A subject-independent pattern-based Brain-Computer Interface

EEG subject-dependent neurofeedback training selectively impairs declarative memories consolidation process

The process of stabilization and storage of memories, known as consolidation, can be modulated by different interventions. Research has shown that self-regulation of brain activity through Neurofeedback (NFB) during the consolidation phase significantly impacts memory stabilization. While some studies have successfully modulated the consolidation phase using traditional EEG-based Neurofeedback (NFB) that focuses on general parameters, such as training a specific frequency band at particular electrodes, they often overlook the unique and complex neurodynamics that underlie each memory content in different individuals, potentially limiting the selective modulation of memories. The main objective of this study is to investigate the effects of a Subject-Dependent NFB (SD-NFB), based on individual models created from the brain activity of each participant, on long-term declarative memories. Participants underwent an experimental protocol involving three sessions. In the first session, they learned images of faces and houses while their brain activity was recorded. This EEG data was used to create individualized models to identify brain patterns related to learning these images. Participants were then divided into three groups, with one group receiving SD-NFB to enhance brain activity linked to faces, another to houses, and a CONTROL sham group that did not receive SD-NFB. Memory performance was evaluated 24 h and seven days later using an 'old-new' recognition task, where participants distinguished between 'old' and 'new' images. The results showed that memory contents (faces or houses) whose brain patterns were trained via SD-NFB scored lower in recognition compared to untrained contents, as evidenced 24 h and seven days post-training. In summary, this study demonstrates that SD-NFB can selectively impact the consolidation of specific declarative memories. This technique could hold significant implications for clinical applications, potentially aiding in the modulation of declarative memory strength in neuropsychiatric disorders where memories are pathologically exacerbated.

Detecting cognitive traits and occupational proficiency using EEG and statistical inference

Machine learning (ML) is widely used in classification tasks aimed at detecting various cognitive states or neurological diseases using noninvasive electroencephalogram (EEG) time series. However, successfully detecting specific cognitive skills in a healthy population, independent of subject, remains challenging. This study compared the subject-independent classification performance of three different pipelines: supervised and Riemann projections with logistic regression and handcrafted power spectral features with light gradient boosting machine (LightGBM). 128-channel EEGs were recorded from 26 healthy volunteers while they solved arithmetic, logical, and verbal tasks. The participants were divided into two groups based on their higher education and occupation: specialists in mathematics and humanities. The balanced accuracy of the education type was significantly above chance for all pipelines: 0.84-0.89, 0.85-0.88, and 0.86-0.88 for each type of task, respectively. All three pipelines allowed us to distinguish mathematical proficiency based on learning experience with different trade-offs between performance and explainability. Our results suggest that ML approaches could also be effective for recognizing individual cognitive traits using EEG.

Transfer learning promotes acquisition of individual BCI skills

Subject training is crucial for acquiring brain-computer interface (BCI) control. Typically, this requires collecting user-specific calibration data due to high inter-subject neural variability that limits the usability of generic decoders. However, calibration is cumbersome and may produce inadequate data for building decoders, especially with naïve subjects. Here, we show that a decoder trained on the data of a single expert is readily transferrable to inexperienced users via domain adaptation techniques allowing calibration-free BCI training. We introduce two real-time frameworks, (i) Generic Recentering (GR) through unsupervised adaptation and (ii) Personally Assisted Recentering (PAR) that extends GR by employing supervised recalibration of the decoder parameters. We evaluated our frameworks on 18 healthy naïve subjects over five online sessions, who operated a customary synchronous bar task with continuous feedback and a more challenging car racing game with asynchronous control and discrete feedback. We show that along with improved task-oriented BCI performance in both tasks, our frameworks promoted subjects' ability to acquire individual BCI skills, as the initial neurophysiological control features of an expert subject evolved and became subject specific. Furthermore, those features were task-specific and were learned in parallel as participants practiced the two tasks in every session. Contrary to previous findings implying that supervised methods lead to improved online BCI control, we observed that longitudinal training coupled with unsupervised domain matching (GR) achieved similar performance to supervised recalibration (PAR). Therefore, our presented frameworks facilitate calibration-free BCIs and have immediate implications for broader populations-such as patients with neurological pathologies-who might struggle to provide suitable initial calibration data.

