Multivariate time series often contain missing values for reasons such as failures in data collection mechanisms. Since these missing values can complicate the analysis of time series data, imputation techniques are typically used to deal with this issue. However, the quality of the imputation directly affects the performance of downstream tasks. In this paper, we propose a selective imputation method that identifies a subset of timesteps with missing values to impute in a multivariate time series dataset. This selection, which will result in shorter and simpler time series, is based on both reducing the uncertainty of the imputations and representing the original time series as good as possible. In particular, the method uses multi-objective optimization techniques to select the optimal set of points, and in this selection process, we leverage the beneficial properties of the Multi-task Gaussian Process (MGP). The method is applied to different datasets to analyze the quality of the imputations and the performance obtained in downstream tasks, such as classification or anomaly detection. The results show that much shorter and simpler time series are able to maintain or even improve both the quality of the imputations and the performance of the downstream tasks.

Major efforts have been conducted on ontology learning, that is, semiautomatic processes for the construction of domain ontologies from diverse sources of information. In the past few years, a research trend has focused on the construction of educational ontologies, that is, ontologies to be used for educational purposes. The identification of the terminology is crucial to build ontologies. Term extraction techniques allow the identification of the domain‐related terms from electronic resources. This paper presents LiTeWi, a novel method that combines current unsupervised term extraction approaches for creating educational ontologies for technology supported learning systems from electronic textbooks. LiTeWi uses Wikipedia as an additional information source. Wikipedia contains more than 30 million articles covering the terminology of nearly every domain in 288 languages, which makes it an appropriate generic corpus for term extraction. Furthermore, given that its content is available in several languages, it promotes both domain and language independence. LiTeWi is aimed at being used by teachers, who usually develop their didactic material from textbooks. To evaluate its performance, LiTeWi was tuned up using a textbook on object oriented programming and then tested with two textbooks of different domains—astronomy and molecular biology.

Technology-supported learning systems have proved to be helpful in many learning situations. These systems require an appropriate representation of the knowledge to be learned, the Domain Module. The authoring of the Domain Module is cost and labor intensive, but its development cost might be lightened by profiting from semiautomatic Domain Module authoring techniques and promoting knowledge reuse. DOM-Sortze is a system that uses natural language processing techniques, heuristic reasoning, and ontologies for the semiautomatic construction of the Domain Module from electronic textbooks. To determine how it might help in the Domain Module authoring process, it has been tested with an electronic textbook, and the gathered knowledge has been compared with the Domain Module that instructional designers developed manually. This paper presents DOM-Sortze and describes the experiment carried out.

Due to the impact that Information and Communication Technologies have in the current society in general, and in academic institutions in particular, there is a growing need for effective creation and management of digital content. But content authoring is known to be an effort and time consuming task. Digital contents used inside Technology Supported Learning Systems with learning purposes are often referred to as Didactic Resources, or Learning Objects if they are annotated with metadata. One of the main advantages of Learning Objects is that they can be reused to support learning in different platforms or environments. Along this paper an experiment carried out with ErauzOnt, a system that automatically builds Learning Objects from electronic textbooks using Natural Language Processing techniques, ontologies and heuristic reasoning is presented. ErauzOnt was able to gather definitions, examples and exercises for the topics of the Object Oriented Programming subject - a compulsory subject studied at the first year of the Computer Engineering degree at the University of the Basque Country - using as a starting point a textbook written in English.

Concept maps are graphical tools for organizing and representing knowledge. The fundamentals of concept mapping are in Ausubel's learning theory which is based on the assumption that meaningful learning occurs when the new concepts are linked to familiar concepts existing in the learner's cognitive structure. Creativity can be seen as a very high level of meaningful learning. Database Principles is a compulsory subject studied in the second year of the Computer Engineering degree at the University of the Basque Country UPV/EHU. The study presented in the paper was designed pursuing a twofold goal: (1) to introduce engineering students the Concept Mapping technique as a way to promote meaningful learning, and (2) to involve engineering students in both a creative and collaborative learning experience using concept maps. Final exam marks showed significant statistical differences among the experimental group and the control group. In addition, participants admitted that the use of the concept mapping technique to fulfill the objectives of this study is applicable to other domains, situations and problems.