Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Fernando Fernández is active.

Publication


Featured researches published by Fernando Fernández.


Human Molecular Genetics | 2012

Predominance of pathogenic missense variants in the RAD51C gene occurring in breast and ovarian cancer families

Ana Osorio; Daniela Endt; Fernando Fernández; Katharina Eirich; Miguel de la Hoya; Rita K. Schmutzler; Trinidad Caldés; Alfons Meindl; Detlev Schindler; Javier Benitez

RAD51C was defined by Meindl et al. in 2010 as a high-risk gene involved in hereditary breast and ovarian cancers. Although this role seems to be clear, nowadays there is controversy about the indication of including the gene in routine clinical genetic testing, due to the lower prevalence or the absence of mutations found in subsequent studies. Here, we present the results of a comprehensive mutational screening of the RAD51C gene in a large series of 785 Spanish breast and/or ovarian cancer families, which, in contrast to the various subsequent studies published to date, includes the functional characterization of suspicious missense variants as reported in the initial study. We have detected 1.3% mutations of RAD51C in breast and ovarian cancer families, while mutations in breast cancer only families seem to be very rare. More than half of the deleterious variants detected were of missense type, which highlights their significance in the gene, and suggest that RAD51C mutations may have been so far partially disregarded and their prevalence underestimated due to the lack of functional complementation assays. Our results provide new evidences, suggesting that the genetic testing of RAD51C should be considered for inclusion into the clinical setting, at least for breast and ovarian cancer families, and encourage re-evaluating its role incorporating functional assays.


IEEE Transactions on Neural Networks | 2008

Local Feature Weighting in Nearest Prototype Classification

Fernando Fernández; Pedro Isasi

The distance metric is the corner stone of nearest neighbor (NN)-based methods, and therefore, of nearest prototype (NP) algorithms. That is because they classify depending on the similarity of the data. When the data is characterized by a set of features which may contribute to the classification task in different levels, feature weighting or selection is required, sometimes in a local sense. However, local weighting is typically restricted to NN approaches. In this paper, we introduce local feature weighting (LFW) in NP classification. LFW provides each prototype its own weight vector, opposite to typical global weighting methods found in the NP literature, where all the prototypes share the same one. Providing each prototype its own weight vector has a novel effect in the borders of the Voronoi regions generated: They become nonlinear. We have integrated LFW with a previously developed evolutionary nearest prototype classifier (ENPC). The experiments performed both in artificial and real data sets demonstrate that the resulting algorithm that we call LFW in nearest prototype classification (LFW-NPC) avoids overfitting on training data in domains where the features may have different contribution to the classification task in different areas of the feature space. This generalization capability is also reflected in automatically obtaining an accurate and reduced set of prototypes.


Carcinogenesis | 2009

Mutational analysis of FANCL, FANCM and the recently identified FANCI suggests that among the 13 known Fanconi Anemia genes, only FANCD1/BRCA2 plays a major role in high-risk breast cancer predisposition

María J. García; Victoria Fernández; Ana Osorio; Alicia Barroso; Fernando Fernández; Miguel Urioste; Javier Benitez

Fanconi Anemia (FA) is a rare recessive syndrome characterized by cellular hypersensitivity to DNA-cross-linking agents. To date, 13 FA complementation groups have been described and all 13 genes associated to each of these groups have been currently identified. Three of the known FA genes are also high-risk (FANCD1/BRCA2) or moderate-risk (FANCN/PALB2 and FANCJ/BRIP1) breast cancer susceptibility genes, which makes all members of the FA pathway particularly attractive breast cancer candidate genes. Most FA genes have been screened for mutations in breast cancer families negative for BRCA1/2 mutations but the role of FANCL, FANCM and the recently identified FANCI has not been evaluated to date. This fact and novel data sustaining greater functional relevance of the three genes within the FA pathway prompted us to scrutinize all coding sequences and splicing sites of FANCI, FANCL and FANCM in 95 BRCA1/2-negative index cases from Spanish high-risk breast cancer families. We identified 68 sequence variants of which 24 were coding and 44 non-coding. Six exonic and 26 non-coding variants had not been described previously. None of the coding changes caused clearly pathogenic changes and computational analysis of all non-described intronic variants did not revealed major impact in splicing. With the present study, all known FA genes have been evaluated within the context of breast cancer high-risk predisposition. Our results rule out a major role of FANCI, FANCL and FANCM in familial breast cancer susceptibility, suggesting that among the 13 known FA genes, only FANCD1/BRCA2 plays a major role in high-risk breast cancer predisposition.


