BRAND: a platform for closed-loop experiments with deep network models.

Objective.Artificial neural networks (ANNs) are state-of-the-art tools for modeling and decoding neural activity, but deploying them in closed-loop experiments with tight timing constraints is challenging due to their limited support in existing real-time frameworks. Researchers need a platform that fully supports high-level languages for running ANNs (e.g. Python and Julia) while maintaining support for languages that are critical for low-latency data acquisition and processing (e.g. C and C++).Approach.To address these needs, we introduce the Backend for Realtime Asynchronous Neural Decoding (BRAND). BRAND comprises Linux processes, termednodes, which communicate with each other in agraphvia streams of data. Its asynchronous design allows for acquisition, control, and analysis to be executed in parallel on streams of data that may operate at different timescales. BRAND uses Redis, an in-memory database, to send data between nodes, which enables fast inter-process communication and supports 54 different programming languages. Thus, developers can easily deploy existing ANN models in BRAND with minimal implementation changes.Main results.In our tests, BRAND achieved <600 microsecond latency between processes when sending large quantities of data (1024 channels of 30 kHz neural data in 1 ms chunks). BRAND runs a brain-computer interface with a recurrent neural network (RNN) decoder with less than 8 ms of latency from neural data input to decoder prediction. In a real-world demonstration of the system, participant T11 in the BrainGate2 clinical trial (ClinicalTrials.gov Identifier: NCT00912041) performed a standard cursor control task, in which 30 kHz signal processing, RNN decoding, task control, and graphics were all executed in BRAND. This system also supports real-time inference with complex latent variable models like Latent Factor Analysis via Dynamical Systems.Significance.By providing a framework that is fast, modular, and language-agnostic, BRAND lowers the barriers to integrating the latest tools in neuroscience and machine learning into closed-loop experiments.

An accurate and rapidly calibrating speech neuroprosthesis.

Brain-computer interfaces can enable rapid, intuitive communication for people with paralysis by transforming the cortical activity associated with attempted speech into text on a computer screen. Despite recent advances, communication with brain-computer interfaces has been restricted by extensive training data requirements and inaccurate word output. A man in his 40's with ALS with tetraparesis and severe dysarthria (ALSFRS-R = 23) was enrolled into the BrainGate2 clinical trial. He underwent surgical implantation of four microelectrode arrays into his left precentral gyrus, which recorded neural activity from 256 intracortical electrodes. We report a speech neuroprosthesis that decoded his neural activity as he attempted to speak in both prompted and unstructured conversational settings. Decoded words were displayed on a screen, then vocalized using text-to-speech software designed to sound like his pre-ALS voice. On the first day of system use, following 30 minutes of attempted speech training data, the neuroprosthesis achieved 99.6% accuracy with a 50-word vocabulary. On the second day, the size of the possible output vocabulary increased to 125,000 words, and, after 1.4 additional hours of training data, the neuroprosthesis achieved 90.2% accuracy. With further training data, the neuroprosthesis sustained 97.5% accuracy beyond eight months after surgical implantation. The participant has used the neuroprosthesis to communicate in self-paced conversations for over 248 hours. In an individual with ALS and severe dysarthria, an intracortical speech neuroprosthesis reached a level of performance suitable to restore naturalistic communication after a brief training period.

BRAND: A platform for closed-loop experiments with deep network models.

Artificial neural networks (ANNs) are state-of-the-art tools for modeling and decoding neural activity, but deploying them in closed-loop experiments with tight timing constraints is challenging due to their limited support in existing real-time frameworks. Researchers need a platform that fully supports high-level languages for running ANNs (e.g., Python and Julia) while maintaining support for languages that are critical for low-latency data acquisition and processing (e.g., C and C++). To address these needs, we introduce the Backend for Realtime Asynchronous Neural Decoding (BRAND). BRAND comprises Linux processes, termed nodes , which communicate with each other in a graph via streams of data. Its asynchronous design allows for acquisition, control, and analysis to be executed in parallel on streams of data that may operate at different timescales. BRAND uses Redis to send data between nodes, which enables fast inter-process communication and supports 54 different programming languages. Thus, developers can easily deploy existing ANN models in BRAND with minimal implementation changes. In our tests, BRAND achieved <600 microsecond latency between processes when sending large quantities of data (1024 channels of 30 kHz neural data in 1-millisecond chunks). BRAND runs a brain-computer interface with a recurrent neural network (RNN) decoder with less than 8 milliseconds of latency from neural data input to decoder prediction. In a real-world demonstration of the system, participant T11 in the BrainGate2 clinical trial performed a standard cursor control task, in which 30 kHz signal processing, RNN decoding, task control, and graphics were all executed in BRAND. This system also supports real-time inference with complex latent variable models like Latent Factor Analysis via Dynamical Systems. By providing a framework that is fast, modular, and language-agnostic, BRAND lowers the barriers to integrating the latest tools in neuroscience and machine learning into closed-loop experiments.

Spatial Distribution and Estimation Model of Soil pH in Coastal Eastern China.

Soil pH is an essential indicator for assessing soil quality and soil health. In this study, based on the Chinese farmland soil survey dataset and meteorological dataset, the spatial distribution characteristics of soil pH in coastal eastern China were analyzed using kriging interpolation. The relationships between hydrothermal conditions and soil pH were explored using regression analysis with mean annual precipitation (MAP), mean annual temperature (MAT), the ratio of precipitation to temperature (P/T), and the product of precipitation and temperature (P*T) as the main explanatory variables. Based on this, a model that can rapidly estimate soil pH was established. The results showed that: (a) The spatial heterogeneity of soil pH in coastal eastern China was obvious, with the values gradually decreasing from north to south, ranging from 4.5 to 8.5; (b) soil pH was significantly correlated with all explanatory variables at the 0.01 level. In general, MAP was the main factor affecting soil pH (r = -0.7244), followed by P/T (r = -0.6007). In the regions with MAP < 800 mm, soil pH was negatively correlated with MAP (r = -0.4631) and P/T (r = -0.7041), respectively, and positively correlated with MAT (r = 0.6093) and P*T (r = 0.3951), respectively. In the regions with MAP > 800 mm, soil pH was negatively correlated with MAP (r = -0.6651), MAT (r = -0.5047), P/T (r = -0.3268), and P*T (r = -0.5808), respectively. (c) The estimation model of soil pH was: y = 23.4572 - 6.3930 × lgMAP + 0.1312 × MAT. It has been verified to have a high accuracy (r = 0.7743, p < 0.01). The mean error, the mean absolute error, and the root mean square error were 0.0450, 0.5300, and 0.7193, respectively. It provides a new path for rapid estimation of the regional soil pH, which is important for improving the management of agricultural production and slowing down soil degradation.

High-Performance Polymers for Membrane CO2 /N2 Separation.

This Concept examines strategies to design advanced polymers with high CO2 permeability and high CO2 /N2 selectivity, which are the key to the success of membrane technology for CO2 capture from fossil fuel-fired power plants. Specifically, polymers with enhanced CO2 solubility and thus CO2 /N2 selectivity are designed by incorporating CO2 -philic groups in polymers such as poly(ethylene oxide)-containing polymers and poly(ionic liquids); polymers with enhanced CO2 diffusivity and thus CO2 permeability are designed with contorted rigid polymer chains to obtain high free volume, such as polymers with intrinsic microporosity and thermally rearranged polymers. The underlying rationales for materials design are discussed and polymers with promising CO2 /N2 separation properties for CO2 capture from flue gas are highlighted.