Raúl Lara-Cabrera

Measuring the Radicalisation Risk in Social Networks

Social networks (SNs) have become a powerful tool for the jihadism as they serve as recruitment assets, live forums, psychological warfare, as well as sharing platforms. SNs enable vulnerable individuals to reach radicalized people, hence triggering their own radicalization process. There are many vulnerability factors linked to socio-economic and demographic conditions that make jihadist militants suitable targets for their radicalization. We focus on these vulnerability factors, studying, understanding, and identifying them on the Internet. Here, we present a set of radicalization indicators and a model to assess them using a data set of tweets published by several Islamic State of Iraq and Sham sympathizers. Results show that there is a strong correlation between the values assigned by the model to the indicators.

EvoDeep: A new evolutionary approach for automatic Deep Neural Networks parametrisation

Abstract Deep Neural Networks (DNN) have become a powerful, and extremely popular mechanism, which has been widely used to solve problems of varied complexity, due to their ability to make models fitted to non-linear complex problems. Despite its well-known benefits, DNNs are complex learning models whose parametrisationand architecture are made usually by hand. This paper proposes a new Evolutionary Algorithm, named EvoDeep, devoted to evolve the parameters and the architecture of a DNN in order to maximise its classification accuracy, as well as maintaining a valid sequence of layers. This model is tested against a widely used dataset of handwritten digits images. The experiments performed using this dataset show that the Evolutionary Algorithm is able to select the parameters and the DNN architecture appropriately, achieving a 98.93% accuracy in the best run.

A taxonomy and state of the art revision on affective games

Abstract Affective games are a sub-field of affective computing that tries to study how to design videogames that are able to react to the emotions expressed by the player, as well as provoking desired emotions to them. To achieve those goals it is necessary to research on how to measure and detect human emotions using a computer, and how to adapt videogames to the perceived emotions to finally provoke them to the players. This work presents a taxonomy for research on affective games centring on the aforementioned issues. Here we devise as well a revision of the most relevant published works known to the authors on this area. Finally, we analyse and discuss which important research problem are yet open and might be tackled by future investigations in the area of affective games.

Extracting Radicalisation Behavioural Patterns from Social Network Data

Social networks (SNs) have become essential communication tools in recent years, generating a large amount of information about its users that can be analysed with data processing algorithms. Recently, a new type of SN user has emerged: jihadists that use SNs as a tool to recruit new militants and share their propaganda. In this paper, we study a set of indicators to assess the risk of radicalisation of a social network user. These radicalisation indicators help law-enforcement agencies, prosecutors and organizations devoted to fight terrorism to detect vulnerable targets even before the radicalisation process is completed. Moreover, these indicators are the first steps towards a software tool to gather, represent, pre-process and analyse behavioural indicators of radicalisation in terrorism.

From ephemeral computing to deep bioinspired algorithms: New trends and applications

Abstract Ephemeral computing is a term that describes computing systems whose nodes or their connectivity have an ephemeral, heterogeneous and possibly also unpredictable nature. These properties will affect the functioning of distributed versions of computer algorithms. Such algorithms, which are usually straightforward extensions of sequential algorithms, will have to be redesigned and, in many cases, rethought from the ground up, to be able to use all ephemerally available resources. Porting algorithms to an inherently ephemeral, unreliable and massively heterogeneous computing substrate is thus one of the main challenges in the ephemeral computing field. Algorithms adapted so that they can be consciously running on this kind of environments require specific properties in terms of flexibility, plasticity and robustness. Bioinspired algorithms are particularly well suited to this endeavor, thanks to their decentralized functioning, intrinsic parallelism, resilience, adaptiveness, and amenability for being endowed with algorithmic components dealing with both the massive complexity of the computational substrate and that of the problem being tackled. Arranging these components and functionalities in a collection of algorithmic strata results in deep architectures, whereby different layers of optimization are organized into loosely-coupled hierarchies that not only are able to use ephemeral computing environments, but also profit from them by making adaptivity and diversity maintenance features of the algorithm. Moreover, the synergies that arise when these massively heterogeneous computing resources are made available to deep versions of bioinspired algorithms may enable hard real-world problems and applications to be successfully faced in the Big Data context (including but not limited to social data analysis) as well as problems in the areas of computational creativity or computer gaming.