A Time-varying Equivalent Circuit Modeling and Measuring Approach for Intracardiac Communication in Leadless Pacemakers.

Intracardiac wireless communication is crucial for the development of multi-chamber leadless cardiac pacemakers (LCP). However, the time-varying characteristics of intracardiac channel pose major challenges. As such, mastering the dynamic conduction properties of the intracardiac channel and modeling the equivalent time-varying channel are imperative for realizing LCP multi-chamber pacing. In this paper, we present a limiting volume variational approach based on the electrical properties of cardiac tissues and trends in chamber volume variation. This approach was used to establish a quasi-static and a continuous time-varying equivalent circuit model of an intracardiac channel. An equivalence analysis was conducted on the model, and a discrete time-varying equivalent circuit phantom grounded on the cardiac cycle was subsequently established. Moreover, an ex vivo cardiac experimental platform was developed for verification. Results indicate that in the frequency domain, the congruence between phantom and ex vivo experimental outcomes is as high as 94.3%, affirming the reliability of the equivalent circuit model. In the time domain, the correlation is up to 75.3%, corroborating its effectiveness. The proposed time-varying equivalent circuit model exhibits stable and standardized dynamic attributes, serving as a powerful tool for addressing time-varying challenges and simplifying in vivo or ex vivo experiments.

Impacts of Cortical Regions on EEG-based Classification of Lexical Tones and Vowels in Spoken Speech.

Speech impairment is one of the most serious problems for patients with communication disorders, e.g., stroke survivors. The brain-computer interface (BCI) systems have shown the potential to alternatively control or rehabilitate the neurological damages in speech production. The effects of different cortical regions in speech-based BCI systems are essential to be studied, which are favorable for improving the performance of speech-based BCI systems. This work aimed to explore the impacts of different speech-related cortical regions in the electroencephalogram (EEG) based classification of seventy spoken Mandarin monosyllables carrying four vowels and four lexical tones. Seven audible speech production-related cortical regions were studied, involving Broca's and Wernicke's areas, auditory cortex, motor cortex, prefrontal cortex, sensory cortex, left brain, right brain, and whole brain. Following the previous studies in which EEG signals were collected from ten subjects during Mandarin speech production, the features of EEG signals were extracted by the Riemannian manifold method, and a linear discriminant analysis (LDA) was regarded as a classifier to classify different vowels and lexical tones. The results showed that when using electrodes from whole brain, the classifier reached the best performances, which were 48.5% for lexical tones and 70.0% for vowels, respectively. The vowel classification results under Broca's and Wernicke's areas, auditory cortex, or prefrontal cortex were higher than those under the motor cortex or sensory cortex. No such differences were observed in the lexical tone classification task.

Fault-Tolerant Attitude Tracking Control Driven by Spiking NNs for Unmanned Aerial Vehicles.

In this article, we proposed a novel fault-tolerant control scheme for quadrotor unmanned aerial vehicles (UAVs) based on spiking neural networks (SNNs), which leverages the inherent features of neural network computing to significantly enhance the reliability and robustness of UAV flight control. Traditional control methods are known to be inadequate in dealing with complex and real-time sensor data, which results in poor performance and reduced robustness in fault-tolerant control. In contrast, the temporal processing, parallelism, and nonlinear capacity of SNNs enable the fault-tolerant control scheme to process vast amounts of sensory data with the ability to accurately identify and respond to faults. Furthermore, SNNs can learn and adjust to new environments and fault conditions, providing effective and adaptive flight control. The proposed SNN-based fault-tolerant control scheme demonstrates significant improvements in control accuracy and robustness compared with conventional methods, indicating its potential applicability and suitability for a range of UAV flight control scenarios.

Modulating Individual Alpha Frequency through Short-Term Neurofeedback for Cognitive Enhancement in Healthy Young Adults.

Human alpha oscillation (7-13 Hz) has been extensively studied over the years for its connection with cognition. The individual alpha frequency (IAF), defined as the frequency that provides the highest power in the alpha band, shows a positive correlation with cognitive processes. The modulation of alpha activities has been accomplished through various approaches aimed at improving cognitive performance. However, very few studies focused on the direct modulation of IAF by shifting the peak frequency, and the understanding of IAF modulation remains highly limited. In this study, IAFs of healthy young adults were up-regulated through short-term neurofeedback training using haptic feedback. The results suggest that IAFs have good trainability and are up-regulated, also that IAFs are correlated with the enhanced cognitive performance in mental rotation and n-back tests compared to sham-neurofeedback control. This study demonstrates the feasibility of self-regulating IAF for cognition enhancement and provides potential therapeutic benefits for cognitive-impaired patients.

