Fuzzy adaptive neurofeedback training: An efficient neurofeedback training procedure providing a more accurate progress rate for trainee

https://doi.org/10.1016/j.bspc.2018.02.009Get rights and content

Highlights

  • Threshold is set adaptively with cortical activity of subject.

  • Scoring index value is set according to the brain activity of subject.

  • A brain mental fatigue index is considered.

Abstract

In this paper, a new fuzzy adaptive neurofeedback training procedure (FNFT) is proposed, in which a more effective performance in neurofeedback training can be expected. In the proposed FNFT, the threshold is adaptively set considering the cortical activity of the subject. Scoring index (SI) (the number of points increased in subject's score) is set according to the brain activity of the subject and is calculated using a fuzzy rule based system. When training feature surpasses the threshold, the SI points are then added to the points of the subject. This adaptive scoring index leads to having an efficient indicator for the success rate of the subject. In addition, the subject is rewarded with an audio or visual feedback. The sound intensity of the audio feedback and the length and width of the video frame are adjusted in accordance with the SI. Finally, an EEG feature is also considered (brain mental fatigue index) to stop the training as the subject becomes mentally fatigued.

Introduction

Neurofeedback is a non-invasive conditioning method, in which individuals can learn to voluntarily regulate their brain activities [[1], [2], [3]]. Athletes, artists and business executives take advantage of neurofeedback to learn how to use the full potential of their brain to reach their superior performance. Neurofeedback is also effective enough to treat the patients with anxiety, depression, epilepsy, etc [[3], [4], [5], [6], [7]].

Neurofeedback training generally consists of recording EEG signals from one or two electrode sites and providing audio or visual feedback for the individuals about their cortical activities [8,9]. Training features are calculated on a moving window that is continuously updated and compared with a threshold. The subject would be rewarded with audio or visual feedback or point increasing when the training feature surpasses the threshold. It must be noted that inappropriate scoring method may confuse subjects when evaluating how successful they were in modifying their brain activity.

Researchers have previously applied various rewarding methods for NFT. One of the most traditional thresholding methods is to have a threshold fixed by a therapist. In this method, the therapist manually sets a fixed threshold for a training session. If the training feature surpasses the threshold, a point would then be added to the score of the subject [10,11]. An open question is how the threshold should be selected. Some therapists set the threshold according to the previous results of the subject and their sensitivity to rewards and punishments [10]. Other therapists determine the threshold according to a schedule upon which the threshold is set to a minimum value in the first session and then is increased during the next sessions. However, a fixed threshold setting would not be adaptive regarding the brain activity of subjects. Therefore, the thresholds should be adaptively modified according to the cortical activity of the subject. In addition, the number of points and the audio or visual feedback should accurately reflect the progress rate of the subject.

Another traditional thresholding method is automatic calculation, done by setting the threshold to the training feature level surpassing 60–85% of the time during the preceding 30 s moving average window [1,8,9,[12], [13], [14], [15], [16], [17], [18]]. When the training feature surpasses the determined threshold, the score would increase by one point and the subject would then be rewarded with an audio or visual feedback. This method is adaptive in nature, and there is no need for the threshold to be manually set by the therapist.

However, this method may confuse the subject and therefore, not provide an appropriate indicator of the success rate. Suppose that it is aimed to train a subject to increase his/her alpha wave activity. For this purpose, the subject starts with a default threshold and then passes the first 30 s window. It is assumed that the new threshold is set to 0.3. If alpha power surpasses 0.3 twenty times, 20 points are then added to the points of the subject. It is also assumed that the second 30 s window is passed and the new threshold is set 0.1. If alpha power surpasses 0.1 twenty times, another 20 points are added to the points of the subject.The determined thresholds show that the subject could, in this way, be more successful in the first 30 s window as compared to the second 30 s window, whereas the obtained points and the received audio or visual feedback would be the same for both 30 s windows. Therefore, the subject does not receive a valid progress rate. In addition, while the second determined threshold is less than the first one, it is more probable for the subject to gain more points in the second 30 s window (as compared to the first 30 s window).

The scoring index has been determined regardless of the threshold in most of the previous studies. The subject's score was often increased by one point for each of the threshold values and scoring index was fixed. However, if scoring indexis determined according to the threshold value, the brain activity mirroring of the neurofeedback training efficiency is improved.

Mental fatigue can be caused by mental states such as sleeplessness, depression, stress, or repetitive tasks, leading to reduced performance [19]. Hence, it can influence the performance of subjects during NFT and demoralize them. Gruzelier et al. observed that performance of subjects falls over time during neurofeedback training [20]. However, most of the previous studies have been conducted in the field of neurofeedback regardless of mental fatigue monitoring during the training. Therefore, it is likely that mental fatigue detection during NFT improves its effectiveness. Taking this point into account, we suggest a new modified reward method.

