Comparison of Feature Selection Methods for Robust Dexterous Decoding of Finger Movements from the Primary Motor Cortex of a Non-human Primate Using Support Vector Machine by

i ABSTRACT Robust and stable decoding of neural signals is imperative for implementing a useful neuroprosthesis capable of carrying out dexterous tasks. A nonhuman primate (NHP) was trained to perform combined flexions of the thumb, index and middle fingers in addition to individual flexions and extensions of the same digits. An array of microelectrodes was implanted in the hand area of the motor cortex of the NHP and used to record action potentials during finger movements. A Support Vector Machine (SVM) was used to classify which finger movement the NHP was making based upon action potential firing rates. The effect of four feature selection techniques, Wilcoxon signed-rank test, Relative Importance, Principal Component Analysis, and Mutual Information Maximization was compared based on SVM classification performance. SVM classification was used to examine the functional parameters of (i) efficacy (ii) endurance to simulated failure and (iii) longevity of classification. The effect of using isolated-neuron and multi-unit firing rates was compared as the feature vector supplied to the SVM. The best classification performance was on post-implantation day 36, when using multi-unit firing rates the worst classification accuracy resulted from features selected with Wilcoxon signed-rank test (51.12 ± 0.65%) and the best classification accuracy resulted from Mutual Information Maximization (93.74 ± 0.32%). On this day when using single-unit firing rates, the classification accuracy from the Wilcoxon signed-rank test was 88.85 ± 0.61 % and Mutual Information Maximization was 95.60 ± 0.52% (degrees of freedom =10, level of chance =10%) ii ACKNOWLEDGMENTS I would like to thank my parents, Padma and Padmanaban, for being supportive and encouraging me throughout my Master's thesis. I am truly indebted to you both for giving me the freedom to pursue my dreams as early on as I can remember. I consider myself fortunate to have carried out my Master's research in the Neural Engineering Laboratory under Dr. Bradley Greger. Thank you Dr. Greger for showing us how to be a good researcher. In addition to promoting crazy ideas, I'm thankful to you for giving me a sense of bigger picture and showing me the right direction during critical moments of my thesis. I would also like to thank Dr. Helms Tillery for their constant feedback which shaped up this thesis. I would like to thank my brother, friends and family for their support.