Explore the vast range of titles available.

How neural correlates of movements are represented in the human brain is of ongoing interest and has been researched with invasive and non-invasive methods. In this study, we analyzed the encoding of single upper limb movements in the time-domain of low-frequency electroencephalography (EEG) signals. Fifteen healthy subjects executed and imagined six different sustained upper limb movements. We classified these six movements and a rest class and obtained significant average classification accuracies of 55% (movement vs movement) and 87% (movement vs rest) for executed movements, and 27% and 73%, respectively, for imagined movements. Furthermore, we analyzed the classifier patterns in the source space and located the brain areas conveying discriminative movement information. The classifier patterns indicate that mainly premotor areas, primary motor cortex, somatosensory cortex and posterior parietal cortex convey discriminative movement information. The decoding of single upper limb movements is specially interesting in the context of a more natural non-invasive control of e.g., a motor neuroprosthesis or a robotic arm in highly motor disabled persons.

The technical world of today fundamentally relies on structural analysis in the form of design and structural mechanic simulations. A traditional and robust simulation method is the physics-based finite element method (FEM) simulation. FEM simulations in structural mechanics are known to be very accurate; however, the higher the desired resolution, the more computational effort is required. Surrogate modeling provides a robust approach to address this drawback. Nonetheless, finding the right surrogate model and its hyperparameters for a specific use case is not a straightforward process. In this paper, we discuss and compare several classes of mesh-free surrogate models based on traditional and thriving machine learning (ML) and deep learning (DL) methods. We show that relatively simple algorithms (such as k-nearest neighbor regression) can be competitive in applications with low geometrical complexity and extrapolation requirements. With respect to tasks exhibiting higher geometric complexity, our results show that recent DL methods at the forefront of literature (such as physics-informed neural networks) are complicated to train and to parameterize and thus, require further research before they can be put to practical use. In contrast, we show that already well-researched DL methods, such as the multi-layer perceptron, are superior with respect to interpolation use cases and can be easily trained with available tools. With our work, we thus present a basis for the selection and practical implementation of surrogate models.

Para cross-country (XC) skiing has become a prominent sport since its debut at the Örnsköldsvik Winter Olympic Games in 1976. Nevertheless, the lack of studies focusing on standing para XC skiing highlights the need to provide a comprehensive description of this sport, investigating how different prosthetic devices may influence the athletic outcome. In this exploratory case study, the biomechanics of an elite standing para-athlete, with a right-sided transfemoral amputation, was investigated. Tests were performed during diagonal XC skiing on a treadmill, at different speeds and inclinations. Specifically, two different prosthetic feet were compared: the athlete used an Ottobock Genium X3 prosthetic knee with either the Ottobock Taleo or the Ottobock Evanto prosthetic foot. Inertial Measurement Units (IMUs) were employed to estimate joint angles and detect pole hits and lifts. Additionally, data were collected using embedded sensors in the knee prosthesis. Diagonal stride spatiotemporal parameters were further calculated. Results revealed that the Evanto foot significantly increased swing phase duration and hip range of motion, while generating higher knee torque, ankle torque, and axial loading compared to the Taleo foot. This research represents the first application of the employed testing methodology to para standing XC skiing, and it therefore provides a framework for future studies on this discipline.

We show that persons with spinal cord injury (SCI) retain decodable neural correlates of attempted arm and hand movements. We investigated hand open, palmar grasp, lateral grasp, pronation, and supination in 10 persons with cervical SCI. Discriminative movement information was provided by the time-domain of low-frequency electroencephalography (EEG) signals. Based on these signals, we obtained a maximum average classification accuracy of 45% (chance level was 20%) with respect to the five investigated classes. Pattern analysis indicates central motor areas as the origin of the discriminative signals. Furthermore, we introduce a proof-of-concept to classify movement attempts online in a closed loop, and tested it on a person with cervical SCI. We achieved here a modest classification performance of 68.4% with respect to palmar grasp vs hand open (chance level 50%).

Using low-frequency time-domain electroencephalographic (EEG) signals we show, for the same type of upper limb movement, that goal-directed movements have different neural correlates than movements without a particular goal. In a reach-and-touch task, we explored the differences in the movement-related cortical potentials (MRCPs) between goal-directed and non-goal-directed movements. We evaluated if the detection of movement intention was influenced by the goal-directedness of the movement. In a single-trial classification procedure we found that classification accuracies are enhanced if there is a goal-directed movement in mind. Furthermore, by using the classifier patterns and estimating the corresponding brain sources, we show the importance of motor areas and the additional involvement of the posterior parietal lobule in the discrimination between goal-directed movements and non-goal-directed movements. We discuss next the potential contribution of our results on goal-directed movements to a more reliable brain-computer interface (BCI) control that facilitates recovery in spinal-cord injured or stroke end-users. [Display omitted]

The last decade has witnessed a rapid growth of the field of exoplanet discovery and characterization. However, several big challenges remain, many of which could be addressed using machine learning methodology. For instance, the most prolific method for detecting exoplanets and inferring several of their characteristics, transit photometry, is very sensitive to the presence of stellar spots. The current practice in the literature is identifying the effects of spots visually and correcting them manually or discarding the affected data. This paper explores a first step towards fully automating the efficient and precise derivation of transit depths from transit light curves in the presence of stellar spots. The primary focus of the paper is to present in detail a diverse arsenal of methods for doing so. The methods and results we present were obtained in the context of the 1st Machine Learning Challenge organized for the European Space Agency’s upcoming Ariel mission. We first present the problem, the simulated Ariel-like data and outline the Challenge while identifying best practices for organizing similar challenges in the future. Finally, we present the solutions obtained by the top five winning teams, provide their code, and discuss their implications. Successful solutions either construct highly non-linear (w.r.t. the raw data) models with minimal pre-processing – deep neural networks and ensemble methods – or amount to obtaining meaningful statistics from the light curves, constructing linear models on which yields comparably good predictive performance.

