Anna I Esparcia-Alcázar

An Evolutionary Framework for Routing Protocol Analysis in Wireless Sensor Networks.- Routing Low-Speed Traffic Requests onto High-Speed Lightpaths by Using a Multiobjective Firefly Algorithm.- Pareto-optimal Glowworm Swarms Optimization for Smart Grids Management.- An Overlay Approach for Optimising Small-World Properties in VANETs.- Impact of the Number of Beacons in PSO-Based Auto-localization in UWB Networks.- Load Balancing in Distributed Applications Based on Extremal Optimization.- A Framework for Modeling Automatic Offloading of Mobile Applications Using Genetic Programming.- Solving the Location Areas Scheme in Realistic Networks by Using a Multi-objective Algorithm.- The Small-World Phenomenon Applied to a Self-adaptive Resources Selection Model.- Partial Imitation Hinders Emergence of Cooperation in the Iterated Prisoner's Dilemma with Direct Reciprocity.- A Memetic Approach to Bayesian Network Structure Learning.- Multiobjective Evolutionary Strategy for Finding Neighbourhoods of Pareto-optimal Solutions.- Genetic Programming-Based Model Output Statistics for Short-Range Temperature Prediction.- Evolutionary Multi-Agent System in Hard Benchmark Continuous Optimisation.- Domestic Load Scheduling Using Genetic Algorithms.- Evolutionary Algorithm Based Control Policies for Flexible Optimal Power Flow over Time.- Using a Genetic Algorithm for the Determination of Power Load Profiles.- Comparing Ensemble-Based Forecasting Methods for Smart-Metering Data.- Evolving Non-Intrusive Load.- On the Utility of Trading Criteria Based Retraining in Forex Markets.- Identifying Market Price Levels Using Differential Evolution.- Evolving Hierarchical Temporal Memory-Based Trading Models.- Robust Estimation of Vector Autoregression (VAR) Models Using Genetic Algorithms.- Usage Patterns of Trading Rules in Stock Market Trading Strategies Optimized with Evolutionary Methods.- Combining Technical Analysis and Grammatical Evolution in a Trading System.- A Card Game Description Language.- Generating Map Sketches for Strategy Games.- A Procedural Balanced Map Generator with Self-adaptive Complexity for the Real-Time Strategy Game Planet Wars.- Mechanic Miner: Reflection-Driven Game Mechanic Discovery and Level Design.- Generating Artificial Neural Networks for Value Function Approximation in a Domain Requiring a Shifting Strategy.- Comparing Evolutionary Algorithms to Solve the Game of MasterMind.- A Genetic Algorithm for Color Image Segmentation.- Multiobjective Projection Pursuit for Semisupervised Feature Extraction.- Land Cover/Land Use Multiclass Classification Using GP with Geometric Semantic Operators.- Adding Chaos to Differential Evolution for Range Image Registration.- Genetic Programming for Automatic Construction of Variant Features in Edge Detection.- Automatic Construction of Gaussian-Based Edge Detectors Using Genetic Programming.- Implicit Fitness Sharing for Evolutionary Synthesis of License Plate Detectors.- Feedback-Based Image Retrieval Using Probabilistic Hypergraph Ranking Augmented by Ant Colony Algorithm.- An Evolutionary Approach for Automatic Seedpoint Setting in Brain Fiber Tracking.- Prediction of Forest Aboveground Biomass: An Exercise on Avoiding Overfitting.- Human Action Recognition from Multi-Sensor Stream Data by Genetic Programming.- Novel Initialisation and Updating Mechanisms in PSO for Feature Selection in Classification.- CodeMonkey a GUI Driven Platform for Swift Synthesis of Evolutionary Algorithms in Java.- Multi-Objective Optimizations of Structural Parameter Determination for Serpentine Channel Heat Sink.- Towards Non-linear ConstraintEstimation for Expensive Optimization Repair Methods for Box Constraints Revisited.- Scalability of Population-Based Search Heuristics for Many-Objective Optimization.- On GPU Based Fitness Evaluation with Decoupled Training Partition Cardinality.-EvoSpace: A Distributed Evolutionary Platform Based on the Tuple Space Model.- Cloud Driven Design of a Distributed Genetic Programming Platform.- Cloud Scale Distributed Evolutionary Strategies for High Dimensional Problems.- Evolving Gaits for Physical Robots with the HyperNEAT Generative Encoding: The Benefits of Simulation.- Co-evolutionary Approach to Design of Robotic Gait.- A Comparison between Different Encoding Strategies for Snake-Like Robot Controllers.- Virtual Spatiality in Agent Controllers: Encoding Compartmentalization.- Evolving Counter-Propagation Neuro-controllers for Multi-objective Robot Navigation.- Toward Automatic Gait Generation for Quadruped Robots Using Cartesian Genetic Programming.- Adapting the Pheromone Evaporation Rate in Dynamic Routing Problems.- Finding Robust Solutions to Dynamic Optimization Problems.- An Ant-Based Selection Hyper heuristic for Dynamic Environments.

