Brain–Machine Interface
Engineering
Justin C. Sanchez and José C. Principe
University of Florida
DOWNLOAD
best book on Brain Machine Interface Engineering
Neural interfaces are one of the most exciting emerging technologies to impact bioengineering and
neuroscience because they enable an alternate communication channel linking directly the nervous
system with man-made devices. This book reveals the essential engineering principles and
signal processing tools for deriving control commands from bioelectric signals in large ensembles
of neurons. The topics featured include analysis techniques for determining neural representation,
modeling in motor systems, computing with neural spikes, and hardware implementation of neural
interfaces. Beginning with an exploration of the historical developments that have led to the decoding
of information from neural interfaces, this book compares the theory and performance of new
neural engineering approaches for BMIs.
neural interfaces, brain, neural engineering, neuroscience, neural representation, motor systems
Contents
1. Introduction to Neural Interfaces .........................................................................1
1.1 Types of Brain–Machine Interfaces ..................................................................... 3
1.2 Beyond State-of-the-Art Technology.................................................................. 4
1.3 Computational Modeling .................................................................................... 6
1.4 Generation of Communication and Control Signals in the Brain ....................... 8
1.5 Motor BMIs ...................................................................................................... 12
References ................................................................................................................... 15
2. Foundations of Neuronal Representations .......................................................... 21
2.1 Cytoarchitecture ................................................................................................ 21
2.2 Connectionism .................................................................................................. 22
2.3 Neural Signaling and Electric Fields of the Brain ............................................. 23
2.4 Spiking Models for the Neuron ......................................................................... 28
2.5 Stochastic Modeling .......................................................................................... 29
2.6 Neural Coding and Decoding ........................................................................... 31
2.7 Methods of Kinematic and Dynamic Representation ....................................... 33
2.7.1 Rate Coding .......................................................................................... 34
2.7.2 Effect of Resolution on Rate Coding .................................................... 34
2.7.3 Multiresolution Analysis of Neural Spike Trains ................................... 35
2.7.4 Using Firing Rates to Compute Tuning ................................................ 40
2.7.5 Information Theoretic Tuning Metrics.................................................. 42
2.7.6 Timing Codes........................................................................................ 43
2.8 Modeling and Assumptions ............................................................................... 46
2.8.1 Correlation Codes ................................................................................. 46
2.9 Implications for BMI Signal Processing ............................................................ 48
References ................................................................................................................... 49
3. Input–output BMI Models ............................................................................... 57
3.1 Multivariate Linear Models ............................................................................... 60
3.1.1 Linear Modeling for BMIs and the Wiener Filter ................................ 62
3.1.2 Iterative Algorithms for Least Squares:
The Normalized LMS ........................................................................... 67
3.2 Nonlinear Models .............................................................................................. 71
3.2.1 Time Delay Neural Networks ............................................................... 71
3.2.2 Recursive MLPs .................................................................................... 76
3.2.2.1 Echo-State Networks ............................................................. 81
3.2.2.2 Design of the ESN ................................................................. 83
3.2.3 Competitive Mixture of Local Linear Models ...................................... 84
3.2.3.1 Gated Competitive Experts .................................................... 88
3.2.3.2 Gated Competitive Experts in BMIs...................................... 91
3.3 Summary ........................................................................................................... 94
References ................................................................................................................... 95
4. Regularization Techniques for BMI Models ....................................................... 99
4.1 Least Squares and Regularization Theory ....................................................... 100
4.1.1 Ridge Regression and Weight Decay ................................................... 103
4.1.2 Gamma Filter ...................................................................................... 104
4.1.3 Subspace Projection ............................................................................. 107
4.2 Channel Selection............................................................................................ 110
4.2.1 Sensitivity-Based Pruning ................................................................... 111
4.2.2
4.2.3 Real-Time Input Selection for Linear Time-Variant
MIMO Systems .............................................................................................. 124
4.3 Experimental Results ....................................................................................... 129
4.4 Summary ......................................................................................................... 137
References ................................................................................................................. 138
L1-Norm Penalty Pruning ................................................................... 1205. Neural decoding Using generative BMI Models .............................................. 141
5.1 Population Vector Coding ............................................................................... 142
5.2 Sequential Estimation ..................................................................................... 144
5.3 Kalman Filter .................................................................................................. 147
5.4 Particle Filters ................................................................................................. 150
5.5 Hidden Markov Models .................................................................................. 153
5.5.1 Application of HMMs in BMIs .......................................................... 158
5.6 Summary ......................................................................................................... 168
References ................................................................................................................. 169
6. adaptive algorithms for Point Processes .......................................................... 173
6.1 Adaptive Filtering for Point Processes With a Gaussian
Assumption ..................................................................................................... 174
viii BRaIN–MaChINE INTERFaCE ENgINEERINg
6.2 Monte Carlo Sequential Estimation for Point Processes ................................. 176
6.3 Simulation of Monte Carlo Sequential Estimation Using
Spike Trains ..................................................................................................... 178
6.4 Encoding/Decoding in Motor Control ........................................................... 182
6.4.1 Spike Generation from Neuronal Tuning ............................................ 183
6.4.1.1 Modeling and Assumptions .................................................. 183
6.4.2 Estimating the Nonlinearity in the LNP Model ................................. 186
6.4.3 Estimating the Time Delay From the Motor Cortex
to Movement ....................................................................................... 188
6.4.4 Point Process Monte Carlo Sequential Estimation
Framework for BMIs ........................................................................... 189
6.4.5 Decoding Results Using Monte Carlo Sequential Estimation ............ 191
6.5 Summary ......................................................................................................... 194
References ................................................................................................................. 195
7. BMI Systems .................................................................................................. 197
7.1 Sensing Neuronal Activity: The Electrodes ..................................................... 200
7.1.1 Microelectrode Design Specifications ................................................. 203
7.1.2 Process Flow ........................................................................................ 204
7.1.3 In Vivo Testing .................................................................................... 204
7.2 Amplification ................................................................................................... 207
7.2.1 Integrated Bioamplifier ........................................................................ 207
7.3 The PICO System ........................................................................................... 210
7.3.1 In Vivo Testing and Results ................................................................. 213
7.4 Portable DSP Designs: The Neural Signal Processor ...................................... 216
7.4.1 Digital Signal Processor ....................................................................... 217
7.5 Florida Wireless Implantable Recording Electrodes ....................................... 221
7.5.1 Neural Signal Processing and Representation ..................................... 222
7.5.2 Wireless ............................................................................................... 225
7.5.2.1 Wireless Power and Data Interface ....................................... 227
7.6 Summary ......................................................................................................... 227
References ................................................................................................................. 228
author Biography .................................................................................................... 233
No comments:
Post a Comment