Real-Time EMG Based Pattern Recognition Control for Hand Prostheses: A Review on Existing Methods, Challenges and Future Implementation.

Upper limb amputation is a condition that significantly restricts the amputees from performing their daily activities. The myoelectric prosthesis, using signals from residual stump muscles, is aimed at restoring the function of such lost limbs seamlessly. Unfortunately, the acquisition and use of such myosignals are cumbersome and complicated. Furthermore, once acquired, it usually requires heavy computational power to turn it into a user control signal. Its transition to a practical prosthesis solution is still being challenged by various factors particularly those related to the fact that each amputee has different mobility, muscle contraction forces, limb positional variations and electrode placements. Thus, a solution that can adapt or otherwise tailor itself to each individual is required for maximum utility across amputees. Modified machine learning schemes for pattern recognition have the potential to significantly reduce the factors (movement of users and contraction of the muscle) affecting the traditional electromyography (EMG)-pattern recognition methods. Although recent developments of intelligent pattern recognition techniques could discriminate multiple degrees of freedom with high-level accuracy, their efficiency level was less accessible and revealed in real-world (amputee) applications. This review paper examined the suitability of upper limb prosthesis (ULP) inventions in the healthcare sector from their technical control perspective. More focus was given to the review of real-world applications and the use of pattern recognition control on amputees. We first reviewed the overall structure of pattern recognition schemes for myo-control prosthetic systems and then discussed their real-time use on amputee upper limbs. Finally, we concluded the paper with a discussion of the existing challenges and future research recommendations.

Fully Open-Access Passive Dry Electrodes BIOADC: Open-Electroencephalography (EEG) Re-Invented.

The Open-electroencephalography (EEG) framework is a popular platform to enable EEG measurements and general purposes Brain Computer Interface experimentations. However, the current platform is limited by the number of available channels and electrode compatibility. In this paper we present a fully configurable platform with up to 32 EEG channels and compatibility with virtually any kind of passive electrodes including textile, rubber and contactless electrodes. Together with the full hardware details, results and performance on a single volunteer participant (limited to alpha wave elicitation), we present the brain computer interface (BCI)2000 EEG source driver together with source code as well as the compiled (.exe). In addition, all the necessary device firmware, gerbers and bill of materials for the full reproducibility of the presented hardware is included. Furthermore, the end user can vary the dry-electrode reference circuitry, circuit bandwidth as well as sample rate to adapt the device to other generalized biopotential measurements. Although, not implemented in the tested prototype, the Biomedical Analogue to Digital Converter BIOADC naturally supports SPI communication for an additional 32 channels including the gain controller. In the appendix we describe the necessary modification to the presented hardware to enable this function.

On the fluid-structure interaction in the cochlea.

The cochlea is known to be a nonlinear system that shows strong fluid-structure coupling. In this work, the monolithic state space approach to cochlear modeling [Rapson et al., J. Acoust. Soc. Am. 131, 3925-3952 (2012)] is used to study the inherent nature of this coupling. Mathematical derivations requiring minimal, widely accepted assumptions about cochlear anatomy provide a clear description of the coupling. In particular, the coupling forces between neighboring cochlear partition segments are demonstrated, with implications for theories of cochlear operation that discount the traveling wave hypothesis. The derivations also reaffirm the importance of selecting a physiologically accurate value for the partition mass in any simulation. Numerical results show that considering the fluid properties in isolation can give a misleading impression of the fluid-structure coupling. Linearization of a nonlinear partition model allows the relationship between the linear and nonlinear fluid-structure interaction to be described. Furthermore, the effect of different classes of nonlinearities on the numerical complexity of a cochlear model is assessed. Cochlear models that assume outer hair cells are able to detect pressure will require implicit solver strategies, should the pressure sensitivity be demonstrated. Classical cochlear models in general do not require implicit solver strategies.

Bayesian Estimation and Inference Using Stochastic Electronics.

