An FSCV Deep Neural Network: Development, Pruning, and Acceleration on an FPGA

Integrated prediction and control of mobility changes of young talents in the field of science and technology based on convolutional neural network

As the scientific and technological levels continue to rise, the dynamics of young talent within these fields are increasingly significant. Currently, there is a lack of comprehensive models for predicting the movement of young professionals in science and technology. To address this gap, this study introduces an integrated approach to forecasting and managing the flow of these talents, leveraging the power of convolutional neural networks (CNNs). The performance test of the proposed method shows that the prediction accuracy of this method is 76.98%, which is superior to the two comparison methods. In addition, the results showed that the average error of the model was 0.0285 lower than that of the model based on the recurrent prediction error (RPE) algorithm learning algorithm, and the average time was 41.6 s lower than that of the model based on the backpropagation (BP) learning algorithm. In predicting the flow of young talent, the study uses flow characteristics including personal characteristics, occupational characteristics, organizational characteristics and network characteristics. Through the above results, the study found that convolutional neural network can effectively use these features to predict the flow of young talents, and its model is superior to other commonly used models in processing speed and accuracy. The above results indicate that the model can provide organizations and government agencies with useful information about the flow trend of young talents, and help them to formulate better talent management strategies.

Novel, User-Friendly Experimental and Analysis Strategies for Fast Voltammetry: Next Generation FSCAV with Artificial Neural Networks

Fast-scan adsorption-controlled voltammetry (FSCAV) was recently derived from fast-scan cyclic voltammetry to estimate the absolute concentrations of neurotransmitters by using the innate adsorption properties of carbon fiber microelectrodes. This technique has improved our knowledge of serotonin dynamics in vivo. However, the analysis of FSCAV data is laborious and technically challenging. First, each electrode requires post-experimental in vitro calibration. Second, current analysis methods are semi-manual and time-consuming and require a steep learning curve. Finally, the calibration methods used do not adapt to nonlinear electrode responses. In this work, we provide freely accessible computational solutions to these issues. First, we design an artificial neural network (ANN) and train it with a large data set (calibrations from 140 electrodes by six different researchers) to achieve calibration-free estimations and improve predictive error. We discuss the power of the ANN to obtain a low predictive error without electrode-specific calibrations as a function of being able to predict the sensitivity of the electrode. We use the ANN to successfully predict the absolute serotonin concentrations of real in vivo data. Finally, we create a fast and user-friendly, fully automated analysis web platform to simplify and reduce the expertise required for the postanalysis of FSCAV signals.

Deep Learning for Voltammetric Sensing in a Living Animal Brain

Numerous neurochemicals have been implicated in the modulation of brain function, making them appealing analytes for sensors and diagnostics. However, it is a grand challenge to selectively measure multiple neurochemicals simultaneously in vivo because of their great variations in concentrations, dynamic nature, and composition. Herein, we present a deep learning-based voltammetric sensing platform for the highly selective and simultaneous analysis of three neurochemicals in a living animal brain. The system features a carbon fiber electrode capable of capturing the mixed dynamics of a neurotransmitter, neuromodulator, and ions. Then a powerful deep neural network is employed to resolve individual chemical and spatial-temporal information. With this, a single electrochemical measurement reveals an interplaying concentration changes of dopamine, ascorbate, and ions in living rat brain, which is unobtainable with existing analytical methodologies. Our strategy provides a powerful means to expedite research in neuroscience and empower sensing-aided diagnostic applications.

Cocaine-Induced Changes in Tonic Dopamine Concentrations Measured Using Multiple-Cyclic Square Wave Voltammetry in vivo

For over 40 years, in vivo microdialysis techniques have been at the forefront in measuring the effects of illicit substances on brain tonic extracellular levels of dopamine that underlie many aspects of drug addiction. However, the size of microdialysis probes and sampling rate may limit this technique’s ability to provide an accurate assessment of drug effects in microneural environments. A novel electrochemical method known as multiple-cyclic square wave voltammetry (M-CSWV), was recently developed to measure second-to-second changes in tonic dopamine levels at microelectrodes, providing spatiotemporal resolution superior to microdialysis. Here, we utilized M-CSWV and fast-scan cyclic voltammetry (FSCV) to measure changes in tonic or phasic dopamine release in the nucleus accumbens core (NAcc) after acute cocaine administration. Carbon-fiber microelectrodes (CFM) and stimulating electrodes were implanted into the NAcc and medial forebrain bundle (MFB) of urethane anesthetized (1.5 g/kg i.p.) Sprague-Dawley rats, respectively. Using FSCV, depths of each electrode were optimized by determining maximal MFB electrical stimulation-evoked phasic dopamine release. Changes in phasic responses were measured after a single dose of intravenous saline or cocaine hydrochloride (3 mg/kg; n = 4). In a separate group, changes in tonic dopamine levels were measured using M-CSWV after intravenous saline and after cocaine hydrochloride (3 mg/kg; n = 5). Both the phasic and tonic dopamine responses in the NAcc were augmented by the injection of cocaine compared to saline control. The phasic and tonic levels changed by approximately x2.4 and x1.9, respectively. These increases were largely consistent with previous studies using FSCV and microdialysis. However, the minimal disruption/disturbance of neuronal tissue by the CFM may explain why the baseline tonic dopamine values (134 ± 32 nM) measured by M-CSWV were found to be 10-fold higher when compared to conventional microdialysis. In this study, we demonstrated phasic dopamine dynamics in the NAcc with acute cocaine administration. M-CSWV was able to record rapid changes in tonic levels of dopamine, which cannot be achieved with other current voltammetric techniques. Taken together, M-CSWV has the potential to provide an unprecedented level of physiologic insight into dopamine signaling, both in vitro and in vivo, which will significantly enhance our understanding of neurochemical mechanisms underlying psychiatric conditions.

Resource-constrained FPGA/DNN co-design

Deep neural networks (DNNs) have demonstrated super performance in most learning tasks. However, a DNN typically contains a large number of parameters and operations, requiring a high-end processing platform for high-speed execution. To address this challenge, hardware-and-software co-design strategies, which involve joint DNN optimization and hardware implementation, can be applied. These strategies reduce the parameters and operations of the DNN, and fit it into a low-resource processing platform. In this paper, a DNN model is used for the analysis of the data captured using an electrochemical method to determine the concentration of a neurotransmitter and the recoding electrode. Next, a DNN miniaturization algorithm is introduced, involving combined pruning and compression, to reduce the DNN resource utilization. Here, the DNN is transformed to have sparse parameters by pruning a percentage of its weights. The Lempel-Ziv-Welch algorithm is then applied to compress the sparse DNN. Next, a DNN overlay is developed, combining the decompression of the DNN parameters and DNN inference, to allow the execution of the DNN on a FPGA on the PYNQ-Z2 board. This approach helps avoid the need for inclusion of a complex quantization algorithm. It compresses the DNN by a factor of 6.18, leading to about 50% reduction in the resource utilization on the FPGA.