Inter-individual single-trial classification of MEG data using M-CCA

Neuroscientific studies often involve some form of group analysis over multiple participants. This requires alignment of recordings across participants. A naive solution is to assume that participants' recordings can be aligned anatomically in sensor space. However, this assumption is likely violated due to anatomical and functional differences between individual brains. In magnetoencephalography (MEG) recordings the problem of inter-subject alignment is exacerbated by the susceptibility of MEG to individual cortical folding patterns as well as the inter-subject variability of sensor locations over the brain due to the use of a fixed helmet. Hence, an approach to combine MEG data over individual brains should relax the assumptions that a) brain anatomy and function are tightly linked and b) that the same sensors capture functionally comparable brain activation across individuals. Here we use multiset canonical correlation analysis (M-CCA) to find a common representation of MEG activations recorded from 15 participants performing a grasping task. The M-CCA algorithm was applied to transform the data of a set of multiple participants into a common space with maximum correlation between participants. Importantly, we derive a method to transform data from a new, previously unseen participant into this common representation. This makes it useful for applications that require transfer of models derived from a group of individuals to new individuals. We demonstrate the usefulness and superiority of the approach with respect to previously used approaches. Finally, we show that our approach requires only a small number of labeled data from the new participant. The proposed method demonstrates that functionally motivated common spaces have potential applications in reducing training time of online brain-computer interfaces, where models can be pre-trained on previous participants/sessions. Moreover, inter-subject alignment via M-CCA has the potential for combining data of different participants and could become helpful in future endeavors on large open datasets.

Comparison of subject-independent and subject-specific EEG-based BCI using LDA and SVM classifiers

Motor imagery brain-computer interface (MI-BCI) is one of the most used paradigms in EEG-based brain-computer interface (BCI). The current state-of-the-art in BCI involves tuning classifiers to subject-specific training data, acquired over several sessions, in order to perform calibration prior to actual use of the so-called subject-specific BCI system (SS-BCI). Herein, the goal is to provide a ready-to-use system requiring minimal effort for setup. Thus, our challenge was to design a subject-independent BCI (SI-BCI) to be used by any new user without the constraint of individual calibration. Outcomes from other studies with the same purpose were used to undertake comparisons and validate our findings. For the EEG signal processing, we used a combination of the delta (0.5-4 Hz), alpha (8-13 Hz), and beta+gamma (13-40 Hz) bands at a stage prior to feature extraction. Next, we extracted features from the 27-channel EEG using common spatial pattern (CSP) and performed binary classification (MI of right- and left-hand) with linear discriminant analysis (LDA) and support vector machine (SVM) classifiers. These analyses were done for both the SS-BCI and SI-BCI models. We employed "leave-one-subject-out" (LOSO) arrangement and 10-fold cross-validation to evaluate our SI-BCI and SS-BCI systems, respectively. Compared with other two studies, our work was the only one that showed higher accuracy for the LDA classifier in SI-BCI as compared to SS-BCI. On the other hand, LDA accuracy was lower than accuracy achieved with SVM in both conditions (SI-BCI and SS-BCI). Our SS-BCI accuracy reached 76.85% using LDA and 94.20% using SVM and for SI-BCI we got 80.30% with LDA and 83.23% with SVM. We conclude that SI-BCI may be a feasible and relevant option, which can be used in scenarios where subjects are not able to submit themselves to long training sessions or to fast evaluation of the so called "BCI illiteracy." Comparatively, our strategy proved to be more efficient, giving us the best result for SI-BCI when faced against the classification performances of other three studies, even considering the caveat that different datasets were used in the comparison of the four studies.

Discrepancy between inter- and intra-subject variability in EEG-based motor imagery brain-computer interface: Evidence from multiple perspectives

Introduction

Inter- and intra-subject variability are caused by the variability of the psychological and neurophysiological factors over time and across subjects. In the application of in Brain-Computer Interfaces (BCI), the existence of inter- and intra-subject variability reduced the generalization ability of machine learning models seriously, which further limited the use of BCI in real life. Although many transfer learning methods can compensate for the inter- and intra-subject variability to some extent, there is still a lack of clear understanding about the change of feature distribution between the cross-subject and cross-session electroencephalography (EEG) signal.

Methods

To investigate this issue, an online platform for motor-imagery BCI decoding has been built in this work. The EEG signal from both the multi-subject (Exp1) and multi-session (Exp2) experiments has been analyzed from multiple perspectives.

Results

Firstly we found that with the similar variability of classification results, the time-frequency response of the EEG signal within-subject in Exp2 is more consistent than cross-subject results in Exp1. Secondly, the standard deviation of the common spatial pattern (CSP) feature has a significant difference between Exp1 and Exp2. Thirdly, for model training, different strategies for the training sample selection should be applied for the cross-subject and cross-session tasks.

