Real-Time Sensor-Based Human Activity Recognition for eFitness and eHealth Platforms.

Human Activity Recognition (HAR) plays an important role in the automation of various tasks related to activity tracking in such areas as healthcare and eldercare (telerehabilitation, telemonitoring), security, ergonomics, entertainment (fitness, sports promotion, human-computer interaction, video games), and intelligent environments. This paper tackles the problem of real-time recognition and repetition counting of 12 types of exercises performed during athletic workouts. Our approach is based on the deep neural network model fed by the signal from a 9-axis motion sensor (IMU) placed on the chest. The model can be run on mobile platforms (iOS, Android). We discuss design requirements for the system and their impact on data collection protocols. We present architecture based on an encoder pretrained with contrastive learning. Compared to end-to-end training, the presented approach significantly improves the developed model's quality in terms of accuracy (F1 score, MAPE) and robustness (false-positive rate) during background activity. We make the AIDLAB-HAR dataset publicly available to encourage further research.

Improving the generalizability of infant psychological research: The ManyBabies model.

Yarkoni's analysis clearly articulates a number of concerns limiting the generalizability and explanatory power of psychological findings, many of which are compounded in infancy research. ManyBabies addresses these concerns via a radically collaborative, large-scale and open approach to research that is grounded in theory-building, committed to diversification, and focused on understanding sources of variation.

Novel Methodological Tools for Behavioral Interventions: The Case of HRV-Biofeedback. Sham Control and Quantitative Physiology-Based Assessment of Training Quality and Fidelity.

Scientific research on heart rate variability (HRV) biofeedback is burdened by certain methodological issues, such as lack of consistent training quality and fidelity assessment or control conditions that would mimic the intervention. In the present study, a novel sham HRV-biofeedback training was proposed as a credible control condition, indistinguishable from the real training. The Yield Efficiency of Training Index (YETI), a quantitative measure based on the spectral distribution of heart rate during training, was suggested for training quality assessment. A training fidelity criterion derived from a two-step classification process based on the average YETI index and its standard deviation (YETISD) was suggested. We divided 57 young, healthy volunteers into two groups, each subjected to 20 sessions of either real or sham HRV-biofeedback. Five standard HRV measures (standard deviation of the NN (SDNN), root mean square of the standard deviation of the NN (RMSSD), total power, low-frequency (LF), and high-frequency (HF) power) collected at baseline, after 10 and 20 sessions were subjected to analysis of variance. Application of a training fidelity criterion improved sample homogeneity, resulting in a substantial gain in effect sizes of the group and training interactions for all considered HRV indices. Application of methodological amendments, including proper control conditions (such as sham training) and quantitative assessment of training quality and fidelity, substantially improves the analysis of training effects. Although presented on the example of HRV-biofeedback, this approach should similarly benefit other behavioral training procedures that interact with any of the many psychophysiological mechanisms in the human body.

Spatiotemporal complexity patterns of resting-state bioelectrical activity explain fluid intelligence: Sex matters.

Neural complexity is thought to be associated with efficient information processing but the exact nature of this relation remains unclear. Here, the relationship of fluid intelligence (gf) with the resting-state EEG (rsEEG) complexity over different timescales and different electrodes was investigated. A 6-min rsEEG blocks of eyes open were analyzed. The results of 119 subjects (57 men, mean age = 22.85 ± 2.84 years) were examined using multivariate multiscale sample entropy (mMSE) that quantifies changes in information richness of rsEEG in multiple data channels at fine and coarse timescales. gf factor was extracted from six intelligence tests. Partial least square regression analysis revealed that mainly predictors of the rsEEG complexity at coarse timescales in the frontoparietal network (FPN) and the temporo-parietal complexities at fine timescales were relevant to higher gf. Sex differently affected the relationship between fluid intelligence and EEG complexity at rest. In men, gf was mainly positively related to the complexity at coarse timescales in the FPN. Furthermore, at fine and coarse timescales positive relations in the parietal region were revealed. In women, positive relations with gf were mostly observed for the overall and the coarse complexity in the FPN, whereas negative associations with gf were found for the complexity at fine timescales in the parietal and centro-temporal region. These outcomes indicate that two separate time pathways (corresponding to fine and coarse timescales) used to characterize rsEEG complexity (expressed by mMSE features) are beneficial for effective information processing.

