Classification of pleasantness of wind by electroencephalography.

Thermal comfort of humans depends on the surrounding environment and affects their productivity. Several environmental factors, such as air temperature, relative humidity, wind or airflow, and radiation, have considerable influence on the thermal comfort or pleasantness; hence, these are generally controlled by electrical devices. Lately, the development of objective measurement methods for thermal comfort or pleasantness using physiological signals is receiving attention to realize a personalized comfortable environment through the automatic control of electrical devices. In this study, we focused on electroencephalography (EEG) and investigated whether EEG signals contain information related to the pleasantness of ambient airflow reproducing natural wind fluctuations using machine learning methods. In a hot and humid artificial climate chamber, we measured EEG signals while the participants were exposed to airflow at four different velocities. Based on the reported pleasantness levels, we performed within-participant classification from the source activity of the EEG and obtained a classification accuracy higher than the chance level using both linear and nonlinear support vector machine classifiers as well as an artificial neural network. The results of this study showed that EEG is useful in identifying people's transient pleasantness when exposed to wind.

Partial maximum correntropy regression for robust electrocorticography decoding.

The Partial Least Square Regression (PLSR) method has shown admirable competence for predicting continuous variables from inter-correlated electrocorticography signals in the brain-computer interface. However, PLSR is essentially formulated with the least square criterion, thus, being considerably prone to the performance deterioration caused by the brain recording noises. To address this problem, this study aims to propose a new robust variant for PLSR. To this end, the maximum correntropy criterion (MCC) is utilized to propose a new robust implementation of PLSR, called Partial Maximum Correntropy Regression (PMCR). The half-quadratic optimization is utilized to calculate the robust projectors for the dimensionality reduction, and the regression coefficients are optimized by a fixed-point optimization method. The proposed PMCR is evaluated with a synthetic example and a public electrocorticography dataset under three performance indicators. For the synthetic example, PMCR realized better prediction results compared with the other existing methods. PMCR could also abstract valid information with a limited number of decomposition factors in a noisy regression scenario. For the electrocorticography dataset, PMCR achieved superior decoding performance in most cases, and also realized the minimal neurophysiological pattern deterioration with the interference of the noises. The experimental results demonstrate that, the proposed PMCR could outperform the existing methods in a noisy, inter-correlated, and high-dimensional decoding task. PMCR could alleviate the performance degradation caused by the adverse noises and ameliorate the electrocorticography decoding robustness for the brain-computer interface.

Differential processing of intrinsic vs. extrinsic coordinates in wrist movement: connectivity and chronometry perspectives.

This study explores brain-network differences between the intrinsic and extrinsic motor coordinate frames. A connectivity model showing the coordinate frames difference was obtained using brain fMRI data of right wrist isometric flexions and extensions movements, performed in two forearm postures. The connectivity model was calculated by machine-learning-based neural representation and effective functional connectivity using psychophysiological interaction and dynamic causal modeling analyses. The model indicated the network difference wherein the inferior parietal lobule receives extrinsic information from the rostral lingual gyrus through the superior parietal lobule and transmits intrinsic information to the Handknob, whereas extrinsic information is transmitted to the Handknob directly from the rostral lingual gyrus. A behavioral experiment provided further evidence on the difference between motor coordinate frames showing onset timing delay of muscle activity of intrinsic coordinate-directed wrist movement compared to extrinsic one. These results suggest that, if the movement is externally directed, intrinsic coordinate system information is bypassed to reach the primary motor area.

Correntropy-Based Logistic Regression With Automatic Relevance Determination for Robust Sparse Brain Activity Decoding.

