María Jesús Verdú

A genetic fuzzy expert system for automatic question classification in a competitive learning environment

Intelligent tutoring systems are efficient tools to automatically adapt the learning process to the students progress and needs. One of the possible adaptations is to apply an adaptive question sequencing system, which matches the difficulty of the questions to the students knowledge level. In this context, it is important to correctly classify the questions to be presented to students according to their difficulty level. Many systems have been developed for estimating the difficulty of questions. However the variety in the application environments makes difficult to apply the existing solutions directly to other applications. Therefore, a specific solution has been designed in order to determine the difficulty level of open questions in an automatic and objective way. This solution can be applied to activities with special temporal and running features, as the contests developed through QUESTOURnament, which is a tool integrated into the e-learning platform Moodle. The proposed solution is a fuzzy expert system that uses a genetic algorithm in order to characterize each difficulty level. From the output of the algorithm, it defines the fuzzy rules that are used to classify the questions. Data registered from a competitive activity in a Telecommunications Engineering course have been used in order to validate the system against a group of experts. Results show that the system performs successfully. Therefore, it can be concluded that the system is able to do the questions classification labour in a competitive learning environment.

A neural network based intelligent system for tile prefetching in web map services

Web mapping has become a popular way of distributing interactive digital maps over the internet. Instead of dynamically generating map images on the fly, those can be pre-generated and served from a server-side cache for faster retrieval. However, these caches can grow unmanageably in size when the cartography covers mid to large areas for multiple rendering scales. This forces modest organizations to use partial caches containing just a subset of the total tiles, and makes their services less attractive than other mapping services like Google Maps or Microsoft Bing Maps. This work proposes a neural-network-based intelligent system that predicts which areas are likely to be requested in the future from a catalog of geographic features and a short history of past requests. These priority regions can be used by a tile prefetching policy to achieve an optimal population of the cache. Neural networks are trained and validated using supervised learning with real data-sets from a public nation-wide web map service. Trace-driven simulations demonstrate that accurate long-term predictions, up to 90% in terms of cache-hit ratio, can be obtained with the proposed model by prefetching a low fraction, only the 20% of the total tiles, and with a short training period.

Motivating Students through On-Line Competition: An Analysis of Satisfaction and Learning Styles

The Bologna model pursues to improve the quality of Higher Education and, in turn, human resources across Europe. One of the action lines of the Bologna Process is the promotion of the attractiveness of the European Higher Education Area (EHEA). In this context, motivated students are a key element. Motivation can be reached in a number of different ways, one of which is explored in this paper, and consists in the use of active e-learning methodologies to force students to compete among themselves during their learning process. The relationship between motivation and competition is analysed through a number of hypotheses focusing on elements such as the level of satisfaction of students with different learning styles (competitive, collaborative...) when using the competitive active e-learning tool called QUESTournament. This system has been used in several University courses belonging to different degrees and diplomas taught at the University of Valladolid (Spain). Data collected from these experiences are analysed and discussed.

An adaptive neural network-based method for tile replacement in a web map cache

Most popular web map services, such as Google Maps, serve pre-generated image tiles from a server-side cache. However, storage needs are often prohibitive, forcing administrators to use partial caches containing a subset of the total tiles. When the cache runs out of space for allocating incoming requests, a cache replacement algorithm must determine which tiles should be replaced. Cache replacement algorithms are well founded and characterized for general Web documents but spatial caches comprises a set of specific characteristics that make them suitable to further research. This paper proposes a cache replacement policy based on neural networks to take intelligent replacement decisions. Neural networks are trained using supervised learning with real data-sets from public web map servers. Hight correct classification ratios have been achieved for both training data and a completely independent validation data set, which indicates good generalization of the neural network. A benchmark of the performance of this policy against several classical cache management policies is given for discussion.

Web Map Tile Services for Spatial Data Infrastructures:: Management and Optimization

Webmapping has become a popular way of distributing online mapping through the Internet. Multiple services, like the popular Google Maps or Microsoft Bing Maps, allow users to visualize cartography by using a simple Web browser and an Internet connection. However, geographic information is an expensive resource, and for this reason standardization is needed to promote its availability and reuse. In order to standardize this kind of map services, the Open Geospatial Consortium (OGC) developed the Web Map Service (WMS) recommendation [1]. This standard provides a simple HTTP interface for requesting geo-referenced map images from one or more distributed geospatial databases. It was designed for custom maps rendering, enabling clients to request exactly the desired map image. This way, clients can request arbitrary sized map images to the server, superposing multiple layers, covering an arbitrary geographic bounding box, in any supported coordinate reference system or even applying specific styles and background colors.

