In this paper, the method of predicting the treatability of patients suffering from hyperactivity with neurofeedback training with the help of extracting the frequency band of the electroencephalogram (EEG) signal and using the brain-functional communication evaluation
More
In this paper, the method of predicting the treatability of patients suffering from hyperactivity with neurofeedback training with the help of extracting the frequency band of the electroencephalogram (EEG) signal and using the brain-functional communication evaluation criterion is done to determine the person's treatability before starting the neurofeedback treatment. This algorithm consists of six steps: In the first step, a data set of EEG signal recording during neurofeedback stimulation from 60 students in the age group of 7 to 14 years (regardless of gender) with hyperactivity in two treatable and non-treatable classes was obtained from the Mendelian database. In the second step, primary filtering has been done to reduce the noise of the data set using a pre-processing block. In the third step, the frequency distribution of the alpha and beta bands is extracted from the noise reduction signals. In this type of data, the difference in the EEG components of each group can be expressed by measuring brain-functional communication and using the phase lock index (PLI), which is used to detect the existence of a connection between the brain lobes involved once using the probability value index. In the t-test statistical test and to increase the accu­ra­c­y, the genetic algorithm was used to identify the effective electrodes in the treatment. So, the fourth step is to extract the feature, which is to measure the amount of brain communication in the brain signal recording electrodes. In the fifth step, it is to reduce the feature space, the results show show that the lobes involved during neurofeedback stimulation are the frontal and central lobes, and among the 32 EEG recording channels, only the data of 6 channels C3, FZ, F4, CZ, C4, and F3 show a significant difference in the amount of brain communication during stimulation. and finally, in the sixth step, by using different classifications, the output of the combination of classifications was the label of one of two classes, treatable or non-treatable. In this proposed method, the correctness cri­te­rion is used to express the research result, and finally the percentage of correctness obtained is 90.6%.
Manuscript profile