We Alberto Conejero (Instituto Universitario de Matemática Pura y Aplicada, IUMPA) and Miguel Rebollo (of the Valencian Research Institute for Artificial Intelligence, VRAIN) of UPV are part of the Data Science Working Group in the Fight against COVID-19 , of the Commissioner for the Presidency of the Generalitat Valenciana on Strategy for Artificial Intelligence and Data Sciences against COVID-19. News appeared in UPV, in El Periodic newspaper and in RUVID website.
Since April 2020, I have been involved in the Data Science Group COVID-19 of the València Region under the supervision of Nuria Oliver. This is a multidisciplinary team of volunteers that work side by side with the General Director of Analysis and Public Policies of the Presidency of the RValencia Region Government. The analysis for COVID-19 is coordinated with the Ministry of Health and the rest of the Councils involved. This working group is led by Nuria Oliver, Commissioner of the Presidency of the Generalitat for the Valencian Strategy for Artificial Intelligence and, especially, for the coordination of data intelligence before the COVID-19 epidemic in the Valencia Region.
They are part of the group of experts from the Jaume I University, the University of Valencia, the Polytechnic University of Valencia, the Miguel Hernández University, the University of Alacant, the CEU Cardenal Herrera University, Fisabio, and Microsoft, with the collaboration of Esri, the INE, the Secretary of State for Artificial Intelligence and the three most important mobile phone companies in the country.
This group is divided into three priority areas with their respective work coordinators: (1) analysis, visualization, and modeling of mobility data, (2) epidemiological models and (3) data science applied to COVID-19. There, I work in epidemiological models with Antonio Falcó, Miguel Rebollo, Miguel A. Lozano, Emilio Sansano, Xavier Barber, and Francisco Escolano.
This is the web page of our data research group http://infocoronavirus.gva.es/es/grup-de-ciencies-de-dades-del-covid-19-de-la-comunitat-valenciana
The lack of representative COVID-19 data is a bottleneck for reliable and generalizable machine learning. Data sharing is insufficient without data quality, where source variability plays an important role. We showcase and discuss potential biases from data source variability for COVID-19 machine learning. In this work, we used the publicly available nCov2019 dataset, including patient level data from several countries. We aimed to the discovery and classification of severity subgroups using symptoms and comorbidities.
Within the context of the collaborative university project «Data Literacy in Context» (DaLiCo), the first summer school with international students as participants and lecturers from all partner countries of the project took place in the last week of September. It was organized by the University of Applied Sciences Hamburg (HAW Hamburg), in a team led by Prof. Christine Gläser (project coordinator, Department Information) with contributions from the partner universities Stichting Hogeschool Utrecht (Netherlands), University of Debrecen (Hungary), and Universitat Politècnica de València (Spain).
During the summer school with the topic of Open (Governmental) Data, the participants studied intensively in lectures and workshops the infrastructures of open data sources, data analysis and visualization as well as data ethical questions and concepts, and finally the aspects of data sharing in the research context.
In data projects, the international teams of PhD, Master and Bachelor students deepened their newly acquired knowledge and put it to practical use. Using the World Happiness Report, I mentored some groups that developed their own research questions and examined whether aspects such as gender equality or unemployment have an influence on the happiness index in different countries. The research results of these projects can be viewed on the project website projects.dalico.info
On September 30th, 2020 we have received funding for the project Ciencias de Datos e Inteligencia Artificial contra el COVID-19, IA4COVID19, from Fundación BBVA among more than 150 proposals presented to the call in the category: Big Data e Inteligencia Artificial (“Data-IA-COVID-19”). This proposal has been lead by the data research scientist Nuria Oliver from Ellis Alicante. The initiative, is linked to the Valencian Strategy in Artificial Intelligence.
Our project is a collaborative work that we have developed voluntarily and altruistically since the beginning of the crisis caused by the pandemic, professors from Valencian universities. The research entitled «Data science against Covid-19» brings together the participation of civil society (through a citizen survey), experts from the academic-research environment, and public administration, with the aim of providing information so that the those responsible for public crisis management can make informed decisions based on scientific evidence obtained from data analysis. In particular, I collaborate in the epidemiological models part and as head of the UPV node together with Miguel Rebollo from the VRAIN Institute. The initiative, linked to the Valencian Strategy in Artificial Intelligence through the commissioner of the presidency occupied by the researcher Nuria Oliver.
