Brain Computer Interface (BCI) inefficiency indicates that there would be 10% to 50% of users are unable operate Motor-Imagery-based BCI systems. Importantly, the almost all previous studieds on were based tests Sensory Motor Rhythm (SMR) feature. In this work, we assessed occurrence with SMR and Movement-Related Cortical Potential (MRCP) features.A pool datasets resting state movements related EEG signals was recorded 93 subjects during 2 sessions in separated days. Two methods, Common...

Versatile and energy-efficient neural signal processors are in high demand brain-machine interfaces closed-loop neuromodulation applications. In this paper, we propose an processor for analyses. The proposed utilizes three key techniques to efficiently improve versatility energy efficiency. 1) Hybrid network design: supports artificial (ANN)- spiking (SNN)-based neuromorphic processing where ANN is used support the of ExG signals SNN handling spike signals. 2) Event-driven processing: can...

Invasive cortical brain-machine interfaces (BMIs) can significantly improve the life quality of motor-impaired patients. Nonetheless, externally mounted pedestals pose an infection risk, which calls for fully implanted systems. Such systems, however, must meet strict latency and energy constraints while providing reliable decoding performance. While recurrent spiking neural networks (RSNNs) are ideally suited ultra-low-power, low-latency processing on neuromorphic hardware, it is unclear...

Spike sorting is a fundamental step in extracting single-unit activity from neural ensemble recordings, which play an important role basic neuroscience and neurotechnologies. A few algorithms have been applied spike sorting. However, when noise level or waveform similarity becomes relatively high, their robustness still faces big challenge. In this study, we propose method combining Linear Discriminant Analysis (LDA) Density Peaks (DP) for feature extraction clustering. Relying on the joint...

One of the most concerned problems in neuroscience is how neurons communicate and convey information through spikes. There abundant evidence sensory systems to support use precise timing spikes encode information. However, it remains unknown whether temporal patterns could be generated drive output primary motor cortex (M1), a brain area containing ample recurrent connections that may destroy fidelity. Here, we used novel brain-machine interface mapped order precision activity auditory...

Despite its better bio-plausibility, goal-driven spiking neural network (SNN) has not achieved applicable performance for classifying biological spike trains, and showed little bio-functional similarities compared to traditional artificial networks. In this study, we proposed the motorSRNN, a recurrent SNN topologically inspired by motor circuit of primates. By employing motorSRNN in decoding trains from primary cortex monkeys, good balance between classification accuracy energy consumption....

Abstract Objective Spike sorting is a fundamental step in extracting single-unit activity from neural ensemble recordings, which play an important role basic neuroscience and neurotechnologies. A few algorithms have been applied spike sorting. However, when noise level or waveform similarity becomes relatively high, their robustness still faces big challenge. Approach In this study, we propose method combining Linear Discriminant Analysis (LDA) Density Peaks (DP) for feature extraction...

One of the extraordinary characteristics biological brain is low energy expense it requires to implement a variety functions and intelligence as compared modern artificial (AI). Spike-based energy-efficient temporal codes have long been suggested contributor for run on expense. Despite this code having largely reported in sensory cortex, whether can be implemented other areas serve broader how evolves throughout learning remained unaddressed. In study, we designed novel brain–machine...

In the modern era of technology Free Space Optics (FSO) communication is a propitious technique for among islands or terminals over sea. However, when beams laser strikes through atmosphere, wavefront that beam opposed by stern influences triggered atmospheric turbulence. this paper, we reassembled aberration with Zernike polynomials and SVD (singular value decomposition) both in sand/water environment. And boxplot employed to relate coefficients reconstructed phenomenon propagating heated...

Intracortical Brain-Computer Interfaces (iBCI) establish a new pathway to restore motor functions in individuals with paralysis by interfacing directly the brain translate movement intention into action. However, development of iBCI applications is hindered non-stationarity neural signals induced recording degradation and neuronal property variance. Many decoders were developed overcome this non-stationarity, but its effect on decoding performance remains largely unknown, posing critical...

The rapid development of neural network dataset distillation in recent years has provided new ideas many areas such as continuous learning, architecture search and privacy preservation. Dataset is a very effective method to distill large training datasets into small data, thus ensuring that the test accuracy models trained on their synthesized matches full dataset. Thus, itself commercially valuable, not only for reducing costs, but also compressing storage costs significantly deep learning....

Although EEG classification for schizophrenia has shown promising results on individual datasets, the cross-dataset generalizability of such remains unknown. This study aimed to assess this through transfer learning at segment and levels, by employing spectral convolutional neural network (CNN-S) two distinct datasets classification. While direct cross-decoding only obtained baseline accuracies 54.72% ± 2.77% 47.78% 3.62% fine-tuned CNN-S achieved average 76.46% 1.17% 56.71% 5.76,...

After the introduction of recurrence, an important property biological brain, spiking neural networks (SNNs) have achieved unprecedented classification performance. But they still cannot outperform many artificial networks. Modularity is another crucial feature brain. It remains unclear if modularity can also improve performance SNNs. To investigate this idea, we proposed modular SNN, and compared its with a uniform SNN without by employing them to classify cortical spike trains. For first...

Neural decoding plays a crucial role in brain-computer interfaces (BCI), which is the basis for applications such as motion control and BCI-based rehabilitation. However, current neural tasks are carried out with bulky, high-latency power-consuming computers, becomes significant bottleneck development of next-generation wearable implantable BCI systems. In this paper, we presented Spiking network (SNN) processor based on adaptive Leaky Integrate-and-Fire (LIF) neurons monkey cortical spike...

Steganography is used for converting communication via embedding secrets in cover media. Though steganography has developed many novel approaches based on GANs, etc., coverless generative steganography, sophisticated steganalysis can always perceive them. So there a great possibility of coercive attacks, which an attacker perceives and coerces the sender or receiver to disclose secret information. Therefore, it necessary bring deniable mimics encryption. Usually training suffers from...

One of the extraordinary characteristics biological brain is its low energy expense to implement a variety functions and intelligence compared modern artificial (AI). Spike-based energy-efficient temporal codes have long been suggested as contributor for run with expense. Despite this code having largely reported in sensory cortex, whether can be implemented other areas serve broader how learns generate it remained unaddressed. In study, we designed novel brain-machine interface (BMI)...