Alzheimer's disease (AD) could be described into following four stages: healthy control (HC), early mild cognitive impairment (EMCI), late MCI (LMCI) and AD dementia. The discriminations between different stages of AD are considerably important issues for future pre-dementia treatment. However, it is still challenging to identify LMCI from EMCI because of the subtle changes in imaging which are not noticeable. In addition, there were relatively few studies to make inferences about the brain dynamic changes in the cognitive progression from EMCI to LMCI to AD. Inspired by the above problems, we proposed an advanced approach of evolutionary weighted random support vector machine cluster (EWRSVMC). Where the predictions of numerous weighted SVM classifiers are aggregated for improving the generalization performance. We validated our method in multiple binary classifications using Alzheimer's Disease Neuroimaging Initiative dataset. As a result, the encouraging accuracy of 90% for EMCI/LMCI and 88.89% for LMCI/AD were achieved respectively, demonstrating the excellent discriminating ability. Furthermore, disease-related brain regions underlying the AD progression could be found out on the basis of the amount of discriminative information. The findings of this study provide considerable insight into the neurophysiological mechanisms in AD development.

Depression is a common mental disorder that seriously affects patients' social function and daily life. Its accurate diagnosis remains a big challenge in depression treatment. In this study, we used electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) and measured the whole brain EEG signals and forehead hemodynamic signals from 25 depression patients and 30 healthy subjects during the resting state. On one hand, we explored the EEG brain functional network properties, and found that the clustering coefficient and local efficiency of the delta and theta bands in patients were significantly higher than those in normal subjects. On the other hand, we extracted brain network properties, asymmetry, and brain oxygen entropy as alternative features, used a data-driven automated method to select features, and established a support vector machine model for automatic depression classification. The results showed the classification accuracy was 81.8% when using EEG features alone and increased to 92.7% when using hybrid EEG and fNIRS features. The brain network local efficiency in the delta band, hemispheric asymmetry in the theta band and brain oxygen sample entropy features differed significantly between the two groups (p < 0.05) and showed high depression distinguishing ability indicating that they may be effective biological markers for identifying depression. EEG, fNIRS and machine learning constitute an effective method for classifying depression at the individual level.

To compare the efficacies of univariate and radiomics analyses of amide proton transfer weighted (APTW) imaging in predicting isocitrate dehydrogenase 1 (IDH1) mutation of grade II/III gliomas.

Laboratory demonstrations of brain-computer interface (BCI) systems show promise for reducing disability associated with paralysis by directly linking neural activity to the control of assistive devices. Surveys of potential users have revealed several key BCI performance criteria for clinical translation of such a system. Of these criteria, high accuracy, short response latencies, and multi-functionality are three key characteristics directly impacted by the neural decoding component of the BCI system, the algorithm that translates neural activity into control signals. Building a decoder that simultaneously addresses these three criteria is complicated because optimizing for one criterion may lead to undesirable changes in the other criteria. Unfortunately, there has been little work to date to quantify how decoder design simultaneously affects these performance characteristics. Here, we systematically explore the trade-off between accuracy, response latency, and multi-functionality for discrete movement classification using two different decoding strategies-a support vector machine (SVM) classifier which represents the current state-of-the-art for discrete movement classification in laboratory demonstrations and a proposed deep neural network (DNN) framework. We utilized historical intracortical recordings from a human tetraplegic study participant, who imagined performing several different hand and finger movements. For both decoders, we found that response time increases (i.e., slower reaction) and accuracy decreases as the number of functions increases. However, we also found that both the increase of response times and the decline in accuracy with additional functions is less for the DNN than the SVM. We also show that data preprocessing steps can affect the performance characteristics of the two decoders in drastically different ways. Finally, we evaluated the performance of our tetraplegic participant using the DNN decoder in real-time to control functional electrical stimulation (FES) of his paralyzed forearm. We compared his performance to that of able-bodied participants performing the same task, establishing a quantitative target for ideal BCI-FES performance on this task. Cumulatively, these results help quantify BCI decoder performance characteristics relevant to potential users and the complex interactions between them.

