Improving a cortical pyramidal neuron model's classification performance on a real-world ecg dataset by extending inputs.

Autor: Kayikcioglu Bozkir I; Department of Computer Engineering, Karadeniz Technical University, Trabzon, Türkiye. ilknurkayikcioglu@ktu.edu.tr.; Department of Computer Engineering, Bulent Ecevit University, Zonguldak, Türkiye. ilknurkayikcioglu@ktu.edu.tr., Ozcan Z; Department of Electrical and Electronics Engineering, Karadeniz Technical University, Trabzon, Türkiye., Kose C; Department of Computer Engineering, Karadeniz Technical University, Trabzon, Türkiye., Kayikcioglu T; Department of Electrical and Electronics Engineering, Karadeniz Technical University, Trabzon, Türkiye.; Department of Electrical and Computer Engineering, University of Illinois at Chicago, Chicago, USA., Cetin AE; Department of Electrical and Computer Engineering, University of Illinois at Chicago, Chicago, USA.
Jazyk: angličtina
Zdroj: Journal of computational neuroscience [J Comput Neurosci] 2022 Aug; Vol. 51 (3), pp. 329-341. Date of Electronic Publication: 2023 May 06.
DOI: 10.1007/s10827-023-00851-1
Abstrakt: Pyramidal neurons display a variety of active conductivities and complex morphologies that support nonlinear dendritic computation. Given growing interest in understanding the ability of pyramidal neurons to classify real-world data, in our study we applied both a detailed pyramidal neuron model and the perceptron learning algorithm to classify real-world ECG data. We used Gray coding to generate spike patterns from ECG signals as well as investigated the classification performance of the pyramidal neuron's subcellular regions. Compared with the equivalent single-layer perceptron, the pyramidal neuron performed poorly due to a weight constraint. A proposed mirroring approach for inputs, however, significantly boosted the classification performance of the neuron. We thus conclude that pyramidal neurons can classify real-world data and that the mirroring approach affects performance in a way similar to non-constrained learning.
(© 2023. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)
Databáze: MEDLINE
Externí odkaz: