Abstract Cardiovascular diseases state as one of the greatest risks death for general population. Late detection in heart highly conditions chances survival patients. Age, sex, cholesterol level, sugar rate, among other factors, are known to have an influence on life-threatening problems, but, due high amount variables, it is often difficult expert evaluate each patient taking this information into account. In manuscript, authors propose using deep learning methods, combined with feature...

The large number of sensors and actuators that make up the Internet Things obliges these systems to use diverse technologies protocols. This means IoT networks are more heterogeneous than traditional networks. gives rise new challenges in cybersecurity protect devices which characterized by being connected continuously Internet. Intrusion detection (IDS) used from various anomalies attacks at network level. Detection Systems can be improved through machine learning techniques. Our work...

The aim of this paper was the detection pathologies through respiratory sounds. ICBHI (International Conference on Biomedical and Health Informatics) Benchmark used. This dataset is composed 920 sounds which 810 are chronic diseases, 75 non-chronic diseases only 35 healthy individuals. As more than 88% samples from same class (Chronic), use a Variational Convolutional Autoencoder proposed to generate new labeled data other well known oversampling techniques after determining that classes...

The quality of service (QoS) parameters in IoT applications plays a prominent role determining the performance an application. Considering significance and popularity systems, it can be predicted that number users devices are going to increase exponentially shortly. Therefore, is extremely important improve QoS provided by their adaptability. Majority systems characterized heterogeneous diverse nature. It challenging for these provide high-quality access all connecting with uninterrupted...

Abstract Parkinson’s disease is easy to diagnose when it advanced, but very difficult in its early stages. Early diagnosis essential be able treat the symptoms. It impacts on daily activities and reduces quality of life both patients their families also second most prevalent neurodegenerative disorder after Alzheimer people over age 60. Most current studies prediction severity are carried out advanced stages disease. In this work, study analyzes a set variables that can easily extracted from...

Technology has provided a new way of life for the adolescent population. Indeed, strategies aimed at improving health-related behaviors through digital platforms can offer promising results. However, since it been shown that peers are capable modifying related to food and physical exercise, is important study whether interventions based on peer influence weight status adolescents.The purpose this was assess effectiveness an eHealth app in population terms improvements their age- sex-adjusted...

In this work, a sentiment analysis method that is capable of accepting audio any length, without being fixed priori, proposed. Mel spectrogram and Frequency Cepstral Coefficients are used as description methods Fully Convolutional Neural Network architecture proposed classifier. The results have been validated using three well known datasets: EMODB, RAVDESS, TESS. obtained were promising, outperforming the state-of-the-art methods. Also, thanks to fact admits audios size, it allows be made...

Socioeconomic status (SES) influences all the determinants of health, conditioning health throughout life. The aim present study was to explore relationship between socioeconomic and obesity in adolescence through an analysis patterns contact peers as a function this parameter. A cross-sectional performed, analyzing sample 235 students aged 14 18 11 class networks. Social network used analyze structural variables centrality from sociocentric perspective. We found that adolescents with...

There is a great concern nowadays regarding alcohol consumption and drug abuse, especially in young people. Analyzing the social environment where these adolescents are immersed, as well series of measures determining abuse risk or personal situation perception using number questionnaires like AUDIT, FAS, KIDSCREEN, others, it possible to gain insight into current given individual his/her behavior. But this analysis, order be achieved, requires use tools that can ease process questionnaire...

COVID-19 disease has affected almost every country in the world. The large number of infected people and different mortality rates between countries given rise to many hypotheses about key points that make virus so lethal some places. In this study, eating habits 170 were evaluated order find correlations these caused by using machine learning techniques group together according distribution fat, energy, protein across 23 types food, as well amount ingested kilograms. Results shown how...

Abstract The COVID-19 pandemic has meant that young university students have had to adapt their learning and a reduced relational context. Adversity contexts build models of human behaviour based on relationships. However, there is lack studies analyse the social structure in context pandemic. This information could be useful making decisions how plan collective responses adversities. Social Network Analysis (SNA) method been chosen address this structural perspective. aim our research...

Eating disorders (ED) are among the most widespread mental illnesses in our society today. This research work presents study of deep learning models applied to domain eating disorders. For this purpose, a collection messages from social network Twitter was compiled using web scraping techniques. After collecting total amount 1,085,957 tweets, subset 2,000 tweets manually classified. classification made it possible differentiate written by people who suffer or have suffered an ED those not...

Industry 4.0 significantly improves productivity by collecting and analyzing data in real time. This, combined with remote access functions, cloud processing that allows Internet of Things IoT, provides information optimizes processes decision support. Also involves a great growth new networks systems special features, which mean they are vulnerable to different attacks. So security requirements emerging the IoT network. To improve an system for transparent way, it is proposed development...

One of the main challenges in simultaneous localization and mapping (SLAM) is real-time processing. High-computational loads linked to data acquisition processing complicate this task. This article presents an efficient feature extraction approach for structured environments. The proposed methodology, weighted conformal LiDAR-mapping (WCLM), based on polygonal profiles propagation uncertainties from raw measurement data. achieved using M bius transformation. algorithm has been validated...

Social Network Analysis (SNA) is a set of techniques developed in the field social and behavioral sciences research, order to characterize study relationships that are established among individuals. When building network for performing an SNA analysis, initial process data gathering achieved extract characteristics individuals their relationships. This usually done by completing questionnaire containing different types questions will be later used obtain measures needed perform study. There...