Evaluation of spike-detection algorithms for a brain-machine interface application.

Recordings of extracellular spikes have been widely used in various fields ranging from basic neuroscientific research to clinical applications. However, in the extracellular recording system, how to accurately detect spikes from the recorded signal in real time is still a major challenging work. Although the existing algorithms for online spike detection have made great progress, there still remains much room for improvement in terms of accuracy. In this paper, we propose a new method for high accuracy and real time spike detection. Concretely, differential operator is firstly employed to accentuate spikes in the signal for its simplicity and strong capacity to detect significant changes. Then, by exploiting the structural features of spikes, the resolution parameter is introduced to improve the performance of differential operator. Finally, a simple and effective measure is utilized to further reduce the influence of background noise, which makes spike detection more accurate. The results of simulated and real data show that the proposed method is able to precisely detect spikes while maintaining low computational complexity.

Objective. Translational efforts on spike-signal-based implantable brain-machine interfaces (BMIs) are increasingly aiming to minimise bandwidth while maintaining decoding performance. Developing these BMIs requires advances in neuroscience and electronic technology, as well as using low-complexity spike detection algorithms and high-performance machine learning models. While some state-of-the-art BMI systems jointly design spike detection algorithms and machine learning models, it remains unclear how the detection performance affects decoding. Approach. We propose the co-design of the neural decoder with an ultra-low complexity spike detection algorithm. The detection algorithm is designed to attain a target firing rate, which the decoder uses to modulate the input features preserving statistical invariance in long term (over several months). Main results. We demonstrate a multiplication-free fixed-point spike detection algorithm with an average detection accuracy of 97% across different noise levels on a synthetic dataset and the lowest hardware complexity among studies we have seen. By co-designing the system to incorporate statistically invariant features, we observe significantly improved long-term stability, with decoding accuracy degrading by less than 10% after 80 days of operation. Our analysis also reveals a nonlinear relationship between spike detection and decoding performance. Increasing the detection sensitivity improves decoding accuracy and long-term stability, which means the activity of more neurons is beneficial despite the detection of more noise. Reducing the spike detection sensitivity still provides acceptable decoding accuracy whilst reducing the bandwidth by at least 30%. Significance. Our findings regarding the relationship between spike detection and decoding performance can provide guidance on setting the threshold for spike detection rather than relying on training or trial-and-error. The trade-off between data bandwidth and decoding performance can be effectively managed using appropriate spike detection settings. We demonstrate improved decoding performance by maintaining statistical invariance of input features. We believe this approach can motivate further research focused on improving decoding performance through the manipulation of data itself (based on a hypothesis) rather than using more complex decoding models.

Spike detection is often the first step in neural signal processing. It has profound effects on subsequent steps down the signal processing pipeline. Most existing spike detection algorithms require manual setting of detection threshold, which is very inconvenient for long-term neural interface. Furthermore, these algorithms are usually only evaluated using simulated dataset. Few studies are devoted to evaluating how different spike detection algorithms affect decoding performance in brain-computer interface. We have proposed a new spike detection algorithm called "exponential component - power component" (EC-PC) that offers fully automatic unsupervised spike detection. In this study, we compared the performance of a motor decoding task when different spike detection algorithms were used. EC-PC is shown to produce a higher decoding accuracy compared with other existing algorithms. Our results suggest that EC-PC can help improve motor decoding performance of brain-computer interface.

One of the main problems in Brain Computer Interface (BCI) systems is the non-stationary behavior of the electroencephalography (EEG) signals causing problems in real time applications. Another common problem in BCI systems is the situation where the labeled data are scarce. In this study, we take a semi-supervised learning perspective and propose solving both types of problems by updating the BCI system with labels obtained from the outputs of the classifier. To test the approach, data from motor imagery BCI system are used. Attributes extracted from EEG signals are classified with Linear Discriminant Analysis (LDA) and Support Vector Machines (SVM). With respect to the static classifiers, accuracy was improved approximately 4% using the proposed adaptation approach in the case of a training dataset. Even though the difference between the performance of static and adaptive classifiers decreases as the size of training data increases, the accuracy of our proposed adaptive classifier remains higher. The proposed approach has also improved the performance of a BCI system around 4% in the case of non-stationary signals as well.

