Abstract

DELGADO CASTILLO, Duniel et al. Machine learning algorithms for classification of pyramidal neurons affected by aging. RCIM [online]. 2016, vol.8, suppl.1, pp.559-571. ISSN 1684-1859.

Accurate morphological characterization of the multiple neuronal classes of the brain would facilitate the elucidation of brain function and the functional changes that underlie neurological disorders such as Parkinson's diseases or Schizophrenia. Manual morphological analysis is very time-consuming and suffers from a lack of accuracy because some cell characteristics are not readily quantified. This paper presents an investigation in the automatic classification of a data set of pyramidal neurons of young and adult monkeys, which degrade his morphologic structure with the aging. A set of 21 features were used to describe their morphology in order to identify differences between neurons. Thispaper evaluates the performance of four popular machine learning methods, in the classification of neural trees. The machine learning methods used are: support vector machines (SVMs), k-nearest neighbors (KNN), multinomial logistic regression (MLR) and back propagation neural network (BPNN). The results showed the advantages of MLR and BPNN with respect to others for this purposes. These automatic classification algorithms offer advantages over manual expert based classification. While neuroscience is rapidly transitioning to digital data, the principles behind automatic classification algorithms remain often inaccessible to neuroscientists, limiting the potential for breakthroughs.

Keywords : neurons; neuroinformatics; machine learning; classifiers.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )