A robust method to help identify the population of neurons used for decoding motor tasks is developed. We use sensitivity analysis to develop a new metric for quantifying the relative contribution of a neuron towards the decoded output, called “fractional sensitivity.” Previous model-based approaches for neuron ranking have been shown to largely depend on the collection of training data. We suggest the use of an ensemble of models that are trained on random subsets of trials to rank neurons. For this work, we tested a decoding algorithm on neuronal data recorded from two male rhesus monkeys while they performed a reach to grasp a bar at three orientations ( , , or ). An ensemble approach led to a statistically significant increase of 5% in decoding accuracy and 25% increase in identification accuracy of simulated noisy neurons, when compared to a single model. Furthermore, ranking neurons based on the ensemble fractional sensitivities resulted in decoding accuracies 10%–20% greater than when randomly selecting neurons or ranking based on firing rates alone. By systematically reducing the size of the input space, we determine the optimal number of neurons needed for decoding the motor output. This selection approach has practical benefits for other BMI applications where limited number of electrodes and training datasets are available, but high decoding accuracies are desirable. 1. Introduction A Brain-Machine Interface (BMI) uses activities recorded from various motor areas, such as the primary motor, premotor and posterior parietal cortex, to translate neural activities recorded from the brain into commands to control an external device. Traditionally, BMI researchers have used extracellular action potentials from localized cortical sites, primarily in the motor cortex, to provide closed-loop control of a computer cursor [1] or a robotic arm in 3D space [2–4]. More recently, researchers have now begun to use implanted microelectrode arrays, which can simultaneously sample neuronal ensembles from various cortical sites [5–7]. These electrode arrays are surgically placed in cortical regions which are correlated to the motor function. The relevant cortical regions are identified using anatomical guidance, preliminary probing of neural activity and imaging techniques such as FMRI. However, in multichannel recordings only 30%–40% of single units are typically relevant to the motor task [8]; the remaining neurons are either noisy or not task-related. This adds uncorrelated dimensions to the input space, thereby degrading the predictive performance of the
References
[1]
M. D. Serruya, N. G. Hatsopoulos, L. Paninski, M. R. Fellows, and J. P. Donoghue, “Instant neural control of a movement signal,” Nature, vol. 416, no. 6877, pp. 141–142, 2002.
[2]
J. M. Carmena, M. A. Lebedev, R. E. Crist, et al., “Learning to control a brain-machine interface for reaching and grasping by primates,” PLoS Biology, vol. 1, no. 2, article E42, 2003.
[3]
J. Wessberg and M. A. Nicolelis, “Optimizing a linear algorithm for real-time robotic control using chronic cortical ensemble recordings in monkeys,” Journal of Cognitive Neuroscience, vol. 16, no. 6, pp. 1022–1035, 2004.
[4]
J. Wessberg, C. R. Stambaugh, J. D. Kralik, et al., “Real-time prediction of hand trajectory by ensembles of cortical neurons in primates,” Nature, vol. 408, no. 6810, pp. 361–365, 2000.
[5]
U. T. Eden, W. Truccolo, M. R. Fellows, J. P. Donoghue, and E. N. Brown, “Reconstruction of hand movement trajectories from a dynamic ensemble of spiking motor cortical neurons,” in Proceedings of the IEEE 26th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC '04), vol. 6, pp. 4017–4020, San Francisco, Calif, USA, September 2004.
[6]
D. M. Taylor, S. I. Tillery, and A. B. Schwartz, “Direct cortical control of 3D neuroprosthetic devices,” Science, vol. 296, no. 5574, pp. 1829–1832, 2002.
[7]
R. Wahnoun, J. He, and S. I. Helms-Tillery, “Selection and parameterization of cortical neurons for neuroprosthetic control,” Journal of Neural Engineering, vol. 3, no. 2, pp. 162–171, 2006.
[8]
D. R. Kipke, R. J. Vetter, J. C. Williams, and J. F. Hetke, “Silicon-substrate intracortical microelectrode arrays for long-term recording of neuronal spike activity in cerebral cortex,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 11, no. 2, pp. 151–155, 2003.
[9]
D. T. Westwick, E. A. Pohlmeyer, S. A. Solla, L. E. Miller, and E. J. Perreault, “Identification of multiple-input systems with highly coupled inputs: application to EMG prediction from multiple intracortical electrodes,” Neural Computation, vol. 18, no. 2, pp. 329–355, 2006.
[10]
J. C. Sanchez, J. M. Carmena, M. A. Lebedev, M. A. L. Nicolelis, J. G. Harris, and J. C. Principe, “Ascertaining the importance of neurons to develop better brain-machine interfaces,” IEEE Transactions on Biomedical Engineering, vol. 51, no. 6, pp. 943–953, 2004.