In this article, a fuzzy neurofeedback training procedure (FNFT) is proposed through which the threshold and scoring index is adaptively determined according to the cortical activity of the subject. In this approach, when the training feature surpasses the threshold, the subject's score would increase according to his/her brain activity while the scoring index is calculated using a fuzzy technique. The sound intensity of audio feedback and the dimensions of video frame also vary according to the cortical activity of the individual. In addition, an EEG feature is also considered as the brain mental fatigue index for stopping the training as the subject becomes mentally fatigued.

Section snippets

Related works

Lee et al. have examined the effect of increased beta and decreased theta activity in C3 or C4 on the treatment of ADHD children. Participants were rewarded if they could keep beta levels above the threshold 20% of the treatment time, and keep theta levels below the threshold 70% of the time. The threshold was manually adjusted by the therapist depending on the participant’s performance [11]. Azarpaikan et al. studied the potential of neurofeedback training (SMR (12–15 Hz) increase and theta

EEG recording interface

A simulation based interface is designed for recording the EEG and neurofeedback training using the FlexCompinfiniti system (Thought Technology Ltd, serial number: A2068, Model: SA7550M, made in Canada). In the designed interface, a monitor is considered for the subject consisting of a video frame, some warning LEDs, and a scoreboard. Another monitor is also considered for therapist to select the training features, video clip, the sound of audio feedback, as well as to adjust the time of

The designed fuzzy NFT interface

Increase in the relatively low beta power (15–18 Hz) and the decrease in relative alpha power (8–12 Hz) protocol was selected for testing the proposed FNFT [30]. In this connection, the subjects with label A were trained to shift their cortical activity in a way that would allow them to be assigned to label B (with significantly higher beta wave activity and significantly lower alpha wave activity as compared to group A).

Accordingly, the relative low beta power and the ratio of alpha/beta

Discussion

A simulation based interface was designed for the NFT compatible with FlexComp infiniti system (Thought Technology Ltd). Matlab codes and functions can be called from the simulation based interface, suggesting that Matlab codes related to various EEG features can be run using the FNFT during training. Therefore, the proposed FNFT can be used for the training of subjects with various EEG features, not limited to the spectral features.

Previous investigations have made use of two various reward

Conclusion

A new fuzzy adaptive neurofeedback training procedure (FNFT) has been proposed in which the threshold was adaptively set considering the brain activity of the subject. Scoring index was adaptively set according to the brain activity of the subject. Therefore, subject could evaluate his/her progress more precisely as compared to the other traditional scoring method (fixed scoring index value). Both the audio and visual feedbacks were used to improve the effectiveness of NFT and increase the

Conflict of interest

The authors declare no conflicts of interest with respect to the research, authorship, and/or publication of this article.

Acknowledgment

The authors would like to thank the Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University for all its support.

References (30)

Cited by (15)

  • A new neurofeedback training method based on feature space clustering to control EEG features within target clusters

    2021, Journal of Neuroscience Methods
    Citation Excerpt :

    If a subject’s performance can be improved over a period of time, the next-time interval threshold can increase and the scoring process can become more difficult. Therefore, getting more points does not necessarily show the subject’s progress in this method and their success rates are not well notified (Hadavi and Sho’ouri, 2019; Sho'ouri, 2020; Shourie et al., 2018b). If a training procedure via NFB can be defined without defining the threshold, it is possible that the subject’s brain activity will be more accurately assessed.

  • Predicting the success rate of healthy participants in beta neurofeedback: Determining the factors affecting the success rate of individuals

    2021, Biomedical Signal Processing and Control
    Citation Excerpt :

    The subjects would be encouraged with visual and auditory feedback and their score would be increased if the beta power value was higher than the threshold. The scoring index was a decimal number in the range of (1–10), in each of which the number of points that had to be added to the total points of the subject for each success determined the dimensions of the screen display images related to visual feedback and audio feedback volume [49,56]. In addition, Katz’s fractal dimension as a mental fatigue index was considered so that training would be discontinued in case of the subject’s fatigue [18,49,56,71].

  • Soft boundary-based neurofeedback training based on fuzzy similarity measures: A method for learning how to control EEG Signal features during neurofeedback training

    2020, Journal of Neuroscience Methods
    Citation Excerpt :

    The decimal SI was also considered in the range between 1 and 10. At each time interval; the points added to each subject’s scores for each success, the dimensions of the visual display frame representing the visual feedback, and the intensity of the audio feedback sound were determined using the SI (Shourie et al., 2018a). In this study, EEG signals of 30 trials from seven trained subjects in the research study by Sho’ouri et al. were available.

View all citing articles on Scopus
View full text