A low cost neuromorphic learning engine based on a high performance supervised SNN learning algorithm.

Spiking neural networks (SNNs) are more energy- and resource-efficient than artificial neural networks (ANNs). However, supervised SNN learning is a challenging task due to non-differentiability of spikes and computation of complex terms. Moreover, the design of SNN learning engines is not an easy task due to limited hardware resources and tight energy constraints. In this article, a novel hardware-efficient SNN back-propagation scheme that offers fast convergence is proposed. The learning scheme does not require any complex operation such as error normalization and weight-threshold balancing, and can achieve an accuracy of around 97.5% on MNIST dataset using only 158,800 synapses. The multiplier-less inference engine trained using the proposed hard sigmoid SNN training (HaSiST) scheme can operate at a frequency of 135 MHz and consumes only 1.03 slice registers per synapse, 2.8 slice look-up tables, and can infer about 0.03[Formula: see text] features in a second, equivalent to 9.44 giga synaptic operations per second (GSOPS). The article also presents a high-speed, cost-efficient SNN training engine that consumes only 2.63 slice registers per synapse, 37.84 slice look-up tables per synapse, and can operate at a maximum computational frequency of around 50 MHz on a Virtex 6 FPGA.

Double-Sided Sapphire Optrodes with Conductive Shielding Layers to Reduce Optogenetic Stimulation Artifacts.

Optrodes, which are single shaft neural probes integrated with microelectrodes and optical light sources, offer a remarkable opportunity to simultaneously record and modulate neural activities using light within an animal's brain; however, a common problem with optrodes is that stimulation artifacts can be observed in the neural recordings of microelectrodes when the light source on the optrode is activated. These stimulation artifacts are undesirable contaminants, and they cause interpretation complexity when analyzing the recorded neural activities. In this paper, we tried to mitigate the effects of the stimulation artifacts by developing a low-noise, double-sided optrode integrated with multiple Electromagnetic Shielding (EMS) layers. The LED and microelectrodes were constructed separately on the top epitaxial and bottom substrate layers, and EMS layers were used to separate the microelectrodes and LED to reduce signal cross-talks. Compared with conventional single-sided designs, in which the LED and microelectrodes are constructed on the same side, our results indicate that double-sided optrodes can significantly reduce the presence of stimulation artifacts. In addition, the presence of stimulation artifacts can further be reduced by decreasing the voltage difference and increasing the rise/fall time of the driving LED pulsed voltage. With all these strategies, the presence of stimulation artifacts was significantly reduced by ~76%. As well as stimulation suppression, the sapphire substrate also provided strong mechanical stiffness and support to the optrodes, as well as improved electronic stability, thus making the double-sided sapphire optrodes highly suitable for optogenetic neuroscience research on animal models.

Adaptive Fiber-Ring Lasers Based on Isopropanol Filled Microfiber Coupler for High-Sensitivity Temperature Sensing.

We demonstrated a new method for temperature measurement inside a fiber ring laser (FRL) cavity. Different from traditional FRL temperature sensing system which need additional filter working as a sensor, a micro-fiber coupler (MFC) was designed as a beam splitter, filter, and temperature sensor. In addition, isopropanol, a liquid with very high photothermal coefficient, is selectively filled in the MFC in order to improve the sensitivity of the system on temperature. In the dynamic range of 20-40 °C, we obtained a good temperature sensitivity of -1.29 nm/°C, with linear fitting up to 0.998. Benefiting from the advantages of laser sensing, the acquired laser has a 3 - dB bandwidth of less than 0.2 nm and a signal-to-noise ratio (SNR) of up to 40 dB. The proposed sensor has a low cost and high sensitivity, which is expected to be used in biomedical health detection, real-time monitoring of ocean temperature, and other application scenarios.

An Approach to Emotion Recognition Using Brain Rhythm Sequencing and Asymmetric Features.

