Pasar al contenido principal

ALGORITMOS DE CLASIFICACION ORDINAL Y PREDICCION EN ENERGIAS RENOVABLES

TIN2014-54583-C2-1-R

•
Nombre agencia financiadora Ministerio de Economía y Competitividad
Acrónimo agencia financiadora MINECO
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2014
Plan Estatal 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Unidad de gestión Secretaría de Estado de Educación, Formación Profesional y Universidades
Centro beneficiario UNIVERSIDAD DE CORDOBA
Identificador persistente http://dx.doi.org/10.13039/501100003329

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

Helvia. Repositorio Institucional de la Universidad de Córdoba
Publicación Artículo científico (JournalArticle)

Multi-objective evolutionary optimization using the relationship between F1 and accuracy metrics in classification tasks

  • Fernández, Juan Carlos
  • Carbonero, Mariano
  • Gutiérrez, Pedro A.
  • Hervás-Martínez, César
This work analyses the complementarity and contrast between two metrics commonly used for evaluating the quality of a binary classifier: the correct classification rate or accuracy, C, and the F1 metric, which is very popular when dealing with imbalanced datasets. Based on this analysis, a set of constraints relating C and F1 are defined as a function of the ratio of positive patterns in the dataset. We evaluate the possibility of using a multi-objective evolutionary algorithm guided by this pair of metrics to optimise binary classification models. To check the validity of the constraints, we perform an empirical analysis considering 26 benchmark datasets obtained from the UCI repository and an interesting liver transplant dataset. The results show that the relation is fulfilled and that the use of the algorithm for simultaneously optimising the pair (C, F1) leads to a generally balanced accuracy for both classes. The experiments also reveal that, in some cases, better results are obtained by using the majority class as the positive class instead of using the minority one, which is the most common approach with imbalanced datasets.
Helvia. Repositorio Institucional de la Universidad de Córdoba
Publicación Tesis de maestría (MasterThesis)

Segmentación de series temporales mediante un algoritmo multiobjetivo evolutivo

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A semi-supervised system for weed mapping in sunflower crops using unmanned aerial vehicles and a crop row detection method

  • Pérez-Ortiz, María
  • Peña Barragán, José Manuel
  • Gutiérrez, Pedro Antonio
  • Torres-Sánchez, Jorge
  • Hervás-Martínez, César
  • López Granados, Francisca
This paper presents a system for weed mapping, using imagery provided by unmanned aerial vehicles (UAVs). Weed control in precision agriculture is based on the design of site-specific control treatments according to weed coverage. A key component is precise and timely weed maps, and one of the crucial steps is weed monitoring, by ground sampling or remote detection. Traditional remote platforms, such as piloted planes and satellites, are not suitable for early weed mapping, given their low spatial and temporal resolutions. Nonetheless, the ultra-high spatial resolution provided by UAVs can be an efficient alternative. The proposed method for weed mapping partitions the image and complements the spectral information with other sources of information. Apart from the well-known vegetation indexes, which are commonly used in precision agriculture, a method for crop row detection is proposed. Given that crops are always organised in rows, this kind of information simplifies the separation between weeds and crops. Finally, the system incorporates classification techniques for the characterisation of pixels as crop, soil and weed. Different machine learning paradigms are compared to identify the best performing strategies, including unsupervised, semi-supervised and supervised techniques. The experiments study the effect of the flight altitude and the sensor used. Our results show that an excellent performance is obtained using very few labelled data complemented with unlabelled data (semi-supervised approach), which motivates the use of weed maps to design site-specific weed control strategies just when farmers implement the early post-emergence weed control., This work was financed by the Recupera 2020 Project (an agreement between CSIC and Spanish MINECO, EU-FEDER funds). Research of Mr. Torres-Sánchez and Dr. Peña was financed by the FPI and Ramón y Cajal Programs, respectively. Research of Dr. Gutiérrez and Dr. Hervás-Martínez has been subsidised by the TIN2014-54583-C2-1-R project of the Spanish Ministerial Commission of Science and Technology (MICYT), FEDER funds and the P11-TIC-7508 project of the “Junta de Andalucía” (Spain)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Contribución de congreso (ConferenceOutput)

A weed monitoring system using UAV- IMAGERY and the hough transform, Un método para cartografiar malas hierbas mediante imágenes de vehículos aéreos no tripulados y la transformada de Hough