We apply gene expression programing to evolve a player for a real-time strategy (RTS) video game. The paper describes the game, evolutionary encoding of strategies and the technical implementation of experimental framework. In the experimental part, we compare two setups that differ with respect to the used approach of task decomposition. One of the setups turns out to be able

On behalf of the Organizing Committee, I would like to welcome you to Vancouver for the 2014 Genetic and Evolutionary Computation Conference (GECCO 2014). This years GECCO is comprised of 20 tracks, including the new Artificial Immune Systems and Hot Off the Press (HOP) tracks. The latter offers authors of outstanding research recently published in journals and other conferences the opportunity to present their work to the GECCO community. Under the guidance of Editor-in-Chief Christian Igel, the Track Chairs and Program Committee have selected 180 out of the 544 submissions received in all tracks (excluding HOP) for oral presentation as full papers, resulting in an acceptance rate of 33%. Close to 100 short papers will be presented in the poster session. Highlights of the conference include keynote talks by Yoshua Bengio on "Deep Learning and Cultural Evolution", and by Dario Floreano on "Bridging Natural and Artificial Evolution", as well as an invited talk by Sumit Gulwani in the Genetic Programming track. Altogether 32 tutorials cover topics ranging from broad and introductory to specialized and at the frontier of current research. GECCO also hosts fifteen workshops, including several new ones as well as at least one that predates GECCO itself. Further high points include the 11th Annual "Humies" Awards for Human-Competitive Results, which are again generously supported by John Koza, and five competitions, ranging from Art, Design, and Creativity to the Industrial Challenge. Finally, Evolutionary Computation in Practice continues to be an important and integral part of GECCO.

Nature-inspired techniques for telecommunication networks and other parallel and distributed systems.- Evolutionary algorithms and complex systems.- Evolutionary computation in energy applications.- Evolutionary and natural computation in finance and economics.- Bio-inspired algorithms in games.- Evolutionary computation in image analysis, signal processing, and pattern recognition.- Nature-inspired techniques in industrial settings.- Bio-inspired algorithms for continuous parameter optimization.- Parallel implementation of evolutionary algorithms.- Computational intelligence for risk management, security and defence applications.- Evolutionary computation in robotics.- Evolutionary algorithms in stochastic and dynamic environments.- EC and related techniques in bioinformatics and computational biology.

Oral Presentations.- Training Time and Team Composition Robustness in Evolved Multi-agent Systems.- Winning Ant Wars: Evolving a Human-Competitive Game Strategy Using Fitnessless Selection.- In Silicon No One Can Hear You Scream: Evolving Fighting Creatures.- Real-Time, Non-intrusive Speech Quality Estimation: A Signal-Based Model.- Good News: Using News Feeds with Genetic Programming to Predict Stock Prices.- A Genetic Programming Approach to Deriving the Spectral Sensitivity of an Optical System.- A SIMD Interpreter for Genetic Programming on GPU Graphics Cards.- Partitioned Incremental Evolution of Hardware Using Genetic Programming.- Population Parallel GP on the G80 GPU.- Operator Equalisation and Bloat Free GP.- Practical Model of Genetic Programming's Performance on Rational Symbolic Regression Problems.- Semantic Building Blocks in Genetic Programming.- A Simple Powerful Constraint for Genetic Programming.- Crossover, Sampling, Bloat and the Harmful Effects of Size Limits.- The Performance of a Selection Architecture for Genetic Programming.- A Comparison of Cartesian Genetic Programming and Linear Genetic Programming.- Evolvability Via Modularity-Induced Mutational Focussing.- A Linear Estimation-of-Distribution GP System.- Feature Discovery in Reinforcement Learning Using Genetic Programming.- Hardware Accelerators for Cartesian Genetic Programming.- Genetic Programming and Class-Wise Orthogonal Transformation for Dimension Reduction in Classification Problems.- Posters.- Evolving Proactive Aggregation Protocols.- GP Classification under Imbalanced Data sets: Active Sub-sampling and AUC Approximation.- Exposing a Bias Toward Short-Length Numbers in Grammatical Evolution.- Cooperative Problem Decomposition in Pareto Competitive Classifier Models of Coevolution.- Integrating Categorical Variables with Multiobjective Genetic Programming for Classifier Construction.- The Effects of Constant Neutrality on Performance and Problem Hardness in GP.- Applying Cost-Sensitive Multiobjective Genetic Programming to Feature Extraction for Spam E-mail Filtering.- PlasmidPL: A Plasmid-Inspired Language for Genetic Programming.- Using Genetic Programming for Turing Machine Induction.- Altering Search Rates of the Meta and Solution Grammars in the mGGA.

