Yago Saez | Universidad Carlos III de Madrid (original) (raw)

Papers by Yago Saez

Lecture Notes in Computer Science, 2015

This paper introduces an approach based on Genetic Algorithms to learn levels from the Mario AI s... more This paper introduces an approach based on Genetic Algorithms to learn levels from the Mario AI simulator, based on the Infinite Mario Bros. game (which is, at the same time, based on the Super Mario World game from Nintendo). In this approach, an autonomous agent playing Mario is able to learn a sequence of actions in order to maximize the score, not looking at the current state of the game at each time. Different parameters for the Genetic Algorithm are explored, and two different stages are executed: in the first, domain independent genetic operators are used; while in the second knowledge about the domain is incorporated to these operators in order to improve the results. Results are encouraging, as Mario is able to complete very difficult levels full of enemies, resembling the behavior of an expert human player.

La generaci6n y distribuci6n de conocimiento dentro de un equipo requiere de un conjunto de m6tod... more La generaci6n y distribuci6n de conocimiento dentro de un equipo requiere de un conjunto de m6todos y t6micas para la motivaci6n y superaci6n de las personas. Se presents como gran reto superar el estado de conocirniento estancado, provocado 'por la reticencia en la comunicaci6n, la falta de t6cnicas apropiadas, el desconocimiento existente sobre estos ternas, y la dificil consecuci6n del flujo de capital intelectual dentro de una entidad. Partiendo de un estudio multidisciplinar desarrollado desde un punto de vista sociol6gico, psicol6gico y tecnol6gico, se establece que tomando como base un conjunto de tnicas y procedimientos vdlidos, y mediante la aplicaci6n de una herramienta de gesti6n de conocimiento, puede imponerse un flujo de conocimiento explicito que evolucione hacia un sistema de mejora continua basado en la calidad del conocimiento. Dicha calidad se obtiene a partir del motor de conocimiento, basado en un modelo de capas de conocimiento alimentado por algoritmos de ...

2017 IEEE Congress on Evolutionary Computation (CEC), 2017

Physical activity is widely known to be a key factor towards achieving a healthy life and reducin... more Physical activity is widely known to be a key factor towards achieving a healthy life and reducing the chance of developing certain diseases. However, there are many different physical activities having different effort requirements or having different benefits on health. The reason why automatic recognition of physical activity is useful is twofold: first, it raises personal awareness about the physical activity a user is carrying out and its impact on health, allowing some apps to give proper credit for it; second, it allows medical staff to monitor the activity levels of patients. In this paper, we follow a proven activity recognition chain to learn a classifier for physical activity recognition, which is trained using data from PAMAP2, a dataset publicly available in UCI ML repository. Once a machine learning dataset is created after signal preprocessing, segmentation and feature extraction, we will explore and compare different feature selection techniques using genetic algorithms in order to maximize the accuracy and reduce the number of dimensions. This reduction improves classification times and reduces costs and energy consumption of sensor devices. By doing so, we have reduced dimensions to almost a half and we have outperformed the best results found so far in literature with an average accuracy of 97.45%.

Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion - GECCO '16 Companion, 2016

2015 11th International Conference on Innovations in Information Technology (IIT), 2015

This work describes the development of a web recommender system implementing both collaborative f... more This work describes the development of a web recommender system implementing both collaborative filtering and content-based filtering. Moreover, it supports two different working modes, either sponsored or related, depending on whether websites are to be recommended based on a list of ongoing ad campaigns or in the user preferences. Novel recommendation algorithms are proposed and implemented , which fully rely on set operations such as union and intersection in order to compute the set of recommendations to be provided to end users. The recommender system is deployed over a real-time big data architecture designed to work with Apache Hadoop ecosystem, thus supporting horizontal scalability, and is able to provide recommendations as a service by means of a RESTful API. The performance of the recommender is measured, resulting in the system being able to provide dozens of recommendations in few milliseconds in a single-node cluster setup.

2015 International Conference on Intelligent Networking and Collaborative Systems, 2015

Medical literature have recognized physical activity as a key factor for a healthy life due to it... more Medical literature have recognized physical activity as a key factor for a healthy life due to its remarkable benefits. However, there is a great variety of physical activities and not all of them have the same effects on health nor require the same effort. As a result, and due to the ubiquity of commodity devices able to track users' motion, there is an increasing interest on performing activity recognition in order to detect the type of activity carried out by the subjects and being able to credit them for their effort, which has been detected as a key requirement to promote physical activity. This paper proposes a novel approach for performing activity recognition using Monte Carlo Schemata Search (MCSS) for feature selection and random forests for classification. To validate this approach we have carried out an evaluation over PAMAP2, a public dataset on physical activity available in UCI Machine Learning repository, enabling replication and assessment. The experiments are conducted using leave-onesubject-out cross validation and attain classification accuracies of over 93% by using roughly one third of the total set of features. Results are promising, as they outperform those obtained in other works on the same dataset and significantly reduce the set of features used, which could translate in a decrease of the number of sensors required to perform activity recognition and, as a result, a reduction of costs.

Procedia Computer Science, 2015

This paper explores an approach to physical rehabilitation using state-of-the-art technologies in... more This paper explores an approach to physical rehabilitation using state-of-the-art technologies in virtual reality and motion tracking; in particular, Oculus Rift DK2 (released in July, 2014) and Intel RealSense (released in November, 2014) are used. A game is developed which requires from the patient to perform an established set of abduction and adduction arm movements to achieve rotator cuff rehabilitation after injury. While conduct of clinical trials is outside the scope of this work, experts in physical rehabilitation working in the medical field have carried out a preliminary evaluation, showing encouraging results.

Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation, 2015

Procedia Engineering, 2012

The European Physical Journal C, 2000

A sample of 2.2 million hadronic Z decays, selected from the data recorded by the Delphi detector... more A sample of 2.2 million hadronic Z decays, selected from the data recorded by the Delphi detector at Lep during 1994-1995 was used for an improved measurement of inclusive distributions of π + , K + and p and their antiparticles in gluon and quark jets. The production spectra of the individual identified particles were found to be softer in gluon jets compared to quark jets, with a higher multiplicity in gluon jets as observed for inclusive charged particles. A significant proton enhancement in gluon jets is observed indicating that baryon production proceeds directly from colour objects. The maxima, ξ * , of the ξ-distributions for kaons in gluon and quark jets are observed to be different.

Expert Systems with Applications, 2019

This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

… , 27 y 28 de febrero y …, 2002

Información del artículo Aplicación de Sistemas de Recomendación a Entornos Virtuales.

Vaccines

Dendrimer peptides are promising vaccine candidates against the foot-and-mouth disease virus (FMD... more Dendrimer peptides are promising vaccine candidates against the foot-and-mouth disease virus (FMDV). Several B-cell epitope (B2T) dendrimers, harboring a major FMDV antigenic B-cell site in VP1 protein, are covalently linked to heterotypic T-cell epitopes from 3A and/or 3D proteins, and elicited consistent levels of neutralizing antibodies and IFN-γ-producing cells in pigs. To address the contribution of the highly polymorphic nature of the porcine MHC (SLA, swine leukocyte antigen) on the immunogenicity of B2T dendrimers, low-resolution (Lr) haplotyping was performed. We looked for possible correlations between particular Lr haplotypes with neutralizing antibody and T-cell responses induced by B2T peptides. In this study, 63 pigs immunized with B2T dendrimers and 10 non-immunized (control) animals are analyzed. The results reveal a robust significant correlation between SLA class-II Lr haplotypes and the T-cell response. Similar correlations of T-cell response with SLA class-I Lr h...

Vaccines, 2020

ArXiv, 2009

We propose a new scheme of attack on the Microsoft's ASIRRA CAPTCHA which represents a signif... more We propose a new scheme of attack on the Microsoft's ASIRRA CAPTCHA which represents a significant shortcut to the intended attacking path, as it is not based in any advance in the state of the art on the field of image recognition. After studying the ASIRRA Public Corpus, we conclude that the security margin as stated by their authors seems to be quite optimistic. Then, we analyze which of the studied parameters for the image files seems to disclose the most valuable information for helping in correct classification, arriving at a surprising discovery. This represents a completely new approach to breaking CAPTCHAs that can be applied to many of the currently proposed image-labeling algorithms, and to prove this point we show how to use the very same approach against the HumanAuth CAPTCHA. Lastly, we investigate some measures that could be used to secure the ASIRRA and HumanAuth schemes, but conclude no easy solutions are at hand.

Brad Alexander Juan Herrero Justyna Petke Shaukat Ali Malcolm Heywood Stjepan Picek Andrea Arcuri... more Brad Alexander Juan Herrero Justyna Petke Shaukat Ali Malcolm Heywood Stjepan Picek Andrea Arcuri Cezary Z. Janikow Nelishia Pillay Ignacio Arnaldo Colin Johnson John Robinson R. Muhammad Atif Azad Anna Jordanous Patricia Ryser-Welch Dylan Banarse Paul Kaufmann Yago Saez Amit Benbassat Edward Keedwell Ivan Sekaj Peter Bentley Krzysztof Krawiec Kisung Seo Michal Bidlo Pavel Kromer Sara Silva Stefano Cagnoni Stuart Lacy Kevin Sim Jeffrey Chan William Langdon James Smith Francis Chicano Xianneng Li Andy Song Vic Ciesielski Luca Manzoni Giovanni Squillero German Creamer James McDermott Kenneth Stanley Márjory Da Costa-Abreu Yi Mei Thomas Stutzle Roland Dobai Maizura Mokhtar Petr Svenda Alan Dorin Kourosh Neshatian Jerry Swan Liang Gao Su Nguyen Marcin Szubert Oscar Garnica Trung Thanh Nguyen Gianluca Tempesti Mario Giacobini Randy Olson Hsing-Chih Tsai

Applied Sciences

This paper summarizes the top state-of-the-art contributions reported on the MNIST dataset for ha... more This paper summarizes the top state-of-the-art contributions reported on the MNIST dataset for handwritten digit recognition. This dataset has been extensively used to validate novel techniques in computer vision, and in recent years, many authors have explored the performance of convolutional neural networks (CNNs) and other deep learning techniques over this dataset. To the best of our knowledge, this paper is the first exhaustive and updated review of this dataset; there are some online rankings, but they are outdated, and most published papers survey only closely related works, omitting most of the literature. This paper makes a distinction between those works using some kind of data augmentation and works using the original dataset out-of-the-box. Also, works using CNNs are reported separately; as they are becoming the state-of-the-art approach for solving this problem. Nowadays, a significant amount of works have attained a test error rate smaller than 1% on this dataset; whic...