Faraón Llorens

The University of Alicante's institutional strategy to promote the open dissemination of knowledge

Purpose – Information and communication technologies have became pervasive in peoples lives and in this changing world education cannot remain anchored in old‐fashioned models which ignore the evolution through which society is going. This paper seeks to present the gamble made by the University of Alicante (Spain) on the promotion of open knowledge.Design/methodology/approach – The educational environment cannot continue to be fixed, closed and isolated, where students – assuming a basically passive role – receive standardised teaching. It must consequently experience a fast and decisive transformation which allows it, amongst other things, to respond to the new challenge posed by society: the need for all of us to share the knowledge we generate, so that further progress can be made.Findings – The Institutional Repository (RUA) and the OpenCourseWare of the University of Alicante (OCW‐UA) were conceived from the very beginning as related projects that could constitute consecutive phases in the open pub...

Is teaching a fractal

This work arises from the reflections of a group of teachers. These reflections have led us to analyse the different perspectives of the student and the teacher facing the reality that takes place in the classroom, dealing with aspects such as motivation and student work, classroom overcrowding and design of training activities. As a result of this study, a teaching model based on the principles of fractal geometry is proposed, in the sense that they present different levels of abstraction for the various training activities and the activities are self-similar, that is, they are decomposed again and again. At each level, an activity decomposes into a lower level tasks and their corresponding evaluation. With this model the immediate feedback and the student motivation are encouraged. The presented model is contextualized in a course of introduction to programming but it is fully generalizable to other subjects.

Cooperation Strategies for Pursuit Games: From a Greedy to an Evolutive Approach

Developing coodination among groups of agents is a big challenge in multi-agent systems. An appropriate enviroment to test new solutions is the prey-predator pursuit problem. As it is stated many times in literature, algorithms and conclusions obtained in this environment can be extended and applied to many particular problems. The first solutions for this problem proposed greedy algorithms that seemed to do the job. However, when concurrency is added to the environment it is clear that inter-agent communication and coordination is essential to achieve good results. This paper proposes two new ways to achieve agent coodination. It starts extending a well-known greedy strategy to get the best of a greedy approach. Next, a simple coodination protocol for prey-sight notice is developed. Finally, under the need of better coordination, a Neuroevolution approach is used to improve the solution. With these solutions developed, experiments are carried out and performance measures are compared. Results show that each new step represents an improvement with respect to the previous one. In conclusion, we consider this approach to be a very promising one, with still room for discussion and more improvements.

Applying distance histograms for robust object recognition

Purpose – One of the main goals of vision systems is to recognize objects in real world to perform appropriate actions. This implies the ability of handling objects and, moreover, to know the relations between these objects and their environment in what we call scenes. Most of the time, navigation in unknown environments is difficult due to a lack of easily identifiable landmarks. Hence, in this work, some geometric features to identify objects are considered. Firstly, a Markov random field segmentation approach is implemented. Then, the key factor for the recognition is the calculation of the so‐called distance histograms, which relate the distances between the border points to the mass center for each object in a scene.Design/methodology/approach – This work, first discusses the features to be analyzed in order to create a reliable database for a proper recognition of the objects in a scene. Then, a robust classification system is designed and finally some experiments are completed to show that the reco...

Extending Korf’s Ideas on the Pursuit Problem

The prey-predator pursuit problem is referenced many times in literature. It is a generic multi-agent problem whose solutions could by applied to many particular instances. Solutions proposed usually apply non-supervised learning algorithms to train prey and predators. Most of these solutions criticize the greedy algorithm originally proposed by Korf. However, we believe that the improvement obtained by these new proposals does not pay off with relation to their complexity.

Mixing Greedy and Evolutive Approaches to Improve Pursuit Strategies

The prey-predator pursuit problem is a generic multi-agent testbed referenced many times in literature. Algorithms and conclusions obtained in this domain can be extended and applied to many particular problems. In first place, greedy algorithms seem to do the job. But when concurrence problems arise, agent communication and coordination is needed to get a reasonable solution. It is quite popular to face these issues directly with non-supervised learning algorithms to train prey and predators. However, results got by most of these approaches still leave a great margin of improvement which should be exploited. In this paper we propose to start from a greedy strategy and extend and improve it by adding communication and machine learning. In this proposal, predator agents get a previous movement decision by using a greedy approach. Then, they focus on learning how to coordinate their own pre-decisions with the ones taken by other surrounding agents. Finally, they get a final decission trying to optimize their chase of the prey without colliding between them. For the learning step, a neuroevolution approach is used. The final results show improvements and leave room for open discussion.

Boosting human‐level AI with videogames: Mad University

Purpose – The main intention of this paper is to state the benefits of using online videogames as a research environment, where AI algorithms are improved by means of learning from real‐human‐behaviour examples.Design/methodology/approach – The manner of taking advantage from the flux of real‐human‐behaviour examples inside an online videogame is stated. Then Mad University, a prototype online videogame specifically conceived and developed for this purpose, is explained.Findings – Human‐like AI in artificial algorithms can be boosted by means of a specific kind of online videogame called MMORPGs, used as a research environment.Research limitations/implications – Mad University is a prototype videogame which has been developed to experiment with AI algorithms that aim to learn strategies in a generalized fashion. The next research step will be to improve Mad University and to put it to work with hundreds of players and then research and test the effectiveness of the AI algorithms.Originality/value – This p...

A Computer-Games-Based AI Research Environment

To develop, test and experiment with new AI algorithms, researchers require an experimentation environment. This is even more necessary when we talk about developing agent and multiagent systems. Moreover, if doing performance comparisons of different algorithms is the goal, it is really important to put all those algorithms to work under the same environment conditions. At present, there is a great variety of environments developed to support AI researchers in their tasks. However, it is usual to find that these environments whether they have too specific aims or they perfom well just with some kind of algoritms. In addition, their tendence to be researcher-oriented prevent us from using them in other fields like education, diffusion or massive testing. In this paper we propose a new kind of multiagent research environment, based on a computer game called Screaming Racers, with which we try to surpass these difficulties. Our computer-games-based research environment is intended to be used simultaneously by researchers, students and general players, powering up research, education, diffusion and massive testing.

Development of morphological operators for real‐time applications

Purpose – Classically, the mathematical morphology operators (i.e. erosion, dilation and its combinations) have not been implemented when working in real‐time constraints, as its computation time is often too high for this kind of applications. There are currently some approaches in order to solve this problem. The purpose of this paper is to present an alternative for this classical operators so as to speed up effectively their running time.Design/methodology/approach – The paper shows the algorithm, calculate the computational complexity and finally, implement the fast operators to compare the increasing velocity of this choice using different kind of gray‐scale images.Findings – The experimental results verify the theoretical results, as is pointed out throughout this work.Originality/value – Highlights two techniques for image processing using mathematical morphology.

A Combined Probabilistic Framework for Learning Gestures and Actions

In this paper we introduce a probabilistic approach to support visual supervision and gesture recognition. Task knowledge is both of geometric and visual nature and it is encoded in parametric eigenspaces. Learning processes for compute modal subspaces (eigenspaces) are the core of tracking and recognition of gestures and tasks. We describe the overall architecture of the system and detail learning processes and gesture design. Finally we show experimental results of tracking and recognition in block-world like assembling tasks and in general human gestures.