Corporate security is usually one of the matters in which companies invest more resources, since the loss of information directly translates into monetary losses. Security issues might have an origin in external attacks or internal security failures, but an important part of the security breaches is related to the lack of awareness that the employees have with regard to the use of the Web. In this work we have focused on the latter problem, describing the improvements to a system able to detect anomalous and potentially insecure situations that could be dangerous for a company. This system was initially conceived as a better alternative to what are known as black/white lists. These lists contain URLs whose access is banned or dangerous (black list), or URLs to which the access is permitted or allowed (white list). In this chapter, we propose a system that can initially learn from existing black/white lists and then classify a new, unknown, URL request either as “should be allowed” or “should be denied”. This system is described, as well as its results and the improvements made by means of an initial data pre-processing step based on applying Rough Set Theory for feature selection. We prove that high accuracies can be obtained even without including a pre-processing step, reaching between 96 and 97 % of correctly classified patterns. Furthermore, we also prove that including the use of Computational Intelligence techniques for pre-processing the data enhances the system performance, in terms of running time, while the accuracies remain close to 97 %. Indeed, among the obtained results, we demonstrate that it is possible to obtain interesting rules which are not based only on the URL string feature, for classifying new unknown URLs access requests as allowed or as denied.

Resumen— El problema de Transporte e Inventa-rio (Inventory and Transportation Problem, ITP) puede entenderse como una generalización del problema de enrutado de vehículos periódico que tiene en conside-ración los costes de inventario, además de una serie de frecuencias de reparto en lugar de una sola fre-cuencia para cada tienda. Asimismo, el ITP puede verse como una generalización del Problema de Ru-tas e Inventario al caso multiproducto. EVITA, si-glas de Evolutionary Inventory and Transportation Algorithm, es una metodología en dos niveles di-señada para abordar este problema. El nivel superior utiliza un algoritmo evolutivo para obtener los patro-nes de reparto semanales de forma que se minimicen los costes de inventario, mientras que el nivel infe-rior resuelve el problema de enrutado de vehículos (Vehicle Routing Problem, VRP) para cada día a fin de obtener los costes de transporte mínimos asociados a un conjunto dado de patrones. En este artículo utilizamos dos enfoques: un ...

Abstract—In this paper we propose an evolutionary algo-rithm to address the problem of allocating products to shelves in a supermarket (Product to Shelf Allocation Problem or P2SAP) and show several instances where it was applied successfully. We first show the main problem ...

Abstract—In this paper we propose new advances towards the development of a commercial tool to address the inventory and transportation problem, ie the problem of minimising both the transport and inventory costs of a retail chain that is supplied from a central warehouse. ...

A learning capability is introduced in the Genetic Programming (GP) paradigm. This is achieved by enhancing GP with Simulated Annealing (SA), where the latter adapts the parameter values (in the form of node gains) in the structures evolved by the former. A special feature of this ...

The SHIP project is an Erasmus+ Knowledge Alliance whose main goal is to strengthen the knowledge triangle between universities, Small and Medium Sized Enterprises (SMEs) and innovation support organizations. The project entails to set-up of 4 Innovation Alliances in 5 countries (Ireland + UK, Germany, Spain, Romania). The goal of these alliances is to consolidate cooperation as a key feature of the knowledge economy, reshaping traditional roles by multiplying outlets for universities to generate direct economic impact from their work, and breaking down barriers so that SMEs of all shapes and sizes can actively implement academic-based innovation to boost their own competitiveness, and that of the wider economy. One of the alliances is the Spanish Software Testing Innovation Alliance, it is this alliance that is mostly described in this showcase. The objective of this Alliance is to bring together key actors in Spain on software testing in order to work together to improve innovatio...