Emotion can be influenced during self-isolation, and to avoid severe mood swings, emotional regulation is meaningful. To achieve this, efficiently recognizing emotion is a vital step, which can be realized by electroencephalography signals. Previously, inspired by the knowledge of sequencing in bioinformatics, a method termed brain rhythm sequencing that analyzes electroencephalography as the sequence consisting of the dominant rhythm has been proposed for seizure detection. In this work, with the help of similarity measure methods, the asymmetric features are extracted from the sequences generated by different channel data. After evaluating all asymmetric features for emotion recognition, the optimal feature that yields remarkable accuracy is identified. Therefore, the classification task can be accomplished through a small amount of channel data. From a music emotion recognition experiment and a public DEAP dataset, the classification accuracies of various test sets are approximately 80-85% when employing an optimal feature extracted from one pair of symmetrical channels. Such performances are impressive when using fewer resources is a concern. Further investigation revealed that emotion recognition shows strongly individual characteristics, so an appropriate solution is to include the subject-dependent properties. Compared to the existing works, this method benefits from the design of a portable emotion-aware device used during self-isolation, as fewer scalp sensors are needed. Hence, it would provide a novel way to realize emotional applications in the future.

The Masking Impact of Intra-Artifacts in EEG on Deep Learning-Based Sleep Staging Systems: A Comparative Study.

Elimination of intra-artifacts in EEG has been overlooked in most of the existing sleep staging systems, especially in deep learning-based approaches. Whether intra-artifacts, originated from the eye movement, chin muscle firing, or heart beating, etc., in EEG signals would lead to a positive or a negative masking effect on deep learning-based sleep staging systems was investigated in this paper. We systematically analyzed several traditional pre-processing methods involving fast Independent Component Analysis (FastICA), Information Maximization (Infomax), and Second-order Blind Source Separation (SOBI). On top of these methods, a SOBI-WT method based on the joint use of the SOBI and Wavelet Transform (WT) is proposed. It offered an effective solution for suppressing artifact components while retaining residual informative data. To provide a comprehensive comparative analysis, these pre-processing methods were applied to eliminate the intra-artifacts and the processed signals were fed to two ready-to-use deep learning models, namely two-step hierarchical neural network (THNN) and SimpleSleepNet for automatic sleep staging. The evaluation was performed on two widely used public datasets, Montreal Archive of Sleep Studies (MASS) and Sleep-EDF Expanded, and a clinical dataset that was collected in Huashan Hospital of Fudan University, Shanghai, China (HSFU). The proposed SOBI-WT method increased the accuracy from 79.0% to 81.3% on MASS, 83.3% to 85.7% on Sleep-EDF Expanded, and 75.5% to 77.1% on HSFU compared with the raw EEG signal, respectively. Experimental results demonstrate that the intra-artifacts bring out a masking negative impact on the deep learning-based sleep staging systems and the proposed SOBI-WT method has the best performance in diminishing this negative impact compared with other artifact elimination methods.

Predicting the Influence of Axon Myelination on Sound Localization Precision Using a Spiking Neural Network Model of Auditory Brainstem.

Spatial hearing allows animals to rapidly detect and localize auditory events in the surrounding environment. The auditory brainstem plays a central role in processing and extracting binaural spatial cues through microsecond-precise binaural integration, especially for detecting interaural time differences (ITDs) of low-frequency sounds at the medial superior olive (MSO). A series of mechanisms exist in the underlying neural circuits for preserving accurate action potential timing across multiple fibers, synapses and nuclei along this pathway. One of these is the myelination of afferent fibers that ensures reliable and temporally precise action potential propagation in the axon. There are several reports of fine-tuned myelination patterns in the MSO circuit, but how specifically myelination influences the precision of sound localization remains incompletely understood. Here we present a spiking neural network (SNN) model of the Mongolian gerbil auditory brainstem with myelinated axons to investigate whether different axon myelination thicknesses alter the sound localization process. Our model demonstrates that axon myelin thickness along the contralateral pathways can substantially modulate ITD detection. Furthermore, optimal ITD sensitivity is reached when the MSO receives contralateral inhibition via thicker myelinated axons compared to contralateral excitation, a result that is consistent with previously reported experimental observations. Our results suggest specific roles of axon myelination for extracting temporal dynamics in ITD decoding, especially in the pathway of the contralateral inhibition.

Single-Channel Selection for EEG-Based Emotion Recognition Using Brain Rhythm Sequencing.

