Ant colony systems have been widely employed in optimization issues primarily focused on path flnding optimization, such as travelling salesman problem. The main advantage lies in the choice of the edge to be explored, deflned using pheromone trails. This paper proposes the use of ant colony systems to explore a Backus-Naur form grammar whose elements are solutions to a given problem. Similar models, without using ant colonies, have been used to solve optimization problems or to automatically genérate programs such as grammatical swarm (based on particle swarm optimization) and grammatical evolution (based on genetic algorithms). This workpresents the application of proposed ant colony rule derivation algorithm and benchmarks this novel approach in a well-known deceptive problem, the Santa Fe Trail. Proposed algorithm opens the way to a new branch of research in swarm intelligence, which until now has been almost nonexistent, using ant colony algorithms to genérate solutions of a given problem described by a BNF grammar with the advantage of genotype/phenotype mapping, described in grammatical evolution. In this case, such mapping is performed based on the pheromone concentration for each production rule. The experimental results demónstrate proposed algorithm outperforms grammatical evolution algorithm in the Santa Fe Trail problem with higher success rates and better solutions in terms of the required steps.

The management and proper use of the Urban Public Transport Systems (UPTS) constitutes a critical field that has not been investigated in accordance to its relevance and urgent idiosyncrasy within the Smart Cities realm. Swarm Intelligence is a very promising paradigm to deal with such complex and dynamic systems. It presents robust, scalable, and self-organized behavior to deal with dynamic and fast changing systems. The intelligence of cities can be modelled as a swarm of digital telecommunication networks (the nerves), ubiquitously embedded intelligence, sensors and tags, and software. In this paper, a new approach based on the use of the Natural Computing paradigm and Collective Computation is shown, more concretely taking advantage of an Ant Colony Optimization algorithm variation and Fireworks algorithms to build a system that makes the complete control of the UPTS a tangible reality.

This paper presents a study and implementation of a convolutional neural network to identify and recognize humpback whale specimens from the unique patterns of their tails. Starting from a dataset composed of images of whale tails, all the phases of the process of creation and training of a neural network are detailed – from the analysis and pre-processing of images to the elaboration of predictions, using TensorFlow and Keras frameworks. Other possible alternatives are also explained when it comes to tackling this problem and the complications that have arisen during the process of developing this paper.

The management and proper use of the Urban Public Transport Systems (UPTS) constitute a field as critical as little investigated according to its relevance and urgent idiosyncrasy within smart cities realm. In this paper, a newfangled approach by using the Natural Computing paradigm and Collective Computation is shown, more concretely taking advantage of an Ant Colony Optimization algorithm variation in order to build a system that makes the complete control of the UPTS a tangible reality.

This Ph.D purpose is, once a thorough theoretical research is given to the reader, and as a result of the investigation in the state of the art and idiosyncrasy regarding the Computing Paradigms belonging Natural Computing, like Fireworks Algorithm, Genetic Algorithm, Ant Colony Optimization, Grammatical Evolution, Grammatical Swarm or Particle Swarm Optimization, among others, to face the empirically-observable algorithmic improvement of one of the aforementioned bioinspired entities, more concretely Fireworks Algorithm, giving birth to Improved Fireworks Algorithm (IFA). Furthermore, a novel synergy among four important elements within the aforementioned set will be presented; Ant Colony Optimization, Grammatical Evolution, Grammatical Swarm and Genetic Algorithms, what disembogues in the creation of the brand new, generic ACORD Algorithm (Ant Colony systems Optimization applied to BNF grammars Rule Derivation), which merges these paradigms in order to explore Backus-Naur Form (BNF) grammars, whose elements represent solutions to a given problem. Thus, should Fireworks Algorithm improvement aligns with a numerical idiosyncrasy, ACORD represents a conceptual creation, empirically demonstrating the colossal effectiveness of the theoretical-practical binomial that Natural Computing hands over.Once that algorithm enrichment has been achieved with IFA, as well as the synergy among entities has been accomplished under Natural Computing spectrum with ACORD, the applied methodology to reach that goal is to be described with the finest granularity level. Hence, elucidating what has been improved and how. All results thrown by means of the pertinent experiments will be shown, as well as its opportune analysis and discussion. It is noteworthy that, among other publications, the theoretical basis on Natural Computing have deserved the publication of [Morales Lucas et al, 2018] (JCR Q2). Along the same lines, ACORD has deserved the publication of [de Mingo et al, 2019] (JCR Q2).Finally, once the achievement of the aforementioned goals has been accomplished, the future investigation paths lead by this Ph.D, accompanied with the applicable conclusions will be shown, reinforced with the relevant annexes in order to complement the needed information.