Detecting memory content in firing rate signals using a machine learning approach: A fractal analysis

Abstract

While top-down modulation can be observed by increases in neuronal firing in some brain areas, modulation in other areas demonstrates complex nonlinear dynamics. When these signal modifications cannot be identified by classical methods, fractal analysis can be used to better describe the resulting changes. It was previously shown that the Higuchi dimension could detect such modification. However, these changes likely extend to multiple fractal dimensions. In this paper, machine learning algorithms were employed to extract the fractal features of neuronal firing and detect the occurrence of top-down modulation. We assessed the performance of classifiers trained on different fractal features as well as the Fourier transform and wavelet transform-based features obtained from the firing rate signals during a spatial memory task to measure the ability of individual neurons in the middle temporal cortex to hold memory information. By comparing the results of the different classifiers, Higuchi fractal dimension was confirmed as the strongest indicator of working memory content in cortical firing patterns compared to other fractal features. We demonstrated the utility of this approach and observed that the middle temporal cortex likely encodes spatial working memory based on linear and nonlinear temporal features rather than simply increasing the average firing rate.