  • Pérez-Ortiz, María
  • Peña Barragán, José Manuel
  • Torres-Sánchez, Jorge
  • Hervás-Martínez, César
  • López Granados, Francisca
Trabajo presentado en el XV Congreso de la Sociedad Española de Malherbologia (SEMh), celebrado en Sevilla del 19 al 22 de octubre de 2015., [EN] Usually, weed-infested crops require the use of herbicides as a useful manner of controlling the quality and quantity of crop production. Although there are weed-free areas, the most common approach is to broadcast herbicides entirely over crops fields, resulting in a potential reduction of profits. Recently, patch spraying has allowed the application of site-specific weed management by using precise and timely weed maps at very early phenological stage obtained either by ground sampling or proximal or remote sensing. Remote imagery from piloted planes and satellites are not suitable for this purpose given their low spatial and temporal resolutions; however, unmanned aerial vehicles (UAV) represent an excellent alternatuve. This paper presents a new classification framework for weed monitoring via UAV showing promising results and accurate generalisation in different scenarios., [ES] Las infestaciones de malas hierbas precisan del uso de herbicidas para controlar la calidad y el rendimiento de los cultivos. Aunque las malas hierbas con frecuencia se distribuyen en rodales o agregados, la práctica más extendida es la aplicación de herbicidas en todo el cultivo, resultando en un aumento de los costes. El control localizado de malas hierbas se hace mediante muestreos en campo, detección próxima o teledetección. En este último caso es necesaria la obtención de mapas de emergencias de malas hierbas en fases fenológicas tempranas para utilizarlos para su control en post-emergencia. Las imágenes remotas de aviones pilotados o satélites no son útiles debido a su baja resolución espacial y temporal. Sin embargo, este no es el caso de los vehículos aéreos no tripulados. Este artículo presenta un nuevo método para monitorización de malas hierbas mediante este tipo de plataformas, mostrando resultados prometedores., This work was financed by the Recupera 2020 project (Spanish MINECO and EU-FEDER Funds). Research of Mr. Torres-Sánchez and Dr. Peña was financed by the FPI and Ramón y Cajal programs, respectively. Research of Dr. Gutiérrez and Dr. Hervás-Martínez has been subsidized by the TIN2014-54583-C2-1-R project of the Spanish Ministerial Commission of Science and Technology (MICYT), FEDER funds and the P11-TIC-7508 project of the “Junta de Andalucía” (Spain)., No
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Toward a study of gene regulatory constraints to morphological evolution of the Drosophila ocellar region

  • Aguilar-Hidalgo, Daniel
  • Becerra-Alonso, David
  • García-Morales, Diana
  • Casares, Fernando
The morphology and function of organs depend on coordinated changes in gene expression during development. These changes are controlled by transcription factors, signaling pathways, and their regulatory interactions, which are represented by gene regulatory networks (GRNs). Therefore, the structure of an organ GRN restricts the morphological and functional variations that the organ can experience—its potential morphospace. Therefore, two important questions arise when studying any GRN: what is the predicted available morphospace and what are the regulatory linkages that contribute the most to control morphological variation within this space. Here, we explore these questions by analyzing a small “three-node” GRN model that captures the Hh-driven regulatory interactions controlling a simple visual structure: the ocellar region of Drosophila. Analysis of the model predicts that random variation of model parameters results in a specific non-random distribution of morphological variants. Study of a limited sample of drosophilids and other dipterans finds a correspondence between the predicted phenotypic range and that found in nature. As an alternative to simulations, we apply Bayesian networks methods in order to identify the set of parameters with the largest contribution to morphological variation. Our results predict the potential morphological space of the ocellar complex and identify likely candidate processes to be responsible for ocellar morphological evolution using Bayesian networks. We further discuss the assumptions that the approach we have taken entails and their validity., Open access funding provided by Max Planck Society (Max Planck Institute for the Physics of Complex Systems). Research at the Casares laboratory is funded by the Spanish Ministry for Economy and Innovation (MINECO) and Feder Funds through grant BFU2012-34324 to FC. DGM is a MINECO PhD Fellow. DBA was supported in part by the Spanish Inter-Ministerial Commission of Science and Technology under Project TIN2014-54583-C2-1-R, the European Regional Development fund, and the “Junta de Andalucía” (Spain), under Project P2011-TIC-7508., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

On the use of nominal and ordinal classifiers for the discrimination of states of development in fish oocytes

  • Pérez-Ortiz, María
  • Fernández-Delgado, M.
  • Cernadas, Eva
  • Domínguez-Petit, Rosario
  • Gutiérrez, Pedro Antonio
  • Hervás-Martínez, César
16 pages, 5 tables, 3 figures, The analysis of microscopic images of fish gonad cells (oocytes) is a useful tool to estimate parameters of fish reproductive ecology and to analyze fish population dynamics. The study of oocyte dynamics is needed to understand ovary development and reproductive cycle of fish. Oocytes go through different developmental states in a continuum temporal sequence providing an interesting example of ordinal classification, which is not exploited by the current oocyte analysis software. This promising paradigm of machine learning known as ordinal classification or ordinal regression focus on classification problems where there exist a natural order between the classes, thus requiring specific methods and evaluation metrics. In this paper we compare 11 ordinal and 15 nominal state-of-the-art classifiers using oocytes of three fish species (Merluccius merluccius, Trisopterus luscus and Reinhardtius hippoglossoides). The best results are achieved by SVMOD, an ordinal decomposition method of the labelling space based on the Support Vector Machine, varying strongly with the number of states for each specie (about 95 and 80 % of accuracy with three and six states respectively). The classifiers designed specially for ordinal classification are able to capture the underlying nature of the state ordering much better than common nominal classifiers. This is demonstrated by several metrics specially designed to measure misclassification errors associated to states far in the ranking scale., We acknowledge support from the “Junta de Andalucía” under project P11-TIC-7508, from the Spanish Ministry of Science and Innovation (MICINN) under projects TIN2011-22935, TIN2012-32262 and TIN2014-54583-C2-1-R, and from FEDER funds, Peer reviewed