OBJECTIVE: Recent studies have used sparse classifications to predict categorical variables from high-dimensional brain activity signals to expose human's mental states and intentions, selecting the relevant features automatically in the model training process. However, existing sparse classification models will likely be prone to the performance degradation which is caused by the noise inherent in the brain recordings. To address this issue, we aim to propose a new robust and sparse classification algorithm in this study. METHODS: To this end, we introduce the correntropy learning framework into the automatic relevance determination based sparse classification model, proposing a new correntropy-based robust sparse logistic regression algorithm. To demonstrate the superior brain activity decoding performance of the proposed algorithm, we evaluate it on a synthetic dataset, an electroencephalogram (EEG) dataset, and a functional magnetic resonance imaging (fMRI) dataset. RESULTS: The extensive experimental results confirm that not only the proposed method can achieve higher classification accuracy in a noisy and high-dimensional classification task, but also it would select those more informative features for the decoding tasks. CONCLUSION: Integrating the correntropy learning approach with the automatic relevance determination technique will significantly improve the robustness with respect to the noise, leading to more adequate robust sparse brain decoding algorithm. SIGNIFICANCE: It provides a more powerful approach in the real-world brain activity decoding and the brain-computer interfaces.

Classification of Parkinson's disease from smartphone recording data using time-frequency analysis and convolutional neural network.

BACKGROUND: Parkinson's disease (PD) is a long-term neurodegenerative disease of the central nervous system. The current diagnosis is dependent on clinical observation and the abilities and experience of a trained specialist. One of the symptoms that affects most patients is voice impairment. OBJECTIVE: Voice samples are non-invasive data that can be collected remotely for diagnosis and disease progression monitoring. In this study, we analyzed voice recording data from a smartphone as a possible medical self-diagnosis tool by using only one-second voice recording. The data from one of the largest mobile PD studies, the mPower study, was used. METHODS: A total of 29,798 ten-second voice recordings on smartphone from 4,051 participants were used for the analysis. The voice recordings were from sustained phonation by participants saying /aa/ for ten seconds into an iPhone microphone. A dataset comprising 385,143 short one-second audio samples was generated from the original ten-second voice recordings. The samples were converted to a spectrogram using a short-time Fourier transform. CNN models were then applied to classify the samples. RESULTS: Classification accuracies of the proposed method with LeNet-5, ResNet-50, and VGGNet-16 are 97.7 ± 0.1%, 98.6 ± 0.2%, and 99.3 ± 0.1%, respectively. CONCLUSIONS: We achieve a respectable classification performance using a generalized approach on a dataset with a large number of samples. The result emphasizes that an analysis based on one-second clip recorded on a smartphone could be a promising non-invasive and remotely available PD biomarker.

Temporal Electroencephalography Traits Dissociating Tactile Information and Cross-Modal Congruence Effects.

To explore whether temporal electroencephalography (EEG) traits can dissociate the physical properties of touching objects and the congruence effects of cross-modal stimuli, we applied a machine learning approach to two major temporal domain EEG traits, event-related potential (ERP) and somatosensory evoked potential (SEP), for each anatomical brain region. During a task in which participants had to identify one of two material surfaces as a tactile stimulus, a photo image that matched ('congruent') or mismatched ('incongruent') the material they were touching was given as a visual stimulus. Electrical stimulation was applied to the median nerve of the right wrist to evoke SEP while the participants touched the material. The classification accuracies using ERP extracted in reference to the tactile/visual stimulus onsets were significantly higher than chance levels in several regions in both congruent and incongruent conditions, whereas SEP extracted in reference to the electrical stimulus onsets resulted in no significant classification accuracies. Further analysis based on current source signals estimated using EEG revealed brain regions showing significant accuracy across conditions, suggesting that tactile-based object recognition information is encoded in the temporal domain EEG trait and broader brain regions, including the premotor, parietal, and somatosensory areas.

Restricted Minimum Error Entropy Criterion for Robust Classification.