Transition of the functional brain network related to increasing cognitive demands.

Network neuroscience provides tools that can easily be used to verify main assumptions of the global workspace theory (GWT), such as the existence of highly segregated information processing during effortless tasks performance, engagement of multiple distributed networks during effortful tasks and the critical role of long-range connections in workspace formation. A number of studies support the assumptions of GWT by showing the reorganization of the whole-brain functional network during cognitive task performance; however, the involvement of specific large scale networks in the formation of workspace is still not well-understood. The aims of our study were: (1) to examine changes in the whole-brain functional network under increased cognitive demands of working memory during an n-back task, and their relationship with behavioral outcomes; and (2) to provide a comprehensive description of local changes that may be involved in the formation of the global workspace, using hub detection and network-based statistic. Our results show that network modularity decreased with increasing cognitive demands, and this change allowed us to predict behavioral performance. The number of connector hubs increased, whereas the number of provincial hubs decreased when the task became more demanding. We also found that the default mode network (DMN) increased its connectivity to other networks while decreasing connectivity between its own regions. These results, apart from replicating previous findings, provide a valuable insight into the mechanisms of the formation of the global workspace, highlighting the role of the DMN in the processes of network integration. Hum Brain Mapp 38:3659-3674, 2017. © 2017 Wiley Periodicals, Inc.

Privacy-Preserving Domain Adaptation for Motor Imagery-Based Brain-Computer Interfaces.

OBJECTIVE: Electroencephalogram (EEG) is one of the most widely used signals in motor imagery (MI) based brain-computer interfaces (BCIs). Domain adaptation has been frequently used to improve the accuracy of EEG-based BCIs for a new user (target domain), by making use of labeled data from a previous user (source domain). However, this raises privacy concerns, as EEG contains sensitive health and mental information. It is very important to perform privacy-preserving domain adaptation, which simultaneously improves the classification accuracy for a new user and protects the privacy of a previous user. METHODS: We propose augmentation-based source-free adaptation (ASFA), which consists of two parts: 1) source model training, where a novel data augmentation approach is proposed for MI EEG signals to improve the cross-subject generalization performance of the source model; and, 2) target model training, which simultaneously considers uncertainty reduction for domain adaptation and consistency regularization for robustness. ASFA only needs access to the source model parameters, instead of the raw EEG data, thus protecting the privacy of the source domain. We further extend ASFA to a stricter privacy-preserving scenario, where the source model's parameters are also inaccessible. RESULTS: Experimental results on four MI datasets demonstrated that ASFA outperformed 15 classical and state-of-the-art MI classification approaches. SIGNIFICANCE: This is the first work on completely source-free domain adaptation for EEG-based BCIs. Our proposed ASFA achieves high classification accuracy and strong privacy protection simultaneously, important for the commercial applications of EEG-based BCIs.

Memetics and neural models of conspiracy theories.

Memetics has so far been developing in social sciences, but to fully understand memetic processes it should be linked to neuroscience models of learning, encoding, and retrieval of memories in the brain. Attractor neural networks show how incoming information is encoded in memory patterns, how it may become distorted, and how chunks of information may form patterns that are activated by many cues, forming the foundation of conspiracy theories. The rapid freezing of high neuroplasticity (RFHN) model is offered as one plausible mechanism of such processes. Illustrations of distorted memory formation based on simulations of competitive learning neural networks are presented as an example. Linking memes to attractors of neurodynamics should help to give memetics solid foundations, show why some information is easily encoded and propagated, and draw attention to the need to analyze neural mechanisms of learning and memory that lead to conspiracies.

SUPFUNSIM: Spatial Filtering Toolbox for EEG.

