The study of neuronal activity with low frequency has shown an increasing interest for its greater stability and reliability recent years. One challenge in analyzing this kind of activity is to find similarities and differences between signals efficiently and effectively. The traditional analysis methods, such as short-time Fourier transform, are easily obscured by background noises and often involve a large number of parameters. Therefore, this paper introduces a novel time-frequency analysis method based on wavelet transformation and half-ellipsoid modeling to extract instantaneous frequency and instantaneous phase information. This method overcomes some shortcomings of conventional time-frequency analysis. In this method, wavelet transformation is used to provide high-level representations of raw signals, and parsimonious half-ellipsoid models are used to extract changes in time domain and frequency domain of neural recordings. The method was validated to local field potentials (LFPs) of olfactory bulb of anesthetized rats during three different odor stimuli. The results suggested that this method could detect odor-relevant features from olfactory signals with large variability. The Odors then were classified with support vector machine (SVM) algorithm and the classification accuracy reached 79.4%.
Algorithms ; Animals ; Evoked Potentials ; Fourier Analysis ; Odorants ; analysis ; Olfactory Bulb ; physiology ; Rats ; Reproducibility of Results ; Smell ; physiology ; Support Vector Machine ; Wavelet Analysis

Brain signals refer to electrical signals or metabolic changes that occur as a consequence of brain cell activity.Among the various non-invasive measurement methods,electroencephalogram(EEG)stands out as a widely employed technique,providing valuable insights into brain patterns.The deviations observed in EEG reading serve as indicators of abnormal brain activity,which is associated with neurological diseases.Brain?computer interface(BCI)systems enable the direct extraction and transmission of information from the human brain,facilitating interaction with external devices.Notably,the emergence of artificial intelligence(AI)has had a profound impact on the enhancement of precision and accuracy in BCI technology,thereby broadening the scope of research in this field.AI techniques,encompassing machine learning(ML)and deep learning(DL)models,have demonstrated remarkable success in classifying and predicting various brain diseases.This comprehensive review investigates the application of AI in EEG-based brain disease diagnosis,highlighting advancements in AI algorithms.