A brain computer interface (BCI) is a real-time communication system designed to allow users to voluntarily send messages or commands without sending them through the brain's normal output pathways. We designed a real-time BCI platform based on Android. A equipment that uses the human to control a portable device through some electroencephalographic (EEG) rhythms has also been presented. The neural signals obtained by EEG recording equipment are sent through a Web Service technology connection to a PC that processes it in real time and sends it wirelessly to Android. Web Service has been used as a wireless technology for sending EEG signals to a PC and vice versa, the Android gets the command from the PC though the Web Service technology, which has been proposed and furthers it showing that the system is reliable and robust enough to work in BCI systems. In this study we have investigated the human’s ability to application by manipulating neuronal motor cortex activity in the presence of a visual feedback environment. This paper presents one of these solutions, which control application by BCI based on motor imagery. This type of BCI solution is translating the motor imagery EEG into three control signals: left, right or transmutation. And then use it as an input device of application to realize the function of operating. The Android digitizes and stores the EEG signal, and exports the results of Signal Analysis on the Monitors to achieve the basic function which is application through the human’s ideas. COM technology allows the BCI platform has strong scalability to meet the needs of various types of brain computer interface solution for the application, and the result is cheering.

Brain-computer interface (BCI) systems have emerged as an augmentative technology that can provide a promising solution for individuals with motor dysfunctions and for the elderly who are experiencing muscle weakness. Steady-state visually evoked potentials (SSVEPs) are widely adopted in BCI systems due to their high speed and accuracy when compared to other BCI paradigms. In this paper, we apply combined magnitude and phase features for class discrimination in a real-time SSVEP-based BCI platform. In the proposed real-time system users gain control of a motorised bed system with seven motion commands and an idle state. Experimental results amongst eight participants demonstrate that the proposed real-time BCI system can successfully discriminate between different SSVEP signals achieving high information transfer rates (ITR) of 82.73 bits/min. The attractive features of the proposed system include noninvasive recording, simple electrode configuration, excellent BCI response and minimal training requirements.

A brain computer interface (BCI) is a real-time communication system designed to allow users to voluntarily send messages or commands without sending them through the brain's normal output pathways. We designed a real-time BCI auxiliary game platform for motion disabled. Firstly, this system digitizes and stores the EEG signal, and exports the results of Signal Analysis on the Monitors to achieve the basic function which is playing pc-game through the human's ideas. COM technology allows the BCI platform has strong scalability to meet the needs of various types of brain computer interface solution for the games. Secondly, Fisher Distance criterion is used to select the features. And classification of Motor Imagery EEG evoked by a sequence of randomly mixed left and right motor imagery is performed by a back-propagation neural networks (BPNN), which is in order to recover the two EEG channels C3/C4. Finally, this paper presents one of these solutions, which control games by BCI based on motor imagery. This type of BCI solution is translating the motor imagery EEG into three control signals: left, right or stop. And then a simple game player can use it as an input device of to realize the function of operating games.

Unsupervised automatic online spike sorting using reward-based online clustering

BackgroundTime-Frequency analysis of electroencephalogram (EEG) during different mental tasks received significant attention. As EEG is non-stationary, time-frequency analysis is essential to analyze brain states during different mental tasks. Further, the time-frequency information of EEG signal can be used as a feature for classification in brain-computer interface (BCI) applications.MethodsTo accurately model the EEG, band-limited multiple Fourier linear combiner (BMFLC), a linear combination of truncated multiple Fourier series models is employed. A state-space model for BMFLC in combination with Kalman filter/smoother is developed to obtain accurate adaptive estimation. By virtue of construction, BMFLC with Kalman filter/smoother provides accurate time-frequency decomposition of the bandlimited signal.ResultsThe proposed method is computationally fast and is suitable for real-time BCI applications. To evaluate the proposed algorithm, a comparison with short-time Fourier transform (STFT) and continuous wavelet transform (CWT) for both synthesized and real EEG data is performed in this paper. The proposed method is applied to BCI Competition data IV for ERD detection in comparison with existing methods.ConclusionsResults show that the proposed algorithm can provide optimal time-frequency resolution as compared to STFT and CWT. For ERD detection, BMFLC-KF outperforms STFT and BMFLC-KS in real-time applicability with low computational requirement.

Brain Machine Interface (BMI) systems demand real-time spike sorting to instantaneously decode the spike trains of simultaneously recorded cortical neurons. Real-time spike sorting, however, requires extensive computational power that is not feasible to implement in implantable BMI architectures, thereby requiring transmission of high-bandwidth raw neural data to an external computer. In this work, we describe a miniaturized, low power, programmable hardware module capable of performing this task within the resource constraints of an implantable chip. The module computes a sparse representation of the spike waveforms followed by "smart" thresholding. This cascade restricts the sparse representation to a subset of projections that preserve the discriminative features of neuron-specific spike waveforms. In addition, it further reduces telemetry bandwidth making it feasible to wirelessly transmit only the important biological information to the outside world, thereby improving the efficiency, practicality and viability of BMI systems in clinical applications.

