阅读说明：本技术 一种信号处理方法及装置 (Signal processing method and device ) 是由 张春会 于 2019-09-30 设计创作，主要内容包括：本发明提供了一种信号处理方法及装置,涉及信号技术领域。其中,该方法包括：获取脑电信号集,包括原始自发脑电信号和原始诱发脑电信号；对原始自发脑电信号进行第一去噪处理,得到第一自发脑电信号,对原始诱发脑电信号进行第二去噪处理,得到第一诱发脑电信号；提取表征第一自发脑电信号的动力学非线性特征的第一特征,提取表征第一诱发脑电信号的受激影响程度的第二特征；将第一特征和第二特征输入预设脑电分类模型,得到脑电信号集所属的目标脑电信号类别。在本发明中,可以从不同刺激场景下的脑电信号中均提取特征,增加了脑电信号的模态和特征维度,进而可根据多模态脑电信号中提取的多维度特征进行分类,提高了脑电信号分类的准确性。(The invention provides a signal processing method and device, and relates to the technical field of signals. Wherein, the method comprises the following steps: acquiring an electroencephalogram signal set comprising an original spontaneous electroencephalogram signal and an original induced electroencephalogram signal; carrying out first denoising processing on the original spontaneous electroencephalogram signals to obtain first spontaneous electroencephalogram signals, and carrying out second denoising processing on the original evoked electroencephalogram signals to obtain first evoked electroencephalogram signals; extracting a first characteristic representing a dynamic nonlinear characteristic of the first spontaneous electroencephalogram signal and a second characteristic representing the stimulated influence degree of the first evoked electroencephalogram signal; and inputting the first characteristic and the second characteristic into a preset electroencephalogram classification model to obtain the target electroencephalogram signal category to which the electroencephalogram signal set belongs. According to the method and the device, the characteristics can be extracted from the electroencephalogram signals under different stimulation scenes, the modes and the characteristic dimensions of the electroencephalogram signals are increased, classification can be performed according to the multi-dimensional characteristics extracted from the multi-mode electroencephalogram signals, and the classification accuracy of the electroencephalogram signals is improved.)

1. A method of signal processing, the method comprising:

acquiring an electroencephalogram signal set; the electroencephalogram signal set comprises original spontaneous electroencephalogram signals and original induced electroencephalogram signals;

carrying out first denoising processing on the original spontaneous electroencephalogram signal to obtain a first spontaneous electroencephalogram signal, and carrying out second denoising processing on the original evoked electroencephalogram signal to obtain a first evoked electroencephalogram signal;

extracting a first feature of the first spontaneous electroencephalogram signal, and extracting a second feature of the first evoked electroencephalogram signal; the first characteristic is used for representing a dynamic nonlinear characteristic of the first spontaneous electroencephalogram signal; the second characteristic is used for representing the stimulated influence degree of the first induced electroencephalogram signal;

and inputting the first characteristic and the second characteristic into a preset electroencephalogram classification model to obtain the target electroencephalogram signal category to which the electroencephalogram signal set belongs.

2. The method of claim 1, wherein said second denoising said raw evoked brain signal to obtain a first evoked brain signal comprises:

removing interference signals from the original induced electroencephalogram signals to obtain second induced electroencephalogram signals;

and removing the first spontaneous electroencephalogram signal from the second evoked electroencephalogram signal to obtain a first evoked electroencephalogram signal.

3. The method of claim 2, wherein the interference signal comprises at least one of a power frequency interference signal, an electro-oculogram interference signal, an electromyogram interference signal, and a baseline wander interference signal.

4. The method of claim 1, wherein the first feature comprises at least one of a complexity, an approximate entropy, and a wavelet entropy of the first spontaneous brain electrical signal; the second characteristic includes at least one of a P300 latency and a P300 waveform peak of the first evoked brain electrical signal.

5. The method of claim 1, wherein the preset brain electrical classification model comprises a random forest classification model, a decision tree classification model, or a support vector machine classification model.