Intercultural and multilingual e-learning to bridge the digital divide

The Internet is changing the economy, the society and the culture. But an inequality in access to information exits and is creating an information digital divide. This article describes the ODISEAME project as an effort to extend the use of the Internet to several very different countries of the Euro-Mediterranean area. One of the main achievements of the project is to share and transfer technology and knowledge, with the aim of reducing the existing barriers for digital inclusion. ODISEAME is an intercultural and multilingual project, which is focused on the application of Information and Communication Technologies to the learning process in the context of University Education. The article firstly examines the barriers of digital inclusion: cost of infrastructure and lack of contents in the mother tongue. It then describes the ODISEAME project and the e-learning experiences, before discussing how the project promotes digital inclusion.

Estimating the difficulty level of the challenges proposed in a competitive e-learning environment

The success of new learning systems depends highly on their ability to adapt to the characteristics and needs of each student. QUESTOURnament is a competitive e-learning tool, which is being re-designed in order to turn it into an adaptive e-learning system, managing different contests adapted to the progress of the students. In this adaptation process, the first step is to design a mechanism that objectively estimates the difficulty level of the challenges proposed in this environment. The present paper describes the designed method, which uses a genetic algorithm in order to discover the characteristics of the answers to the questions corresponding to the different difficulty levels. The fitness function, which evaluates the quality of the different potential solutions, as well as other operators of the genetic algorithm are described. Finally, an experiment with a real data set is presented in order to show the performance of this approach.

A Proposal of User Interface for a Distributed Asynchronous Remote Evaluation System: An Evolution of the QUESTOURnament Tool

This paper presents a distributed asynchronous system which allows remote evaluation of students’ submissions. This system is being developed in the context of the EduJudge project whose aim is to provide a greater pedagogic character for the UVa Online Judge, an on-line programming trainer. The UVa Online Judge has been integrated into the e-learning platform Moodle and a competitive tool called QUESTOURnament. More specifically, this paper focuses on the design of the user interface of the evolved QUESTOURnament tool. It has been adapted to be able to manage different competition strategies and to have a centralized system for the management of questionnaires.

A Diversity-Enhanced Genetic Algorithm to Characterize the Questions of a Competitive e-Learning System

Nowadays, the practice of different teaching methodologies is easier thanks to the technology-enhanced learning systems. However, in order to effectively center the learning process in the student it should be adapted to the student’s progress. Adaptive e-learning systems have been proved to be valuable tools, which facilitate this adaptation. QUESTOURnament, an active and competitive Moodle tool, is being re-designed in order to become an adaptive system. One of the first steps in this adaptation is the estimation of the difficulty level of the questions proposed in this environment. This paper describes a solution based on a genetic algorithm with enhanced diversity methods that automatically characterizes the answers to the challenges. The algorithm has been tested with data registered from a contest made in a Telecommunications Engineering course. It finds diverse good solutions, from which several rules can be defined to classify the questions according to their difficulty level.

Effects of competitive learning tools on medical students: A case study

Objective Competitive learning techniques are being successfully used in courses of different disciplines. However, there is still a significant gap in analyzing their effects in medical students competing individually. The authors conducted this study to assess the effectiveness of the use of a competitive learning tool on the academic achievement and satisfaction of medical students. Methods The authors collected data from a Human Immunology course in medical students (n = 285) and conducted a nonrandomized (quasi-experimental) control group pretest-posttest design. They used the Mann-Whitney U-test to measure the strength of the association between two variables and to compare the two student groups. Results The improvement and academic outcomes of the experimental group students were significantly higher than those of the control group students. The students using the competitive learning tool had better academic performance, and they were satisfied with this type of learning. The study, however, had some limitations. The authors did not make a random assignment to the control and experimental groups and the groups were not completely homogenous. Conclusion The use of competitive learning techniques motivates medical students, improves their academic outcomes and may foster the cooperation among students and provide a pleasant classroom environment. The authors are planning further studies with a more complete evaluation of cognitive learning styles or incorporating chronometry as well as team-competition.