https://joseangelmartin.com/en/tags/news/NewsHugoBlox Kit (https://hugoblox.com)en-usMon, 30 Sep 2024 00:00:00 +0000https://joseangelmartin.com/media/icon_hu_e1d52914376ca381.pnghttps://joseangelmartin.com/en/tags/news/https://joseangelmartin.com/en/post/2024-09-premio-abertis/Mon, 30 Sep 2024 00:00:00 +0000https://joseangelmartin.com/en/post/2024-09-premio-abertis/<p>The Abertis Foundation recognised on 30th September 2024 the best works in the field of transport infrastructure management and road safety in the XXI edition of the Abertis Awards for sustainable mobility. In the doctoral thesis category, the jury awarded the first prize to José Ángel Martín Baos, for his doctoral thesis titled “Machine learning methods applied to transport demand modelling”. This work focuses on the application of advanced machine learning (ML) techniques to optimise transport demand modelling, a crucial aspect for enhancing sustainable mobility and the planning and management of transport infrastructures.</p> <p>The award, which highlights innovation in transport and road safety research, emphasises the approach taken in this doctoral thesis, demonstrating how machine learning models, such as neural networks, can outperform traditional random utility models (RUM) in predicting transport demand. These models are fundamental in assessing the social and economic impact of new infrastructures and promoting transport policies that drive sustainability.</p> <p>In my thesis, I also address a significant limitation of ML models: the difficulty in generating reliable econometric indicators, which are essential for infrastructure planning. To address this, I proposed a reinterpretation of a model called Kernel Logistic Regression (KLR), which combines the advantages of RUM with machine learning techniques, achieving more accurate predictions without losing the ability to derive these indicators.</p> <p>The award ceremony took place at the headquarters of Vocento in Madrid, at the conclusion of the ABC Forum on Sustainable Economy, with the participation of prominent figures in the sector. The awards were presented by Elena Salgado, President of the Abertis Foundation; José Manuel Vassallo, Director of the Abertis-UPM Chair; José Miguel Atienza, Director of the School of Civil Engineering at UPM; and Georgina Flamme, Director of Institutional Relations, Communication and Sustainability of Abertis and the Abertis Foundation.</p> <p>I shared this recognition with two other outstanding researchers: Tasneem Falah Mohammad Miqdady from the University of Granada, and Javier Caimari Tur from the Polytechnic University of Catalonia. The awardees received a financial grant as well as a sculpture, symbolising the Abertis Foundation&rsquo;s commitment to research and the development of sustainable mobility solutions.</p> <h2 id="related-news">Related news</h2> <ul> <li> </li> <li> </li> </ul> <h2 id="photo-gallery">Photo gallery</h2> <div class="post-gallery"> <img src="https://joseangelmartin.com/uploads/posts/2024-09-premio-abertis/PremioAbertis1.jpeg" alt="Abertis Awards ceremony in Madrid" loading="lazy"> <img src="https://joseangelmartin.com/uploads/posts/2024-09-premio-abertis/PremioAbertis3.jpeg" alt="José Ángel Martín Baos receiving the Abertis Award" loading="lazy"> <img src="https://joseangelmartin.com/uploads/posts/2024-09-premio-abertis/PremioAbertis2.jpeg" alt="Recipients and organisers of the XXI Abertis Awards" loading="lazy"> <img src="https://joseangelmartin.com/uploads/posts/2024-09-premio-abertis/PremioAbertis4.jpeg" alt="Abertis Award for sustainable mobility" loading="lazy"> </div>https://joseangelmartin.com/en/post/2024-01-needs-talk/Tue, 09 Jan 2024 00:00:00 +0000https://joseangelmartin.com/en/post/2024-01-needs-talk/<p>I am excited to announce that on March 4, at 16:30 CET, I will be taking part in the Online Seminar Series Machine Learning NeEDS Mathematical Optimization, hosted by Emilio Carrizosa, Dolores Romero Morales, and Nuria Gómez Vargas. During this session, I will be presenting &ldquo;Can machine learning methods effectively model travel mode choice? Beyond predictive performance&rdquo;. This presentation is the result of a collaborative effort alongside Ricardo García Ródenas, Luis Rodríguez Benítez, Julio Alberto López Gómez, and Tim Hillel. .</p> <p> .