I am a passionate researcher focused on applying artificial intelligence to real-world applications. My applications extract hidden knowledge from large datasets in applications like energy efficiency and cyber-crime. I also teach at the university about operating systems, graphic design… Sometimes, I work on some fun projects like kaggle competitions, etc.
UCL was rated 2nd in the UK for research power in the Research Excellence Framework 2021. UCL is ranked 8th in the 2022 QS World University Rankings. There have been 30 Nobel Prize laureates amongst UCL’s alumni and current and former staff to date.
Mar 2013 - Dic 2021, Granada, Spain
The University of Granada is a world top university in data science and computer science.
Sep 2020 - Dic 2021
Mar 2019 - May 2021
Nov 2019 - Mar 2019
Dic 2017 - Nov 2019
Mar 2015 - Nov 2015
Oct 2013 - Jun 2014
Mar 2013 - Aug 2013
International outbound and inbound parcel processing efficiency increased using Machine Learning.
Oct 2017 - Jan 2018, London
Ranked 9th in the world in the QS World University Rankings 2020.
Sep 2018 - Jan 2018
Oct 2017 - Jan 2018
Dic 2020 - Present, Online
The International University of La Rioja is a private Spanish online education university, with headquarters in Logroño and presence in Mexico, Colombia, Ecuador and Peru. In mid-2020 it had more than 48,000 students in official studies, of which more than 17,000 are international.
2016-2020 Ph.D in Computer ScienceScore: 10 summa cum laude out of 10Publications
| |||||||||||
2016-2016 Executive Program in Big Data & Business AnalyticsCGPA: 4 out of 4PublicationsTaken Courses
| |||||||||||
2015-2016 Master in Big Data and Data ScienceCGPA: 3.5 out of 4PublicationsTaken Courses
Extracurricular Activities
| |||||||||||
2015-2015 Programa de Creación de Empresas de Base Tecnólogicascore: 10 out of 10 | |||||||||||
2009-2015 B.Sc. in Computer Science & EngineeringCGPA: 7.4 out of 10Taken Courses
Extracurricular Activities
|
The COPKIT project focuses on the problem of analysing, investigating, mitigating and preventing the use of new information and communication technologies by organised crime and terrorist groups. For this purpose, COPKIT proposes an intelligence-led Early Warning (EW) / Early Action (EA) system for both strategic and operational levels.
DetailsThe aim of the project is to develop a Smart Energy Simulation Based Control method which will reduce the energy consumption in the operational stage of existing non-residential buildings, resulting in energy savings of up to 20%.
DetailsData analysis in medicine: from medical records to Big Data.
Deep Learning for Energy-Efficient Building Control PROFICIENT developing novel deep reinforcement learning techniques capable of: (1) learning a more efficient predictive model of the building from sensor data; and (2) optimizing the computation of operational plans without using heuristic knowledge.
DetailsApplication of data mining and artificial intelligence techniques to sensorised buildings to improve maintenance and energy efficiency.
In this paper we have addressed the extraction of hidden knowledge from medical records using data mining techniques such as association rules in conjunction with fuzzy logic in a distributed environment. A significant challenge in this domain is that although there are a lot of studies devoted to analysing health data, very few focus on the understanding and interpretability of the data and the hidden patterns present within the data. A major challenge in this area is that many health data analysis studies have focussed on classification, prediction or knowledge extraction and end users find little interpretability or understanding of the results. This is due to the use of black-box algorithms or because the nature of the data is not represented correctly. This is why it is necessary to focus the analysis not only on knowledge extraction but also on the transformation and processing of the data to improve the modelling of the nature of the data. Techniques such as association rule mining and fuzzy logic help to improve the interpretability of the data and treat it with the inherent uncertainty of real-world data. To this end, we propose a system that automatically a) pre-processes the database by transforming and adapting the data for the data mining process and enriching the data to generate more interesting patterns, b) performs the fuzzification of the medical database to represent and analyse real-world medical data with its inherent uncertainty, c) discovers interrelations and patterns amongst different features (diagnostic, hospital discharge, etc.), and d) visualizes the obtained results efficiently to facilitate the analysis and improve the interpretability of the information extracted. Our proposed system yields a significant increase in the compression and interpretability of medical data for end-users, allowing them to analyse the data correctly and make the right decisions. We present one practical case using two health-related datasets to demonstrate the feasibility of our proposal for real data.
DetailsThe enormous quantity of data handled by Building management systems are key to develop more efficient energy operational systems. However, the inability of current systems to take benefit from the generated data may waste good opportunities of improving building performance. Big Data appears as a suitable framework to sustain the management system and conduct future prospective analysis. In this work we present a Big Data based architecture for the efficient management of buildings. The different Big Data components are involved not only in the data acquisition phase, but also in the implementation of algorithms capable of analysing massive data collected from very heterogeneous sources. They also enable fast computations that can help the generation of optimal operational plan generations to improve the building functioning. The proposed architecture has been effectively introduced in four different-purpose buildings, demonstrating that Big Data can help during the energy cycle of the building.
DetailsThe high computational impact when mining fuzzy association rules grows significantly when managing very large data sets, triggering in many cases a memory overflow error and leading to the experiment failure without its conclusion. It is in these cases when the application of Big Data techniques can help to achieve the experiment completion. Therefore, in this paper several Spark algorithms are proposed to handle with massive fuzzy data and discover interesting association rules. For that, we based on a decomposition of interestingness measures in terms of α-cuts, and we experimentally demonstrate that it is sufficient to consider only 10 equidistributed α-cuts in order to mine all significant fuzzy association rules. Additionally, all the proposals are compared and analysed in terms of efficiency and speed up, in several datasets, including a real dataset comprised of sensor measurements from an office building.
DetailsThe discovery and exploitation of hidden information in collected data have gained attention in many areas, particularly in the energy field due to their economic and environmental impact. Data mining techniques have then emerged as a suitable toolbox for analyzing the data collected in modern network management systems in order to obtain a meaningful insight into consumption patterns and equipment operation. However, the enormous amount of data generated by sensors, occupational, and meteorological data involve the use of new management systems and data processing. Big Data presents great opportunities for implementing new solutions to manage these massive data sets. In addition, these data present values whose nature complicates and hides the understanding and interpretation of the data and results. Therefore, the use of fuzzy methods to adequately transform the data can improve their interpretability. This article presents an automatic fuzzification method implemented using the Big Data paradigm, which enables, in a later step, the detection of interrelations and patterns among different sensors and weather data recovered from an office building.
DetailsThe amount of information generated in social media channels or economical/business transactions exceeds the usual bounds of static databases and is in continuous growing. In this work, we propose a frequent itemset mining method using sliding windows capable of extracting tendencies from continuous data flows. For that aim, we develop this method using Big Data technologies, in particular, using the Spark Streaming framework enabling distributing the computation along several clusters and thus improving the algorithm speed. The experimentation carried out shows the capability of our proposal and its scalability when massive amounts of data coming from streams are taken into account.
DetailsDespite the increasing capabilities of information technologies for data acquisition and processing, building energy management systems still require manual configuration and supervision to achieve optimal performance. Model predictive control (MPC) aims to leverage equipment control-particularly heating, ventilation, and air conditioning (HVAC)-by using a model of the building to capture its dynamic characteristics and to predict its response to alternative control scenarios. Usually, MPC approaches are based on simplified linear models, which support faster computation but also present some limitations regarding interpretability, solution diversification, and longer-term optimization. In this paper, we propose a novel MPC algorithm that uses a full-complexity grey-box simulation model to optimize HVAC operation in non-residential buildings. Our system generates hundreds of candidate operation plans, typically …
Details