Recently, electroencephalography (EEG) signals have shown great potential for emotion recognition. Nevertheless, multichannel EEG recordings lead to redundant data, computational burden, and hardware complexity. Hence, efficient channel selection, especially single-channel selection, is vital. For this purpose, a technique termed brain rhythm sequencing (BRS) that interprets EEG based on a dominant brain rhythm having the maximum instantaneous power at each 0.2 s timestamp has been proposed. Then, dynamic time warping (DTW) is used for rhythm sequence classification through the similarity measure. After evaluating the rhythm sequences for the emotion recognition task, the representative channel that produces impressive accuracy can be found, which realizes single-channel selection accordingly. In addition, the appropriate time segment for emotion recognition is estimated during the assessments. The results from the music emotion recognition (MER) experiment and three emotional datasets (SEED, DEAP, and MAHNOB) indicate that the classification accuracies achieve 70-82% by single-channel data with a 10 s time length. Such performances are remarkable when considering minimum data sources as the primary concerns. Furthermore, the individual characteristics in emotion recognition are investigated based on the channels and times found. Therefore, this study provides a novel method to solve single-channel selection for emotion recognition.

EEG-based Emotion Recognition Using Similarity Measure of Brain Rhythm Sequencing.

The similarity is a fundamental measure from the homology theory in bioinformatics, and the biological sequence can be classified based on it. However, such an approach has not been utilized for electroencephalography (EEG)-based emotion recognition. To this end, the sequence generated by choosing the dominant brain rhythm owning maximum instantaneous power at each 0.2 s timestamp of the EEG signal has been proposed. Then, to recognize emotional arousal and valence, the similarity measures between pairwise sequences have been performed by dynamic time warping (DTW). After evaluations, the sequence that provides the highest accuracy has been obtained. Thus, the representative channel has been found. Besides, the appropriate time segment for emotion recognition has been estimated. Those findings helpfully exclude redundant data for assessing emotion. Results from the DEAP dataset displayed that the classification accuracies between 72%-75% can be realized by applying the single-channel data with a 5 s length, which is impressive when considering fewer data sources as the primary concern. Hence, the proposed idea would open a new way that uses the similarity measures of sequences for EEG-based emotion recognition.

Axonal Conduction Delay Shapes the Precision of the Spatial Hearing in A Spiking Neural Network Model of Auditory Brainstem.

One method by which the mammalian sound localization pathway localizes sound sources is by analyzing the microsecond-level difference between the arrival times of a sound at the two ears. However, how the neural circuits in the auditory brainstem precisely integrate signals from the two ears, and what the underlying mechanisms are, remains to be understood. Recent studies have reported that variations of axon myelination in the auditory brainstem produces various axonal conduction velocities and sophisticated temporal dynamics, which have not been well characterized in most existing models of sound localization circuits. Here, we present a spiking neural network model of the auditory brainstem to investigate how axon myelinations affect the precision of sound localization. Sound waves with different interaural time differences (ITDs) are encoded and used as stimuli, and the axon properties in the network are adjusted, and the corresponding axonal conduction delays are computed with a multi-compartment axon model. Through the simulation, the sensitivity of ITD perception varies with the myelin thickness of axons in the contralateral input pathways to the medial superior olive (MSO). The ITD perception becomes more precise when the contralateral inhibitory input propagates faster than the contralateral excitatory input. These results indicate that axon myelination and contralateral spike timing influence spatial hearing perception.

Influence of the Surface Material and Illumination upon the Performance of a Microelectrode/Electrolyte Interface in Optogenetics.

Integrated optrodes for optogenetics have been becoming a significant tool in neuroscience through the combination of offering accurate stimulation to target cells and recording biological signals simultaneously. This makes it not just be widely used in neuroscience researches, but also have a great potential to be employed in future treatments in clinical neurological diseases. To optimize the integrated optrodes, this paper aimed to investigate the influence of surface material and illumination upon the performance of the microelectrode/electrolyte interface and build a corresponding evaluation system. In this work, an integrated planar optrode with a blue LED and microelectrodes was designed and fabricated. The charge transfer mechanism on the interface was theoretically modeled and experimentally verified. An evaluation system for assessing microelectrodes was also built up. Using this system, the proposed model of various biocompatible surface materials on microelectrodes was further investigated under different illumination conditions. The influence of illumination on the microelectrode/electrolyte interface was the cause of optical artifacts, which interfere the biological signal recording. It was found that surface materials had a great effect on the charge transfer capacity, electrical stability and recoverability, photostability, and especially optical artifacts. The metal with better charge transfer capacity and electrical stability is highly possible to have a better performance on the optical artifacts, regardless of its electrical recoverability and photostability under the illumination conditions of optogenetics. Among the five metals used in our investigation, iridium served as the best surface material for the proposed integrated optrodes. Thus, optimizing the surface material for optrodes could reduce optical interference, enhance the quality of the neural signal recording for optogenetics, and thus help to advance the research in neuroscience.

