Over recent decades, database sizes have grown considerably. Larger sizes present new challenges, because machine learning algorithms are not prepared to process such large volumes of information. Instance selection methods can alleviate this problem when the size of the data set is medium to large. However, even these methods face similar problems with very large-to-massive data sets.\ud \ud In this paper, two new algorithms with linear complexity for instance selection purposes are presented. Both algorithms use locality-sensitive hashing to find similarities between instances. While the complexity of conventional methods (usually quadratic, O(n2), or log-linear, O(nlogn)) means that they are unable to process large-sized data sets, the new proposal shows competitive results in terms of accuracy. Even more remarkably, it shortens execution time, as the proposal manages to reduce complexity and make it linear with respect to the data set size. The new proposal has been compared with some of the best known instance selection methods for testing and has also been evaluated on large data sets (up to a million instances).Supported by the Research Projects TIN 2011-24046 and TIN 2015-67534-P from the Spanish Ministry of Economy and Competitiveness

Purpose: Recent research in higher education has pointed out that personalized e-learning through the use of learning management systems, such as Moodle, improves the academic results of students and facilitates the detection of at-risk students.Design/methodology/approach: A sample of 124 students following the Degree in Health Sciences at the University of Burgos participated in this study. The objectives were as follows: to verify whether the use of a Moodle-based personalized e-learning system will predict the learning outcomes of students and the use of effective learning behaviour patterns and to study whether it will increase student satisfaction with teaching practice.Findings: The use of a Moodle-based personalized e-learning system that included problem-based learning (PBL) methodology predicted the learning outcomes by 42.3 per cent, especially with regard to the results of the quizzes. In addition, it predicted effective behavioural patterns by 74.2 per cent. Increased student satisfaction levels were also identified through the conceptual feedback provided by the teacher, arguably because it facilitated a deeper understanding of the subject matter.Research limitations/implications: The results of this work should be treated with caution, because of the sample size and the specificity of the branch of knowledge of the students, as well as the design type. Future studies will be directed at increasing the size of the sample and the diversity of the qualifications.Originality/value: Learning methodology in the twenty-first century has to be guided towards carefully structured work from the pedagogic point of view in the learning management systems allowing for process-oriented feedback and PBL both included in personalized e-learning systems.

Early detection of at-risk students is essential, especially in the university environment. Moreover, personalized learning has been shown to increase motivation and lower student dropout rates. At present, the average dropout rates among students following courses leading to the award of Spanish university degrees are around 18% and 42.8% for presential teaching and online courses, respectively. The objectives of this study are: (1) to design and to implement a Modular Object-Oriented Dynamic Learning Environment (Moodle) plugin, “eOrientation”, for the early detection of at-risk students; (2) to test the effectiveness of the “eOrientation” plugin on university students. We worked with 279 third-year students following health sciences degrees. A process for extracting information records was also implemented. In addition, a learning analytics module was developed, through which both supervised and unsupervised Machine Learning techniques can be applied. All these measures facilitated the personalized monitoring of the students and the easier detection of students at academic risk. The use of this tool could be of great importance to teachers and university governing teams, as it can assist the early detection of students at academic risk. Future studies will be aimed at testing the plugin using the Moodle environment on degree courses at other universities.