Brain activity pattern recognition from EEG or MEG signal analysis is one of the most important method in cognitive neuroscience. The SUPFUNSIM library is a new MATLAB toolbox which generates accurate EEG forward model and implements a collection of spatial filters for EEG source reconstruction, including the linearly constrained minimum-variance (LCMV), eigenspace LCMV, nulling (NL), and minimum-variance pseudo-unbiased reduced-rank (MV-PURE) filters in various versions. It also enables source-level directed connectivity analysis using partial directed coherence (PDC) measure. The SUPFUNSIM library is based on the well-known FIELDTRIP toolbox for EEG and MEG analysis and is written using object-oriented programming paradigm. The resulting modularity of the toolbox enables its simple extensibility. This paper gives a complete overview of the toolbox from both developer and end-user perspectives, including description of the installation process and use cases.

Early deafness leads to re-shaping of functional connectivity beyond the auditory cortex.

Early sensory deprivation, such as deafness, shapes brain development in multiple ways. Deprived auditory areas become engaged in the processing of stimuli from the remaining modalities and in high-level cognitive tasks. Yet, structural and functional changes were also observed in non-deprived brain areas, which may suggest the whole-brain network changes in deaf individuals. To explore this possibility, we compared the resting-state functional network organization of the brain in early deaf adults and hearing controls and examined global network segregation and integration. Relative to hearing controls, deaf adults exhibited decreased network segregation and an altered modular structure. In the deaf, regions of the salience network were coupled with the fronto-parietal network, while in the hearing controls, they were coupled with other large-scale networks. Deaf adults showed weaker connections between auditory and somatomotor regions, stronger coupling between the fronto-parietal network and several other large-scale networks (visual, memory, cingulo-opercular and somatomotor), and an enlargement of the default mode network. Our findings suggest that brain plasticity in deaf adults is not limited to changes in the auditory cortex but additionally alters the coupling between other large-scale networks and the development of functional brain modules. These widespread functional connectivity changes may provide a mechanism for the superior behavioral performance of the deaf in visual and attentional tasks.

Author Correction: Dynamic reconfiguration of functional brain networks during working memory training.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Dynamic reconfiguration of functional brain networks during working memory training.

The functional network of the brain continually adapts to changing environmental demands. The consequence of behavioral automation for task-related functional network architecture remains far from understood. We investigated the neural reflections of behavioral automation as participants mastered a dual n-back task. In four fMRI scans equally spanning a 6-week training period, we assessed brain network modularity, a substrate for adaptation in biological systems. We found that whole-brain modularity steadily increased during training for both conditions of the dual n-back task. In a dynamic analysis,we found that the autonomy of the default mode system and integration among task-positive systems were modulated by training. The automation of the n-back task through training resulted in non-linear changes in integration between the fronto-parietal and default mode systems, and integration with the subcortical system. Our findings suggest that the automation of a cognitively demanding task may result in more segregated network organization.

Neurolinguistic approach to natural language processing with applications to medical text analysis.

Understanding written or spoken language presumably involves spreading neural activation in the brain. This process may be approximated by spreading activation in semantic networks, providing enhanced representations that involve concepts not found directly in the text. The approximation of this process is of great practical and theoretical interest. Although activations of neural circuits involved in representation of words rapidly change in time snapshots of these activations spreading through associative networks may be captured in a vector model. Concepts of similar type activate larger clusters of neurons, priming areas in the left and right hemisphere. Analysis of recent brain imaging experiments shows the importance of the right hemisphere non-verbal clusterization. Medical ontologies enable development of a large-scale practical algorithm to re-create pathways of spreading neural activations. First concepts of specific semantic type are identified in the text, and then all related concepts of the same type are added to the text, providing expanded representations. To avoid rapid growth of the extended feature space after each step only the most useful features that increase document clusterization are retained. Short hospital discharge summaries are used to illustrate how this process works on a real, very noisy data. Expanded texts show significantly improved clustering and may be classified with much higher accuracy. Although better approximations to the spreading of neural activations may be devised a practical approach presented in this paper helps to discover pathways used by the brain to process specific concepts, and may be used in large-scale applications.

Computational models of dementia and neurological problems.