The minimum error entropy (MEE) criterion is a powerful approach for non-Gaussian signal processing and robust machine learning. However, the instantiation of MEE on robust classification is a rather vacancy in the literature. The original MEE purely focuses on minimizing Renyi's quadratic entropy of the prediction errors, which could exhibit inferior capability in noisy classification tasks. To this end, we analyze the optimal error distribution with adverse outliers and introduce a specific codebook for restriction, which optimizes the error distribution toward the optimal case. Half-quadratic-based optimization and convergence analysis of the proposed learning criterion, called restricted MEE (RMEE), are provided. The experimental results considering logistic regression and extreme learning machine on synthetic data and UCI datasets, respectively, are presented to demonstrate the superior robustness of RMEE. Furthermore, we evaluate RMEE on a noisy electroencephalogram dataset, so as to strengthen its practical impact.

An fMRI-study of leading and following using rhythmic tapping.

Leading and following is about synchronizing and joining actions in accordance with the differences that the leader and follower roles provide. The neural reactivity representing these roles was measured in an explorative fMRI-study, where two persons lead and followed each other in finger tapping using simple, individual, pre-learnt rhythms. All participants acted both as leader and follower. Neural reactivity for both lead and follow related to social awareness and adaptation distributed over the lateral STG, STS and TPJ. Reactivity for follow contrasted with lead mostly reflected sensorimotor and rhythmic processing in cerebellum IV, V, somatosensory cortex and SMA. During leading, as opposed to following, neural reactivity was observed in the insula and bilaterally in the superior temporal gyrus, pointing toward empathy, sharing of feelings, temporal coding and social engagement. Areas for continuous adaptation, in the posterior cerebellum and Rolandic operculum, were activated during both leading and following. This study indicated mutual adaptation of leader and follower during tapping and that the roles gave rise to largely similar neuronal reactivity. The differences between the roles indicated that leading was more socially focused and following had more motoric- and temporally related neural reactivity.

Electroencephalography Reflects User Satisfaction in Controlling Robot Hand through Electromyographic Signals.

This study addresses time intervals during robot control that dominate user satisfaction and factors of robot movement that induce satisfaction. We designed a robot control system using electromyography signals. In each trial, participants were exposed to different experiences as the cutoff frequencies of a low-pass filter were changed. The participants attempted to grab a bottle by controlling a robot. They were asked to evaluate four indicators (stability, imitation, response time, and movement speed) and indicate their satisfaction at the end of each trial by completing a questionnaire. The electroencephalography signals of the participants were recorded while they controlled the robot and responded to the questionnaire. Two independent component clusters in the precuneus and postcentral gyrus were the most sensitive to subjective evaluations. For the moment that dominated satisfaction, we observed that brain activity exhibited significant differences in satisfaction not immediately after feeding an input but during the later stage. The other indicators exhibited independently significant patterns in event-related spectral perturbations. Comparing these indicators in a low-frequency band related to the satisfaction with imitation and movement speed, which had significant differences, revealed that imitation covered significant intervals in satisfaction. This implies that imitation was the most important contributing factor among the four indicators. Our results reveal that regardless of subjective satisfaction, objective performance evaluation might more fully reflect user satisfaction.

Brain Activity Reflects Subjective Response to Delayed Input When Using an Electromyography-Controlled Robot.

In various experimental settings, electromyography (EMG) signals have been used to control robots. EMG-based robot control requires intrinsic parameters for control, which makes it difficult for users to understand the input protocol. When a proper input is not provided, the response time of the system varies; as such, the user's subjective delay should be investigated regardless of the actual delay. In this study, we investigated the influence of the subjective perception of delay on brain activation. Brain recordings were taken while subjects used EMG signals to control a robot hand, which requires a basic processing delay. We used muscle synergy for the grip command of the robot hand. After controlling the robot by grasping their hand, one of four additional delay durations (0 ms, 50 ms, 125 ms, and 250 ms) was applied in every trial, and subjects were instructed to answer whether the delay was natural, additional, or whether they were not sure. We compared brain activity based on responses ("sure" and "not sure"). Our results revealed a significant power difference in the theta band of the parietal lobe, and this time range included the interval in which the subjects could not feel the delay. Our study provides important insights that should be considered when constructing an adaptive system and evaluating its usability.

