Brain-computer interface (BCI) is a direct communication pathway between brain and external devices, and BCI-based prosthetic devices are promising to provide new rehabilitation options for people with motor disabilities. Electrocorticography (ECoG) signals contain rich information correlated with motor activities, and have great potential in hand gesture decoding. However, most existing decoders use long time windows, thus ignore the temporal dynamics within the period. In this study, we propose to use recurrent neural networks (RNNs) to exploit the temporal information in ECoG signals for robust hand gesture decoding. With RNN's high nonlinearity modeling ability, our method can effectively capture the temporal information in ECoG time series for robust gesture recognition. In the experiments, we decode three hand gestures using ECoG signals of two participants, and achieve an accuracy of 90%. Specially, we investigate the possibility of recognizing the gestures in a time interval as short as possible after motion onsets. Our method rapidly recognizes gestures within 0.5 s after motion onsets with an accuracy of about 80%. Experimental results also indicate that the temporal dynamics is especially informative for effective and rapid decoding of hand gestures.

A current challenge of neurotechnologies is to develop speech brain-computer interfaces aiming at restoring communication in people unable to speak. To achieve a proof of concept of such system, neural activity of patients implanted for clinical reasons can be recorded while they speak. Using such simultaneously recorded audio and neural data, decoders can be built to predict speech features using features extracted from brain signals. A typical neural feature is the spectral power of field potentials in the high-gamma frequency band, which happens to overlap the frequency range of speech acoustic signals, especially the fundamental frequency of the voice. Here, we analyzed human electrocorticographic and intracortical recordings during speech production and perception as well as a rat microelectrocorticographic recording during sound perception. We observed that several datasets, recorded with different recording setups, contained spectrotemporal features highly correlated with those of the sound produced by or delivered to the participants, especially within the high-gamma band and above, strongly suggesting a contamination of electrophysiological recordings by the sound signal. This study investigated the presence of acoustic contamination and its possible source. We developed analysis methods and a statistical criterion to objectively assess the presence or absence of contamination-specific correlations, which we used to screen several datasets from five centers worldwide. Not all but several datasets, recorded in a variety of conditions, showed significant evidence of acoustic contamination. Three out of five centers were concerned by the phenomenon. In a recording showing high contamination, the use of high-gamma band features dramatically facilitated the performance of linear decoding of acoustic speech features, while such improvement was very limited for another recording showing no significant contamination. Further analysis and in vitro replication suggest that the contamination is caused by the mechanical action of the sound waves onto the cables and connectors along the recording chain, transforming sound vibrations into an undesired electrical noise affecting the biopotential measurements. Although this study does not per se question the presence of speech-relevant physiological information in the high-gamma range and above (multiunit activity), it alerts on the fact that acoustic contamination of neural signals should be proofed and eliminated before investigating the cortical dynamics of these processes. To this end, we make available a toolbox implementing the proposed statistical approach to quickly assess the extent of contamination in an electrophysiological recording (https://doi.org/10.5281/zenodo.3929296).

Reinforcement learning (RL)-based brain machine interfaces (BMIs) enable the user to learn from the environment through interactions to complete the task without desired signals, which is promising for clinical applications. Previous studies exploited Q-learning techniques to discriminate neural states into simple directional actions providing the trial initial timing. However, the movements in BMI applications can be quite complicated, and the action timing explicitly shows the intention when to move. The rich actions and the corresponding neural states form a large state-action space, imposing generalization difficulty on Q-learning. In this paper, we propose to adopt attention-gated reinforcement learning (AGREL) as a new learning scheme for BMIs to adaptively decode high-dimensional neural activities into seven distinct movements (directional moves, holdings and resting) due to the efficient weight-updating. We apply AGREL on neural data recorded from M1 of a monkey to directly predict a seven-action set in a time sequence to reconstruct the trajectory of a center-out task. Compared to Q-learning techniques, AGREL could improve the target acquisition rate to 90.16% in average with faster convergence and more stability to follow neural activity over multiple days, indicating the potential to achieve better online decoding performance for more complicated BMI tasks.

The accurate monitoring of vital physiological parameters, exemplified by heart rate, respiratory rate, and intracranial pressure (ICP), is of paramount importance, particularly for managing severe cranial injuries. Despite the rapid development of implantable ICP sensing systems over the past decades, they still suffer from, for example, wire connection, low sensitivity, poor resolution, and the inability to monitor multiple variables simultaneously. Here, we propose an ultrasensitive multimodal biotelemetric system that amalgamates an iontronic pressure transducer with exceptional point (EP) operation for the monitoring of ICP signals. The proposed system can exhibit extraordinary performance regarding the detection of minuscule ICP fluctuation, demonstrated by the sensitivity of 115.95 kHz/mmHg and the sensing resolution down to 0.003 mmHg. Our system excels not only in the accurate quantification of ICP levels but also in distinguishing respiration and cardiac activities from ICP signals, thereby achieving the multimodal monitoring of ICP, respiratory, and heart rates within a single system. Our work may provide a pragmatic avenue for the real-time wireless monitoring of ICP and thus hold great potential to be extended to the monitoring of other vital physiological indicators.

Objective: Continuous measurement of key physiological parameters, such as heart rate (HR), pulse oxygen saturation (SpO ₂ ), and sweat pH value, has very broad applications in healthcare, disease surveillance, and fitness and sports training. In this study, a stretchable optical sensing patch system was developed for real-time continuous noninvasive monitoring of the HR, SpO ₂ , and sweat pH, and the sensing data were transmitted to a smartphone through Bluetooth. Methods: The sensor patch system adopted serpentine stretchable interconnects between the optical sensor and microcontroller chip with wireless function on a flexible substrate. The pH sensing function was implemented by coating a pH sensitive organically modified silicate film on the surface of a commercial blood oxygen sensor, achieving simultaneous measurement of HR, SpO ₂ , and sweat pH with a single sensor. Results: Real-time on-body assessment was carried out to evaluate the sensor patch system, showing its excellent repeatability and applicability. The sensor patch system could withstand up to 35% extension and exhibited a pH sensitivity of 4.42 mV/pH from 4.0 to 8.0, while the accuracy of HR from 25 to 250 b/min and SpO ₂ from 70% to 100% sensing were ±1 b/min and ±2%, respectively. Conclusion: The triple sensing functions was achieved through a single optical sensor on a flexible substrate while holding excellent contact with the body. Significance: The sensor patch system can be used for fitness guidance, skin disease detection, and wound monitoring and management by replacing related sensitive films.