A critical goal of neuroscience is to fully understand neural processes and their relations to mental processes, and cognitive, affective, and behavioral disorders. Computational modeling, although still in its infancy, continues to play a central role in this endeavor. Presented here is a review of different aspects of computational modeling that help to explain many features of neuropsychological syndromes and psychiatric disease. Recent advances in computational modeling of epilepsy, cortical reorganization after lesions, Parkinson's and Alzheimer diseases are also reviewed. Additionally, this chapter will also identify some trends in the computational modeling of brain functions.

Neural network modelling of the influence of channelopathies on reflex visual attention.

This paper introduces a model of Emergent Visual Attention in presence of calcium channelopathy (EVAC). By modelling channelopathy, EVAC constitutes an effort towards identifying the possible causes of autism. The network structure embodies the dual pathways model of cortical processing of visual input, with reflex attention as an emergent property of neural interactions. EVAC extends existing work by introducing attention shift in a larger-scale network and applying a phenomenological model of channelopathy. In presence of a distractor, the channelopathic network's rate of failure to shift attention is lower than the control network's, but overall, the control network exhibits a lower classification error rate. The simulation results also show differences in task-relative reaction times between control and channelopathic networks. The attention shift timings inferred from the model are consistent with studies of attention shift in autistic children.

Uncertainty of data, fuzzy membership functions, and multilayer perceptrons.

Probability that a crisp logical rule applied to imprecise input data is true may be computed using fuzzy membership function (MF). All reasonable assumptions about input uncertainty distributions lead to MFs of sigmoidal shape. Convolution of several inputs with uniform uncertainty leads to bell-shaped Gaussian-like uncertainty functions. Relations between input uncertainties and fuzzy rules are systematically explored and several new types of MFs discovered. Multilayered perceptron (MLP) networks are shown to be a particular implementation of hierarchical sets of fuzzy threshold logic rules based on sigmoidal MFs. They are equivalent to crisp logical networks applied to input data with uncertainty. Leaving fuzziness on the input side makes the networks or the rule systems easier to understand. Practical applications of these ideas are presented for analysis of questionnaire data and gene expression data.

LVQ algorithm with instance weighting for generation of prototype-based rules.

Crisp and fuzzy-logic rules are used for comprehensible representation of data, but rules based on similarity to prototypes are equally useful and much less known. Similarity-based methods belong to the most accurate data mining approaches. A large group of such methods is based on instance selection and optimization, with the Learning Vector Quantization (LVQ) algorithm being a prominent example. Accuracy of LVQ depends highly on proper initialization of prototypes and the optimization mechanism. This paper introduces prototype initialization based on context dependent clustering and modification of the LVQ cost function that utilizes additional information about class-dependent distribution of training vectors. This approach is illustrated on several benchmark datasets, finding simple and accurate models of data in the form of prototype-based rules.

Visualization for understanding of neurodynamical systems.

Complex neurodynamical systems are quite difficult to analyze and understand. New type of plots are introduced to help in visualization of high-dimensional trajectories and show global picture of the phase space, including relations between basins of attractors. Color recurrence plots (RPs) display distances from each point on the trajectory to all other points in a two-dimensional matrix. Fuzzy Symbolic Dynamics (FSD) plots enhance this information mapping the whole trajectory to two or three dimensions. Each coordinate is defined by the value of a fuzzy localized membership function, optimized to visualize interesting features of the dynamics, showing to which degree a point on the trajectory belongs to some neighborhood. The variance of the trajectory within the attraction basin plotted against the variance of the synaptic noise provides information about sizes and shapes of these basins. Plots that use color to show the distance between each trajectory point and a larger number of selected reference points (for example centers of attractor basins) are also introduced. Activity of 140 neurons in the semantic layer of dyslexia model implemented in the Emergent neural simulator is analyzed in details showing different aspects of neurodynamics that may be understood in this way. Influence of connectivity and various neural properties on network dynamics is illustrated using visualization techniques. A number of interesting conclusions about cognitive neurodynamics of lexical concept activations are drawn. Changing neural accommodation parameters has very strong influence on the dwell time of the trajectories. This may be linked to attention deficits disorders observed in autism in case of strong enslavement, and to ADHD-like behavior in case of weak enslavement.