In this paper, we present the implementation of two types of Bayesian inference problems to demonstrate the potential of building probabilistic algorithms in hardware using single set of building blocks with the ability to perform these computations in real time. The first implementation, referred to as the BEAST (Bayesian Estimation and Stochastic Tracker), demonstrates a simple problem where an observer uses an underlying Hidden Markov Model (HMM) to track a target in one dimension. In this implementation, sensors make noisy observations of the target position at discrete time steps. The tracker learns the transition model for target movement, and the observation model for the noisy sensors, and uses these to estimate the target position by solving the Bayesian recursive equation online. We show the tracking performance of the system and demonstrate how it can learn the observation model, the transition model, and the external distractor (noise) probability interfering with the observations. In the second implementation, referred to as the Bayesian INference in DAG (BIND), we show how inference can be performed in a Directed Acyclic Graph (DAG) using stochastic circuits. We show how these building blocks can be easily implemented using simple digital logic gates. An advantage of the stochastic electronic implementation is that it is robust to certain types of noise, which may become an issue in integrated circuit (IC) technology with feature sizes in the order of tens of nanometers due to their low noise margin, the effect of high-energy cosmic rays and the low supply voltage. In our framework, the flipping of random individual bits would not affect the system performance because information is encoded in a bit stream.

A neuromorphic implementation of multiple spike-timing synaptic plasticity rules for large-scale neural networks.

We present a neuromorphic implementation of multiple synaptic plasticity learning rules, which include both Spike Timing Dependent Plasticity (STDP) and Spike Timing Dependent Delay Plasticity (STDDP). We present a fully digital implementation as well as a mixed-signal implementation, both of which use a novel dynamic-assignment time-multiplexing approach and support up to 2(26) (64M) synaptic plasticity elements. Rather than implementing dedicated synapses for particular types of synaptic plasticity, we implemented a more generic synaptic plasticity adaptor array that is separate from the neurons in the neural network. Each adaptor performs synaptic plasticity according to the arrival times of the pre- and post-synaptic spikes assigned to it, and sends out a weighted or delayed pre-synaptic spike to the post-synaptic neuron in the neural network. This strategy provides great flexibility for building complex large-scale neural networks, as a neural network can be configured for multiple synaptic plasticity rules without changing its structure. We validate the proposed neuromorphic implementations with measurement results and illustrate that the circuits are capable of performing both STDP and STDDP. We argue that it is practical to scale the work presented here up to 2(36) (64G) synaptic adaptors on a current high-end FPGA platform.

A new biomarker for subthalamic deep brain stimulation for patients with advanced Parkinson's disease--a pilot study.

OBJECTIVE: Deep brain stimulation (DBS) has become the standard treatment for advanced stages of Parkinson's disease (PD) and other motor disorders. Although the surgical procedure has improved in accuracy over the years thanks to imaging and microelectrode recordings, the underlying principles that render DBS effective are still debated today. The aim of this paper is to present initial findings around a new biomarker that is capable of assessing the efficacy of DBS treatment for PD which could be used both as a research tool, as well as in the context of a closed-loop stimulator. APPROACH: We have used a novel multi-channel stimulator and recording device capable of measuring the response of nervous tissue to stimulation very close to the stimulus site with minimal latency, rejecting most of the stimulus artefact usually found with commercial devices. We have recorded and analyzed the responses obtained intraoperatively in two patients undergoing DBS surgery in the subthalamic nucleus (STN) for advanced PD. MAIN RESULTS: We have identified a biomarker in the responses of the STN to DBS. The responses can be analyzed in two parts, an initial evoked compound action potential arising directly after the stimulus onset, and late responses (LRs), taking the form of positive peaks, that follow the initial response. We have observed a morphological change in the LRs coinciding with a decrease in the rigidity of the patients. SIGNIFICANCE: These initial results could lead to a better characterization of the DBS therapy, and the design of adaptive DBS algorithms that could significantly improve existing therapies and help us gain insights into the functioning of the basal ganglia and DBS.

Sound stream segregation: a neuromorphic approach to solve the "cocktail party problem" in real-time.

The human auditory system has the ability to segregate complex auditory scenes into a foreground component and a background, allowing us to listen to specific speech sounds from a mixture of sounds. Selective attention plays a crucial role in this process, colloquially known as the "cocktail party effect." It has not been possible to build a machine that can emulate this human ability in real-time. Here, we have developed a framework for the implementation of a neuromorphic sound segregation algorithm in a Field Programmable Gate Array (FPGA). This algorithm is based on the principles of temporal coherence and uses an attention signal to separate a target sound stream from background noise. Temporal coherence implies that auditory features belonging to the same sound source are coherently modulated and evoke highly correlated neural response patterns. The basis for this form of sound segregation is that responses from pairs of channels that are strongly positively correlated belong to the same stream, while channels that are uncorrelated or anti-correlated belong to different streams. In our framework, we have used a neuromorphic cochlea as a frontend sound analyser to extract spatial information of the sound input, which then passes through band pass filters that extract the sound envelope at various modulation rates. Further stages include feature extraction and mask generation, which is finally used to reconstruct the targeted sound. Using sample tonal and speech mixtures, we show that our FPGA architecture is able to segregate sound sources in real-time. The accuracy of segregation is indicated by the high signal-to-noise ratio (SNR) of the segregated stream (90, 77, and 55 dB for simple tone, complex tone, and speech, respectively) as compared to the SNR of the mixture waveform (0 dB). This system may be easily extended for the segregation of complex speech signals, and may thus find various applications in electronic devices such as for sound segregation and speech recognition.