A Time-Frequency Measurement and Evaluation Approach for Body Channel Characteristics in Galvanic Coupling Intrabody Communication.

Intrabody communication (IBC) can achieve better power efficiency and higher levels of security than other traditional wireless communication technologies. Currently, the majority of research on the body channel characteristics of galvanic coupling IBC are motionless and have only been evaluated in the frequency domain. Given the long measuring times of traditional methods, the access to dynamic variations and the simultaneous evaluation of the time-frequency domain remains a challenge for dynamic body channels such as the cardiac channel. To address this challenge, we proposed a parallel measurement methodology with a multi-tone strategy and a time-parameter processing approach to obtain a time-frequency evaluation for dynamic body channels. A group search algorithm has been performed to optimize the crest factor of multitone excitation in the time domain. To validate the proposed methods, in vivo experiments, with both dynamic and motionless conditions were measured using the traditional method and the proposed method. The results indicate that the proposed method is more time efficient (Tmeas = 1 ms) with a consistent performance (ρc > 98%). Most importantly, it is capable of capturing dynamic variations in the body channel and provides a more comprehensive evaluation and richer information for the study of IBC.

Robotic stereotaxic system based on 3D skull reconstruction to improve surgical accuracy and speed.

BACKGROUND: Some experimental approaches in neuroscience research require the precise placement of a recording electrode, pipette or other tool into a specific brain area that can be quite small and/or located deep beneath the surface. This process is typically aided with stereotaxic methods but remains challenging due to a lack of advanced technology to aid the experimenter. Currently, procedures require a significant amount of skill, have a high failure rate, and take up a significant amount of time. NEW METHOD: We developed a next generation robotic stereotaxic platform for small rodents by combining a three-dimensional (3D) skull profiler sub-system and a full six degree-of-freedom (6DOF) robotic platform. The 3D skull profiler is based on structured illumination in which a series of horizontal and vertical line patterns are projected onto an animal skull. These patterns are captured by two two-dimensional (2D) CCD cameras which reconstruct an accurate 3D skull surface profile based on structured illumination and geometrical triangulation. Using the reconstructed 3D profile, the skull can be repositioned using a 6DOF robotic platform to accurately align a surgical tool. RESULTS: The system was evaluated using mechanical measurement techniques, and the accuracy of the platform was demonstrated using agar brain phantoms and animal skulls. Additionally, a small and deep brain nucleus (the medial nucleus of the trapezoid body) were targeted in rodents to confirm the targeting accuracy. CONCLUSIONS: The new stereotaxic system can accomplish "skull-flat" rapidly and precisely and with minimal user intervention, and thus reduces the failure rate of such experiments.

Experimental Characterization of an Embossed Capacitive Micromachined Ultrasonic Transducer Cell.

Capacitive Micromachined Ultrasonic Transducer (CMUT) is a promising ultrasonic transducer in medical diagnosis and therapeutic applications that demand a high output pressure. The concept of a CMUT with an annular embossed pattern on a membrane working in collapse mode is proposed to further improve the output pressure. To evaluate the performance of an embossed CMUT cell, both the embossed and uniform membrane CMUT cells were fabricated in the same die with a customized six-mask sacrificial release process. An annular nickel pattern with the dimension of 3 µm × 2 µm (width × height) was formed on a full top electrode CMUT to realize an embossed CMUT cell. Experimental characterization was carried out with optical, electrical, and acoustic instruments on the embossed and uniform CMUT cells. The embossed CMUT cell achieved 27.1% improvement of output pressure in comparison to the uniform CMUT cell biased at 170 V voltage. The fractional bandwidths of the embossed and uniform CMUT cells were 52.5% and 41.8%, respectively. It substantiated that the embossed pattern should be placed at the vibrating center of the membrane for achieving a higher output pressure. The experimental characterization indicated that the embossed CMUT cell has better operational performance than the uniform CMUT cell in collapse region.

Nondestructive and objective assessment of the vestibular function in rodent models: A review.