It is our great pleasure to welcome you to the all-new 2014 Workshop on Genetic and Evolutionary Computation in Defense, Security, and Risk Management (SecDef'14). With the constant appearance of new threats, research in the areas of defense, security and risk management has acquired an increasing importance over the past few years. These new challenges often require innovative solutions and Computational Intelligence techniques can play a significant role in finding them. The workshop encouraged the submission of papers describing both theoretical developments and applications of Genetic and Evolutionary Computation and their hybrids to the following (and other related) topics: Cyber-crime and cyber-defense : anomaly detection systems, attack prevention and defense, threat forecasting systems, anti-spam, antivirus systems, cyber warfare, cyber fraud IT Security: Intrusion detection, behavior monitoring, network traffic analysis Corporate security, with special focus on BYOD policies and usability of security Risk management: identification, prevention, monitoring and handling of risks, risk impact and probability estimation systems, contingency plans, real time risk management Critical Infrastructure Protection (CIP) Advanced Persistent Threats (APTs) Design of military systems and sub-systems. Logistics and scheduling of military operations. Strategic planning and tactical decision making. Multi-objective techniques for examining tradeoffs in military, security, and counter-terrorism procedures. Automated discovery of tactics and procedures for site security, force protection, and consequence management. Other computational intelligence techniques for applications in the areas listed above. The workshop invited completed or ongoing work, with the aim to encourage communication between active researchers and practitioners to better understand the current scope of efforts within this domain. The ultimate goal is to understand, discuss, and help set future directions for computational intelligence in security and defense problems. As a first-year workshop, the organizers received and accepted four high-quality submissions from North America and Europe: On the Role of Multi-Objective Optimization in Risk Mitigation for Critical Infrastructures with Robotic Sensor Networks by Jamieson McCausland, Rami Abielmona, Rafael Falcon (Larus Technologies Corp., Canada); Ana-Maria Cretu (Université du Quebec en Outaouais, Canada); and Emil Petriu (University of Ottawa, Canada) On Botnet Behaviour Analysis using GP and C4.5 by Fariba Haddadi, Dylan Runkel, Nur Zincir-Heywood, and Malcolm Heywood (Dalhousie University, Canada) Evolutionary Based Moving Target Cyber Defense by David John, Robert Smith, William Turkett, Daniel Canas, and Errin Fulp (Wake Forest University, USA) Enforcing Corporate Security Policies via Computational Intelligence Techniques by Antonio Mora, Paloma De las Cuevas, J.J. Merelo (University of Granada, Spain); Sergio Zamarripa, and Anna I. Esparcia-Alcázar (S2 Grupo, Spain)

Abstract We consider a form of phenotype plasticityin Genetic Program-ming (GP). This takes the form of a set of real-valued numerical para-meters associated with each individual, an optimisation (or learning) algorithm for adapting their values, and an inheritance strategy for propa- ...

ABSTRACT After more than fifteen years, JavaScript has finally risen as a popular language for implementing all kind of applications, from server-based to rich internet applications. The fact that it is implemented in the browser and in server-side tools makes it interesting for designing evolutionary algorithm frameworks that encompass both tiers, but besides, they allow a change in paradigm that goes beyond the canonical evolutionary algorithm. In this paper we will experiment with different architectures, client-server and peer to peer to assess which ones offer most advantages in terms of performance, scalability and ease of use for the computer scientist. All implementations have been released as open source, and besides showing that the concept of working with evolutionary algorithms in JavaScript can be done efficiently, we prove that a master-slave parallel architecture offers the best combination of time and algorithmic improvements in a parallel evolutionary algorithm that leverages JavaScript implementation features.

As the Internet of Things (IoT) becomes a reality, the need of ensuring the security and reliability of massively interconnected devices becomes a pressing necessity. A means of satisfying this need would be automated testing of IoT devices; however, this presents many difficulties, such as the lack of standards, multitude of manufacturers, restricted capabilities (such as power), etc.

Page 1. Prune and Plant: A New Bloat Control Method for Genetic Programming Eva Alfaro-Cid Instituto Tecnológico de Informática UPV, Valencia, Spain evalfaro@iti.upv.es AnnaEsparcia-Alcázar Instituto Tecnológico de Informática UPV, Valencia, Spain anna@iti.upv.es ...