Racing to learn: statistical inference and learning in a single spiking neuron with adaptive kernels.

This paper describes the Synapto-dendritic Kernel Adapting Neuron (SKAN), a simple spiking neuron model that performs statistical inference and unsupervised learning of spatiotemporal spike patterns. SKAN is the first proposed neuron model to investigate the effects of dynamic synapto-dendritic kernels and demonstrate their computational power even at the single neuron scale. The rule-set defining the neuron is simple: there are no complex mathematical operations such as normalization, exponentiation or even multiplication. The functionalities of SKAN emerge from the real-time interaction of simple additive and binary processes. Like a biological neuron, SKAN is robust to signal and parameter noise, and can utilize both in its operations. At the network scale neurons are locked in a race with each other with the fastest neuron to spike effectively "hiding" its learnt pattern from its neighbors. The robustness to noise, high speed, and simple building blocks not only make SKAN an interesting neuron model in computational neuroscience, but also make it ideal for implementation in digital and analog neuromorphic systems which is demonstrated through an implementation in a Field Programmable Gate Array (FPGA). Matlab, Python, and Verilog implementations of SKAN are available at: http://www.uws.edu.au/bioelectronics_neuroscience/bens/reproducible_research.

A mixed-signal implementation of a polychronous spiking neural network with delay adaptation.

We present a mixed-signal implementation of a re-configurable polychronous spiking neural network capable of storing and recalling spatio-temporal patterns. The proposed neural network contains one neuron array and one axon array. Spike Timing Dependent Delay Plasticity is used to fine-tune delays and add dynamics to the network. In our mixed-signal implementation, the neurons and axons have been implemented as both analog and digital circuits. The system thus consists of one FPGA, containing the digital neuron array and the digital axon array, and one analog IC containing the analog neuron array and the analog axon array. The system can be easily configured to use different combinations of each. We present and discuss the experimental results of all combinations of the analog and digital axon arrays and the analog and digital neuron arrays. The test results show that the proposed neural network is capable of successfully recalling more than 85% of stored patterns using both analog and digital circuits.

Synthesis of neural networks for spatio-temporal spike pattern recognition and processing.

The advent of large scale neural computational platforms has highlighted the lack of algorithms for synthesis of neural structures to perform predefined cognitive tasks. The Neural Engineering Framework (NEF) offers one such synthesis, but it is most effective for a spike rate representation of neural information, and it requires a large number of neurons to implement simple functions. We describe a neural network synthesis method that generates synaptic connectivity for neurons which process time-encoded neural signals, and which makes very sparse use of neurons. The method allows the user to specify-arbitrarily-neuronal characteristics such as axonal and dendritic delays, and synaptic transfer functions, and then solves for the optimal input-output relationship using computed dendritic weights. The method may be used for batch or online learning and has an extremely fast optimization process. We demonstrate its use in generating a network to recognize speech which is sparsely encoded as spike times.

The ripple pond: enabling spiking networks to see.

We present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network which performs a transformation converting two dimensional images to one dimensional temporal patterns (TP) suitable for recognition by temporal coding learning and memory networks. The RPN has been developed as a hardware solution linking previously implemented neuromorphic vision and memory structures such as frameless vision sensors and neuromorphic temporal coding spiking neural networks. Working together such systems are potentially capable of delivering end-to-end high-speed, low-power and low-resolution recognition for mobile and autonomous applications where slow, highly sophisticated and power hungry signal processing solutions are ineffective. Key aspects in the proposed approach include utilizing the spatial properties of physically embedded neural networks and propagating waves of activity therein for information processing, using dimensional collapse of imagery information into amenable TP and the use of asynchronous frames for information binding.