http://hdl.handle.net/10366/142735 2026-05-08T08:34:12Z http://hdl.handle.net/10366/142773 2019-11-13T00:00:00Z http://hdl.handle.net/10366/142772 This paper presents the application of a Methodology to Obtain Genetic fuzzy rule-based systems Under the iterative rule Learning approach (MOGUL) to forecast energy consumption. Historical data referring to the energy consumption gathered from three groups, namely lights, HVAC and electrical socket, are used to train the proposed approach and achieve forecasting results for the future. The performance of the proposed method is compared to that of previous approaches, namely Hybrid Neural Fuzzy Interface System (HyFIS) and Wang and Mendel’s Fuzzy Rule Learning Method (WM). Results show that the proposed methodology achieved smaller forecasting errors for the following hours, with a smaller standard deviation. Thus, the proposed approach is able to achieve more reliable results than the other state of the art methodologies 2019-06-18T00:00:00Z http://hdl.handle.net/10366/142771 This paper presents a multi-agent system that is able to search people on a database of images recognizing patterns of facial features on each person, based on the main features of the face (eyes, nose and mouth). Using that multi-agent architecture, the system can do the work faster applying Fisherfaces algorithm for the face recognition and classification. This technology can be used for several purposes like specific ads in each user group to suit better their interests or search for the age and gender of people that usually go to different places like malls or shops. 2019-01-18T00:00:00Z http://hdl.handle.net/10366/142770 Global warming affects us all, that is why we must all act to stop it. It has been shown that this undoubted problem can be solved to a large extend if we make small individual efforts. How can we do this? Making prudent use of electricity. If we manage to make more efficient use of the energy we consume in our homes, we will contribute enormously in this common cause. With the help of virtual agents, we will get a better management of the energy we consume. 2019-01-18T00:00:00Z http://hdl.handle.net/10366/142769 A multi-agent system is proposed that simulates a network of vehicle rental stations in a city. The paper studies the relationship between the agents and the client, analyses the casuistry associated with possible problems that may be encountered in the absence of transport in a given stop, as well as the decisions that could be taken by the interested party. Subsequently, an architecture capable of being scalable in terms of functionalities and the number of agents involved in it will be proposed. The aim of this paper is to revise the original paper, which is more focused on the possibility of studying a particular city, raising and solving the problems associated with public vehicle sharing services. 2019-01-18T00:00:00Z http://hdl.handle.net/10366/142768 Pollution nowadays is a really important issue that must be solved. Big cities suffer from overcrowding which result in traffic congestion and a lot of air pollution. Adapting to the idea of cities bike lane expansion, we design a Multi-agent simulation to distribute among the users green energy vehicles; concretely bikes, scooters and electric cars.; Pollution nowadays is a really important issue that must be solved. Big cities suffer from overcrowding which result in traffic congestion and a lot of air pollution. Adapting to the idea of cities bike lane expansion, we design a Multi-agent simulation to distribute among the users green energy vehicles; concretely bikes, scooters and electric cars. 2019-01-18T00:00:00Z http://hdl.handle.net/10366/142767 This paper presents a multi-agent system that looks for the most optimum algorithm of its type. For that purpose it will use several agents which will be in charge of testing the algorithms and comparing the outcome to see which is the most efficient.  Thanks to this procedure the most optimum procedure can be obtained. 2019-06-18T00:00:00Z http://hdl.handle.net/10366/142766 A multi-agent architecture has been developed for tutorial assignation scheduling. It has two main types of agents: the students and the teachers. These two are coordinated by an algorithm which assigns the classes in order of arrival. The architecture will provide the necessary tools to the students, so they get the maximum profit from the tutorials. Students and Lecturers can coordinate their tutorial meeting in an efficient way with the help of the multi-agent system. 2019-01-18T00:00:00Z http://hdl.handle.net/10366/142765 2019-12-21T00:00:00Z