This paper presents a methodology to biological image classification through a Rough-Fuzzy Artificial Neural Network (RFANN). This approach is used in order to improve the learning process by Rough Sets Theory (RS) focusing on the feature selection, considering that the RS feature selection allows the use of low dimension features from the image database. This result could be achieved, once the image features are characterized using membership functions and reduced it by Fuzzy Sets rules. The RS identifies the attributes relevance and the Fuzzy relations influence on the Artificial Neural Network (ANN) surface response. Thus, the features filtered by Rough Sets are used to train a Multilayer Perceptron Neuro Fuzzy Network. The reduction of feature sets reduces the complexity of the neural network structure therefore improves its runtime. To measure the performance of the proposed RFANN the runtime and training error were compared to the unreduced features.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Biological image classification using rough-fuzzy artificial neural network



    Erscheinungsdatum :

    30.12.2015


    Anmerkungen:

    orcid:0000-0002-0363-6800



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Application of Fuzzy ARTMAP Neural Network in TM Image Classification

    Han, M. / Cheng, L. / Tang, X.-l. et al. | British Library Online Contents | 2004


    Image Classification using Neural Network Technology

    Collins, C. E. | British Library Online Contents | 1991


    Fuzzy-rough feature selection aided support vector machines for Mars image classification

    Shang, C. / Barnes, D. | British Library Online Contents | 2013


    Contruction of an SVM Rough Neural Network and Its Classification Decision

    Xiao, D. / Hu, S.-s. | British Library Online Contents | 2004


    Radar-based Object Classification Using An Artificial Neural Network

    Lee, Dajung / Cheung, Colman / Pritsker, Dan | IEEE | 2019