Por favor, use este identificador para citar o enlazar este ítem: https://repositorio.uci.cu/jspui/handle/123456789/9465
Título : Classification of Neuron Sets from Non-disease States Using Time Series Obtained Through Nonlinear Analysis of the 3D Dendritic Structures
Autor : Hernández Pérez, Leonardo Agustín
López Cabrera, José Daniel
Orozco Morales, Rubén
Lorenzo Ginori, Juan Valentín
Fecha de publicación : 2018
Editorial : Springer
Citación : Hernández-Pérez L.A., López-Cabrera J.D., Orozco-Morales R., Lorenzo-Ginori J.V. (2018) Classification of Neuron Sets from Non-disease States Using Time Series Obtained Through Nonlinear Analysis of the 3D Dendritic Structures. In: Hernández Heredia Y., Milián Núñez V., Ruiz Shulcloper J. (eds) Progress in Artificial Intelligence and Pattern Recognition. IWAIPR 2018. Lecture Notes in Computer Science, vol 11047. Springer, Cham. https://doi.org/10.1007/978-3-030-01132-1_2
Resumen : The nonlinear dynamic analysis of time series is a powerful tool which has extended its application to many branches of scientific research. Topological equivalence is one of the main concepts that sustain theoretically the nonlinear dynamics procedures that have been implemented to characterize the discrete time series. Based on this concept, in this work a novel way to analyze dendritic trees with high complexity is reported, using features obtained through splitting the 3D structure of the dendritic trees of traced neurons into time series. Digitally reconstructed neurons were separated into control and pathological sets, which are related to two categories of alterations caused by the reduced activity of the adult born neurons (ABNs) in the mouse olfactory bulb. In the first category, a viral vector encoding a small interfering RNA (siRNA) to knock-down sodium channel expression and a second category a naris occlusion (NO) method is applied to reduce the activity of ABNs that migrate to the olfactory bulb. Using the method proposed in this study the mean result of the correct classification was improved in 4.8 and 2.76% for the NO and siRNA sets respectively, while the maximum correct classification rates were improved in 9.53 and 2.5% respectively, when compared to methods based in the use of morphological features.
URI : https://repositorio.uci.cu/jspui/handle/123456789/9465
Aparece en las colecciones: Eventos

Ficheros en este ítem:
Fichero Tamaño Formato  
A022.pdf105.09 kBAdobe PDFVisualizar/Abrir

Los ítems del Repositorio están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.