This paper presents a real-time fine gesture recognition system for multi-articulating hand prosthesis control, using an embedded convolutional neural network (CNN) to classify hand-muscle contractions sensed at the forearm. The sensor consists in a custom non-intrusive, compact, and easy-to-install 32-channel high-density surface electromyography (HDsEMG) electrode array, built on a flexible printed circuit board (PCB) to allow wrapping around the forearm. The sensor provides a low-noise digitization interface with wireless data transmission through an industrial, scientific and medical (ISM) radio link. An original frequency-time-space cross-domain preprocessing method is proposed to enhance gesture-specific data homogeneity and generate reliable muscle activation maps, leading to 98.15% accuracy when using a majority vote over 5 subsequent inferences by the proposed CNN. The obtained real-time gesture recognition, within 100 to 200 ms, and CNN properties show reliable and promising results to improve on the state-of-the-art of commercial hand prostheses. Moreover, edge computing using a specialized embedded artificial intelligence (AI) platform ensures reliable, secure and low latency real-time operation as well as quick and easy access to training, fine-tuning and calibration of the neural network. Co-design of the signal processing, AI algorithms and sensing hardware ensures a reliable and power-efficient embedded gesture recognition system.

The notion of gating as a mechanism capable of controlling the flow of information from one set of neurons to another, has been studied in many regions of the central nervous system. In the nucleus accumbens, where evidence is especially clear, gating seems to rely on the action of bistable neurons, i.e. of neurons that oscillate between a quiescent “down” state and a firing “up” state, and that act as AND-gates relative to their entries. Independently from these observations, a growing body of evidence now indicates that bistable neurons are also quite abundant in the cortex, although their exact functions in the dynamics of the brain remain to be determined. Here, we propose that at least some of these bistable cortical neurons are part of circuits devoted to gating information flow within the cortex. We also suggest that currently available structural, electrophysiological and imaging data support the existence of at least three different types of gating architectures. The first architecture involves gating directly by the cortex itself. The second architecture features circuits spanning the cortex and the thalamus. The third architecture extends itself through the cortex, the basal ganglia and the thalamus. These propositions highlight the variety of mechanisms that could regulate the passage of action potentials between cortical neurons sets. They also suggest that gating mechanisms require larger-scale neural circuitry to control the state of the gates themselves, in order to fit in the overall wiring of the brain and complement its dynamics.

Neurotransmitters as electrochemical signaling molecules are essential for proper brain function and their dysfunction is involved in several mental disorders. Therefore, the accurate detection and monitoring of these substances are crucial in brain studies. Neurotransmitters are present in the nervous system at very low concentrations, and they mixed with many other biochemical molecules and minerals, thus making their selective detection and measurement difficult. Although numerous techniques to do so have been proposed in the literature, neurotransmitter monitoring in the brain is still a challenge and the subject of ongoing research. This article reviews the current advances and trends in neurotransmitters detection techniques, including in vivo sampling and imaging techniques, electrochemical and nano-object sensing techniques for in vitro and in vivo detection, as well as spectrometric, analytical and derivatization-based methods mainly used for in vitro research. The document analyzes the strengths and weaknesses of each method, with the aim to offer selection guidelines for neuro-engineering research.

Myoelectric hand prostheses offer a way for upper-limb amputees to recover gesture and prehensile abilities to ease rehabilitation and daily life activities. However, studies with prosthesis users found that a lack of intuitiveness and ease-of-use in the human-machine control interface are among the main driving factors in the low user acceptance of these devices. This paper proposes a highly intuitive, responsive and reliable real-time myoelectric hand prosthesis control strategy with an emphasis on the demonstration and report of real-time evaluation metrics. The presented solution leverages surface high-density electromyography (HD-EMG) and a convolutional neural network (CNN) to adapt itself to each unique user and his/her specific voluntary muscle contraction patterns. Furthermore, a transfer learning approach is presented to drastically reduce the training time and allow for easy installation and calibration processes. The CNN-based gesture recognition system was evaluated in real-time with a group of 12 able-bodied users. A real-time test for 6 classes/grip modes resulted in mean and median positive predictive values (PPV) of 93.43% and 100%, respectively. Each gesture state is instantly accessible from any other state, with no mode switching required for increased responsiveness and natural seamless control. The system is able to output a correct prediction within less than 116 ms latency. 100% PPV has been attained in many trials and is realistically achievable consistently with user practice and/or employing a thresholded majority vote inference. Using transfer learning, these results are achievable after a sensor installation, data recording and network training/fine-tuning routine taking less than 10 min to complete, a reduction of 89.4% in the setup time of the traditional, non-transfer learning approach.

Typical bidirectional associative memories (BAM) use an offline, one-shot learning rule, have poor memory storage capacity, are sensitive to noise, and are subject to spurious steady states during recall. Recent work on BAM has improved network performance in relation to noisy recall and the number of spurious attractors, but at the cost of an increase in BAM complexity. In all cases, the networks can only recall bipolar stimuli and, thus, are of limited use for grey-level pattern recall. In this paper, we introduce a new bidirectional heteroassociative memory model that uses a simple self-convergent iterative learning rule and a new nonlinear output function. As a result, the model can learn online without being subject to overlearning. Our simulation results show that this new model causes fewer spurious attractors when compared to others popular BAM networks, for a comparable performance in terms of tolerance to noise and storage capacity. In addition, the novel output function enables it to learn and recall grey-level patterns in a bidirectional way.