Galvanic Vestibular Stimulation-Based Prediction Error Decoding and Channel Optimization.

A significant problem in brain-computer interface (BCI) research is decoding - obtaining required information from very weak noisy electroencephalograph signals and extracting considerable information from limited data. Traditional intention decoding methods, which obtain information from induced or spontaneous brain activity, have shortcomings in terms of performance, computational expense and usage burden. Here, a new methodology called prediction error decoding was used for motor imagery (MI) detection and compared with direct intention decoding. Galvanic vestibular stimulation (GVS) was used to induce subliminal sensory feedback between the forehead and mastoids without any burden. Prediction errors were generated between the GVS-induced sensory feedback and the MI direction. The corresponding prediction error decoding of the front/back MI task was validated. A test decoding accuracy of 77.83-78.86% (median) was achieved during GVS for every 100[Formula: see text]ms interval. A nonzero weight parameter-based channel screening (WPS) method was proposed to select channels individually and commonly during GVS. When the WPS common-selected mode was compared with the WPS individual-selected mode and a classical channel selection method based on correlation coefficients (CCS), a satisfactory decoding performance of the selected channels was observed. The results indicated the positive impact of measuring common specific channels of the BCI.

Multi-Joint Angles Estimation of Forearm Motion Using a Regression Model.

To improve the life quality of forearm amputees, prosthetic hands with high accuracy, and robustness are necessary. The application of surface electromyography (sEMG) signals to control a prosthetic hand is challenging. In this study, we proposed a time-domain CNN model for the regression prediction of joint angles in three degrees of freedom (3-DOFs, include two wrist joint motion and one finger joint motion), and five-fold cross validation was used to evaluate the correlation coefficient (CC). The CC value results of wrist flexion/extension motion obtained from 10 participants was 0.87-0.92, pronation/supination motion was 0.72-0.95, and hand grip/open motion was 0.75-0.94. We backtracked the fully connected layer weights to create a geometry plot for analyzing the motion pattern to investigate the learning of the proposed model. In order to discuss the daily updateability of the model by transfer learning, we performed a second experiment on five of the participants in another day and conducted transfer learning based on smaller amount of dataset. The CC results improved (wrist flexion/extension was 0.90-0.97, pronation/supination was 0.84-0.96, hand grip/open was 0.85-0.92), suggesting the effectiveness of the transfer learning by incorporating the small amounts of sEMG data acquired in different days. We compared our CNN-based model with four conventional regression models, the result illustrates that proposed model significantly outperforms the four conventional models with and without transfer learning. The offline result suggests the reliability of the proposed model in real-time control in different days, it can be applied for real-time prosthetic control in the future.

Binary Semantic Classification Using Cortical Activation with Pavlovian-Conditioned Vestibular Responses in Healthy and Locked-In Individuals.

To develop a more reliable brain-computer interface (BCI) for patients in the completely locked-in state (CLIS), here we propose a Pavlovian conditioning paradigm using galvanic vestibular stimulation (GVS), which can induce a strong sensation of equilibrium distortion in individuals. We hypothesized that associating two different sensations caused by two-directional GVS with the thoughts of "yes" and "no" by individuals would enable us to emphasize the differences in brain activity associated with the thoughts of yes and no and hence help us better distinguish the two from electroencephalography (EEG). We tested this hypothesis with 11 healthy and 1 CLIS participant. Our results showed that, first, conditioning of GVS with the thoughts of yes and no is possible. And second, the classification of whether an individual is thinking "yes" or "no" is significantly improved after the conditioning, even in the absence of subsequent GVS stimulations. We observed average classification accuracy of 73.0% over 11 healthy individuals and 85.3% with the CLIS patient. These results suggest the establishment of GVS-based Pavlovian conditioning and its usability as a noninvasive BCI.

Exploring EEG Characteristics to Identify Emotional Reactions under Videogame Scenarios.