Last July we received funding for the project «Data Sciences against Covid-19» (CD4COVID), from the Supera Covid-19 fund that Banco Santander launched in April, together with CRUE Spanish Universities and the Higher Council for Scientific Research ( CSIC). The fund, endowed with 8.5 million euros to finance programs, projects and support measures, aims to minimize the impact of the crisis generated by the pandemic and focuses on three lines of action: research, impact projects social and strengthening the technological capacity of Spanish universities.
Our project is a collaborative work that we have developed voluntarily and altruistically since the beginning of the crisis caused by the pandemic, professors from Valencian universities. The research entitled «Data science against Covid-19» brings together the participation of civil society (through a citizen survey), experts from the academic-research environment and public administration, with the aim of providing information so that the those responsible for public crisis management can make informed decisions based on scientific evidence obtained from data analysis. In particular, I collaborate in the epidemiological models part and as head of the UPV node together with Miguel Rebollo from the VRAIN Institute. The initiative, linked to the Valencian Strategy in Artificial Intelligence through the commissioner of the presidency occupied by the researcher Nuria Oliver.
I have recently been elected as member of the Editorial Board of AIMS Mathematics. This is an international bimonthly publication devoted to publishing peer-reviewed, high quality, research articles in all major fields of mathematics. Its impact factor in 2019 is 0.882.
I recently obtained a Msc in Bioinformatics and Biostatitsics from Universitat Oberta de Catalunya and Universitat de Barcelona. My capstone project was entitled «Machine learning methods for characterizing single-particle trajectories with anomalous diffusion» under the supervision of Ferran Reverter Comes.
Single-Particle Tracking (SPT) appears to be a potential approach to studying different dynamic processes in the life sciences with recent advances in light microscopy. The physics of life molecules has an inherent instability due to the heterogeneity of free energy states that different types of molecules can show, far from thermal equilibrium and ranging at different scales, from the nanoscale of a single molecule up to the cellular or even organism level. The classification of trajectories is a relevant topic, not only in the biological field at the molecular level but also at the level of animal and human behavior. Besides, this topic combines physical principles with some degree of uncertainty, which habilitates us for exploring the use of ML techniques.
I have recently presented a contribution in the with Francisco Pedroche on rankings. We have particularized to Spotify. While people around the world stopped, music didn’t: we have shown that during the worst months of the pandemic, the list of the Top-200 hits on Spotify, produced from the streams registered on the popular app, had 18% more songs. The most played songs worldwide, during the months studied, were Dance Monkey (Tones and I), Blinding Lights (The Weeknd), and The Box (Roddy Ricch).
This means that, regardless of whether record companies published new material or not, listeners changed their preferences more often during the pandemic, thus causing an increase in the number of songs that made the lists. Thus, the first quarter of 2019 registered 474 songs on the Top 200 list, whereas in the same period of this year, the number of hits was 557, which represents an 18% increase. This figure reveals a significant increase when compared to the 1% decrease that took place during the same period from 2018 to 2019, or the 9% increase from 2017 to 2018.
It has already been published our paper «Community detection based deep neural network (CD-DNN) architectures: a fully automated framework for Likert scales» in the mathematical journal Mathematical Methods in Applied Science, where we apply network community detection in order a suitable infrastructure for an Artificial Neural Network. This permits to efficiently use raw data from psychological questionnaires based on Likert scales.
Mathematics can also contribute to the modeling of side problems to the pandemics. We point out some of them, such as data quality analysis, network medicine, healthcare services management, the physical spreading of the virus in the environment, the subsequent impact on the economy, and the social response to confinement government measures.