</p> <h3 id="about-the-seminar-series">About the seminar series</h3> <p>Machine Learning NeEDS Mathematical Optimization is an online seminar series, organized by Emilio Carrizosa (IMUS – Instituto de Matemáticas de la Universidad de Sevilla) and Dolores Romero Morales (CBS – Copenhagen Business School) with the collaboration of PhD Students Nuria Gómez-Vargas (IMUS) and Thomas Halskov (CBS). One of the goals of this activity is to brand the role of Operations Research in Artificial Intelligence with the support of EURO.</p> <p>This series includes a number of presentations from leading academics in the field of Data Science and Analytics that will cover important topics such as explainability, fairness, fraud, privacy, etc. Mathematical Modeling and Mathematical Optimization will be at the core of their presentations. We also have the YOUNG Online Seminar Series “Machine Learning NeEDS Mathematical Optimization”. In each YOUNG session, three junior academics will show their latest results in this burgeoning area.</p> <p>The format is a weekly session that takes place every Monday, at 16.30 (CET), and has been active since January 11, 2021. It is 100% online-access, and it has speakers from around the globe. The Online Seminar Series is free thanks to the funding the EU gives to our H2020 MSCA NeEDS project, as well as the support given by Universidad de Sevilla (US) and Copenhagen Business School (CBS). This support is gratefully acknowledged.</p>https://joseangelmartin.com/en/post/2023-07-phd/Mon, 10 Jul 2023 00:00:00 +0000https://joseangelmartin.com/en/post/2023-07-phd/<p>On Friday, July 7, 2023, I successfully defended my doctoral thesis titled &lsquo;Machine learning methods applied to transport demand modelling,&rsquo; under the supervision of Professors Ricardo García Ródenas and Luis Rodríguez Benítez. The doctoral thesis, which has received the distinction of international mention, has been evaluated by the committee with the highest grade, receiving a unanimous decision of summa cum laude.</p> <h2 id="photo-gallery">Photo gallery</h2> <div class="post-gallery"> <img src="https://joseangelmartin.com/uploads/posts/2023-07-phd/tesis_josea2.jpg" alt="José Ángel Martín Baos during his PhD defence" loading="lazy"> <img src="https://joseangelmartin.com/uploads/posts/2023-07-phd/tesis_josea3.jpg" alt="Cover of the doctoral thesis" loading="lazy"> </div> <h2 id="abstract">Abstract</h2> <p>Transport demand modelling plays a critical role in transportation planning, enabling the accurate prediction of future transport demand and the evaluation of transport policies and infrastructure plans. However, as transport systems become increasingly complex and recent advances in technology result in massive data collection, traditional analytical methods like Random Utility Models (RUMs) are no longer sufficient to manage this complexity. Therefore, it is necessary to incorporate new techniques to overcome this limitation. This thesis investigates the potential of Machine Learning (ML) methods in this context.</p> <p>Firstly, it is analysed whether state-of-the-art ML models such as artificial neural networks, support vector machines, and ensemble methods like random forests or gradient boosting decision trees, are superior to RUMs in this research field. To achieve this, the models are compared considering as differential criteria the predictive performance and the ability to derive indicators of decision-makers’ behaviour, always in the context of transport demand modelling.</p> <p>The results show that classical techniques are outperformed by ML models, but also show that the latter have difficulties in generating reliable econometric indicators. For this reason, a ML model called Kernel Logistic Regression (KLR) is proposed as an alternative to model the utility functions of RUMs, enabling the derivation of econometric indicators. The experiments conducted demonstrate that KLR provides good results on real-world datasets used in previous comparisons in the literature, while providing unbiased estimates of behavioural indicators.</p> <p>Additionally, it is proposed to extend the application of KLR to a wider range of ML problems by means of an extension of the KLR models called Generalized Kernel Logistic Regression (GKLR). For instance, the GKLR theory has led to the derivation of a novel model called Nested Kernel Logistic Regression (NKLR), which enables the application of KLR to datasets with hierarchically structured data.