Nearest neighbor-based methods are classic techniques that, due to their efficiency, still are widely used today. However, they have not been broadly applied to solve the multi-instance multi-label (MIML) problem, a supervised learning paradigm that combines multi-instance (MI) and multi-label (ML) learning. This work presents new neighbor-based approaches for solving MIML problems. On the one hand, MIML data are transformed into ML data and ML nearest neighbor algorithms are used. On the other hand, algorithms that directly address MIML data and use a bag-based distance are proposed. A comprehensive study and an overall comparison have been conducted to study the performance of these methods using different configurations. Experiments included 16 datasets and 8 performance metrics. The results and statistical tests showed that the problem transformation applied and the distance function used impacted the performance and that the approaches that do not transform the problem obtained the best predictive results. Furthermore, most of the proposed algorithms outperformed the MIMLkNN algorithm, the state-of-art algorithm for MIML learning based on nearest-neighbor. Therefore, the relevance and capabilities of neighbor-based approaches to obtain competitive results in MIML learning are shown. Finally, all the algorithms developed in this paper have been included in the MIML library to facilitate the comparison with other future proposals.

MIML library is a Java software tool to develop, test, and compare classification algorithms for multi-instance multi-label (MIML) learning. The library includes 43 algorithms and provides a specific format and facilities for data managing and partitioning, holdout and cross-validation methods, standard metrics for performance evaluation, and generation of reports. In addition, algorithms can be executed through xml configuration files without needing to program. It is platform-independent, extensible, free, open-source, and available on GitHub under the GNU General Public License.

Multi-label classification paradigm has had a growing interest because of the emergence of a large number of classification problems where each of the instances of the data can be associated with several output labels simultaneously. Several ensemble methods were proposed to solve the multilabel classification problem. However, most of them simply create diversity in the ensemble by following a random procedure and give the same importance to all members. In this paper, we propose a Grammar-Guided Genetic Programming algorithm to build ensembles of multi-label classifiers. Given a pool of multilabel classifiers, each of them modeling dependencies among a subset of k labels, they are combined into a tree-shaped ensemble. At each node of the tree, predictions of its children nodes are combined, while each leaf represents a classifier from the pool. We propose two configurations for the method: using a fixed value of k for all classifiers in the pool, or using a variable value of k for each classifier, thus being able to capture relationships among groups of labels of different size in the ensemble. The experiments performed over sixteen multi-label dataset and using five evaluation metrics demonstrated that our method performs significantly better than the state-of-the-art ensembles of multilabel classifiers.

Multi-label classification deals with problems where each of the data instances has several labels associated with it. Although many ensemble-based approaches for multi-label classification have been proposed, several of them do not take into account intrinsic characteristics of the data during their design. In this paper we present a cooperative coevolutionary algorithm which considers such specific characteristics to build an ensemble of accurate and diverse multi-label classifiers. The algorithm evolves several subpopulations simultaneously, each using a different subset of the training data. Also, each individual is focused only on a small subset of labels. These two characteristics provide greater diversity of members to generate the ensemble. As it evolves separate members, we also define a procedure to build an ensemble given the individuals. The experimental study comparing the proposed method to the state-of-the-art in multi-label classification using thirteen datasets and five evaluation metrics demonstrated that the developed cooperative coevolutionary algorithm performed consistently and statistically better than the other methods.

