Method, apparatus, device and storage medium for filtering out power frequency interference of brain waves

Abstract

The application discloses a method, device and equipment for filtering out power frequency interference of brain waves, and a storage medium, relates to the technical field of brain waves, and discloses a method for filtering out power frequency interference of brain waves, which comprises the following steps: collecting brain wave signals and performing pretreatment, wherein the pretreatment comprises removing noise, impedance correction and amplifying signals, and the signal-to-noise ratio of the brain wave signals is improved; extracting features of the pretreated brain wave signals, wherein the features comprise time domain features, frequency domain features, space-time features and nonlinear features, and the complexity and dynamics of brain activities are more comprehensively and accurately reflected; a linear phase harmonic filter is established according to the features, and the linear phase harmonic filter can be customized for the characteristics of the brain wave signals. The pretreated brain wave signals are filtered through the linear phase harmonic filter, interference components related to specific frequencies are effectively removed, useful components are retained, the quality of the signals is improved, and the accuracy of anesthesia depth monitoring is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of brain wave technology, and particularly relates to a method, device and equipment for filtering out power frequency interference of brain waves and a storage medium. BACKGROUND

[0002] Electroencephalogram is a method of recording brain activity using electrophysiological indicators. It records the changes in brain waves during brain activity, which is the overall reflection of the electrophysiological activity of brain nerve cells on the cerebral cortex or scalp surface. It has wide application value in the scene of monitoring anesthesia depth.

[0003] Brain wave signals contain rich information. By recording the rhythm and amplitude of brain electrical activity, the functional state of the brain can be reflected in real time, thereby providing anesthesiologists with objective information about the depth of anesthesia of patients. SUMMARY

[0004] The main purpose of the present application is to provide a method, device and equipment for filtering out power frequency interference of brain waves and a storage medium, aiming to solve the technical problem of poor filtering result of brain wave signals in the prior art, which leads to the decrease in accuracy of anesthesia depth monitoring.

[0005] To achieve the above-mentioned purpose, the present application provides a method for filtering out power frequency interference of brain waves, which comprises the following steps: collecting brain wave signals and performing pretreatment, wherein the pretreatment comprises removing noise, impedance correction and amplifying signals; extracting features of the pretreated brain wave signals, wherein the features comprise time domain features, frequency domain features, space-time features and nonlinear features; establishing a linear phase harmonic filter according to the features; and filtering the pretreated brain wave signals through the linear phase harmonic filter.

[0006] In an embodiment, the step of extracting features of the pretreated brain wave signals comprises the following steps: drawing a waveform of the pretreated brain wave signals; performing time domain analysis, frequency domain analysis, space-time analysis and nonlinear analysis on the pretreated brain wave signals based on the waveform, and obtaining analysis results; and performing feature selection and dimensionality reduction processing on the analysis results to screen out features of the pretreated brain wave signals.

[0007] In an embodiment, the step of establishing a linear phase harmonic filter according to the features comprises the following steps: obtaining the order, cutoff frequency, passband attenuation and transition bandwidth of the filter based on the features of the pretreated brain wave signals; and building a linear phase harmonic filter based on the order, cutoff frequency, passband attenuation and transition bandwidth of the filter.

[0008] In an embodiment, the step of building the linear phase harmonic filter based on the order, the cutoff frequency, the passband attenuation and the transition bandwidth further comprises: inputting a test signal through the linear phase harmonic filter to obtain a filtered test signal; evaluating the quality of the filtered test signal based on the test signal and the filtered test signal; determining whether the filtering result of the linear phase harmonic filter is qualified based on the quality of the filtered test signal; and determining that the linear phase harmonic filter is qualified if the filtering result of the linear phase harmonic filter is within a preset range.

[0009] In an embodiment, the step of determining that the linear phase harmonic filter is qualified if the filtering result of the linear phase harmonic filter is within a preset range further comprises: determining that the linear phase harmonic filter is unqualified if the filtering result of the linear phase harmonic filter is outside the preset range; and performing the step of obtaining the order, the cutoff frequency, the passband attenuation and the transition bandwidth of the filter based on the preprocessed electroencephalogram signal feature when the linear phase harmonic filter is unqualified.