Knowledge Based Systems | 2009

Reinforcement learning of pedagogical policies in adaptive and intelligent educational systems

Ana Iglesias; Paloma Martínez; Ricardo Aler; Fernando Fernández

In an adaptive and intelligent educational system (AIES), the process of learning pedagogical policies according the students needs fits as a Reinforcement Learning (RL) problem. Previous works have demonstrated that a great amount of experience is needed in order for the system to learn to teach properly, so applying RL to the AIES from scratch is unfeasible. Other works have previously demonstrated in a theoretical way that seeding the AIES with an initial value function learned with simulated students reduce the experience required to learn an accurate pedagogical policy. In this paper we present empirical results demonstrating that a value function learned with simulated students can provide the AIES with a very accurate initial pedagogical policy. The evaluation is based on the interaction of more than 70 Computer Science undergraduate students, and demonstrates that an efficient and useful guide through the contents of the educational system is obtained.


Simulation Modelling Practice and Theory | 2014

MARL-Ped: a Multi-Agent Reinforcement Learning Based Framework to Simulate Pedestrian Groups

Francisco Martinez-Gil; Miguel Lozano; Fernando Fernández

Abstract Pedestrian simulation is complex because there are different levels of behavior modeling. At the lowest level, local interactions between agents occur; at the middle level, strategic and tactical behaviors appear like overtakings or route choices; and at the highest level path-planning is necessary. The agent-based pedestrian simulators either focus on a specific level (mainly in the lower one) or define strategies like the layered architectures to independently manage the different behavioral levels. In our Multi-Agent Reinforcement-Learning-based Pedestrian simulation framework (MARL-Ped) the situation is addressed as a whole. Each embodied agent uses a model-free Reinforcement Learning (RL) algorithm to learn autonomously to navigate in the virtual environment. The main goal of this work is to demonstrate empirically that MARL-Ped generates learned behaviors adapted to the level required by the pedestrian scenario. Three different experiments, described in the pedestrian modeling literature, are presented to test our approach: (i) election of the shortest path vs. quickest path; (ii) a crossing between two groups of pedestrians walking in opposite directions inside a narrow corridor; (iii) two agents that move in opposite directions inside a maze. The results show that MARL-Ped solves the different problems, learning individual behaviors with characteristics of pedestrians (local control that produces adequate fundamental diagrams, route-choice capability, emergence of collective behaviors and path-planning). Besides, we compared our model with that of Helbing’s social forces, a well-known model of pedestrians, showing similarities between the pedestrian dynamics generated by both approaches. These results demonstrate empirically that MARL-Ped generates variate plausible behaviors, producing human-like macroscopic pedestrian flow.


Journal of Medical Genetics | 2011

The rs12975333 variant in the miR-125a and breast cancer risk in Germany, Italy, Australia and Spain

Paolo Peterlongo; Laura Caleca; Elisa Cattaneo; Fernando Ravagnani; Tiziana Bianchi; Laura Galastri; Loris Bernard; Filomena Ficarazzi; Valentina Dall'Olio; Frederik Marme; Anne Langheinz; Christoph Sohn; Barbara Burwinkel; Graham G. Giles; Laura Baglietto; Gianluca Severi; Fabrice Odefrey; Melissa C. Southey; Ana Osorio; Fernando Fernández; María R. Alonso; Javier Benitez; Monica Barile; Bernard Peissel; Siranoush Manoukian; Paolo Radice

The rare variant rs12975333 is a G→T change located at the eighth nucleotide of the mature microRNA-125a (miR-125a). The T allele has been reported to block the processing of pri-miRNA to pre-miRNA precursor and to be extremely rare, being detected only once in a panel of 1200 individuals from diverse ethnic backgrounds assessed by the Centre dEtude du Polymorphisme Humain.1 A study by Li et al 2 showed the T allele of rs12975333 to be strongly associated with breast cancer risk, with 6 of 72 (8.3%) breast cancer cases from two hospitals in Antwerp, Belgium, being carriers of the T allele and none of 282 controls collected from the general population in the Antwerp area or 587 Caucasian controls collected in the USA.2 The breast cancers were all lymph node negative and received only local treatment (mastectomy or lumpectomy followed by radiation treatment). Genotyping was performed by means of the TaqMan assay, as previously described,1 using whole-genome-amplified DNA obtained from …


Autonomous Agents and Multi-Agent Systems | 2015

Strategies for simulating pedestrian navigation with multiple reinforcement learning agents