The multi-label classification task has gained a lot of attention in the last decade thanks to its good application to many real-world problems where each object could be attached to several labels simultaneously. Several approaches based on ensembles for multi-label classification have been proposed in the literature; however, the vast majority are based on randomly selecting the different aspects that make the ensemble diverse and they do not consider the characteristics of the data to build it. In this paper we propose an evolutionary method called Evolutionary AlGorithm for multi-Label Ensemble opTimization, EAGLET, for the selection of simple, accurate and diverse multi-label classifiers to build an ensemble considering the characteristics of the data, such as the relationship among labels and the imbalance degree of the labels. In order to model the relationships among labels, each classifier of the ensemble is focused on a small subset of the label space, resulting in models with a relative low computational complexity and lower imbalance in the output space. The resulting ensemble is generated incrementally given the population of multi-label classifiers, so the member that best fits to the ensemble generated so far, considering both predictive performance and diversity, is selected. The experimental study comparing EAGLET with state-of-the-art methods in multi-label classification over a wide set of sixteen datasets and five evaluation measures, demonstrated that EAGLET significantly outperformed standard MLC methods and obtained better and more consistent results than state-of-the-art multi-label ensembles.

Learning objects are digital resources that can be deployed by means of a web system for supporting teaching. A key advantage is reuse, and this is possible thanks to learning objects repositories that allow learning object search, management and categorization. In this work, we propose a novel approach towards automatically learning object categorization taking into consideration learning object usage information. We use a multi-label learning approach since each learning object might be associated with multiple categories. We have developed a methodology with three main stages allowing us to firstly select the most suitable set of text features from learning objects metadata, secondly selecting how much historical learning object usage information can enhance classification performance, and finally selecting the best multilabel classification algorithms with our data. We have carried out an experimental work using 519 learning objects gathered from the AGORA repository for 8 years. We have compared 13 multi-label classification algorithms over 16 evaluation measures. The results obtained show that usage information about the learning object can improve the classification.

Multi-label classification has attracted increasing attention of the scientific community in recent years, given its ability to solve problems where each of the examples simultaneously belongs to multiple labels. From all the techniques developed to solve multi-label classification problems, Classifier Chains has been demonstrated to be one of the best performing techniques. However, one of its main drawbacks is its inherently sequential definition. Although many research works aimed to reduce the runtime of multi-label classification algorithms, to the best of our knowledge, there are no proposals to specifically reduce the runtime of Classifier Chains. Therefore, in this paper we propose a method called Parallel Classifier Chains which enables the parallelization of Classifier Chain. In this way, Parallel Classifier Chains builds k binary classifiers in parallel, where each of them includes as extra input features the predictions of those labels that have been previously built. We performed an experimental evaluation over 20 datasets using 5 metrics to analyze both the runtime and the predictive performance of our proposal. The results of the experiments affirmed that our proposal was able to significantly reduce the runtime of Classifier Chains while the predictive performance was not statistically significantly harmed.

In recent years, the multi-label classification task has gained the attention of the scientific community given its ability to solve problems where each of the instances of the dataset may be associated with several class labels at the same time instead of just one. The main problems to deal with in multi-label classification are the imbalance, the relationships among the labels, and the high complexity of the output space. A large number of methods for multi-label classification has been proposed, but although they aimed to deal with one or many of these problems, most of them did not take into account these characteristics of the data in their building phase. In this paper we present an evolutionary algorithm for automatic generation of ensembles of multi-label classifiers by tackling the three previously mentioned problems, called Evolutionary Multi-label Ensemble (EME). Each multi-label classifier is focused on a small subset of the labels, still considering the relationships among them but avoiding the high complexity of the output space. Further, the algorithm automatically designs the ensemble evaluating both its predictive performance and the number of times that each label appears in the ensemble, so that in imbalanced datasets infrequent labels are not ignored. For this purpose, we also proposed a novel mutation operator that considers the relationship among labels, looking for individuals where the labels are more related. EME was compared to other state-of-the-art algorithms for multi-label classification over a set of fourteen multi-label datasets and using five evaluation measures. The experimental study was carried out in two parts, first comparing EME to classic multi-label classification methods, and second comparing EME to other ensemble-based methods in multi-label classification. EME performed significantly better than the rest of classic methods in three out of five evaluation measures. On the other hand, EME performed the best in one measure in the second experiment and it was the only one that did not perform significantly worse than the control algorithm in any measure. These results showed that EME achieved a better and more consistent performance than the rest of the state-of-the-art methods in MLC.