We describe a novel technique for evolving a machine that can learn. The machine is evolved using a Genetic Programming (GP) algorithm that incorporates in its function set what we have called a "learning node". Such a node is tuned by a second optimization algorithm (in this case Simulated Annealing), mimicking a natural learning process and providing the GP tree

Anna I Esparcia-Alcázar, Anaís Martínez-García Instituto Tecnológico de Informática Universidad Politécnica de Valencia, Spain {anna,amartinez}@iti.upv.es ... Antonio M. Mora, JJ Merelo, Pablo García-Sánchez Dept. of Architecture and Computer Technology University of Granada, ...

This paper reports a comparison of several bloat control methods and also evaluates a recent proposal for limiting the size of the individuals: a genetic operator called prune and plant. The aim of this work is to test the adequacy of this method. Since a preliminary study of the method has already shown promising results, we have performed a thorough study in a set of benchmark problems aiming at demonstrating the utility of the new approach. Prune and plant has obtained results that maintain the quality of the final solutions in terms of fitness while achieving a substantial reduction of the mean tree size in all four problem domains considered. In addition, in one of these problem domains, prune and plant has demonstrated to be better in terms of fitness, size reduction, and time consumption than any of the other bloat control techniques under comparison. The experimental part of the study presents a comparison of performance in terms of phenotypic and genotypic diversity. This c...

ABSTRACT In this work we address the problem of inventory and routing management in a retail chain. This involves the minimisation of two contradicting objectives, inventory holding costs and transportation costs, but which can be compounded in to a single one, the global costs. In previous work we addressed this using a single objective evolutionary algorithm but the duality inherent in the problem prompts us to consider a multiobjective approach; the aim is to determine what advantages each can bring. A number of experiments are carried out on several simulated and one real retail chain.

ABSTRACT This paper studies SofEA, an architecture for distributing evolutionary algorithms (EAs) across computer networks in an asynchronous and decentralized way. SofEA is based on a pool architecture which is implemented using an object store interacting asynchronously with several clients. The fact that each client is autonomous leads to a complex behavior that will be examined in this paper, so that the design can be validated, rules of thumb can be extracted and the limits of scalability found. We will show how, beyond the usual measures employed in EA, specific measures such as the number of conflicts across clients can give us hints on the algorithm behavior, and how implementation details can change not only the running time, but also the behavior of the evolutionary algorithm itself. By using these measures we try to find ideal values for parameters such as the simultaneous number of individuals evaluated by a client or the way these are chosen from the pool.

... Page 14. 18 Ken Sharman and Anna Esparcia-Alcázar References Algazi, VR, Duda, RO, Thompson, DM and Avendano, C. (2001) “The CIPIC HRTF database”. Proceedings of the 2001 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, ed. IEEE, pp. ...

Abstract—The newscast algorithm has the purpose of building a distributed computing system with a random topology where independent nodes can operate in a pure peer-to-peer fashion. The main advantages of this algorithm and the topology it builds are their robustness and efficiency to spread information. This article gives a formal input / output automata model for each node running this algorithm and thus for the entire network. The viability of the algorithm is proved and a solid basis for future development is laid.1

We propose a novel design paradigm for recurrent neural networks. This employs a two-stage Genetic Programming/Simulated Annealing hybrid algorithm to produce a neural network which satisfies a set of design constraints. The Genetic Programming part of the algorithm is used to evolve the general topology of the network, along with specifications for the neuronal transfer functions, while the Simulated Annealing component of the algorithm adapts the network's connection weights in response to a set of training data. Our approach offers important advantages over existing methods for automated network design. Firstly, it allows us to develop recurrent network connections; secondly, we are able to employ neurones with arbitrary transfer functions, and thirdly, the approach yields an efficient and easy to implement on-line training algorithm. The procedures involved in using the GP/SA hybrid algorithm are illustrated by using it to design a neural network for adaptive filtering in a...

Abstract—In recent years, software testing and maintenance services are key factors of customers ’ perception of software quality. Nowadays, customers are more demanding about these services, while contribution of maintenance and testing services to products total cost of ownership should be reduced. Reducing these costs is even more crucial for SME’s. To do this, new methods and techniques that will be aligned with the needs of companies are required. This paper presents the preliminary results of an interactive workshop celebrated by researchers and three companies. In the workshop, researchers present the