José Antonio Gutiérrez

Competency-Based Learning Object Sequencing Using Particle Swarms

This paper describes the process of learning taxonomic relations automatically from Modern Greek economic corpora. Supervised learning (Decision trees, Support Vector Machines, Meta-learning) is applied to economic term pairs; each pair is represented through a set of statistical, semantic and syntactic features. The resulting set of feature-value vectors presents a high imbalance in the class distribution, due to the large number of term pairs that do not present a direct semantic relation. This problem is addressed using One-sided Sampling, which reduces the number of the majority class instances by removing examples that are noisy, misleading or redundant. The approach makes use of no external resources (merely an economic corpus that is annotated with elementary morphological and phrase chunking information) and limited language-dependent elements to facilitate its portability to other languages and domains. An overall f-measure of 71 % is achieved.In e-learning initiatives, sequencing problem concerns arranging a particular set of learning units in a suitable succession for a particular learner. Sequencing is usually performed by instructors, who create general and ordered series rather than learner personalized sequences. This paper proposes an innovative intelligent technique for learning object automated sequencing using particle swarms. E-learning standards are promoted in order to ensure interoperability. Competencies are used to define relations between learning objects within a sequence, so that the sequencing problem turns into a permutation problem and AI techniques can be used to solve it. Particle Swarm Optimization (PSO) is one of such techniques and it has proven with good performance solving a wide variety of problems. An implementation of the PSO, for learning object sequencing, is presented and its performance in a real scenario is discussed.

Swarm intelligence in e-learning: a learning object sequencing agent based on competencies

In e-learning initiatives content creators are usually required to arrange a set of learning resources in order to present them in a comprehensive way to the learner. Course materials are usually divided into reusable chunks called Learning Objects (LOs) and the ordered set of LOs is called sequence, so the process is called LO sequencing. In this paper an intelligent agent that performs the LO sequencing process is presented. Metadata and competencies are used to define relations between LOs so that the sequencing problem can be characterized as a Constraint Satisfaction Problem (CSP) and artificial intelligent techniques can be used to solve it. A Particle Swarm Optimization (PSO) agent is proposed, built, tuned and tested. Results show that the agent succeeds in solving the problem and that it handles reasonably combinatorial explosion inherent to this kind of problems.

A System for Adaptation of Educational Contents to Learners and their Mobile Device

In this paper we propose a system that allows to adapt educational contents to learners, based on the knowledge of a learner who is conducting the training through his mobile device, contents will also be tailored to the features of the device and to the context where the learner is at the present moment.

Evaluating Simple Query Interface Compliance in Public Repositories

Standards and specifications widely accepted and used lay the foundations to enable and facilitate the interoperability among systems, and the software maintenance and reuse, especially within the scope of learning objects’ search systems. One of these standards is the SQI (Standard Query Interface) specification by the European Committee for Standardization in which many search systems, including public ones, are based. This paper analyzes the degree of compliance with this specification by a significant number of learning objects repositories.

Assessment design: A step towards interoperability

The assessment in e‐learning systems is a basic element to successfully complete any formative action. In this article we present a generic, flexible, interoperable and reusable language for design assessments, and its implementation in the EDVI Learning Management System. This language is based on XML and we have used XML Schema technology. We also describe the language attributes required to set the assessment plan based on our practical experience in e‐learning courses. The main purpose of this language is to make the assessment design interoperable among systems in a simple and efficient way. An adequate implementation will also reduce the time required to configure assessment activities, simplifying and automating them.

Competency-Based Intelligent Curriculum Sequencing: Comparing Two Evolutionary Approaches

The process of creating e-learning contents using reusable learning objects (LOs) can be broken down in two sub-processes: LOs finding and LO sequencing. Although semiautomatic tools that aid in the finding process exits, sequencing is usually performed by instructors, who create courses targeting generic profiles rather than personalized materials. This paper proposes an evolutionary approach to automate this latter problem while, simultaneously, encourages reusability and interoperability by promoting standards employment. A model that enables automated curriculum sequencing is proposed. By means of interoperable competency records and LO metadata, the sequencing problem is turn into a constraint satisfaction problem. Particle swarm optimization (PSO) and genetic algorithm (GA) agents are designed, built and tested in real and simulated scenarios. Results show both approaches succeed in all test cases, and that they handle reasonably computational complexity inherent to this problem, but PSO approach outperforms GA.

Competency-Based Intelligent Curriculum Sequencing Using Particle Swarms

As a part of many e-learning initiatives, a set of learning units must be arranged in a particular order to meet the learnerspsila requirements. This process is known as sequencing and it is typically performed by instructors, who create wide-public ordered series rather than learner personalized sequences. This paper proposes an innovative intelligent technique for learning object automated sequencing using particle swarms. E-learning standards are promoted in order to ensure interoperability. Competencies are used to define relations among learning objects within a sequence, so that the sequencing problem turns into a permutation problem and a particle swarm optimization algorithm can be applied to solve it. Results demonstrate that the new agent succeeds and it shows a good performance in real and tests scenarios.

Particle Swarms for Competency-Based Curriculum Sequencing

In e-learning initiatives content creators are usually required to arrange a set of learning resources in order to present them in a comprehensive way to the learner. Course materials are usually divided into reusable chunks called Learning Objects (LOs) and the ordered set of LOs is called sequence, so the process is called LO sequencing. In this paper an intelligent agent that performs the LO sequencing process is presented. Metadata and competencies are used to define relations between LOs so that the sequencing problem can be characterized as a Constraint Satisfaction Problem (CSP) and artificial intelligent techniques can be used to solve it. A Particle Swarm Optimization (PSO) agent is proposed, built, tuned and tested. Results show that the agent succeeds in solving the problem and that it handles reasonably combinatorial explosion inherent to this kind of problems.

A multidisciplinary computer science master program

This paper presents the University of Alcala attempt to join computer science and information engineering with other fields (business, law, pedagogy, nursery and humanities) in a Masters Program. The main objective of this approach is to attract graduate students to computer science offering them an alternative way to join its own knowledge and competencies with those in computing skills which are closely related.

The integration of SQI in a reusable learning objects system: advantages and disadvantages

Current e-learning applications should provide universal access to educational information, regardless of the standards, protocols or programming languages used. This would maximize the reuse of learning objects and help this technology to gain its place as a fundamental and, in some cases only, support tool for present day educational systems. To achieve this, it is necessary that standards are adopted that guarantee, both the development of learning objects and the search systems that provide access to the repositories that contain them; this being the only way to guarantee universal access. In this article the effects produced by one of the standards attempting to guarantee universal access are studied. The main features of the principal systems that execute it are identified, as well as its more notable advantages and disadvantages. The integration of the SQI (Simple Query Interface) standard in a reusable learning objects system, previously developed by the authors, is put forward, describing the conclusions of the process.