Frequency domain feature extracting algorithm applied to single-lead portable brainwave equipment

Abstract

The invention relates to the field of brainwave signal processing, in particular to a frequency domain feature extracting algorithm applied to single-lead portable brainwave equipment. The algorithm is applicable feature extraction of the single-lead portable brainwave equipment and capable of reflecting cognition states. The algorithm includes: preprocessing, and feature expressing, extracting and indexation indicating. The algorithm outputs an alertness level index and a nervousness level index. The alertness level index: S1(t)=c(t) / a(t), wherein t refers to time, and a and c respectively refer to the energy of alpha and theta; the nervousness level index: S2(t)=b()t*c(t), wherein t refers to time, and b and c respectively refer to the energy of beta and theta. Compared with judgments totally depending on experiences and subjectivity in the prior art, the algorithm has the advantages that the mental state of a testee can be judged scientifically and objectively, the multi-index synergy degree indexes reflecting the optimal working states can be further extracted, and whether brain activity states is suitable for work or not can be comprehensively expressed.

Description

[0001] technical field [0002] The invention relates to the field of EEG signal processing, in particular to a frequency-domain feature extraction algorithm applied to single-lead portable EEG equipment, which is suitable for feature extraction of single-lead portable EEG equipment and reflects the state of cognition. [0003] Background technique [0004] Scalp EEG signals are derived from human brain nerve activity. There are many components in EEG signals that can reflect a person's mental state, including attention or fatigue, and can reflect the subject's mental state in a real-time, dynamic, and direct manner. In many occasions, it is of great significance to know whether the subject is in the awakened state, especially the two scientific indicators that are sensitive to reflect the degree of alertness and tension. Single-lead portable EEG devices can better promote the application of mental state decoding based on EEG signals. Compared with multi-lead EEG equipment...

AI Technical Summary

Problems solved by technology

However, since EEG is a very weak electrical signal (microvolt level), single-lead EEG generally uses dry electrodes, and there is no coupling medium to reduce the admiration resistance, and a large amount of interference noise is introduced in the recording in the actual environment. Signal processing and feature extraction algorithms have high requirements, requiring special denoising and feature extraction algorithms

The denoising and feature extraction algorithms are specially proposed for single-lead, dry-electrode portable EEG equipment, and are applicable to the indicators used in real life or work. No literature or patent reports have been consulted.

Images