6. A signal processing apparatus, characterized in that the apparatus comprises:

the acquisition module is used for acquiring an electroencephalogram signal set; the electroencephalogram signal set comprises original spontaneous electroencephalogram signals and original induced electroencephalogram signals;

the de-noising module is used for carrying out first de-noising processing on the original spontaneous electroencephalogram signal to obtain a first spontaneous electroencephalogram signal and carrying out second de-noising processing on the original evoked electroencephalogram signal to obtain a first evoked electroencephalogram signal;

the extraction module is used for extracting a first feature of the first spontaneous electroencephalogram signal and extracting a second feature of the first evoked electroencephalogram signal; the first characteristic is used for representing a dynamic nonlinear characteristic of the first spontaneous electroencephalogram signal; the second characteristic is used for representing the stimulated influence degree of the first induced electroencephalogram signal;

and the classification module is used for inputting the first characteristic and the second characteristic into a preset electroencephalogram classification model to obtain a target electroencephalogram category to which the electroencephalogram signal set belongs.

7. The apparatus of claim 6, wherein the denoising module comprises:

the first removing submodule is used for removing interference signals from the original induced electroencephalogram signals to obtain second induced electroencephalogram signals;

and the second removing submodule is used for removing the first spontaneous electroencephalogram signal from the second induced electroencephalogram signal to obtain a first induced electroencephalogram signal.

8. The apparatus of claim 6, in which the first feature comprises at least one of a complexity, an approximate entropy, and a wavelet entropy of the first spontaneous brain electrical signal; the second characteristic includes at least one of a P300 latency and a P300 waveform peak of the first evoked brain electrical signal.

9. An electronic device, comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the signal processing method according to any one of claims 1 to 5.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the signal processing method according to any one of claims 1 to 5.

Technical Field

The present invention relates to the field of signal technology, and in particular, to a signal processing method and apparatus.

Background

In recent years, with the development of signal technology, the application field of signal technology is becoming wider and wider, for example, in the medical field, medical signal data such as electroencephalogram signals and electrocardiosignals can be processed, and the obtained processing result can assist clinical analysis.

At present, people pay more and more attention to early intervention of diseases, such as mild cognitive dysfunction, which is a state between normal old people and Alzheimer's disease (also called senile dementia), and researches show that the probability of the mild cognitive dysfunction patients developing senile dementia is dozens of times higher than that of the normal old people, and the early intervention on the mild cognitive dysfunction can greatly help to treat the senile dementia. The electroencephalogram signal is an index which can generate response to event stimulation, and has important significance for early intervention of mild cognitive dysfunction, so that people pay attention to how to process the electroencephalogram signal to obtain some important body information.

In the related technology, the common electroencephalogram signal processing process generally only extracts a plurality of common potential parameters, and the processing result is single, so that the requirements of more data analysis cannot be met.

Disclosure of Invention

The invention provides a signal processing method and a signal processing device, which are used for solving the problems that the existing electroencephalogram signal processing result is single and more data analysis requirements cannot be met.

In order to solve the above problem, the present invention discloses a signal processing method, comprising:

acquiring an electroencephalogram signal set; the electroencephalogram signal set comprises original spontaneous electroencephalogram signals and original induced electroencephalogram signals;

carrying out first denoising processing on the original spontaneous electroencephalogram signal to obtain a first spontaneous electroencephalogram signal, and carrying out second denoising processing on the original evoked electroencephalogram signal to obtain a first evoked electroencephalogram signal;

extracting a first feature of the first spontaneous electroencephalogram signal, and extracting a second feature of the first evoked electroencephalogram signal; the first characteristic is used for representing a dynamic nonlinear characteristic of the first spontaneous electroencephalogram signal; the second characteristic is used for representing the stimulated influence degree of the first induced electroencephalogram signal;

and inputting the first characteristic and the second characteristic into a preset electroencephalogram classification model to obtain the target electroencephalogram signal category to which the electroencephalogram signal set belongs.

Optionally, the performing a second denoising process on the original evoked brain electrical signal to obtain a first evoked brain electrical signal includes:

removing interference signals from the original induced electroencephalogram signals to obtain second induced electroencephalogram signals;

and removing the first spontaneous electroencephalogram signal from the second evoked electroencephalogram signal to obtain a first evoked electroencephalogram signal.

