, a questionnaire was passed to see the general knowledge of these people in relation to bullying. Then a training program was carried out and finally the questionnaire was passed again to see if the data improved. From the data it appears that people with SEN/D lack skills, knowledge, and resources to deal with bullying. After the completion of the training program the data obtained from the questionnaire improved in many respects. Sometimes people with SEN/D are not aware that they are suffering from this type of situation due to lack of knowledge, so it is necessary to continue implementing training programs to help improve this situation.

Fall detection is a challenging task that has received the attention of the research community in the recent years. This study focuses on FD using data gathered from wearable devices with tri-axial accelerometers, developing a solution centered in elderly people living autonomously. This research includes three different ways to improve a FD method: an analysis of the event detection stage, comparing several alternatives, an evaluation of features to extract for each detected event and an appraisal of up to 6 different clustering scenarios to split the samples in subsets that might enhance the classification. For each clustering scenario, a specific classification stage is defined. The experimentation includes publicly available simulated fall data sets. Results show the guidelines for defining a more robust and efficient FD method for on-wrist 3DACC wearable devices.

Several researchers have recently established that for every Turing degree \, the real closed field of all \-computable real numbers has spectrum \. We investigate the spectra of real closed fields further, focusing first on subfields of the field \ of computable real numbers, then on archimedean real closed fields more generally, and finally on non-archimedean real closed fields. For each noncomputable, computably enumerable set C, we produce a real closed C-computable subfield of \ with no computable copy. Then we build an archimedean real closed field with no computable copy but with a computable enumeration of the Dedekind cuts it realizes, and a computably presentable nonarchimedean real closed field whose residue field has no computable presentation.

We make use of natural induction to propose, following John Ju Sakurai, a generalization of Bell's inequality for two spin s=n/2(n=1,2,...) particle systems in a singlet state. We have found that for any finite integer or half-integer spin Bell's inequality is violated when the terms in the inequality are calculated from a quantum mechanical point of view. In the final expression for this inequality the two members therein are expressed in terms of a single parameter θ. Violation occurs for θ in some interval of the form (α,π/2) where α parameter becomes closer and closer to π/2, as the spin grows, that is, the greater the spin number the size of the interval in which violation occurs diminishes to zero. Bell's inequality is a relationship among observables that discriminates between Einstein's locality principle and the non-local point of view of orthodox quantum mechanics. So our conclusion may also be stated by saying that for large spin numbers the non-local and local points of view agree