Discussion

All these findings have deepened the understanding of inter- and intra-subject variability. They can also guide practice for the new transfer learning methods development in EEG-based BCI. In addition, these results also proved that BCI inefficiency was not caused by the subject's unable to generate the event-related desynchronization/synchronization (ERD/ERS) signal during the motor imagery.

A Subject-Independent Brain-Computer Interface Framework Based on Supervised Autoencoder

A calibration procedure is required in motor imagery-based brain-computer interface (MI-BCI) to tune the system for new users. This procedure is time-consuming and prevents naive users from using the system immediately. Developing a subject-independent MI-BCI system to reduce the calibration phase is still challenging due to the subject-dependent characteristics of the MI signals. Many algorithms based on machine learning and deep learning have been developed to extract high-level features from the MI signals to improve the subject-to-subject generalization of a BCI system. However, these methods are based on supervised learning and extract features useful for discriminating various MI signals. Hence, these approaches cannot find the common underlying patterns in the MI signals and their generalization level is limited. This paper proposes a subject-independent MI-BCI based on a supervised autoencoder (SAE) to circumvent the calibration phase. The suggested framework is validated on dataset 2a from BCI competition IV. The simulation results show that our SISAE model outperforms the conventional and widely used BCI algorithms, common spatial and filter bank common spatial patterns, in terms of the mean Kappa value, in eight out of nine subjects.

Can neurofeedback provide evidence of direct brain-behavior causality?

Neurofeedback is a procedure that measures brain activity in real-time and presents it as feedback to an individual, thus allowing them to self-regulate brain activity with effects on cognitive processes inferred from behavior. One common argument is that neurofeedback studies can reveal how the measured brain activity causes a particular cognitive process. The causal claim is often made regarding the measured brain activity being manipulated as an independent variable, similar to brain stimulation studies. However, this causal inference is vulnerable to the argument that other upstream brain activities change concurrently and cause changes in the brain activity from which feedback is derived. In this paper, we outline the inference that neurofeedback may causally affect cognition by indirect means. We further argue that researchers should remain open to the idea that the trained brain activity could be part of a "causal network" that collectively affects cognition rather than being necessarily causally primary. This particular inference may provide a better translation of evidence from neurofeedback studies to the rest of neuroscience. We argue that the recent advent of multivariate pattern analysis, when combined with implicit neurofeedback, currently comprises the strongest case for causality. Our perspective is that although the burden of inferring direct causality is difficult, it may be triangulated using a collection of various methods in neuroscience. Finally, we argue that the neurofeedback methodology provides unique advantages compared to other methods for revealing changes in the brain and cognitive processes but that researchers should remain mindful of indirect causal effects.

Weighted neurofeedback facilitates greater self-regulation of functional connectivity between the primary motor area and cerebellum

Objective.Brain-computer interface (BCI) is a tool that can be used to train brain self-regulation and influence specific activity patterns, including functional connectivity, through neurofeedback. The functional connectivity of the primary motor area (M1) and cerebellum play a critical role in motor recovery after a brain injury, such as stroke. The objective of this study was to determine the feasibility of achieving control of the functional connectivity between M1 and the cerebellum in healthy subjects. Additionally, we aimed to compare the brain self-regulation of two different feedback modalities and their effects on motor performance.Approach.Nine subjects were trained with a real-time functional magnetic resonance imaging BCI system. Two groups were conformed: equal feedback group (EFG), which received neurofeedback that weighted the contribution of both regions of interest (ROIs) equally, and weighted feedback group (WFG) that weighted each ROI differentially (30% cerebellum; 70% M1). The magnitude of the brain activity induced by self-regulation was evaluated with the blood-oxygen-level-dependent (BOLD) percent change (BPC). Functional connectivity was assessed using temporal correlations between the BOLD signal of both ROIs. A finger-tapping task was included to evaluate the effect of brain self-regulation on motor performance.Main results.A comparison between the feedback modalities showed that WFG achieved significantly higher BPC in M1 than EFG. The functional connectivity between ROIs during up-regulation in WFG was significantly higher than EFG. In general, both groups showed better tapping speed in the third session compared to the first. For WFG, there were significant correlations between functional connectivity and tapping speed.Significance.The results show that it is possible to train healthy individuals to control M1-cerebellum functional connectivity with rtfMRI-BCI. Besides, it is also possible to use a weighted feedback approach to facilitate a higher activity of one region over another.

