Tracking times in temporal patterns embodied in intra-cortical data for controling neural prosthesis an animal simulation study

Abdessalam Kifouche, Abderrezak Guessoum


Brain-machinescapture brain signals inorder to restore communication and movement to disabled people suffering from motor disorders or even brain palsy. In brain regions, the ensemble firing of populations of neurons represents spatio-temporal patterns that are transformed into outgoing spatio-temporal patterns which encode complex cognitive task. This transformation is dynamic, non-stationary (time-varying) and highly nonlinear. Hence, modeling such complex biological patterns requires specific model structures to uncover the underlying physiological mechanisms and their influences on system behavior. In this study, a recent multi-electrode technology allows the record of the simultaneous neuron activities in behaving animals. Intra-cortical data are processed in successive stages: spike detection, spike sorting, and intention extraction from the firing rate signal. We focus on the following important questions: is it realistic to link time events from the primary motor cortex with some time-delay mapping tool? Are some inputs more suitable than others for this mapping? Shall we consider separated channels or a special representation based on multidimensional statistics?
This paper concentrates mostly on the analysis of parallel spike train when certain critical assumptions for the method to work are violated by the data. We have put efforts in defining explicitly if the underlying assumptions are indeed fulfilled.In this paper, we propose an algorithm to determine the embedded memory order of NARX recurrent neural networks in the hand trajectory decoding process. We also show that this algorithm can demonstrate improved performance on inference tasks.


Multiple input single output; Decoding algorithm; Spatiotemporal pattern ; Spike ; Time delay neural network

Total views : 17 times


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.