In any case, all the contributions and developments will be beneficial in many ways aside from coping with pandemics. Some potential topics that this Special Issue will cover, but is not limited to, are as follows: Epidemiological dynamics, diffusion modeling, compartmental and SIR type models, human dynamics, agent modeling of structured populations, network medicine, data quality, artificial intelligence and deep learning models, and data analysis of social media
Further information in https://www.mdpi.com/journal/mathematics/special_issues/Mathematics_COVID-19 Your work is welcome!!!
On May 8th, my PhD student Miguel E. Iglesias-Martínez presented his dissertation Development of algorithms of statistical signal processing for the detection and pattern recognition in time series. Application to the diagnosis of electrical machines and to the features extraction in actigraphy signals, supervised Jose A. Antonino Daviu and Pedro Fdez. de Córdoba, obtaining the qualification of summa cum Claude. Congratulations for your excellent work, Miguel.
News appeared in Diario Libre of the Dominican Republic about my joint work with my students Pedro A. Solares Hernández and Fernando A. Manzano, together with Fco. Javier Pérez Benito. In this work, we study divisibility properties of Pascal’s triangle numbers. Link to the article.
Link to the publication in the mathematical journal Mathematics, from MDPI publisher, https://www.mdpi.com/2227-7390/8/2/254
Interview published on Monday April 13th in the newspaper Faro de Melilla, in which I talk about the importance of the availability of good data to make good decisions in these times of crisis. (Link to the article)
Today I have been invited to deliver a talk at the Master’s Degree in Languages and Technology In this talk I have briefly introduced several notions of data science, and in particular network science, in connection with linguistics. Among other things we have discussed that many structural patterns are inherent to linguistics, and are common to different languages.
Among these patterns, we can find Zipf’s law, Benford’s law, and unusual frequencies of certain motifs. We have also seen a tool called SocioViz that permits to download and visualize tweets from Twitter.
En este proyecto, investigadores del Instituto Universitario de Matemática Pura y Aplicada (IUMPA) y de la Escuela Técnica Superior de Arquitectura (ETSA) de la UPV hemos desarrollado un modelo completo para evaluar las prestaciones de uno de los productos de la compañía como aislante térmico en la construcción. La Vanguardia y otros medios se han hecho eco de nuestro trabajo.
Podéis leer también la noticia completa también en la página web de la UPV.
La UPV va a ofertar el próximo curso dobles grados en Matemáticas con Ingeniería de Telecomunicaciones e Ingeniería Civil.
El diario Levante-EMV ha publicado un reportaje al respecto, «LAS MATEMÁTICAS SUMAN EN LOS CAMPUS» en el que me entrevistan sobre la puesta en marcha de los mismos y la orientación y salidas profesionales de estos títulos. Adjunto un link a la noticia publicada y el artículo publicado Las Matemáticas Suman en los Campus.
I am responsible of the UPV group participating in the Erasmus + project DaLiCo (Data Literacy in Context), jointly with Nacho Despujol and Carlos Turró. Our partners are: Hamburg University of Applied Sciences (HAW), University of Debrecren (ED), and the University of Applied Sciences of Utrecht (HU). We had the kick off meeting in November 7-8n 2019 in Hamburg.
Data Literacy (DL) is defined as the ability to collect, to manage also complex information, to evaluate and to apply data in a critical manner (Ridsdale 2015). This does also include smart use of digital resources. All students in advanced learning, irrespective of discipline, need to acquire this key competence that will allow them to thrive.
Our project, DaLiCo (Data Literacy in Context) will be focused on increasing the visibility, quality and usage of existing Data Literacy activities at the participating universities.
You can find a further description in https://albertoconejero.webs.upv.es/education/dalico/
I have taken part in the ICIAM conference held in València. I have been involved as a member of the local committee, and also as a coorganizer of a minisymposia on Dynamical systems with applications to science and engineering. I have also delivered a talk entitled «Dynamics of the data dissemination in 5G opportunistic networks», of a joint collaboration with the Grupo de Redes de Computadores (GRC) of the UPV.
I have also had the opportunity of publishing and outreach article on Mathematical Modelling in Energy Efficiency Problems, jointly with P. Fernández de Córdoba, in the Intelligencer delivered to all participants.