Affective Neurofeedback Under Naturalistic Conditions: A Mini-Review of Current Achievements and Open Challenges

Affective neurofeedback training allows for the self-regulation of the putative circuits of emotion regulation. This approach has recently been studied as a possible additional treatment for psychiatric disorders, presenting positive effects in symptoms and behaviors. After neurofeedback training, a critical aspect is the transference of the learned self-regulation strategies to outside the laboratory and how to continue reinforcing these strategies in non-controlled environments. In this mini-review, we discuss the current achievements of affective neurofeedback under naturalistic setups. For this, we first provide a brief overview of the state-of-the-art for affective neurofeedback protocols. We then discuss virtual reality as a transitional step toward the final goal of "in-the-wild" protocols and current advances using mobile neurotechnology. Finally, we provide a discussion of open challenges for affective neurofeedback protocols in-the-wild, including topics such as convenience and reliability, environmental effects in attention and workload, among others.

Progress in Brain Computer Interface: Challenges and Opportunities

Brain computer interfaces (BCI) provide a direct communication link between the brain and a computer or other external devices. They offer an extended degree of freedom either by strengthening or by substituting human peripheral working capacity and have potential applications in various fields such as rehabilitation, affective computing, robotics, gaming, and neuroscience. Significant research efforts on a global scale have delivered common platforms for technology standardization and help tackle highly complex and non-linear brain dynamics and related feature extraction and classification challenges. Time-variant psycho-neurophysiological fluctuations and their impact on brain signals impose another challenge for BCI researchers to transform the technology from laboratory experiments to plug-and-play daily life. This review summarizes state-of-the-art progress in the BCI field over the last decades and highlights critical challenges.

Subject-independent Classification on Brain-Computer Interface using Autonomous Deep Learning for finger movement recognition

The degradation of the subject-independent classification on a brain-computer interface is a challenging issue. One method mostly taken to overcome this problem is by collecting as many subjects as possible and then training the system across all subjects. This article introduces streaming online learning called autonomous deep learning (ADL) to classify five individual fingers based on electroencephalography (EEG) signals to overcome the issue above. ADL is a deep learning architecture that can construct its structure by itself through streaming learning and adapt its structure to the changes occurring in the input. In this article, the input of ADL is a common spatial pattern (CSP) extracted from the EEG signal of healthy subjects. The experimental results on the subject-dependence classification across four subjects using 5fold cross-validation show that that ADL achieved the classification accuracy of around 77%. This performance was excellent compared to a random forest (RF) and a convolutional neural network (CNN). They achieved accuracies of about 53% and 72%, respectively. On the subject-independent classification, ADL outperforms CNN by resulting stable accuracies for both training and testing, different from CNN that experience accuracy degradation to approximately 50%. These results imply that ADL is a promising machine learning in dealing with the issue in the subject-independent classification.

Subject-Independent Brain-Computer Interfaces Based on Deep Convolutional Neural Networks

For a brain-computer interface (BCI) system, a calibration procedure is required for each individual user before he/she can use the BCI. This procedure requires approximately 20-30 min to collect enough data to build a reliable decoder. It is, therefore, an interesting topic to build a calibration-free, or subject-independent, BCI. In this article, we construct a large motor imagery (MI)-based electroencephalography (EEG) database and propose a subject-independent framework based on deep convolutional neural networks (CNNs). The database is composed of 54 subjects performing the left- and right-hand MI on two different days, resulting in 21 600 trials for the MI task. In our framework, we formulated the discriminative feature representation as a combination of the spectral-spatial input embedding the diversity of the EEG signals, as well as a feature representation learned from the CNN through a fusion technique that integrates a variety of discriminative brain signal patterns. To generate spectral-spatial inputs, we first consider the discriminative frequency bands in an information-theoretic observation model that measures the power of the features in two classes. From discriminative frequency bands, spectral-spatial inputs that include the unique characteristics of brain signal patterns are generated and then transformed into a covariance matrix as the input to the CNN. In the process of feature representations, spectral-spatial inputs are individually trained through the CNN and then combined by a concatenation fusion technique. In this article, we demonstrate that the classification accuracy of our subject-independent (or calibration-free) model outperforms that of subject-dependent models using various methods [common spatial pattern (CSP), common spatiospectral pattern (CSSP), filter bank CSP (FBCSP), and Bayesian spatio-spectral filter optimization (BSSFO)].