Memory-augmented neural networks (MANNs) can perform algorithmic tasks such as sorting. However, they often fail to generalise to input sequence lengths not encountered during training. We introduce two approaches that constrain the state space of the MANN's controller network: state compression and state regularisation. We empirically demonstrated that both approaches can improve generalisation to input sequences of out-of-distribution lengths for a specific type of MANN: the differentiable neural computer (DNC). The constrained DNC could process input sequences that were up to 2.3 times longer than those processed by an unconstrained baseline controller network. Notably, the applied constraints enabled the extension of the DNC's memory matrix without the need for retraining and thus allowed the processing of input sequences that were 10.4 times longer. However, the improvements were not consistent across all tested algorithmic tasks. Interestingly, solutions that performed better often had a highly structured state space, characterised by state trajectories exhibiting increased curvature and loop-like patterns. Our experimental work demonstrates that state-space constraints can enable the training of a DNC using shorter input sequences, thereby saving computational resources and facilitating training when acquiring long sequences is costly.

Memory-augmented neural networks (MANNs) can solve algorithmic tasks like sorting. However, they often do not generalize to lengths of input sequences not seen in the training phase. Therefore, we introduce two approaches constraining the state-space of the network controller to improve the generalization to out-of-distribution-sized input sequences: state compression and state regularization. We show that both approaches can improve the generalization capability of a particular type of MANN, the differentiable neural computer (DNC), and compare our approaches to a stateful and a stateless controller on a set of algorithmic tasks. Furthermore, we show that especially the combination of both approaches can enable a pre-trained DNC to be extended post hoc with a larger memory. Thus, our introduced approaches allow to train a DNC using shorter input sequences and thus save computational resources. Moreover, we observed that the capability for generalization is often accompanied by loop structures in the state-space, which could correspond to looping constructs in algorithms.

We investigated whether the same modulations in spinal motor neurons parallel power modulations of cortical oscillations induced by mental tasks. We recruited 15 participants and recorded high-density electromyography signals (HD-EMG) from the tibialis anterior muscle, as well as electroencephalography (EEG) signals. The cumulative spike train (CST) was computed from the activity of spinal motor neurons decoded from HD-EMG signals. The participants performed sustained dorsiflexion concurrent with foot motor imagery, hand motor imagery, mental arithmetic, or no specific mental task. We found significant power correlations between CST and EEG across trials irrespective of the mental task and across mental tasks at the intra-muscular coherence peak (τ_trial = 0.08 ± 0.10, τ_task = 0.33 ± 0.19, respectively; mean ± std. dev.). CST power in beta and low-gamma bands could provide a novel control signal for neural interface applications, as power changes in these bands are not translated into actual force changes. To evaluate the potential of CST bands as a control signal, we classified the mental tasks from CST bandpower with a linear classifier and obtained classification accuracies slightly but significantly above chance level (30% ± 5%; chance level = 25%). These results show for the first time that mental tasks can modulate the power of cortical and spinal oscillations concurrently. This supports the notion that movement-unrelated oscillations can leak down from the cortex to the spinal level. We further show that mental tasks can be classified from CST, although further research is necessary to boost the classification performance to an adequate level for neural interface applications.Competing Interest StatementThe authors have declared no competing interest.

The conventional framework of motor-unit (MU) control assumes that MUs in a MU pool are constrained by a fixed recruitment order and a common input. This rigid-control framework has been challenged by recent findings suggesting that MU activity could be flexibly modulated, potentially mediated by descending cortical inputs. In this study, rather than evaluating flexibility from the perspective of recruitment thresholds, we investigated control flexibility by assessing if human participants can voluntarily modulate MU firing rates beyond rigid-control constraints. Specifically, we examined whether participants could voluntarily modulate the firing rates of a pair of MUs from the tibialis anterior muscle during real-time feedback. Two tasks involving target-reach with different visual feedback derived from the MUs firing rates were conducted. In both tasks, there was no evidence that participants were able to change MU firing rates in a way that would violate rigid control robustly. Our findings demonstrate limited flexibility in MU control in human tibialis anterior muscle within single-session training, even when real-time MU activity feedback was provided. The results suggest that MU flexibility is not inherently present in the human lower limb.Competing Interest StatementDario Farina is inventor of two patents (Neural Interface. UK Patent application no. GB1813762.0. August 23, 2018 and Neural interface. UK Patent application no. GB2014671.8. September 17, 2020) related to the methods and applications of this work. Dario Farina is also Scientific Advisor for neural interfacing for Meta, Reality Labs, and for high-density EMG technology for OT Bioelettronica, Italy.