David Vernet

Unsupervised case memory organization: analysing computational time and soft computing capabilities

There are problems that present a huge volume of information or/and complex data as imprecision and approximated knowledge. Consequently, a Case-Based Reasoning system requires two main characteristics. The first one consists of offering a good computational time without reducing the accuracy rate of the system, specially when the response time is critical. On the other hand, the system needs soft computing capabilities in order to construct CBR systems more tractable, robust and tolerant to noise. The goal of this paper is centred on achieving a compromise between computational time and complex data management by focusing on the case memory organization (or clustering) through unsupervised techniques. In this sense, we have adapted two approaches: 1) neural networks (Kohonen Maps); and 2) inductive learning (X-means). The results presented in this work are based on datasets acquired from medical and telematics domains, and also from UCI repository.

Master in Teacher Training: A real implementation of Active Learning

Teaching methods based on lectures often result in student passivity rather than pro-activity with the only goal of the student being to pass the final exam. Consequently, content retention is temporary and true learning is not achieved. Lack of student motivation can be solved by using Active Learning methodologies: serious games, Project-Based Learning (PBL), blended learning, etc. In addition, these methodologies enhance the development of the competences of students and provide a better evaluation of outcomes, provided adequate tools are used. However, apart from this, a more profound use of Information and Communications Technology (ICT) is needed to improve the effectiveness of learning and to create a learning system adapted to our current society. Learning Management Systems (LMS), social networks and blogs are indispensable for the efficient application of innovative learning methodologies. The Master in Teacher Training (MTT) provides an ideal case study as the most relevant features of Active Learning are present. The main contributions to this learning environment have been the incorporation of Active Learning methodologies (using real scenarios and project-based collaborative learning), an innovative method for assessing the Master and the impact of technology in learning. All of these have resulted in very positive results in relative to academic marks, surveys and entrepreneurship.

A Genetic QoS-Aware Routing Protocol for the Smart Electricity Networks

This paper presents a QoS-aware routing protocol suitable for distribution of smart electricity grids based on heterogeneous machine to machine communications. The distribution Smart Grid needs high performance communication networks capable of handling QoS, an issue that is addressed by the present paper. The proposed algorithm is a merger between a genetic algorithm (GA) and Ticket-Based Routing (TBR), which is an on-demand routing protocol for ad hoc networks that provide quality of service. A suitable parameterization of the GA parameters is needed in order to use this protocol in the coming Smart Grid networks. The resulting routing protocol, named genetic algorithm with TBR algorithm for Smart Grids (GATAS), is an adapted intelligent evolution of the TBR. The performance of TBR has been improved by reducing the overhead of routing packets in the network and by minimizing the communication latency due to its on-demand behavior. Experimental evidence indicates that the likelihood of finding the optimum route using multiobjective dynamic metrics increases when the genetic algorithm is applied. In this paper, the main simulation results on the parameterization carried out are discussed, and the proposed attributes of the GA are described.

High performance web of things architecture for the Smart Grid domain

The increasing complexity in the management of Smart Grids is an essential factor in the creation of new technological infrastructures capable of managing the different devices involved in the network. This network has been converted into an example of the Internet of Things. In this regard, the Web of Things enables an improvement in the processing of these data. Besides, the large amount of data in the Smart Grid domain means that a high performance architectural design is able to manage concurrently the entire information processing ability. This paper presents an initial approach for a new architecture and the first results after the system implementation.

Work in progress — Intelligent tutoring system framework for the acquisition of knowledge and competences

Even though there are many tutoring systems to help students achieve their goals in terms of theoretical knowledge, as yet there is no system to foment the acquisition of the competences which form an integral part of university degree programs. This issue is crucial because the Higher Education System is changing in Europe. New educational models are being created to introduce competences which correspond specifically to degree programs. In this work-in-progress the general framework to develop an Intelligent Tutoring System (ITS) based on competences is presented. The system monitorizes the acquisition of theoretical knowledge and also the assessment of the competences related to the subject and it takes corrective actions when needed to fix a negative evolution of the student. The framework is divided into four main phases based on artificial intelligence techniques: construction, location, prediction and reinforcement. The main feature of the proposed framework is the fact that it promotes the academic development of the student in the future educational context by providing guidance and supervision to ensure the successful acquisition of both theoretical knowledge and the corresponding subject-related competences.