In this article we present the study of electroencephalography (EEG) traits for emotion recognition process using a videogame as a stimuli tool, and considering two different kind of information related to emotions: arousal-valence self-assesses answers from participants, and game events that represented positive and negative emotional experiences under the videogame context. We performed a statistical analysis using Spearman's correlation between the EEG traits and the emotional information. We found that EEG traits had strong correlation with arousal and valence scores; also, common EEG traits with strong correlations, belonged to the theta band of the central channels. Then, we implemented a regression algorithm with feature selection to predict arousal and valence scores using EEG traits. We achieved better result for arousal regression, than for valence regression. EEG traits selected for arousal and valence regression belonged to time domain (standard deviation, complexity, mobility, kurtosis, skewness), and frequency domain (power spectral density-PDS, and differential entropy-DE from theta, alpha, beta, gamma, and all EEG frequency spectrum). Addressing game events, we found that EEG traits related with the theta, alpha and beta band had strong correlations. In addition, distinctive event-related potentials where identified in the presence of both types of game events. Finally, we implemented a classification algorithm to discriminate between positive and negative events using EEG traits to identify emotional information. We obtained good classification performance using only two traits related with frequency domain on the theta band and on the full EEG spectrum.

Constructing Brain Connectivity Model Using Causal Network Reconstruction Approach.

Studying brain function is a challenging task. In the past, we could only study brain anatomical structures post-mortem, or infer brain functions from clinical data of patients with a brain injury. Nowadays technology, such as functional magnetic resonance imaging (fMRI), enable non-invasive brain activity observation. Several approaches have been proposed to interpret brain activity data. The brain connectivity model is a graphical tool that represents the interaction between brain regions, during certain states. It depicts how a brain region cause changes to other parts of the brain, which can be implied as information flow. This model can be used to help interpret how the brain works. There are several mathematical frameworks that can be used to infer the connectivity model from brain activity signals. Granger causality is one such approach and is one of the first that has been applied to brain activity data. However, due to the concept of the framework, such as the use of pairwise correlation, combined with the limitation of brain activity data such as low temporal resolution in case of fMRI signal, makes the interpretation of the connectivity difficult. We therefore propose the application of the Tigramite causal discovery framework on fMRI data. The Tigramite framework uses measures such as causal effect to analyze causal relations in the system. This enables the framework to identify both direct and indirect pathways or connectivities. In this paper, we applied the framework to the Human Connectome Project motor task-fMRI dataset. We then present the results and discuss how the framework improves interpretability of the connectivity model. We hope that this framework will help us understand more complex brain functions such as memory, consciousness, or the resting-state of the brain, in the future.

Computational reproductions of external force field adaption without assuming desired trajectories.

Optimal feedback control is an established framework that is used to characterize human movement. However, it is not fully understood how the brain computes optimal gains through interactions with the environment. In the past study, we proposed a model of motor learning that identifies a set of feedback and feedforward controllers and a state predictor of the arm musculoskeletal system to control free reaching movements. In this study, we applied the model to force field adaptation tasks where normal reaching movements are disturbed by an external force imposed on the hand. Without a priori knowledge about the arm and environment, the model was able to adapt to the force field by generating counteracting forces to overcome it in a manner similar to what is reported in the behavioral literature. The kinematics of the movements generated by our model share characteristic features of human movements observed before and after force field adaptation. In addition, we demonstrate that the structure and learning algorithm introduced in our model induced a shift in the end-point's equilibrium position and a static force modulation, accompanied by a fast and a slow learning process. Importantly, our model does not require desired trajectories, yields movements without specifying movement duration, and predicts force generation patterns by exploring the environment. Our model demonstrates a possible mechanism through which the central nervous system may control and adapt a point-to-point reaching movement without specifying a desired trajectory by continuously updating the body's musculoskeletal model.

Electroencephalography of completely locked-in state patients with amyotrophic lateral sclerosis.