Los Grados Universitarios en sus planes de estudios tienen asignados una serie de créditos optativos, en los que el estudiante tiene libertad para elegir las asignaturas que más le interesen. Esta elección suele ser bastante complicada para los estudiantes, que si bien cuentan con una guía docente de cada asignatura, que les permite conocer los contenidos teóricos y prácticos, los profesores que la imparten, la metodología y los criterios de evaluación, no suele ser suficiente para decidirse. En este contexto, los estudiantes están interesados en las valoraciones que le pueden ofrecer otros compañeros o compañeras que las cursaron, siendo una práctica habitual que los estudiantes recurran a los estudiantes de otros cursos para que les orienten en el proceso. No obstante, se debe tener cierta precaución con esta práctica, porque no todas las valoraciones que se reciban deberían tener la misma consideración. Por un lado, los intereses y propósitos del estudiante que pide opinión y los del estudiante que la proporciona puede que sean diferentes, y por otro lado, puede que la información se encuentre distorsionada por haber pasado por varios intermediarios. En este escenario, los sistemas de recomendación aparecen como herramientas para ayudar a la toma de decisiones generando recomendaciones a los estudiantes sobre un determinado objeto de estudio, a partir de preferencias y opiniones dadas por otros estudiantes que tienen unos intereses o preferencias similares a los suyos. En este proyecto se ha diseñado e implementado una aplicación móvil, fácil de manejar por los estudiantes y que permite que cualquier estudiante registrado en un determinado Grado pueda obtener una recomendación sobre las asignaturas que más le pueden interesar.

Este artículo describe un proyecto de innovación educativa centrado en diseñar y desarrollar un nuevo módulo de Moodle que permita obtener modelos predictivos basados en árboles de decisión a partir de los datos de uso almacenados en Moodle. Debido a las características de los modelos basados en árboles de decisión, es posible relacionar el trabajo personal realizado por los alumnos en Moodle con la calificación final obtenida, proporcionándonos así una descripción de los recursos y actividades que resultan clave para superar/suspender una asignatura. Con esta información, el profesor podría detectar alumnos con alta probabilidad de no superar la asignatura e intentar reconducir la situación. Este módulo puede ser aplicado en cualquier asignatura de la plataforma Moodle. Concretamente, para comprobar su funcionamiento, ha sido aplicado la asignatura Introducción a la Programación impartida en el grado de Ingeniería Informática de la Universidad de Córdoba.

The automatic classification of LOs into different categories enables us to search for, access, and reuse them in an effective and efficient way. Following this idea, in this paper, we focus specifically on how to automatically recommend the classification attribute of the IEEE LOM when a user adds a new LO to a repository. To do it, we propose the use of the multi-label classification approach, since each LO might be simultaneously associated with multiple labels. An initial problem we have found is that the number of terms or pure text features that characterize LOs tends to be very high. So, we propose to apply a dimensionality reduction process. We have carried out an experiment using 515 LOs from the AGORA repository in order to try to reduce the number of features or attributes used, improving execution time without losing prediction accuracy.

The great attention given by the scientific community to multi-label learning in recent years has led to the development of a large number of methods, many of them based on ensembles. A comparison of the state-of-theart in ensembles of multi-label classifiers over a wide set of 20 datasets have been carried out in this paper, evaluating their performance based on the characteristics of the datasets such as imbalance, dependence among labels and dimensionality. In each case, suggestions are given to choose the algorithm that fits best. Further, given the absence of taxonomies of ensembles of multi-label classifiers, a novel taxonomy for these methods is proposed.