Mouse behavior is a primary outcome in evaluations of therapeutic efficacy. Exhaustive, continuous, multiparametric behavioral phenotyping is a valuable tool for understanding the pathophysiological status of mouse brain diseases. Automated home cage behavior analysis produces highly granulated data both in terms of number of features and sampling frequency. Previously, we demonstrated several ways to reduce feature dimensionality. In this study, we propose novel approaches for analyzing 33-Hz data generated by CleverSys software. We hypothesized that behavioral patterns within short time windows are reflective of physiological state, and that computer modeling of mouse behavioral routines can serve as a predictive tool in classification tasks. To remove bias due to researcher decisions, our data flow is indifferent to the quality, value, and importance of any given feature in isolation. To classify day and night behavior, as an example application, we developed a data preprocessing flow and utilized logistic regression (LG), support vector machines (SVM), random forest (RF), and one-dimensional convolutional neural networks paired with long short-term memory deep neural networks (1DConvBiLSTM). We determined that a 5-min video clip is sufficient to classify mouse behavior with high accuracy. LG, SVM, and RF performed similarly, predicting mouse behavior with 85% accuracy, and combining the three algorithms in an ensemble procedure increased accuracy to 90%. The best performance was achieved by combining the 1DConv and BiLSTM algorithms yielding 96% accuracy. Our findings demonstrate that computer modeling of the home-cage ethome can clearly define mouse physiological state. Furthermore, we showed that continuous behavioral data can be analyzed using approaches similar to natural language processing. These data provide proof of concept for future research in diagnostics of complex pathophysiological changes that are accompanied by changes in behavioral profile.

Vicarious trial and error behaviors (VTEs) indicate periods of indecision during decision-making, and have been proposed as a behavioral marker of deliberation. In order to understand the neural underpinnings of these putative bridges between behavior and neural dynamics, researchers need the ability to readily distinguish VTEs from non-VTEs. Here we utilize a small set of trajectory-based features and standard machine learning classifiers to identify VTEs from non-VTEs for rats performing a spatial delayed alternation task (SDA) on an elevated plus maze. We also show that previously reported features of the hippocampal field potential oscillation can be used in the same types of classifiers to separate VTEs from non-VTEs with above chance performance. However, we caution that the modest classifier success using hippocampal population dynamics does not identify many trials where VTEs occur, and show that combining oscillation-based features with trajectory-based features does not improve classifier performance compared to trajectory-based features alone. Overall, we propose a standard set of features useful for trajectory-based VTE classification in binary decision tasks, and support previous suggestions that VTEs are supported by a network including, but likely extending beyond, the hippocampus.

The fruit fly compound eye is a premier experimental system for modeling human neurodegenerative diseases. The disruption of the retinal geometry has been historically assessed using time-consuming and poorly reliable techniques such as histology or pseudopupil manual counting. Recent semiautomated quantification approaches rely either on manual region-of-interest delimitation or engineered features to estimate the extent of degeneration. This work presents a fully automated classification pipeline of bright-field images based on orientated gradient descriptors and machine learning techniques. An initial region-of-interest extraction is performed, applying morphological kernels and Euclidean distance-to-centroid thresholding. Image classification algorithms are trained on these regions (support vector machine, decision trees, random forest, and convolutional neural network), and their performance is evaluated on independent, unseen datasets. The combinations of oriented gradient + gaussian kernel Support Vector Machine [0.97 accuracy and 0.98 area under the curve (AUC)] and fine-tuned pre-trained convolutional neural network (0.98 accuracy and 0.99 AUC) yielded the best results overall. The proposed method provides a robust quantification framework that can be generalized to address the loss of regularity in biological patterns similar to the Drosophila eye surface and speeds up the processing of large sample batches.