Prototyping a Web-of-Energy Architecture for Smart Integration of Sensor Networks in Smart Grids Domain

Sensor networks and the Internet of Things have driven the evolution of traditional electric power distribution networks towards a new paradigm referred to as Smart Grid. However, the different elements that compose the Information and Communication Technologies (ICTs) layer of a Smart Grid are usually conceived as isolated systems that typically result in rigid hardware architectures which are hard to interoperate, manage, and to adapt to new situations. If the Smart Grid paradigm has to be presented as a solution to the demand for distributed and intelligent energy management system, it is necessary to deploy innovative IT infrastructures to support these smart functions. One of the main issues of Smart Grids is the heterogeneity of communication protocols used by the smart sensor devices that integrate them. The use of the concept of the Web of Things is proposed in this work to tackle this problem. More specifically, the implementation of a Smart Grid’s Web of Things, coined as the Web of Energy is introduced. The purpose of this paper is to propose the usage of Web of Energy by means of the Actor Model paradigm to address the latent deployment and management limitations of Smart Grids. Smart Grid designers can use the Actor Model as a design model for an infrastructure that supports the intelligent functions demanded and is capable of grouping and converting the heterogeneity of traditional infrastructures into the homogeneity feature of the Web of Things. Conducted experimentations endorse the feasibility of this solution and encourage practitioners to point their efforts in this direction.

LSMaker: A robotic platform for Engineering Education

In this paper we present an educational resource called LSMaker, a caterpillar mobile robot that has been introduced in the curricula of Engineering Education. The platform has been used to link subjects, so common tasks and challenges have been defined. We are looking for updating contents and educational methodology, enhancing the motivation of students and not less important, increasing the number of new students in our engineering school. The interdisciplinary nature of the robotic project should facilitate the assimilation of new concepts. We present how this project has introduced in the first year course in La Salle Engineering school, and then we analyse the results obtained after two years of running this educational methodology.

Implementation of Traffic Engineering in NGNs Using Hybrid Genetic Algorithms

Traffic engineering, particularly routing optimization, is one of the most important aspects to take into account when providing QoS in next generation networks (NGN). The problem of weight setting with conventional link state routing protocols for routing optimization has been object of study by a few authors. To solve this problem for big networks artificial intelligence heuristics have been used, in concrete genetic algorithms (GA). Some of the proposals incorporate local search procedures in order to optimize the GA results, in the so-called hybrid genetic algorithm (HGA) or memetic algorithm. This paper presents an inedited comparative analysis of the main hybrid genetic algorithms (HGA) proposals, as well as comparing them with other algorithms for the same problem by means of simulations. One of the HGA algorithms was chosen from the results analysis and was implemented over a real testbed with commercial routers with successful OSPFv3 routing optimization.

Web of Energy: hacia la integración inteligente para las redes de sensores en Smart Grids

Parte de esta investigacion ha estado financiada por la SUR de la DEC de la Generalitat de Cataluna y por Fondos Sociales Europeos 2017 FI_B 00583.

The Management System of INTEGRIS

The recent growth experimented by the Internet has fostered the interaction of many heterogeneous technologies under a common environment (i.e., the Internet of Things). Smart Grids entail a sound example of such situation where several devices from different vendors, running different protocols and policies, are integrated in order to reach a common goal: bring together energy delivery and smart services. Latest advances on this domain have led to effective architectures that support this idea from a technical perspective, but fail at providing powerful tools to assist this new business model. Hence, the purpose of this paper is to present a novel unified and ubiquitous management interface, driven by an intelligent system, that uses the advantages featured by the Web of Things to manage the Smart Grid. Therefore, this work opens a new path between the Internet of Things and the Web of Things resulting in a new concept coined as the Web of Energy.