Optimized artificial neural network based performance analysis of wheelchair movement for ALS patients

Individuals with neurodegenerative attacks loose the entire motor neuron movements. These conditions affect the individual actions like walking, speaking impairment and totally make the person in to locked in state (LIS). To overcome the miserable condition the person need rehabilitation devices through a Brain Computer Interfaces (BCI) to satisfy their needs. BMI using Electroencephalogram (EEG) receives the mental thoughts from brain and converts into control signals to activate the exterior communication appliances in the absence of biological channels. To design the BCI, we conduct our study with three normal male subjects, three normal female subjects and three ALS affected individuals from the age of 20-60 with three electrode systems for four tasks. One Dimensional Local Binary Patterns (LBP) technique was applied to reduce the digitally sampled features collected from nine subjects was treated with Grey wolf optimization Neural Network (GWONN) to classify the mentally composed words. Using these techniques, we compared the three types of subjects to identify the performances. The study proves that subjects from normal male categories performance was maximum compared with the other subjects. To assess the individual performance of the subject, we conducted the recognition accuracy test in offline mode. From the accuracy test also, we obtained the best performance from the normal male subjects compared with female and ALS subjects with an accuracy of 98.33 %, 95.00 % and 88.33 %. Finally our study concludes that patients with ALS attack need more training than that of the other subjects.

Rapid calibration of an intracortical brain-computer interface for people with tetraplegia

OBJECTIVE

Brain-computer interfaces (BCIs) can enable individuals with tetraplegia to communicate and control external devices. Though much progress has been made in improving the speed and robustness of neural control provided by intracortical BCIs, little research has been devoted to minimizing the amount of time spent on decoder calibration.

APPROACH

We investigated the amount of time users needed to calibrate decoders and achieve performance saturation using two markedly different decoding algorithms: the steady-state Kalman filter, and a novel technique using Gaussian process regression (GP-DKF).

MAIN RESULTS

Three people with tetraplegia gained rapid closed-loop neural cursor control and peak, plateaued decoder performance within 3 min of initializing calibration. We also show that a BCI-naïve user (T5) was able to rapidly attain closed-loop neural cursor control with the GP-DKF using self-selected movement imagery on his first-ever day of closed-loop BCI use, acquiring a target 37 s after initiating calibration.

SIGNIFICANCE

These results demonstrate the potential for an intracortical BCI to be used immediately after deployment by people with paralysis, without the need for user learning or extensive system calibration.

Single-Trial Decoding of Scalp EEG under Natural Conditions

There is significant current interest in decoding mental states from electroencephalography (EEG) recordings. EEG signals are subject-specific, are sensitive to disturbances, and have a low signal-to-noise ratio, which has been mitigated by the use of laboratory-grade EEG acquisition equipment under highly controlled conditions. In the present study, we investigate single-trial decoding of natural, complex stimuli based on scalp EEG acquired with a portable, 32 dry-electrode sensor system in a typical office setting. We probe generalizability by a leave-one-subject-out cross-validation approach. We demonstrate that support vector machine (SVM) classifiers trained on a relatively small set of denoised (averaged) pseudotrials perform on par with classifiers trained on a large set of noisy single-trial samples. We propose a novel method for computing sensitivity maps of EEG-based SVM classifiers for visualization of EEG signatures exploited by the SVM classifiers. Moreover, we apply an NPAIRS resampling framework for estimation of map uncertainty, and thus show that effect sizes of sensitivity maps for classifiers trained on small samples of denoised data and large samples of noisy data are similar. Finally, we demonstrate that the average pseudotrial classifier can successfully predict the class of single trials from withheld subjects, which allows for fast classifier training, parameter optimization, and unbiased performance evaluation in machine learning approaches for brain decoding.

Across-subject offline decoding of motor imagery from MEG and EEG

Long calibration time hinders the feasibility of brain-computer interfaces (BCI). If other subjects’ data were used for training the classifier, BCI-based neurofeedback practice could start without the initial calibration. Here, we compare methods for inter-subject decoding of left- vs. right-hand motor imagery (MI) from MEG and EEG. Six methods were tested on data involving MEG and EEG measurements of healthy participants. Inter-subject decoders were trained on subjects showing good within-subject accuracy, and tested on all subjects, including poor performers. Three methods were based on Common Spatial Patterns (CSP), and three others on logistic regression with l₁ - or l_2,1 -norm regularization. The decoding accuracy was evaluated using (1) MI and (2) passive movements (PM) for training, separately for MEG and EEG. With MI training, the best accuracies across subjects (mean 70.6% for MEG, 67.7% for EEG) were obtained using multi-task learning (MTL) with logistic regression and l_2,1-norm regularization. MEG yielded slightly better average accuracies than EEG. With PM training, none of the inter-subject methods yielded above chance level (58.7%) accuracy. In conclusion, MTL and training with other subject’s MI is efficient for inter-subject decoding of MI. Passive movements of other subjects are likely suboptimal for training the MI classifiers.