Hepatic encephalopathy (HE) is a neurocognitive dysfunction based on metabolic disorders caused by severe liver disease, which has a high one-year mortality. Mild hepatic encephalopathy (MHE) has a high risk of converting to overt HE, and thus the accurate identification of MHE from cirrhosis with no HE (noHE) is of great significance in reducing mortality. Previously, most studies focused on studying abnormality in the static brain networks of MHE to find biomarkers. In this study, we aimed to use multi-layer modular algorithm to study abnormality in dynamic graph properties of brain network in MHE patients and construct a machine learning model to identify individual MHE from noHE. Here, a time length of 500-second resting-state functional MRI data were collected from 41 healthy subjects, 32 noHE patients and 30 MHE patients. Multi-layer modular algorithm was performed on dynamic brain functional connectivity graph. The connection-stability score was used to characterize the loyalty in each brain network module. Nodal flexibility, cohesion and disjointness were calculated to describe how the node changes the network affiliation across time. Results show that significant differences between MHE and noHE were found merely in nodal disjointness in higher cognitive network modules (ventral attention, fronto-parietal, default mode networks) and these abnormalities were associated with the decline in patients' attention and visual memory function evaluated by Digit Symbol Test. Finally, feature extraction from node disjointness with the support vector machine classifier showed an accuracy of 88.71% in discrimination of MHE from noHE, which was verified by different window sizes, modular partition parameters and machine learning parameters. All these results show that abnormal nodal disjointness in higher cognitive networks during brain network evolution can be seemed as a biomarker for identification of MHE, which help us understand the disease mechanism of MHE at a fine scale.

Traumatic brain injury (TBI) can cause progressive neuropathology that leads to chronic impairments, creating a need for biomarkers to detect and monitor this condition to improve outcomes. This study aimed to analyze the ability of data-driven analysis of diffusion tensor imaging (DTI) and neurite orientation dispersion imaging (NODDI) to develop biomarkers to infer symptom severity and determine whether they outperform conventional T1-weighted imaging.

An important goal in neuroscience is to elucidate the causal relationships between the brain's different regions. This can help reveal the brain's functional circuitry and diagnose lesions. Currently there are a lack of approaches to functional connectome estimation that leverage the state-of-the-art in deep learning architectures and training methodologies. Therefore, we propose a new framework based on a vector auto-regressive deep neural network (VARDNN) architecture. Our approach consists of a set of nodes, each with a deep neural network structure. These nodes can be mapped to any spatial sub-division based on the data to be analyzed, such as anatomical brain regions from which representative neural signals can be obtained. VARDNN learns to reproduce experimental time series data using modern deep learning training techniques. Based on this, we developed two novel directed functional connectivity (dFC) measures, namely VARDNN-DI and VARDNN-GC. We evaluated our measures against a number of existing functional connectome estimation measures, such as partial correlation and multivariate Granger causality combined with large dimensionality counter-measure techniques. Our measures outperformed them across various types of ground truth data, especially as the number of nodes increased. We applied VARDNN to fMRI data to compare the dFC between 41 healthy control vs. 32 Alzheimer's disease subjects. Our VARDNN-DI measure detected lesioned regions consistent with previous studies and separated the two groups well in a subject-wise evaluation framework. Summarily, the VARDNN framework has powerful capabilities for whole brain dFC estimation. We have implemented VARDNN as an open-source toolbox that can be freely downloaded for researchers who wish to carry out functional connectome analysis on their own data.

Automatic algorithms for disease diagnosis are being thoroughly researched for use in clinical settings. They usually rely on pre-identified biomarkers to highlight the existence of certain problems. However, finding such biomarkers for neurodevelopmental disorders such as Autism Spectrum Disorder (ASD) has challenged researchers for many years. With enough data and computational power, machine learning (ML) algorithms can be used to interpret the data and extract the best biomarkers from thousands of candidates. In this study, we used the fMRI data of 816 individuals enrolled in the Autism Brain Imaging Data Exchange (ABIDE) to introduce a new biomarker extraction pipeline for ASD that relies on the use of graph theoretical metrics of fMRI-based functional connectivity to inform a support vector machine (SVM). Furthermore, we split the dataset into 5 age groups to account for the effect of aging on functional connectivity. Our methodology achieved better results than most state-of-the-art investigations on this dataset with the best model for the >30 years age group achieving an accuracy, sensitivity, and specificity of 95, 97, and 95%, respectively. Our results suggest that measures of centrality provide the highest contribution to the classification power of the models.

