Browsing by Subject "Instance Selection"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    Open Access
    A k-nearest neighbors based approach applied to more realistic activity recognition datasets
    (IOS Press, 2018) Cadenas Figueredo, J. M.; Garrido Carrera, María del Carmen; Martínez España, R.; Muñoz, A.; Ingeniería de la Información y las Comunicaciones
    Due to the latest technological advances, the current society has the possibility to store large volumes of data in the majority of the problems of the daily life. These data are useless if there is not a set of techniques available to analyze them with the objective of obtaining knowledge that facilitates the problem resolution. This paper focuses on the techniques provided by data mining as a tool for intelligent data analysis in the field of human activity recognition, specifically in the application of two techniques of data mining capable of carrying out the extraction of knowledge from data that are not as accurate and exact as desirable. This type of data reflects the true nature of the information collected on a day-to-day basis. The proposed techniques allow us to perform a preprocessing of the data by means of an instance selection that improves the computational requirements of the system response, obtaining satisfactory accuracy results. Several experiments are carried out on a real world dataset and various datasets obtained from the previous one in a synthetic way to simulate more realistic datasets that illustrate the potential of the techniques proposed.
  • Thumbnail Image
    Publication
    Open Access
    Three-objective constrained evolutionary instance selection for classification: Wrapper and filter approaches
    (Elsevier, International Federation of Automatic Control (IFAC), 2021-11-11) Jiménez Barrionuevo, Fernando; Sánchez, Gracia; Palma Méndez, José Tomás; Sciavicco, Guido; Ingeniería de la Información y las Comunicaciones
    The large amount of data that is produced today with new technologies is an impediment for machine learning algorithms to work correctly, both due to the memory requirements and the necessary execution times. That is why the processes of reducing both the quantity and the size of the data are increasingly important. One of these processes is the so-called instance selection. In this paper we propose three-objective constrained optimization models to formulate instance selection wrapper and filter methods (separately) for classification problems, which are solved with multi-objective evolutionary algorithms and multi-objective differential evolution. In the proposed instance selection wrapper method, an objective is added to the usual ones to minimize the generalization error of the classifier. The proposed instance selection filter method simultaneously optimizes the correlation, redundancy and consistency of the datasets. Instance retention constraints are imposed on optimization models to retain a maximum percentage of samples, established by the decision maker, in big data scenarios. The experiments have been designed to compare (1) the NSGA-II and MODE algorithms, (2) two- and three-objective optimization models, (3) two different constraint handling techniques, and (4) the proposed evolutionary approaches and other 12 non-evolutionary approaches used in literature. The proposed wrapper and filter instance selection methods have been used in a real-world business engineering application, and have also been validated using three public datasets to facilitate the replicability of the research results. The results of the experiments show the superiority of the three-objective constrained evolutionary techniques proposed in this paper over the non-evolutionary techniques and over the two-objective evolutionary approaches used in the literature.