Gumpy is a free and open source software, which allows end-users to perform online hybrid BCIs and provides different techniques for processing and decoding of EEG and EMG signals. More importantly, the achieved results reveal that gumpy's deep learning toolbox can match or outperform the state-of-the-art in terms of accuracy. This can therefore enable BCI researchers to develop more robust decoding algorithms using novel techniques and hence chart a route ahead for new BCI improvements.

Objective: To study the neural control of movement, it is often necessary to estimate how muscles are activated across a variety of behavioral conditions. One approach is to try extracting the underlying neural command signal to muscles by applying latent variable modeling methods to electromyographic (EMG) recordings. However, estimating the latent command signal that underlies muscle activation is challenging due to its complex relation with recorded EMG signals. Common approaches estimate each muscle activation independently or require manual tuning of model hyperparameters to preserve behaviorally-relevant features. Approach: Here, we adapted AutoLFADS, a large-scale, unsupervised deep learning approach originally designed to de-noise cortical spiking data, to estimate muscle activation from multi-muscle EMG signals. AutoLFADS uses recurrent neural networks (RNNs) to model the spatial and temporal regularities that underlie multi-muscle activation. Main Results: We first tested AutoLFADS on muscle activity from the rat hindlimb during locomotion and found that it dynamically adjusts its frequency response characteristics across different phases of behavior. The model produced single-trial estimates of muscle activation that improved prediction of joint kinematics as compared to low-pass or Bayesian filtering. We also applied AutoLFADS to monkey forearm muscle activity recorded during an isometric wrist force task. AutoLFADS uncovered previously uncharacterized high-frequency oscillations in the EMG that enhanced the correlation with measured force. The AutoLFADS-inferred estimates of muscle activation were also more closely correlated with simultaneously-recorded motor cortical activity than were other tested approaches. Significance: This method leverages dynamical systems modeling and artificial neural networks to provide estimates of muscle activation for multiple muscles. Ultimately, the approach can be used for further studies of multi-muscle coordination and its control by upstream brain areas.

The dynamics and connectivity of neural circuits continuously change on timescales ranging from milliseconds to an animal’s lifetime. Therefore, to understand biological networks, minimally invasive methods are required to repeatedly record them in behaving animals. Here we describe a suite of devices that enable long-term optical recordings of the adult Drosophila melanogaster ventral nerve cord (VNC). These consist of transparent, numbered windows to replace thoracic exoskeleton, compliant implants to displace internal organs, a precision arm to assist implantation, and a hinged stage to repeatedly tether flies. To validate and illustrate our toolkit we (i) show minimal impact on animal behavior and survival, (ii) follow the degradation of chordotonal organ mechanosensory nerve terminals over weeks after leg amputation, and (iii) uncover waves of neural activity caffeine ingestion. Thus, our long-term imaging toolkit opens up the investigation of premotor and motor circuit adaptations in response to injury, drug ingestion, aging, learning, and disease.