Neuronal damage presents a major health issue necessitating extensive research to identify mechanisms of neuronal cell death and potential therapeutic targets. Commonly used models are slice cultures out of different brain regions extracted from mice or rats, excitotoxically, ischemic, or traumatically lesioned and subsequently treated with potential neuroprotective agents. Thereby cell death is regularly assessed by measuring the propidium iodide (PI) uptake or counting of PI-positive nuclei. The applied methods have a limited applicability, either in terms of objectivity and time consumption or regarding its applicability. Consequently, new tools for analysis are needed. Here, we present a framework to mimic manual counting using machine learning algorithms as tools for semantic segmentation of PI-positive dead cells in hippocampal slice cultures. Therefore, we trained a support vector machine (SVM) to classify images into either "high" or "low" neuronal damage and used naïve Bayes, discriminant analysis, random forest, and a multilayer perceptron (MLP) as classifiers for segmentation of dead cells. In our final models, pixel-wise accuracies of up to 0.97 were achieved using the MLP classifier. Furthermore, a SVM-based post-processing step was introduced to differentiate between false-positive and false-negative detections using morphological features. As only very few false-positive objects and thus training data remained when using the final model, this approach only mildly improved the results. A final object splitting step using Hough transformations was used to account for overlap, leading to a recall of up to 97.6% of the manually assigned PI-positive dead cells. Taken together, we present an analysis tool that can help to objectively and reproducibly analyze neuronal damage in brain-derived slice cultures, taking advantage of the morphology of pycnotic cells for segmentation, object splitting, and identification of false positives.

Speech perception in noisy environments depends on complex interactions between sensory and cognitive systems. In older adults, such interactions may be affected, especially in those individuals who have more severe age-related hearing loss. Using a data-driven approach, we assessed the temporal (when in time) and spatial (where in the brain) characteristics of cortical speech-evoked responses that distinguish older adults with or without mild hearing loss. We performed source analyses to estimate cortical surface signals from the EEG recordings during a phoneme discrimination task conducted under clear and noise-degraded conditions. We computed source-level ERPs (i.e., mean activation within each ROI) from each of the 68 ROIs of the Desikan-Killiany (DK) atlas, averaged over a randomly chosen 100 trials without replacement to form feature vectors. We adopted a multivariate feature selection method called stability selection and control to choose features that are consistent over a range of model parameters. We use parameter optimized support vector machine (SVM) as a classifiers to investigate the time course and brain regions that segregate groups and speech clarity. For clear speech perception, whole-brain data revealed a classification accuracy of 81.50% [area under the curve (AUC) 80.73%; F1-score 82.00%], distinguishing groups within ∼60 ms after speech onset (i.e., as early as the P1 wave). We observed lower accuracy of 78.12% [AUC 77.64%; F1-score 78.00%] and delayed classification performance when speech was embedded in noise, with group segregation at 80 ms. Separate analysis using left (LH) and right hemisphere (RH) regions showed that LH speech activity was better at distinguishing hearing groups than activity measured in the RH. Moreover, stability selection analysis identified 12 brain regions (among 1428 total spatiotemporal features from 68 regions) where source activity segregated groups with >80% accuracy (clear speech); whereas 16 regions were critical for noise-degraded speech to achieve a comparable level of group segregation (78.7% accuracy). Our results identify critical time-courses and brain regions that distinguish mild hearing loss from normal hearing in older adults and confirm a larger number of active areas, particularly in RH, when processing noise-degraded speech information.

