Automatic Classification of Traced Neurons Using Morphological Features
Fuente:
Redalyc
Saved in:
| Main Author: | |
|---|---|
| Format: | Artículo científico |
| Language: | en |
| Published: |
Instituto Politécnico Nacional
2017
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1876485460774092800 |
|---|---|
| author | José D. López- Cabrera |
| author_facet | José D. López- Cabrera |
| contents | Automatic Classification of Traced Neurons Using Morphological Features José D. López- Cabrera Juan V. Lorenzo-Ginori Computación non Neuron tracing parametric tests feature selection morphological features The great advances in the field of neuron tracing have made possible a high availability of free - access data in the Internet , which motivates the realization of automatic classifications. The increas e of neuronal reconstruction databases makes the manual classification of neuron s a time - consuming and tedious task for the analysts . Classification by human experts is also p rone to inter - and intra - an alyst variability due to the process’ inherent subjectivity. In this context, the need arises to find new descriptors having discriminative properties which allow separating the various neuron classes , and this constitutes currently an open problem . Such descriptors would contribute to improve the results of automatic classification. In this study the attention is focused on the use of new mo rphological features in supervised classification of traced neurons . Furthermore, we present a comparative analysis of different supervised learning algorithms oriented to the classification of reconstructed neuron s . The results were validate d using non - parametric statistical test s and they show the usefulness of the proposed solution . 2017 artículo científico 1405-5546 https://www.redalyc.org/articulo.oa?id=61552758014 en http://www.redalyc.org/revista.oa?id=615 Computación y Sistemas application/pdf Instituto Politécnico Nacional Computación y Sistemas (México) Num.3 Vol.21 |
| format | Artículo científico |
| id | redalyc_61552758014 |
| institution | Redalyc |
| language | en |
| publishDate | 2017 |
| publisher | Instituto Politécnico Nacional |
| spellingShingle | Automatic Classification of Traced Neurons Using Morphological Features José D. López- Cabrera Computación non Neuron tracing parametric tests feature selection morphological features Automatic Classification of Traced Neurons Using Morphological Features José D. López- Cabrera Juan V. Lorenzo-Ginori Computación non Neuron tracing parametric tests feature selection morphological features The great advances in the field of neuron tracing have made possible a high availability of free - access data in the Internet , which motivates the realization of automatic classifications. The increas e of neuronal reconstruction databases makes the manual classification of neuron s a time - consuming and tedious task for the analysts . Classification by human experts is also p rone to inter - and intra - an alyst variability due to the process’ inherent subjectivity. In this context, the need arises to find new descriptors having discriminative properties which allow separating the various neuron classes , and this constitutes currently an open problem . Such descriptors would contribute to improve the results of automatic classification. In this study the attention is focused on the use of new mo rphological features in supervised classification of traced neurons . Furthermore, we present a comparative analysis of different supervised learning algorithms oriented to the classification of reconstructed neuron s . The results were validate d using non - parametric statistical test s and they show the usefulness of the proposed solution . 2017 artículo científico 1405-5546 https://www.redalyc.org/articulo.oa?id=61552758014 en http://www.redalyc.org/revista.oa?id=615 Computación y Sistemas application/pdf Instituto Politécnico Nacional Computación y Sistemas (México) Num.3 Vol.21 |
| title | Automatic Classification of Traced Neurons Using Morphological Features |
| topic | Computación non Neuron tracing parametric tests feature selection morphological features |
| url | https://www.redalyc.org/articulo.oa?id=61552758014 |