Patients in completely locked-in state (CLIS) due to amyotrophic lateral sclerosis (ALS) lose the control of each and every muscle of their body rendering them motionless and without any means of communication. Though some studies have attempted to develop brain-computer interface (BCI)-based communication methods with CLIS patients, little information is available of the neuroelectric brain activity of CLIS patients. However, because of the difficulties with and often loss of communication, the neuroelectric signature may provide some indications of the state of consciousness in these patients. We recorded electroencephalography (EEG) signals from 10 CLIS patients during resting state and compared their power spectral densities with those of healthy participants in fronto-central, central, and centro-parietal channels. The results showed significant power reduction in the high alpha, beta, and gamma bands in CLIS patients, indicating the dominance of slower EEG frequencies in their oscillatory activity. This is the first study showing group-level EEG change of CLIS patients, though the reason for the observed EEG change cannot be concluded without any reliable communication methods with this population.

Generation of diverse insect-like gait patterns using networks of coupled Rössler systems.

The generation of walking patterns is central to bio-inspired robotics and has been attained using methods encompassing diverse numerical as well as analog implementations. Here, we demonstrate the possibility of synthesizing viable gaits using a paradigmatic low-dimensional non-linear entity, namely, the Rössler system, as a dynamical unit. Through a minimalistic network wherein each instance is univocally associated with one leg, it is possible to readily reproduce the canonical gaits as well as generate new ones via changing the coupling scheme and the associated delays. Varying levels of irregularity can be introduced by rendering individual systems or the entire network chaotic. Moreover, through tailored mapping of the state variables to physical angles, adequate leg trajectories can be accessed directly from the coupled systems. The functionality of the resulting generator was confirmed in laboratory experiments by means of an instrumented six-legged ant-like robot. Owing to their simple form, the 18 coupled equations could be rapidly integrated on a bare-metal microcontroller, leading to the demonstration of real-time robot control navigating an arena using a brain-machine interface.

The Effect of ICA and Non-negative Matrix Factorization Analysis for EMG Signals Recorded From Multi-Channel EMG Sensors.

Surface electromyography (EMG) measurements are affected by various noises such as power source and movement artifacts and adjacent muscle activities. Hardware solutions have been found that use multi-channel EMG signal to attenuate noise signals related to sensor positions. However, studies addressing the overcoming of crosstalk from EMG and the division of overlaid superficial and deep muscles are scarce. In this study, two signal decompositions-independent component analysis and non-negative matrix factorization-were used to create a low-dimensional input signal that divides noise, surface muscles, and deep muscles and utilizes them for movement classification based on direction. In the case of index finger movement, it was confirmed that the proposed decomposition method improved the classification performance with the least input dimensions. These results suggest a new method to analyze more dexterous movements of the hand by separating superficial and deep muscles in the future using multi-channel EMG signals.

Age-Related Decline of Sensorimotor Integration Influences Resting-State Functional Brain Connectivity.

Age-related decline in sensorimotor integration involves both peripheral and central components related to proprioception and kinesthesia. To explore the role of cortical motor networks, we investigated the association between resting-state functional connectivity and a gap-detection angle measured during an arm-reaching task. Four region pairs, namely the left primary sensory area with the left primary motor area (S1left-M1left), the left supplementary motor area with M1left (SMAleft-M1left), the left pre-supplementary motor area with SMAleft (preSMAleft-SMAleft), and the right pre-supplementary motor area with the right premotor area (preSMAright-PMdright), showed significant age-by-gap detection ability interactions in connectivity in the form of opposite-sign correlations with gap detection ability between younger and older participants. Morphometry and tractography analyses did not reveal corresponding structural effects. These results suggest that the impact of aging on sensorimotor integration at the cortical level may be tracked by resting-state brain activity and is primarily functional, rather than structural. From the observation of opposite-sign correlations, we hypothesize that in aging, a "low-level" motor system may hyper-engage unsuccessfully, its dysfunction possibly being compensated by a "high-level" motor system, wherein stronger connectivity predicts higher gap-detection performance. This hypothesis should be tested in future neuroimaging and clinical studies.