Although mounting neuroimaging studies have greatly improved our understanding of the neurobiological mechanism underlying internet addiction (IA), the results based on traditional group-level comparisons are insufficient in guiding individual clinical practice directly. Specific neuroimaging biomarkers are urgently needed for IA diagnosis and the evaluation of therapy efficacy. Therefore, this study aimed to develop support vector machine (SVM) models to identify IA and assess the efficacy of cognitive behavior therapy (CBT) based on unbiased functional connectivity density (FCD). Resting-state fMRI data were acquired from 27 individuals with IA before and after 8-week CBT sessions and 30 demographically matched healthy controls (HCs). The discriminative FCDs were computed as the features of the support vector classification (SVC) model to identify individuals with IA from HCs, and the changes in these discriminative FCDs after treatment were further used as features of the support vector regression (SVR) model to evaluate the efficacy of CBT. Based on the informative FCDs, our SVC model successfully differentiated individuals with IA from HCs with an accuracy of 82.5% and an area under the curve (AUC) of 0.91. Our SVR model successfully evaluated the efficacy of CBT using the FCD change ratio with a correlation efficient of 0.59. The brain regions contributing to IA classification and CBT efficacy assessment were the left inferior frontal cortex (IFC), middle frontal cortex (MFC) and angular gyrus (AG), the right premotor cortex (PMC) and middle cingulate cortex (MCC), and the bilateral cerebellum, orbitofrontal cortex (OFC) and superior frontal cortex (SFC). These findings confirmed the FCDs of hyperactive impulsive habit system, hypoactive reflecting system and sensitive interoceptive reward awareness system as potential neuroimaging biomarkers for IA, which might provide objective indexes for the diagnosis and efficacy evaluation of IA.

This study demonstrates the feasibility of detecting motor intent from brain activity of chronic stroke patients using an asynchronous electroencephalography (EEG)-based brain machine interface (BMI). Intent was inferred from movement related cortical potentials (MRCPs) measured over an optimized set of EEG electrodes. Successful intent detection triggered the motion of an upper-limb exoskeleton (MAHI Exo-II), to guide movement and to encourage active user participation by providing instantaneous sensory feedback. Several BMI design features were optimized to increase system performance in the presence of single-trial variability of MRCPs in the injured brain: (1) an adaptive time window was used for extracting features during BMI calibration; (2) training data from two consecutive days were pooled for BMI calibration to increase robustness to handle the day-to-day variations typical of EEG, and (3) BMI predictions were gated by residual electromyography (EMG) activity from the impaired arm, to reduce the number of false positives. This patient-specific BMI calibration approach can accommodate a broad spectrum of stroke patients with diverse motor capabilities. Following BMI optimization on day 3, testing of the closed-loop BMI-MAHI exoskeleton, on 4th and 5th days of the study, showed consistent BMI performance with overall mean true positive rate (TPR) = 62.7 ± 21.4% on day 4 and 67.1 ± 14.6% on day 5. The overall false positive rate (FPR) across subjects was 27.74 ± 37.46% on day 4 and 27.5 ± 35.64% on day 5; however for two subjects who had residual motor function and could benefit from the EMG-gated BMI, the mean FPR was quite low (< 10%). On average, motor intent was detected -367 ± 328 ms before movement onset during closed-loop operation. These findings provide evidence that closed-loop EEG-based BMI for stroke patients can be designed and optimized to perform well across multiple days without system recalibration.

