Real-Time Neural Signals Decoding onto Off-the-Shelf DSP Processors for Neuroprosthetic Applications

Pani, Danilo; Barabino, Gianfranco; Citi, Luca; Meloni, Paolo; Raspopović, Staniša; Micera, Silvestro; Raffo, Luigi

doi:10.1109/tnsre.2016.2527696

Cited by 14 publications

(22 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At first, each electrogram underwent a wavelet denoising stage. A translation-invariant à trous (undecimated) algorithm was adopted, to achieve translation-invariance at a low computational cost compared to other approaches [12].…”

Section: Methodsmentioning

confidence: 99%

Automatic Recognition of Ventricular Abnormal Potentials in Intracardiac Electrograms

Baldazzi¹,

Orrù²,

Matraxia³

et al. 2019

Computing in Cardiology Conference (CinC)

Self Cite

View full text Add to dashboard Cite

Ventricular abnormal potentials are low-amplitude electrical signals that appear in intracardiac electrograms during a QRS or with an unpredictable delay with respect to it. Their spatial localization can be exploited by cardiologists for the identification of the ablation targets in substrate-guided mapping and ablation procedures. In this work, an automatic approach for a reliable detection of such potentials in intracardiac electrograms is proposed. To this aim, 86 intracardiac electrograms from five patients with post-ischemic ventricular tachycardia, acquired by the CARTO3 System, were retrospectively annotated by an expert cardiologist, to be used for a supervised classifier training and test. The automatic detection was based on a non-linear denoising followed by a timescale decomposition based on the continuous wavelet transform. Then, different morphological features were extracted from both the timescale domain and the time domain, and used to feed a support vector machine trained to discriminate between physiological and abnormal potentials. The recognition accuracy exceeded 93%, paving the way to further developments and more extensive studies.

show abstract

Section: Methodsmentioning

confidence: 99%

Automatic Recognition of Ventricular Abnormal Potentials in Intracardiac Electrograms

Baldazzi¹,

Orrù²,

Matraxia³

et al. 2019

Computing in Cardiology Conference (CinC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…For this reason, when moving toward the hardware simulation systems, it is obvious the success of architectures exploiting efficient signal processing cores, such as ParSPIKE (Wolff et al, 1999 ), which is based on the Analog Devices ADSP21060 Digital Signal Processor. In fact, Digital Signal Processors revealed better performance than high-end mainstream processors in several biomedical and signal processing applications, with a power consumption that could be even two orders of magnitude lower (Pani et al, 2013 , 2014 ) and they are currently being used for studies in neuroprosthetics (Pani et al, 2011 , 2016 ).…”

Section: Discussionmentioning

confidence: 99%

An FPGA Platform for Real-Time Simulation of Spiking Neuronal Networks

et al. 2017

Self Cite

View full text Add to dashboard Cite

In the last years, the idea to dynamically interface biological neurons with artificial ones has become more and more urgent. The reason is essentially due to the design of innovative neuroprostheses where biological cell assemblies of the brain can be substituted by artificial ones. For closed-loop experiments with biological neuronal networks interfaced with in silico modeled networks, several technological challenges need to be faced, from the low-level interfacing between the living tissue and the computational model to the implementation of the latter in a suitable form for real-time processing. Field programmable gate arrays (FPGAs) can improve flexibility when simple neuronal models are required, obtaining good accuracy, real-time performance, and the possibility to create a hybrid system without any custom hardware, just programming the hardware to achieve the required functionality. In this paper, this possibility is explored presenting a modular and efficient FPGA design of an in silico spiking neural network exploiting the Izhikevich model. The proposed system, prototypically implemented on a Xilinx Virtex 6 device, is able to simulate a fully connected network counting up to 1,440 neurons, in real-time, at a sampling rate of 10 kHz, which is reasonable for small to medium scale extra-cellular closed-loop experiments.

show abstract

“…where ∆ i [j] denotes the j-th inter-spike interval of the ith MU; card(∆ i ) is the number of inter-spike intervals of the i-th MU; m ∆,i [n] is the expectation value of the interspike intervals of the i-th MU at the time index n; andṽ[n] is the same as the formula (14) and the prediction of the variance of innovation…”

Section: B Estimation Of Inter-spike Law Parametersmentioning

confidence: 99%

“…This algorithm was designed to estimate the cumulative discharge rate of MNs but does not provide resolution of action potentials superimposed in time. Similar challenges as in iEMG decomposition are present in spike sorting algorithms for extracellular recordings from multiple cortical neurons [10], [11], [12] and from nerves (electroneurogram) [13], [14].…”

mentioning

confidence: 95%

On-Line Recursive Decomposition of Intramuscular EMG Signals Using GPU-Implemented Bayesian Filtering

Akhmadeev

Carpentier

et al. 2020

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Real-time intramuscular electromyography (iEMG) decomposition, which is largely required in the neurological studies and applications, is a complex procedure that involves identifying the motor neuron spike trains from a streaming iEMG recording. We have previously proposed a sequential decomposition algorithm based on a Hidden Markov Model of EMG, that used Bayesian filter to estimate unknown parameters of motor units (MUs) spike trains, as well as their action potentials (MUAPs). In this paper we present a parallel computation implementation of this algorithm on Graphics Processing Unit (GPU), as well as a number of modifications applied to the original model in order to achieve a real-time performance of the algorithm. Specifically, the Kalman filter, previously used to estimate the MUAPs, is replaced by a least-mean-square filter. Additionally, we introduce a number of heuristics that help to omit the most improbable decomposition scenarios while searching for the best solution. Then, a GPU-implementation of the proposed algorithm is presented. Dozens of simulated iEMG signals containing up to 10 active MUs, as well as five experimental fine-wire iEMG signals acquired from tibialis anterior, were decomposed in real time. The accuracy of decompositions depended on the level of muscle activation, but in all cases exceeded 85%.

show abstract

Real-Time Neural Signals Decoding onto Off-the-Shelf DSP Processors for Neuroprosthetic Applications

Cited by 14 publications

References 22 publications

Automatic Recognition of Ventricular Abnormal Potentials in Intracardiac Electrograms

Automatic Recognition of Ventricular Abnormal Potentials in Intracardiac Electrograms

An FPGA Platform for Real-Time Simulation of Spiking Neuronal Networks

On-Line Recursive Decomposition of Intramuscular EMG Signals Using GPU-Implemented Bayesian Filtering

Contact Info

Product

Resources

About