Search

The evolution of Smartphone devices with their powerful computing capabilities and their ever increasing number of sensors has recently introduced an unprecedented array of applications and games. The Smartphone users who are constantly moving and sensing are able to provide large amounts of opportunistic/participatory data that can contribute to complex and novel problem solving, unfolding in this way the full potential of crowdsourcing. Crowdsourced data can therefore be utilized for optimally modeling human-like behavior and improving the realizablity of AI gaming. In this study, we have developed an Augmented Reality First Person Shooter game, coined AR Shooter, that allows the crowd to constantly contribute their game play along with various spatio-temporal information. The crowdsourced data are used for modeling the human player’s behavior with Artificial Neural Networks. The resulting models are utilized back to the game’s environment through AI agents making it more realistic and challenging. Our experimental studies have shown that our AI agents are quite competitive, while being very difficult to distinguish from human players.

This work examines the Capacitated Vehicle Routing Problem with Balanced Routes and Time Windows (CVRPBRTW). The problem aims at optimizing the total distance cost, the number of vehicles used, and the route balancing, under the existence of time windows and other constraints. The problem is formulated as a Multi-Objective Optimization Problem where all objectives are tackled simultaneously, so as to effect a better solution space coverage. A Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D), hybridized with local search elements, is proposed. The application of local search heuristics is not uniform but depends on specific objective preferences and instance requirements of the decomposed subproblems. To test the efficacy of the proposed solutions, extensive experiments were conducted on well known benchmark problem instances and results were compared with other MOEAs.

Setting appropriate parameters of an evolutionary algorithm (EA) is challenging in real world applications. On one hand, the characteristics of a real world problem are usually unknown. On the other hand, in different running stages of an EA, the best parameters may be different. Thus adaptively tuning algorithm parameters online is preferred. In this paper, we propose to use an estimation of distribution algorithm (EDA) to do this for a particle swarm optimization (PSO) algorithm. The major characteristic of our approach is that there are two evolving processes simultaneously: one for tackling the original problem, and the other for optimizing PSO parameters. For the former evolving process, a set of particles are maintained; while for the later, a probability distribution model of the PSO parameters is maintained throughout the run. In the reproduction procedure, the PSO parameters are firstly sampled from the model, and then new particles are generated by the PSO operator. The feedback from the newly generated particles is used to evaluate the PSO parameters and thus to update the probability model. The new approach is applied to a set of test instances and the preliminary results are promising.

Total Electron Content (TEC) is an ionospheric characteristic used to derive the signal delay imposed by the ionosphere on trans-ionospheric links and subsequently overwhelm its negative impact in accurate position determination. In this paper, an Evolutionary Algorithm (EA), and particularly a Genetic Programming (GP) based model is designed. The proposed model is based on the main factors that influence the variability of the predicted parameter on a diurnal, seasonal and long-term time-scale. Experimental results show that the GP-model, which is based on TEC measurements obtained over a period of 11 years, has produced a good approximation of the modeled parameter and can be implemented as a local model to account for the ionospheric imposed error in positioning. The GP-based approach performs better than the existing Neural Network-based approach in several cases.

This paper will present ELEVATE that aims to deliver an innovative training, educational and certification environment integrating the application software to be taught with the training procedure. ELEVATE aspires to address the training needs of software development SMEs and the solution proposed is based on three basic notions: to provide competence training that is tailored to the needs of the individual trainee, to allow the trainee to carry out authentic activities as well as problem based learning that draws from real life scenarios and finally to allow for the assessment and certification of the skills and competences acquired. In order to achieve the desired results the ELEVATE architecture utilises an Interactive Interoperability Layer, an Intelligent Personalization Trainer as well as the Training, Evaluation & Certification component. As an end product, the ELEVATE project The ELEVATE pedagogical model is based on blended learning, the e-Training component (an intelligent system that provides tailored training) and Learning 2.0.