Functional brain–heart interplay extends to the multifractal domain

The study of functional brain–heart interplay has provided meaningful insights in cardiology and neuroscience. Regarding biosignal processing, this interplay involves predominantly neural and heartbeat linear dynamics expressed via time and frequency domain-related features. However, the dynamics of central and autonomous nervous systems show nonlinear and multifractal behaviours, and the extent to which this behaviour influences brain–heart interactions is currently unknown. Here, we report a novel signal processing framework aimed at quantifying nonlinear functional brain–heart interplay in the non-Gaussian and multifractal domains that combines electroencephalography (EEG) and heart rate variability series. This framework relies on a maximal information coefficient analysis between nonlinear multiscale features derived from EEG spectra and from an inhomogeneous point-process model for heartbeat dynamics. Experimental results were gathered from 24 healthy volunteers during a resting state and a cold pressor test, revealing that synchronous changes between brain and heartbeat multifractal spectra occur at higher EEG frequency bands and through nonlinear/complex cardiovascular control. We conclude that significant bodily, sympathovagal changes such as those elicited by cold-pressure stimuli affect the functional brain–heart interplay beyond second-order statistics, thus extending it to multifractal dynamics. These results provide a platform to define novel nervous-system-targeted biomarkers. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.

Optimization and evaluation of motion sequences of an averaged human motion model by using kinematic techniques and new evaluation methods

Signal processing, pattern recognition as well as modelling and simulation require a large amount of reference data, both for the development of new methods and for their evaluation. Depending on the application, the availability of databases is rather low. In the field of biosignal processing with a focus on the functionalization of furniture for nursing and hospital facilities, a database from a motion capturing system (MoCap), and a method to generate averaged human motion sequences was presented in subsequent works by our research group. Evaluations revealed that the averaged motion sequences partly contain artifacts caused by the averaging and thus are not directly usable. To use the averaged motion sequences e.g., in simulation tasks, this paper presents an extension with kinematic methods to combine averaged motion sequences and to suppress and thus optimize inappropriate motion artifacts by error correction. To check whether the results are usable after the processing steps, four evaluation criteria are proposed. The evaluation of the resulting motion sequences shows that sequences are generated which do not fully correspond to human motion sequences but are well suited for simulation tasks.

BioPyC, an Open-Source Python Toolbox for Offline Electroencephalographic and Physiological Signals Classification

Research on brain–computer interfaces (BCIs) has become more democratic in recent decades, and experiments using electroencephalography (EEG)-based BCIs has dramatically increased. The variety of protocol designs and the growing interest in physiological computing require parallel improvements in processing and classification of both EEG signals and bio signals, such as electrodermal activity (EDA), heart rate (HR) or breathing. If some EEG-based analysis tools are already available for online BCIs with a number of online BCI platforms (e.g., BCI2000 or OpenViBE), it remains crucial to perform offline analyses in order to design, select, tune, validate and test algorithms before using them online. Moreover, studying and comparing those algorithms usually requires expertise in programming, signal processing and machine learning, whereas numerous BCI researchers come from other backgrounds with limited or no training in such skills. Finally, existing BCI toolboxes are focused on EEG and other brain signals but usually do not include processing tools for other bio signals. Therefore, in this paper, we describe BioPyC, a free, open-source and easy-to-use Python platform for offline EEG and biosignal processing and classification. Based on an intuitive and well-guided graphical interface, four main modules allow the user to follow the standard steps of the BCI process without any programming skills: (1) reading different neurophysiological signal data formats, (2) filtering and representing EEG and bio signals, (3) classifying them, and (4) visualizing and performing statistical tests on the results. We illustrate BioPyC use on four studies, namely classifying mental tasks, the cognitive workload, emotions and attention states from EEG signals.

A new analgesic index for postoperative pain assessment based on a photoplethysmographic spectrogram and convolutional neural network (Preprint)

BACKGROUND Although commercially available analgesic indices based on biosignal processing have been used to quantify nociception during general anaesthesia, the performance of these indices is not high in awake patients. Therefore, there is a need for the development of a new analgesic index with improved performance to quantify postoperative pain in awake patients. OBJECTIVE The aim of this study was to develop a new analgesic index using spectrogram of photoplethysmogram and convolutional neural network to objectively assess pain in awake patients. METHODS Photoplethysmograms (PPGs) were obtained for 6 min both in the absence (preoperatively) and presence (postoperatively) of pain in a group of surgical patients. Of these, 5 min worth of PPG data, barring the first minute, were used for analysis. Based on the spectrogram from the photoplethysmography and convolutional neural network, we developed a spectrogram-CNN index (SCI) for pain assessment. The area under the curve (AUC) of the receiver-operating characteristic (ROC) curve was measured to evaluate the performance of the two indices. RESULTS PPGs from 100 patients were used to develop the SCI. When there was pain, the mean [95% confidence interval, CI] SCI value increased significantly (baseline: 28.5 [24.2 - 30.7] vs. recovery area: 65.7 [60.5 - 68.3]; P<0.01). The AUC of ROC curve and balanced accuracy were 0.76 and 71.4%, respectively. The cut-off value for detecting pain was 48 on the SCI, with a sensitivity of 68.3% and specificity of 73.8%. CONCLUSIONS Although there were limitations to the study design, we confirmed that the SCI can efficiently detect postoperative pain in conscious patients. Further studies are needed to assess feasibility and prevent overfitting in various populations, including patients under general anaesthesia. CLINICALTRIAL KCT0002080

Performance Evaluation of Convolutional Neural Network for Hand Gesture Recognition Using EMG

Electromyography (EMG) is a measure of electrical activity generated by the contraction of muscles. Non-invasive surface EMG (sEMG)-based pattern recognition methods have shown the potential for upper limb prosthesis control. However, it is still insufficient for natural control. Recent advancements in deep learning have shown tremendous progress in biosignal processing. Multiple architectures have been proposed yielding high accuracies (>95%) for offline analysis, yet the delay caused due to optimization of the system remains a challenge for its real-time application. From this arises a need for optimized deep learning architecture based on fine-tuned hyper-parameters. Although the chance of achieving convergence is random, however, it is important to observe that the performance gain made is significant enough to justify extra computation. In this study, the convolutional neural network (CNN) was implemented to decode hand gestures from the sEMG data recorded from 18 subjects to investigate the effect of hyper-parameters on each hand gesture. Results showed that the learning rate set to either 0.0001 or 0.001 with 80-100 epochs significantly outperformed (p < 0.05) other considerations. In addition, it was observed that regardless of network configuration some motions (close hand, flex hand, extend the hand and fine grip) performed better (83.7% ± 13.5%, 71.2% ± 20.2%, 82.6% ± 13.9% and 74.6% ± 15%, respectively) throughout the course of study. So, a robust and stable myoelectric control can be designed on the basis of the best performing hand motions. With improved recognition and uniform gain in performance, the deep learning-based approach has the potential to be a more robust alternative to traditional machine learning algorithms.