The primary goal of this work was to apply data-driven machine learning regression to assess if resting state functional connectivity (rs-FC) could estimate measures of behavioral domains in stroke subjects who completed brain-computer interface (BCI) intervention for motor rehabilitation. The study cohort consisted of 20 chronic-stage stroke subjects exhibiting persistent upper-extremity motor deficits who received the intervention using a closed-loop neurofeedback BCI device. Over the course of this intervention, resting state functional MRI scans were collected at four distinct time points: namely, pre-intervention, mid-intervention, post-intervention and 1-month after completion of intervention. Behavioral assessments were administered outside the scanner at each time-point to collect objective measures such as the Action Research Arm Test, Nine-Hole Peg Test, and Barthel Index as well as subjective measures including the Stroke Impact Scale. The present analysis focused on neuroplasticity and behavioral outcomes measured across pre-intervention, post-intervention and 1-month post-intervention to study immediate and carry-over effects. Rs-FC, changes in rs-FC within the motor network and the behavioral measures at preceding stages were used as input features and behavioral measures and associated changes at succeeding stages were used as outcomes for machine-learning-based support vector regression (SVR) models. Potential clinical confounding factors such as age, gender, lesion hemisphere, and stroke severity were included as additional features in each of the regression models. Sequential forward feature selection procedure narrowed the search for important correlates. Behavioral outcomes at preceding time-points outperformed rs-FC-based correlates. Rs-FC and changes associated with bilateral primary motor areas were found to be important correlates of across several behavioral outcomes and were stable upon inclusion of clinical variables as well. NIH Stroke Scale and motor impairment severity were the most influential clinical variables. Comparatively, linear SVR models aided in evaluation of contribution of individual correlates and seed regions while non-linear SVR models achieved higher performance in prediction of behavioral outcomes.

Objective: Brain-machine interfaces (BMIs) are useful for inducing plastic changes in cortical representation. A BMI first decodes hand movements using cortical signals and then converts the decoded information into movements of a robotic hand. By using the BMI robotic hand, the cortical representation decoded by the BMI is modulated to improve decoding accuracy. We developed a BMI based on real-time magnetoencephalography (MEG) signals to control a robotic hand using decoded hand movements. Subjects were trained to use the BMI robotic hand freely for 10 min to evaluate plastic changes in the cortical representation due to the training. Method: We trained nine young healthy subjects with normal motor function. In open-loop conditions, they were instructed to grasp or open their right hands during MEG recording. Time-averaged MEG signals were then used to train a real decoder to control the robotic arm in real time. Then, subjects were instructed to control the BMI-controlled robotic hand by moving their right hands for 10 min while watching the robot's movement. During this closed-loop session, subjects tried to improve their ability to control the robot. Finally, subjects performed the same offline task to compare cortical activities related to the hand movements. As a control, we used a random decoder trained by the MEG signals with shuffled movement labels. We performed the same experiments with the random decoder as a crossover trial. To evaluate the cortical representation, cortical currents were estimated using a source localization technique. Hand movements were also decoded by a support vector machine using the MEG signals during the offline task. The classification accuracy of the movements was compared among offline tasks. Results: During the BMI training with the real decoder, the subjects succeeded in improving their accuracy in controlling the BMI robotic hand with correct rates of 0.28 ± 0.13 to 0.50 ± 0.11 (p = 0.017, n = 8, paired Student's t-test). Moreover, the classification accuracy of hand movements during the offline task was significantly increased after BMI training with the real decoder from 62.7 ± 6.5 to 70.0 ± 11.1% (p = 0.022, n = 8, t(7) = 2.93, paired Student's t-test), whereas accuracy did not significantly change after BMI training with the random decoder from 63.0 ± 8.8 to 66.4 ± 9.0% (p = 0.225, n = 8, t(7) = 1.33). Conclusion: BMI training is a useful tool to train the cortical activity necessary for BMI control and to induce some plastic changes in the activity.