</p> <p>Finally, this thesis addresses one of the main limitations of the KLR method, which is the high computational and spatial complexity in large-scale problems. To overcome this limitation, it is suggested the use of the Nyström technique and the implementation of accelerated versions of line search training methods. The results demonstrate that by incorporating these techniques, KLR can efficiently tackle large-scale problems involving hundreds of thousands of data points.</p> <h2 id="news">News</h2> <ul> <li> </li> </ul>https://joseangelmartin.com/en/post/2020-04-webpage-covid-19/Thu, 16 Apr 2020 00:00:00 +0000https://joseangelmartin.com/en/post/2020-04-webpage-covid-19/<p>The Models and Algorithms for Transport Systems (MAT) group from the University of Castilla-La Mancha (UCLM), to which I belong, has developed a web page for the monitoring, and visualization of the COVID-19 disease. This site, through the use of mathematical techniques, as well as data analysis and artificial intelligence, analyzes the evolution and expansion of the coronavirus with the aim of providing information to monitor the progress of the pandemic. These analytical techniques, according to the group led by UCLM Mathematics Department professor Ricardo Garcia Ródenas, &ldquo;allow to support decision making processes&rdquo;.</p> <p>The website is available at .</p> <p>For each country, it is possible to view the total number of cases, the active cases, deaths and recoveries. The data for each country is updated daily and has been obtained from a public repository. In addition, for each of the countries, a one-week view forecast of the number of new cases, recoveries and deaths is provided.</p> <p>Similarly, the website shows the evolution of the virus at the level of the Autonomous Communities in Spain. The data of each one of the communities is daily obtained from the database provided by the Instituto de Salud Carlos III de Madrid, whose data is used by the Spanish Health Ministry. Thus, for each of the Autonomous Communities, the number of total cases, active cases, deaths and recoveries is reported, as well as the number of patients hospitalised or critical (in the ICU). In addition, it is possible to view a one-week view forecast of the number of new cases, recoveries and deaths for each autonomous community.</p> <p>Finally, the website shows the evolution of the COVID-19 infection rate over time for each country and for all the autonomous communities of Spain, together with a prediction at one week&rsquo;s time. I is also possible to compare the rate with an equilibrium point that allows to clarify if a country or a certain autonomous community is in an expansion or contraction phase of the epidemic. The aim is to monitor the state of the epidemic and provide information and knowledge to authorities who are working hard on a daily basis to reduce its effects.</p>https://joseangelmartin.com/en/post/2019-06-sysorm-19/Fri, 07 Jun 2019 00:00:00 +0000https://joseangelmartin.com/en/post/2019-06-sysorm-19/<p>This week I have attended the 2nd Spanish Young Statisticians and Operational Researchers Meeting (SYSORM) where I have presented a platform for monitoring air pollution an road traffic in cities.</p> <p>This meeting has taken place in El Escorial from 5th-7th of June 2019. The meeting, promoted by the Spanish Society of Statistics and Operations Research (SEIO), is organised for and by young researchers (young: with less than three years of postdoctoral experience). The scope of the meeting is to represent and give visibility to the newer generations of talented researchers in statistics and operational research, ranging from methodological to applied research topics, and to foster professional communication between them.</p> <blockquote class="twitter-tweet" data-lang="es"><p lang="ro" dir="ltr">José Ángel Martín talking about a platform for monitoring air pollution and road traffic in cities <a href="https://twitter.com/hashtag/sysorm2019?src=hash&amp;ref_src=twsrc%5Etfw">#sysorm2019</a> <a href="https://t.co/8Lra0As68B">pic.twitter.com/8Lra0As68B</a></p>&mdash; SYSORM2019 (@sysorm2019) <a href="https://twitter.com/sysorm2019/status/1136279081127948288?ref_src=twsrc%5Etfw">5 de junio de 2019</a></blockquote> <script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>