The normal function of the vestibular system is crucial for the sense of balance. The techniques used to assess the vestibular function plays a vital role in the research of the vestibular system. In this article, we have systematically reviewed some popular methods employing vestibular reflexes and vestibular evoked potentials for assessing the vestibular function in rodent models. These vestibular reflexes and vestibular evoked potentials to effective stimuli have been used as nondestructive and objective functional measures. The main types of vestibular reflexes include the vestibulo-ocular reflex (VOR), vestibulocollic reflex (VCR), and vestibulo-sympathetic reflex (VSR). They are all capable of indicating the functions of the semicircular canals and otoliths. However, the VOR assessment is much more prevalently used because of the relatively stereotypical inputoutput relationship and simple motion pattern of the ocular response. In contrast, the complicated motion pattern and small gain of the VCR response, as well as the undesired component possibly contributed from the acceleration receptors outside the labyrinths in the VSR response, restrict the widespread applications of VCR and VSR in the assessment of the vestibular system. The vestibular evoked myogenic potentials (VEMPs) and vestibular sensory evoked potentials (VsEPs) are the two typical evoked potentials that have been also employed for evaluating the vestibular function. Through exploiting different types of the VEMPs, the saccular and utricular functions can be evaluated separately. The sound-induced VEMPs, moreover, are capable of noninvasively assessing the unilateral vestibular function. The VsEPs, via the morphology of their signal waveforms, enable the access to the location-specific information that indicates the functional statuses of different components within the vestibular neural pathway.

Low-latency single channel real-time neural spike sorting system based on template matching.

Recent technical advancements in neural engineering allow for precise recording and control of neural circuits simultaneously, opening up new opportunities for closed-loop neural control. In this work, a rapid spike sorting system was developed based on template matching to rapidly calculate instantaneous firing rates for each neuron in a multi-unit extracellular recording setting. Cluster templates were first generated by a desktop computer using a non-parameter spike sorting algorithm (Super-paramagnetic clustering) and then transferred to a field-programmable gate array digital circuit for rapid sorting through template matching. Two different matching techniques-Euclidean distance (ED) and correlational matching (CM)-were compared for the accuracy of sorting and the performance of calculating firing rates. The performance of the system was first verified using publicly available artificial data and was further confirmed with pre-recorded neural spikes from an anesthetized Mongolian gerbil. Real-time recording and sorting from an awake mouse were also conducted to confirm the system performance in a typical behavioral neuroscience experimental setting. Experimental results indicated that high sorting accuracies were achieved for both template-matching methods, but CM can better handle spikes with non-Gaussian spike distributions, making it more robust for in vivo recording. The technique was also compared to several other off-line spike sorting algorithms and the results indicated that the sorting accuracy is comparable but sorting time is significantly shorter than these other techniques. A low sorting latency of under 2 ms and a maximum spike sorting rate of 941 spikes/second have been achieved with our hybrid hardware/software system. The low sorting latency and fast sorting rate allow future system developments of neural circuit modulation through analyzing neural activities in real-time.

Computationally inexpensive enhanced growing neural gas algorithm for real-time adaptive neural spike clustering.

OBJECTIVE: Real-time closed-loop neural feedback control requires the analysis of action potential traces within several milliseconds after they have been recorded from the brain. The current generation of spike clustering algorithms were mostly designed for off-line use and also require a significant amount of computational resources. A new spike clustering algorithm, termed 'enhanced growing neural gas (EGNG)', was therefore developed that is computationally lightweight and memory conserving. The EGNG algorithm can adapt to changes of the electrophysiological recording environment and can classify both pre-recorded and streaming action potentials. APPROACH: The algorithm only uses a small number of EGNG nodes and edges to learn the neural spike distributions which eliminates the need of retaining the neural data in the system memory to conserve computational resources. Most of the computations revolve around calculating Euclidian distances, which is computationally inexpensive and can be implemented in parallel using digital circuit technology. MAIN RESULTS: EGNG was evaluated off-line using both synthetic and pre-recorded neural spikes. Streaming synthetic neural spikes were also used to evaluate the ability of EGNG to classify action potentials in real-time. The algorithm was also implemented in hardware with a Field Programming Gate Array (FPGA) chip, and the worst-case clustering latency was 3.10 µs, allowing a minimum of 322 580 neural spikes to be clustered per second. SIGNIFICANCE: The EGNG algorithm provides a viable solution to classification of neural spikes in real-time and can be implemented with limited computational resources as a front-end spike clustering unit for future tethered-free and miniaturized closed-loop neural feedback systems.