Purpose: The purpose of this study is classifying multiple sclerosis (MS) patients in the four clinical forms as defined by the McDonald criteria using machine learning algorithms trained on clinical data combined with lesion loads and magnetic resonance metabolic features. Materials and Methods: Eighty-seven MS patients [12 Clinically Isolated Syndrome (CIS), 30 Relapse Remitting (RR), 17 Primary Progressive (PP), and 28 Secondary Progressive (SP)] and 18 healthy controls were included in this study. Longitudinal data available for each MS patient included clinical (e.g., age, disease duration, Expanded Disability Status Scale), conventional magnetic resonance imaging and spectroscopic imaging. We extract N-acetyl-aspartate (NAA), Choline (Cho), and Creatine (Cre) concentrations, and we compute three features for each spectroscopic grid by averaging metabolite ratios (NAA/Cho, NAA/Cre, Cho/Cre) over good quality voxels. We built linear mixed-effects models to test for statistically significant differences between MS forms. We test nine binary classification tasks on clinical data, lesion loads, and metabolic features, using a leave-one-patient-out cross-validation method based on 100 random patient-based bootstrap selections. We compute F1-scores and BAR values after tuning Linear Discriminant Analysis (LDA), Support Vector Machines with gaussian kernel (SVM-rbf), and Random Forests. Results: Statistically significant differences were found between the disease starting points of each MS form using four different response variables: Lesion Load, NAA/Cre, NAA/Cho, and Cho/Cre ratios. Training SVM-rbf on clinical and lesion loads yields F1-scores of 71-72% for CIS vs. RR and CIS vs. RR+SP, respectively. For RR vs. PP we obtained good classification results (maximum F1-score of 85%) after training LDA on clinical and metabolic features, while for RR vs. SP we obtained slightly higher classification results (maximum F1-score of 87%) after training LDA and SVM-rbf on clinical, lesion loads and metabolic features. Conclusions: Our results suggest that metabolic features are better at differentiating between relapsing-remitting and primary progressive forms, while lesion loads are better at differentiating between relapsing-remitting and secondary progressive forms. Therefore, combining clinical data with magnetic resonance lesion loads and metabolic features can improve the discrimination between relapsing-remitting and progressive forms.

The utility of premovement electroencephalography (EEG) for decoding movement intention during a reaching task has been demonstrated. However, the kind of information the brain represents regarding the intended target during movement preparation remains unknown. In the present study, we investigated which movement parameters (i.e., direction, distance, and positions for reaching) can be decoded in premovement EEG decoding. Eight participants performed 30 types of reaching movements that consisted of 1 of 24 movement directions, 7 movement distances, 5 horizontal target positions, and 5 vertical target positions. Event-related spectral perturbations were extracted using independent components, some of which were selected via an analysis of variance for further binary classification analysis using a support vector machine. When each parameter was used for class labeling, all possible binary classifications were performed. Classification accuracies for direction and distance were significantly higher than chance level, although no significant differences were observed for position. For the classification in which each movement was considered as a different class, the parameters comprising two vectors representing each movement were analyzed. In this case, classification accuracies were high when differences in distance were high, the sum of distances was high, angular differences were large, and differences in the target positions were high. The findings further revealed that direction and distance may provide the largest contributions to movement. In addition, regardless of the parameter, useful features for classification are easily found over the parietal and occipital areas.

Emotional singing can affect vocal performance and the audience's engagement. Chinese universities use traditional training techniques for teaching theoretical and applied knowledge. Self-imagination is the predominant training method for emotional singing. Recently, virtual reality (VR) technologies have been applied in several fields for training purposes. In this empirical comparative study, a VR training task was implemented to elicit emotions from singers and further assist them with improving their emotional singing performance. The VR training method was compared against the traditional self-imagination method. By conducting a two-stage experiment, the two methods were compared in terms of emotions' elicitation and emotional singing performance. In the first stage, electroencephalographic (EEG) data were collected from the subjects. In the second stage, self-rating reports and third-party teachers' evaluations were collected. The EEG data were analyzed by adopting the max-relevance and min-redundancy algorithm for feature selection and the support vector machine (SVM) for emotion recognition. Based on the results of EEG emotion classification and subjective scale, VR can better elicit the positive, neutral, and negative emotional states from the singers than not using this technology (i.e., self-imagination). Furthermore, due to the improvement of emotional activation, VR brings the improvement of singing performance. The VR hence appears to be an effective approach that may improve and complement the available vocal music teaching methods.