Francisco Martinez-Gil; Miguel Lozano; Fernando Fernández

In this paper, a new multi-agent reinforcement learning approach is introduced for the simulation of pedestrian groups. Unlike other solutions, where the behaviors of the pedestrians are coded in the system, in our approach the agents learn by interacting with the environment. The embodied agents must learn to control their velocity, avoiding obstacles and the other pedestrians, to reach a goal inside the scenario. The main contribution of this paper is to propose this new methodology that uses different iterative learning strategies, combining a vector quantization (state space generalization) with the Q-learning algorithm (VQQL). Two algorithmic schemas, Iterative VQQL and Incremental, which differ in the way of addressing the problems, have been designed and used with and without transfer of knowledge. These algorithms are tested and compared with the VQQL algorithm as a baseline in two scenarios where agents need to solve well-known problems in pedestrian modeling. In the first, agents in a closed room need to reach the unique exit producing and solving a bottleneck. In in the second, two groups of agents inside a corridor need to reach their goal that is placed in opposite sides (they need to solve the crossing). In the first scenario, we focus on scalability, use metrics from the pedestrian modeling field, and compare with the Helbing’s social force model. The emergence of collective behaviors, that is, the shell-shaped clogging in front of the exit in the first scenario, and the lane formation as a solution to the problem of the crossing, have been obtained and analyzed. The results demonstrate that the proposed schemas find policies that carry out the tasks, suggesting that they are applicable and generalizable to the simulation of pedestrians groups.


motion in games | 2012

Calibrating a Motion Model Based on Reinforcement Learning for Pedestrian Simulation

Francisco Martinez-Gil; Miguel Lozano; Fernando Fernández

In this paper, the calibration of a framework based in Multi-agent Reinforcement Learning (RL) for generating motion simulations of pedestrian groups is presented. The framework sets a group of autonomous embodied agents that learn to control individually its instant velocity vector in scenarios with collisions and friction forces. The result of the process is a different learned motion controller for each agent. The calibration of both, the physical properties involved in the motion of our embodied agents and the corresponding dynamics, is an important issue for a realistic simulation. The physics engine used has been calibrated with values taken from real pedestrian dynamics. Two experiments have been carried out for testing this approach. The results of the experiments are compared with databases of real pedestrians in similar scenarios. As a comparison tool, the diagram of speed versus density, known as fundamental diagram in the literature, is used.


algorithmic learning theory | 2004

Learning Content Sequencing in an Educational Environment According to Student Needs

Ana Iglesias; Paloma Martínez; Ricardo Aler; Fernando Fernández

One of the most important issues in educational systems is to define effective teaching policies according to the students learning characteristics. This paper proposes to use the Reinforcement Learning (RL) model in order for the system to learn automatically sequence of contents to be shown to the student, based only in interactions with other students, like human tutors do. An initial clustering of the students according to their learning characteristics is proposed in order the system adapts better to each student. Experiments show convergence to optimal teaching tactics for different clusters of simulated students, concluding that the convergence is faster when the system tactics have been previously initialised.


Simulation Modelling Practice and Theory | 2017

Emergent behaviors and scalability for multi-agent reinforcement learning-based pedestrian models

Francisco Martinez-Gil; Miguel Lozano; Fernando Fernández

Abstract This paper analyzes the emergent behaviors of pedestrian groups that learn through the multiagent reinforcement learning model developed in our group. Five scenarios studied in the pedestrian model literature, and with different levels of complexity, were simulated in order to analyze the robustness and the scalability of the model. Firstly, a reduced group of agents must learn by interaction with the environment in each scenario. In this phase, each agent learns its own kinematic controller, that will drive it at a simulation time. Secondly, the number of simulated agents is increased, in each scenario where agents have previously learnt, to test the appearance of emergent macroscopic behaviors without additional learning. This strategy allows us to evaluate the robustness and the consistency and quality of the learned behaviors. For this purpose several tools from pedestrian dynamics, such as fundamental diagrams and density maps, are used. The results reveal that the developed model is capable of simulating human-like micro and macro pedestrian behaviors for the simulation scenarios studied, including those where the number of pedestrians has been scaled by one order of magnitude with respect to the situation learned.

Collaboration


Dive into the Fernando Fernández's collaboration.

Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Ana Osorio

Instituto de Salud Carlos III

View shared research outputs
Top Co-Authors

Avatar

Javier Benitez

Instituto de Salud Carlos III

View shared research outputs
Top Co-Authors

Avatar

Ana Martínez

University of Santiago de Compostela

View shared research outputs
Top Co-Authors

Avatar

Ana Villegas Martínez

Complutense University of Madrid

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Cristina Fernández

Complutense University of Madrid

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Researchain Logo
Decentralizing Knowledge