In this article we present an evolutionary algorithm for the optimization of sequences of targets for the multi-target regression algorithm Ensemble of Regressor Chains. This algorithm selects several random sequences or chains of targets where to predict each target, the values of previous targets in the chain are included as features, considering in this way the relationship among them. Under the assumption that a target may be better predicted if it is highly correlated with the targets which were included as feature, our proposal, called CCO-ERC, looks for chains where each target is highly correlated with previous targets in the chain. Several methods for the combination of predictions in the ensemble and for the selection of the chains which forms the ensemble are also proposed. CCO-ERC is compared to other state-of-the-art algorithms in multi-target regression, presenting statistically better performance than them.

The objective of this paper is to present MLDA, a tool for the exploration and analysis of multi-label datasets with both simple and multiple views. MLDA comprises a GUI and a Java API, providing the user with a wide set of charts, metrics, methods for transforming and preprocessing data, as well as comparison of several datasets. The paper introduces the main features of the framework, and introduces its use toward some illustrative examples. (C) 2017 Elsevier B.V. All rights reserved.

The reduction of energy consumption in buildings is one of the goals to improve energy efficiency. One way to achieve energy savings in buildings is to develop intelligent control strategies for heating systems that are able to reduce power consumption without affecting the thermal comfort. An intelligent control system must be able to predict the temperature of the building in order to manage the heating system. In this paper, we present a rule-based model that is able to predict the indoor temperature for different values of k (hours ahead in time). The model has been learned with FRULER, a genetic fuzzy system that generates accurate and simple knowledge bases. Our approach has been validated with real data from a residential college.

Multi-label learning is a challenging task in data mining which has attracted growing attention in recent years. Despite the fact that many multi-label datasets have continuous features, general algorithms developed specially to transform multi-label datasets with continuous attributes' values into a finite number of intervals have not been proposed to date. Many classification algorithms require discrete values as the input and studies have shown that supervised discretization may improve classification performance. This paper presents a Label-Attribute Interdependence Maximization (LAIM) discretization method for multi-label data. LAIM is inspired in the discretization heuristic of CAIM for single-label classification. The maximization of the label-attribute interdependence is expected to improve labels prediction in data separated through disjoint intervals. The main aim of this paper is to present a discretization method specifically designed to deal with multi-label data and to analyze whether this can improve the performance of multi-label learning methods. To this end, the experimental analysis evaluates the performance of 12 multi-label learning algorithms (transformation, adaptation, and ensemble-based) on a series of 16 multi-label datasets with and without supervised and unsupervised discretization, showing that LAIM discretization improves the performance for many algorithms and measures.

Multi-label classification with multiple data views is a recent research field not much explored. This more flexible learning approach allows each pattern to be represented by several sets of attributes and each pattern can have simultaneously associated several labels. In this work, an ensemble-based approach, which enables the fusion of views at decision level by majority voting, is proposed. The study carried out on four data sets considering 27 multi-label evaluation metrics shows that our proposal overcomes and improves the results obtained by the individual views as well as the execution time and the performance of the classic approach which concatenates all the views in a single set of features.

Multilabel learning has become a relevant learning paradigm in the past years due to the increasing number of fields where it can be applied and also to the emerging number of techniques that are being developed. This article presents an up-to-date tutorial about multilabel learning that introduces the paradigm and describes the main contributions developed. Evaluation measures, fields of application, trending topics, and resources are also presented.

Recommending classification algorithms is an open research problem the solution to which is of tremendous value for practitioners and non-experts data mining users such as educators. This paper proposes a new meta-learning framework for educational domains based on the use of multi-label learning for selecting the best classification algorithms in order to predict students’ performance. In short, the framework considers an offline phase where statistical tests are performed to find the subset of algorithms that achieves the best performance over the repository of educational data sets. The subset of algorithms along with the meta-features extracted from the training data are used to generate a multi-label data set. A multi-label classifier is then trained and, in an online phase, this model is used to recommend the most suitable classification algorithms to be applied to new unseen data sets. This new multi-label meta-learning approach has been applied to a repository of educational data sets generated from Moodle usage data. The results obtained show significant improvement compared with a previous nearest neighbor proposal, demonstrating the suitability of the new framework.