Optionally, the interference signal includes at least one of a power frequency interference signal, an electro-oculogram interference signal, an electromyogram interference signal, and a baseline wander interference signal.

Optionally, the first feature comprises at least one of a complexity, approximate entropy, and wavelet entropy of the first spontaneous brain electrical signal; the second characteristic includes at least one of a P300 latency and a P300 waveform peak of the first evoked brain electrical signal.

Optionally, the preset electroencephalogram classification model includes a random forest classification model, a decision tree classification model or a support vector machine classification model.

In order to solve the above problem, the present invention also discloses a signal processing apparatus, comprising:

the acquisition module is used for acquiring an electroencephalogram signal set; the electroencephalogram signal set comprises original spontaneous electroencephalogram signals and original induced electroencephalogram signals;

the de-noising module is used for carrying out first de-noising processing on the original spontaneous electroencephalogram signal to obtain a first spontaneous electroencephalogram signal and carrying out second de-noising processing on the original evoked electroencephalogram signal to obtain a first evoked electroencephalogram signal;

the extraction module is used for extracting a first feature of the first spontaneous electroencephalogram signal and extracting a second feature of the first evoked electroencephalogram signal; the first characteristic is used for representing a dynamic nonlinear characteristic of the first spontaneous electroencephalogram signal; the second characteristic is used for representing the stimulated influence degree of the first induced electroencephalogram signal;

and the classification module is used for inputting the first characteristic and the second characteristic into a preset electroencephalogram classification model to obtain a target electroencephalogram category to which the electroencephalogram signal set belongs.

Optionally, the denoising module includes:

the first removing submodule is used for removing interference signals from the original induced electroencephalogram signals to obtain second induced electroencephalogram signals;

and the second removing submodule is used for removing the first spontaneous electroencephalogram signal from the second induced electroencephalogram signal to obtain a first induced electroencephalogram signal.

Optionally, the first feature comprises at least one of a complexity, approximate entropy, and wavelet entropy of the first spontaneous brain electrical signal; the second characteristic includes at least one of a P300 latency and a P300 waveform peak of the first evoked brain electrical signal.

In order to solve the above problem, the present invention also discloses an electronic device, which includes a processor, a memory, and a computer program stored on the memory and operable on the processor, wherein the computer program, when executed by the processor, implements the steps of the signal processing method described above.

In order to solve the above problem, the present invention also discloses a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the above signal processing method.

Compared with the prior art, the invention has the following advantages:

in the embodiment of the invention, the signal processing device can firstly obtain an electroencephalogram signal set, the electroencephalogram signal set comprises an original spontaneous electroencephalogram signal and an original induced electroencephalogram signal, then can perform first denoising processing on the original spontaneous electroencephalogram signal to obtain a first spontaneous electroencephalogram signal, and perform second denoising processing on the original induced electroencephalogram signal to obtain a first induced electroencephalogram signal, then can extract a first characteristic used for representing a dynamic nonlinear characteristic from the first spontaneous electroencephalogram signal, and extract a second characteristic used for representing a stimulated influence degree from the first induced electroencephalogram signal, namely can perform characteristic extraction from electroencephalograms under different stimulation scenes, thereby increasing the mode and characteristic dimensions of the electroencephalogram signal, and further can input multi-dimensional characteristics extracted from multi-mode electroencephalograms into a preset electroencephalogram classification model, and obtaining the target electroencephalogram signal category to which the electroencephalogram signal set belongs, so that the accuracy of electroencephalogram signal classification is improved.

Drawings

Fig. 1 is a flow chart of a signal processing method according to a first embodiment of the present invention;

FIG. 2 is a schematic diagram showing a graphical display of a delay matching sample paradigm test according to a first embodiment of the present invention;

FIG. 3 is a schematic diagram showing the electrode placement of a 19-lead electroencephalogram acquisition device according to a first embodiment of the present invention;

fig. 4 is a block diagram showing a signal processing apparatus according to a second embodiment of the present invention.

Detailed Description

In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.