[0010] In an embodiment, the step of filtering the preprocessed electroencephalogram signal through the linear phase harmonic filter further comprises: extracting an anesthesia depth feature from the filtered electroencephalogram signal; performing pattern recognition on the extracted anesthesia depth feature by using a machine learning or deep learning algorithm to determine the current anesthesia depth; and confirming the current anesthesia state of the patient based on the current anesthesia depth.

[0011] In addition, to achieve the above-mentioned purpose, the present application also proposes a device for filtering out power frequency interference of electroencephalogram, the device comprises: a collection module for collecting and preprocessing electroencephalogram signals; an identification module for extracting features of the preprocessed electroencephalogram signals; a filtering module for establishing a linear phase harmonic filter according to the features; and further for filtering the preprocessed electroencephalogram signals through the linear phase harmonic filter.

[0012] In addition, to achieve the above-mentioned purpose, the present application also proposes a device for filtering out power frequency interference of electroencephalogram, the device comprises: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program is configured to implement the steps of the method for filtering out power frequency interference of electroencephalogram as described above.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, the storage medium is a computer readable storage medium, and the storage medium stores a computer program, the computer program is executed by a processor to implement the steps of the method for filtering out power frequency interference of electroencephalogram as described above.

[0014] In addition, to achieve the above object, the present application also provides a computer program product, which comprises a computer program, and the computer program realizes the steps of the method for filtering out power frequency interference of brain waves when executed by a processor.

[0015] The one or more technical solutions provided by the present application have at least the following technical effects:

[0016] The pre-processing step improves the signal-to-noise ratio of the brain wave signal. On the basis of high-quality signals, multi-directional features are extracted to more comprehensively and accurately reflect the complexity and dynamics of brain activity. The linear phase harmonic filter established based on the extracted features can be customized for the characteristics of the brain wave signal, effectively removing interference components related to specific frequencies while retaining useful signal components. The filtering result is more optimal, thereby further improving the quality of the signal and the accuracy of anesthesia depth monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application, together with the description.

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative labor.

[0019] Figure 1 A flowchart is provided for the first embodiment of the method for filtering out power frequency interference of brain waves of the present application;

[0020] Figure 2 A flowchart is provided for a feasible implementation of establishing a linear phase harmonic filter based on the features for the first embodiment of the method for filtering out power frequency interference of brain waves of the present application;

[0021] Figure 3 A module structure diagram is provided for the device for filtering out power frequency interference of brain waves of the present application;

[0022] Figure 4 A device structure diagram is provided for the hardware operating environment involved in the method for filtering out power frequency interference of brain waves in the embodiments of the present application.

[0023] The object implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0024] It should be understood that the specific embodiments described herein are merely for the purpose of illustration of the technical solutions of the present application and are not used to limit the present application.

[0025] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the drawings of the specification and specific embodiments.

[0026] At present, in the application of electroencephalogram to anesthesia depth monitoring, the software technology for filtering out power frequency interference mainly includes the following methods: filter method, notch filter method, window function method, wavelet transform method, deep learning method, etc. The above methods face the problems of complexity of filter design and adjustment, instability of power frequency interference removal effect, high calculation cost and long time, insufficient real-time performance, and adverse effects of filter on useful signals, resulting in decreased accuracy of anesthesia depth monitoring.

[0027] The main solution of the embodiment of the present application is: collecting and preprocessing electroencephalogram signals, the preprocessing including removing noise, impedance correction and amplifying signals; extracting features of the preprocessed electroencephalogram signals, the features including time domain features, frequency domain features, space-time features and nonlinear features; establishing a linear phase harmonic filter according to the features; and filtering the preprocessed electroencephalogram signals through the linear phase harmonic filter.

