A Survey on EEG Signal Processing Techniques and Machine Learning: Applications to the Neurofeedback of Autobiographical Memory Deficits in Schizophrenia

Abstract

In this paper, a general overview regarding neural recording, classical signal processing techniques and machine learning classification algorithms applied to monitor brain activity is presented. Currently, several approaches classified as electrical, magnetic, neuroimaging recordings and brain stimulations are available to obtain neural activity of the human brain. Among them, non-invasive methods like electroencephalography (EEG) are commonly employed, as they can provide a high degree of temporal resolution (on the order of milliseconds) and acceptable space resolution. In addition, it is simple, quick, and does not create any physical harm or stress to patients. Concerning signal processing, once the neural signals are acquired, different procedures can be applied for feature extraction. In particular, brain signals are normally processed in time, frequency, and/or space domains. The features extracted are then used for signal classification depending on its characteristics such us the mean, variance or band power. The role of machine learning in this regard has become of key importance during the last years due to its high capacity to analyze complex amounts of data. The algorithms employed are generally classified in supervised, unsupervised and reinforcement techniques. A deep review of the most used machine learning algorithms and the advantages/drawbacks of most used methods is presented. Finally, a study of these procedures utilized in a very specific and novel research field of electroencephalography, i.e., autobiographical memory deficits in schizophrenia, is outlined.

Evaluation of Machine Learning Algorithms for Classification of EEG Signals

“…With F1-Score, one can represent both concerns with a single score [86]. Once Accuracy and Recall for a binary or multiclass classification task have been computed, the two scores may be combined to calculate the F1-Score metric; it can be calculated by (13):…”

“…The frequency ranges span from 0 Hz to 100 Hz. Based on these ranges, the signals are classified as follows: delta, which ranges from 0 Hz to 4 Hz; theta, which contains signals from 4 Hz to 7 Hz; alpha, where the information range is between 8 Hz and 12 Hz; beta, where the range is between 12 Hz and 30 Hz; and gamma, with a range that covers from 30 Hz to 100 Hz [12,13]. Different ranges of signals are essential for identifying different clinical problems, such as schizophrenia [14], Alzheimer's, insomnia, epileptic disorders, brain tumors, and different injuries and infections related to the central nervous system.…”

Accurate neural network classification model for schizophrenia disease based on electroencephalogram data

“…EEGs offers an effective means of evaluating brain function, remaining an essential tool in neurology, particularly in serious neurological conditions. Besides, it can be employed with relative low damage to patients due to its non-invasive nature [12][13][14][15]. Although the EEG does not precisely determine the etiology of the brain disfunction, the subsequent processing of the data recoded by the electrodes can be very helpful to make diagnostics.…”

“…By these means, different brain diseases, including schizophrenia, have been successfully identi ed compared with healthy controls by examining the neuronal activity of the brain. Generally, machine learning is classi ed in supervised learning, unsupervised learning, deep learning, and reinforcement learning [13,20], but during the last years, methods based on deep learning employed for classi cation have increased signi cantly due to its interesting properties. For instance, deep learning systems can create new features from datasets without human intervention, it is able to work with unstructured data or allows to develop e cient models at learning complex features due to the use of multiple hidden layers.…”

Improved Neurocognitive Classification by Means of Deep Learning Algorithms through Electroencephalograms

“…In this regard, the use of electrophysiological activity can provide important information for the clinical diagnosis of patients. The measured electroencephalogram (EEG) signals appear to be very useful for the identification of brain rhythms, diagnosis of brain disorders, detection of brain impairments, and consequently the possibility to provide precise treatment to correct or improve certain brain-health conditions [2]- [5].…”