[11]
W. Jensen and P. J. Rousche, “On variability and use of rat primary motor cortex responses in behavioral task discrimination,” Journal of Neural Engineering, vol. 3, no. 1, pp. L7–L13, 2006.
[12]
N. Kumar and A. G. Andreou, “Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognition,” Speech Communication, vol. 26, no. 4, pp. 283–297, 1998.
[13]
Y. Gao, M. J. Black, E. Bienenstock, W. Wu, and J. P. Donoghue, “A quantitative comparison of linear and non-linear models of motor cortical activity for the encoding and decoding of arm motions,” in Proceedings of the 1st International IEEE/EMBS Conference on Neural Engineering, pp. 189–192, Los Alamitos, Calif, USA, 2003.
[14]
J. C. Sanchez, S.-P. Kim, D. Erdogmus, et al., “Input-output mapping performance of linear and nonlinear models for estimating hand trajectories from cortical neuronal firing patterns,” in Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing (NNSP '02), pp. 139–148, Martigny, Switzerland, September 2002.
[15]
W. Wu, M. J. Black, Y. Gao, E. Bienenstock, M. D. Serruya, and J. P. Donoghue, “Inferring hand motion from multi-cell recordings in motor cortex using a Kalman filter,” in Proceedings of the Workshop on Motor Control in Humans and Robots: On the Interplay of Real Brains and Artificial Devices (SAB '02), pp. 66–73, Edinburgh, Scotland, 2002.
[16]
S. Acharya, F. Tenore, V. Aggarwal, R. Etienne-Cummings, M. H. Schieber, and N. V. Thakor, “Decoding finger movements using volume-constrained neuronal ensembles in the M1 hand area,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 16, no. 1, pp. 15–23, 2008.
[17]
V. Aggarwal, S. Acharya, F. Tenore, et al., “Asynchronous decoding of dexterous finger movements using M1 neurons,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 16, no. 1, pp. 3–14, 2008.
[18]
J. K. Chapin, K. A. Moxon, R. S. Markowitz, and M. A. L. Nicolelis, “Real-time control of a robot arm using simultaneously recorded neurons in the motor cortex,” Nature Neuroscience, vol. 2, no. 7, pp. 664–670, 1999.
[19]
J. C. Sanchez, D. Erdogmus, M. A. L. Nicolelis, J. Wessberg, and J. C. Principe, “Interpreting spatial and temporal neural activity through a recurrent neural network brain-machine interface,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 13, no. 2, pp. 213–219, 2005.
[20]
G. Singhal, S. Acharya, N. Davidovics, J. He, and N. Thakor, “Including planning activity in feature space distributes activation over a broader neuron population,” in Proceedings of the IEEE/EMBS Annual International Conference of the Engineering in Medicine and Biology (EMBC '07), pp. 5349–5352, Lyon, France, August 2007.
[21]
G. Singhal, S. Acharya, N. Davidovics, J. He, and N. Thakor, “Including planning activity in feature space distributes activation over a broader neuron population,” in Proceedings of the IEEE/EMBS Annual International Conference of the Engineering in Medicine and Biology (EMBC '07), pp. 5349–5352, Lyon, France, August 2007.
[22]
S.-P. Kim, J. C. Sanchez, Y. N. Rao, et al., “A comparison of optimal MIMO linear and nonlinear models for brain-machine interfaces,” Journal of Neural Engineering, vol. 3, no. 2, pp. 145–161, 2006.
[23]
M. Leshno, V. Y. Lin, A. Pinkus, and S. Schocken, “Multilayer feedforward networks with a nonpolynomial activation function can approximate any function,” Neural Networks, vol. 6, no. 6, pp. 861–867, 1993.
[24]
V. Y. Kreinovich, “Arbitrary nonlinearity is sufficient to represent all functions by neural networks: a theorem,” Neural Networks, vol. 4, no. 3, pp. 381–383, 1991.
[25]
O. Intrator and N. Intrator, “Interpreting neural-network results: a simulation study,” Computational Statistics and Data Analysis, vol. 37, no. 3, pp. 373–393, 2001.
[26]
M. Velliste, S. Perel, M. C. Spalding, A. S. Whitford, and A. B. Schwartz, “Cortical control of a prosthetic arm for self-feeding,” Nature, vol. 453, no. 7198, pp. 1098–1101, 2008.
[27]
M. D. Serruya, N. G. Hatsopoulos, L. Paninski, M. R. Fellows, and J. P. Donoghue, “Instant neural control of a movement signal,” Nature, vol. 416, no. 6877, pp. 141–142, 2002.