Objective. Deep learning algorithms employed in brain computer interfaces (BCIs) need large electroencephalographic (EEG) datasets to be trained. These datasets are usually unbalanced, particularly when error potential (ErrP) experiment are considered, being ErrP’s epochs much rarer than non-ErrP ones. To face the issue of unbalance of rare epochs, this paper presents a novel, data balancing methods based on ARX–modelling. Approach. AutoRegressive with eXogenous input (ARX)-models are identified on the EEG data of the ‘Monitoring error-related potentials’ dataset of the BNCI Horizon 2020 and then employed to generate new synthetic data of the minority class of ErrP epochs. The balanced dataset is used to train a classifier of non-ErrP vs. ErrP epochs based on EEGNet. Main results. Compared to classical techniques (e.g. class weights, CW) for data balancing, the new method outperforms the others in terms of resulting accuracy (i.e. ARX 91.5% vs CW 88.3% ), F1-score (i.e. ARX 78.3% vs CW 73.7% ) and balanced accuracy (i.e. ARX 87.0% vs CW 81.1% ) and also reduces the number of false positive detection (i.e. ARX 51 vs CW 104). Moreover, the ARX-based method shows a better generalization capability of the whole model to classify and predict new data. Significance. The results obtained suggest that the proposed method can be used in BCI application for tackling the issue of data unbalance and obtain more reliable and robust performances.

Current Brain Computer Interface (BCI) systems are still not commercialized due to their insufficient accuracies. Although Common Spatial Pattern (CSP) is an effective method for BCI applications, it does not consider the channels' co-activation information. This study is aimed at modifying CSP method by incorporating synchronization of channels in the CSP formula and then passes the values through a nonlinear kernel function to enhance the discrimination rate between the left and right imagery movements. Inserting the synchronization of every two channels into the kernel CSP formula is performed in two different ways. Experimental results on a set of EEG signals belonged to three subjects for discrimination of left and right hand imagery movements reveal that the proposed kernel synchronous CSP method outperformed the standard CSP, synchronous CSP and kernel CSP methods for all subjects.

Signaling of information in the vertebrate central nervous system is often carried by populations of neurons rather than individual neurons. Also propagation of suprathreshold spiking activity involves populations of neurons. Empirical studies addressing cortical function directly thus require recordings from populations of neurons with high resolution. Here we describe an optical method and a deconvolution algorithm to record neural activity from up to 100 neurons with single-cell and single-spike resolution. This method relies on detection of the transient increases in intracellular somatic calcium concentration associated with suprathreshold electrical spikes (action potentials) in cortical neurons. High temporal resolution of the optical recordings is achieved by a fast random-access scanning technique using acousto-optical deflectors (AODs). Two-photon excitation of the calcium-sensitive dye results in high spatial resolution in opaque brain tissue. Reconstruction of spikes from the fluorescence calcium recordings is achieved by a maximum-likelihood method. Simultaneous electrophysiological and optical recordings indicate that our method reliably detects spikes (>97% spike detection efficiency), has a low rate of false positive spike detection (< 0.003 spikes/sec), and a high temporal precision (about 3 msec). This optical method of spike detection can be used to record neural activity in vitro and in anesthetized animals in vivo.

Command of a simulated wheelchair on a virtual environment using a brain-computer interface

We report a scalable neural recording interface with embedded lossless compression to reduce dynamic power consumption ( $\text{P}_{D}$ ) for data transmission in high-density neural recording systems. We investigated the characteristics of neural signals and implemented effective lossless compression for local field potential (LFP) and extracellular action potential (EAP or spike) in separate signal paths. For LFP, spatial–temporal (spatiotemporal) correlation of the LFP signals is exploited in a $\Delta $ -modulated $\Delta \Sigma $ analog-to-digital converter ( $\Delta -\Delta \Sigma $ ADC) and a dedicated digital difference circuit. Then, statistical redundancy is further eliminated through entropy encoding without information loss. For spikes, only essential parts of waveforms in the spikes are extracted from the raw data by using spike detectors and reconfigurable analog memories. The prototype chip was fabricated using 180-nm CMOS processes, incorporating 128 channels into a modular architecture that is easily scalable and expandable for high-density neural recordings. The fabricated chip achieved the data rate reduction for the LFPs and spikes by a factor of 5.35 and 10.54, respectively, from the proposed compression scheme. Consequently, $P_{D}$ was reduced by 89%, when compared to the uncompressed case. We also achieved the state-of-the-art recording performance of 3.37 $\mu \text{W}$ per channel, 5.18 $\mu V_{\mathrm {rms}}$ noise, and 3.41 ${\text {NEF}}^{2}V_{\mathrm {DD}}$ .