Abstract:
Many real-time brain-machine interface (BMI) applications require quickest detection of abrupt changes in observed neural signals in an online manner. In the presence of ...Show MoreMetadata
Abstract:
Many real-time brain-machine interface (BMI) applications require quickest detection of abrupt changes in observed neural signals in an online manner. In the presence of multi-neuronal recordings, we propose both model-based and model-free approaches to detect the change in neuronal ensemble spiking activity. The model-based approach is motivated from state space modeling and recursive Bayesian filtering. The model-free approach is motivated from the CUSUM algorithm that computes the cumulative log-likelihood statistics. In the application of detecting the onset of acute thermal pain signals, we validate these approaches using experimental population spike data recorded from freely behaving rats.
Date of Conference: 25-28 May 2017
Date Added to IEEE Xplore: 14 August 2017
ISBN Information:
Electronic ISSN: 1948-3554