Abstract
This paper presents a new method to solve the problem of identification of neurons. Firstly, the neurons are divided into 7 categories based on their functions and geometrical characteristics. In order to get the key feature of neurons, the principal component analysis (PCA) technique was used to do the decorrelation processing with the geometrical characteristic data extracted from space geometric data of neurons. Then the BP neural network algorithm was used to classify and identify the neurons and to establish the mapping relationship between the key characteristics of neuronal geometry and the categories, thus the classification and identification of the neurons was completed. The experimental results shown that this method on neurons identification accuracy is high by 91.4%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bedenbaugh, P., Sarko, D.K., et al.: Prosody-Preserving Voice Transformation to Evaluate Brain Representations of Speech Sounds. IEEE Transactions Audio, Speech, and Language Processing (2010)
Ascoli, G., Goldin, R.F.: Coordinate systems for dendritic spines: a somatocentric approach. J. Complexity 2(4), 40–48 (1997)
lei, Y., shu-qin, L.: Principal component analysis in the application of wheat stripe rust prediction. J. Computer engineering and design 31(2), 459–461 (2010) (in Chinese)
fa-jun, Y., yuan-li, Z.: Principal component analysis combined with perceptron application in medical spectral classification. J. Spectroscopy and spectral analysis 10, 2396–2400 (2008) (in Chinese)
Panagakis, Y., Kotropoulos, C., Arce, G.R.: Non-Negative Multilinear Principal Component Analysis of Auditory Temporal Modulations for Music Genre Classification. IEEE Transactions Audio, Speech, and Language Processing, 576–588 (2010)
Han, X.: Nonnegative Principal Component Analysis for Cancer Molecular Pattern Discovery. IEEE/ACM Transactions Computational Biology and Bioinformatics,, 537–549 (2010)
Zou, w.-f., Zhu, z.-d.: The color images target recognition method of space and distance conversion. Journal of Nanjing University of Aeronautics 39(5), 601–606 (2007) (in Chinese)
Berger, T.W., Dong, S., et al.: The Neurobiological Basis of Cognition: Identification by Multi-Input, Multioutput Nonlinear Dynamic Modeling. Proceedings of the IEEE (2010)
Tomas, P., Sousa, L.A.: A Feature Selection Algorithm for the Regularization of Neuron Models. IEEE Transactions Instrumentation and Measurement (2009)
Liu, y.-j., Zhu, j.-y., Zeng, j.: The improvment of the BP neural network in engine performance trend analysis and the application of fault diagnosis. Journal of the institute of technology of nanjing university (natural science edition) 34(1), 24–29 (2010) (in Chinese)
Zong-Ben, X., Rui, Z., Wen-Feng, J.: When Does Online BP Training Converge? IEEE Transactions Neural Networks (2009)
Muzhou, H., Xuli, H.: Constructive Approximation to Multivariate Function by Decay RBF Neural Network. IEEE Transactions Neural Networks (2010)
Wang, j.-g., Ding, y.: Long distance pipeline across structure damage test simulation and recognition. Journal of tianjin university 43(3), 229–233 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, X., Lv, D. (2011). A Method of Neurons Classification and Identification. In: Ma, M. (eds) Communication Systems and Information Technology. Lecture Notes in Electrical Engineering, vol 100. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21762-3_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-21762-3_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21761-6
Online ISBN: 978-3-642-21762-3
eBook Packages: EngineeringEngineering (R0)