Across-subject offline decoding of motor imagery from MEG and EEG

Long calibration time hinders the feasibility of brain-computer interfaces (BCI). If other subjects' data were used for training the classifier, BCI-based neurofeedback practice could start without the initial calibration. Here, we compare methods for inter-subject decoding of left- vs. right-hand motor imagery (MI) from MEG and EEG. Six methods were tested on data involving MEG and EEG measurements of healthy participants. Inter-subject decoders were trained on subjects showing good within-subject accuracy, and tested on all subjects, including poor performers. Three methods were based on Common Spatial Patterns (CSP), and three others on logistic regression with l₁ - or l_2,1 -norm regularization. The decoding accuracy was evaluated using (1) MI and (2) passive movements (PM) for training, separately for MEG and EEG. With MI training, the best accuracies across subjects (mean 70.6% for MEG, 67.7% for EEG) were obtained using multi-task learning (MTL) with logistic regression and l_2,1-norm regularization. MEG yielded slightly better average accuracies than EEG. With PM training, none of the inter-subject methods yielded above chance level (58.7%) accuracy. In conclusion, MTL and training with other subject's MI is efficient for inter-subject decoding of MI. Passive movements of other subjects are likely suboptimal for training the MI classifiers.

Enhanced inter-subject brain computer interface with associative sensorimotor oscillations

Electroencephalography (EEG) captures electrophysiological signatures of cortical events from the scalp with high-dimensional electrode montages. Usually, excessive sources produce outliers and potentially affect the actual event related sources. Besides, EEG manifests inherent inter-subject variability of the brain dynamics, at the resting state and/or under the performance of task(s), caused probably due to the instantaneous fluctuation of psychophysiological states. A wavelet coherence (WC) analysis for optimally selecting associative inter-subject channels is proposed here and is being used to boost performances of motor imagery (MI)-based inter-subject brain computer interface (BCI). The underlying hypothesis is that optimally associative inter-subject channels can reduce the effects of outliers and, thus, eliminate dissimilar cortical patterns. The proposed approach has been tested on the dataset IVa from BCI competition III, including EEG data acquired from five healthy subjects who were given visual cues to perform 280 trials of MI for the right hand and right foot. Experimental results have shown increased classification accuracy (81.79%) using the WC-based selected 16 channels compared to the one (56.79%) achieved using all the available 118 channels. The associative channels lie mostly around the sensorimotor regions of the brain, reinforced by the previous literature, describing spatial brain dynamics during sensorimotor oscillations. Apparently, the proposed approach paves the way for optimised EEG channel selection that could boost further the efficiency and real-time performance of BCI systems.

How feedback, motor imagery, and reward influence brain self-regulation using real-time fMRI

The learning process involved in achieving brain self-regulation is presumed to be related to several factors, such as type of feedback, reward, mental imagery, duration of training, among others. Explicitly instructing participants to use mental imagery and monetary reward are common practices in real-time fMRI (rtfMRI) neurofeedback (NF), under the assumption that they will enhance and accelerate the learning process. However, it is still not clear what the optimal strategy is for improving volitional control. We investigated the differential effect of feedback, explicit instructions and monetary reward while training healthy individuals to up-regulate the blood-oxygen-level dependent (BOLD) signal in the supplementary motor area (SMA). Four groups were trained in a two-day rtfMRI-NF protocol: GF with NF only, GF,I with NF + explicit instructions (motor imagery), GF,R with NF + monetary reward, and GF,I,R with NF + explicit instructions (motor imagery) + monetary reward. Our results showed that GF increased significantly their BOLD self-regulation from day-1 to day-2 and GF,R showed the highest BOLD signal amplitude in SMA during the training. The two groups who were instructed to use motor imagery did not show a significant learning effect over the 2 days. The additional factors, namely motor imagery and reward, tended to increase the intersubject variability in the SMA during the course of training. Whole brain univariate and functional connectivity analyses showed common as well as distinct patterns in the four groups, representing the varied influences of feedback, reward, and instructions on the brain. Hum Brain Mapp 37:3153-3171, 2016. © 2016 Wiley Periodicals, Inc.