[0028] The present application improves the signal-to-noise ratio of electroencephalogram signals through the preprocessing step. On the basis of high-quality signals, multi-directional features are extracted to more comprehensively and accurately reflect the complexity and dynamics of brain activity. The linear phase harmonic filter established based on the extracted features can be customized for the characteristics of electroencephalogram signals, effectively removing interference components related to specific frequencies while retaining useful signal components, resulting in better filtering results and further improving the quality of signals and the accuracy of anesthesia depth monitoring. The technical problem of poor electroencephalogram signal filtering results in the prior art, resulting in decreased accuracy of anesthesia depth monitoring, is solved.

[0029] It should be noted that the execution subject of the embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, etc.

[0030] Based on this, the embodiment of the present application provides a method for filtering out electroencephalogram power frequency interference, which is described in detail with reference to Figure 1 , Figure 1 The flowchart provided by the first embodiment of the method for filtering out electroencephalogram power frequency interference of the present application is shown in the figure.

[0031] In the embodiment, the method for filtering out electroencephalogram power frequency interference includes steps S10-S40:

[0032] Step S10, collecting and preprocessing the brain wave signal, the preprocessing including removing noise, impedance correction and amplifying the signal.

[0033] It should be noted that the brain wave signal contains rich information, through recording the rhythm and amplitude of brain electrical activity, the functional state of the brain can be reflected in real time. The collection of brain wave signal is usually collected by brain wave collection device. The brain wave collection device usually includes electrodes, amplifiers and recording devices, etc.

[0034] It can be understood that the electrodes are fixed on the scalp by electrode cap or electrode disc, wherein the standard position of the electrodes on the scalp can be consulted in international standards. At the same time, conductive gel is applied between the electrodes and the scalp to reduce the impedance between the electrodes and the scalp and improve the signal quality.

[0035] It can be understood that when collecting brain wave signal data, the electrical activity of the brain will be captured by the electrodes and transmitted to the amplifier for amplification and recording. During the collection process, the subject is required to remain as still as possible to reduce motion artifacts and avoid interference from other bioelectric signals such as electrooculogram, electromyogram and electrocardiogram.

[0036] It should be noted that preprocessing of brain wave signal data is a crucial step in data analysis, which directly affects the accuracy of subsequent signal processing, feature extraction and classification. The preprocessing includes amplifying the signal as described above, and usually includes removing noise, impedance correction, etc.

[0037] It can be understood that the removal of noise usually uses a band-pass filter or a notch filter for simple filtering to remove DC drift and high-frequency noise. The impedance correction is usually completed by ensuring that the impedance of all electrodes is below a certain threshold during data collection. If the data set contains impedance information and you find that the impedance of some electrodes is abnormally high, you may need to re-collect these data or perform interpolation processing.

[0038] It can be understood that by removing noise and impedance correction, the preprocessing step significantly improves the signal-to-noise ratio of the brain wave signal. The reduction of noise makes the subsequent analysis more accurate and reliable, avoiding misjudgment or error caused by noise interference. Impedance correction ensures the consistency and stability of the signal during the collection process, further improving the signal quality.

[0039] Step S20, extracting the features of the preprocessed brain wave signal, the features including time domain features, frequency domain features, space-time features and nonlinear features.

[0040] It can be understood that the characteristics of the brain wave signal generally include time domain characteristics (such as mean, standard deviation, amplitude, etc.), frequency domain characteristics (such as power spectral density, harmonic amplitude, etc.), space-time characteristics (signal characteristics of different spatial positions and different time periods), nonlinear characteristics (correlation analysis, complexity analysis). The purpose of feature extraction is to better analyze the information contained in the signal and provide a basis for subsequent filtering.

[0041] In order to accurately obtain the above characteristics, in a feasible implementation, the waveform of the preprocessed brain wave signal can be drawn; based on the waveform, time domain analysis, frequency domain analysis, space-time analysis and nonlinear analysis are performed on the preprocessed brain wave signal, and analysis results are obtained; the analysis results are subjected to feature selection and dimensionality reduction processing to screen out the preprocessed brain wave signal characteristics.

[0042] It should be noted that the waveform of the preprocessed brain wave signal can be obtained by a recording device. Based on the waveform, time domain characteristics such as amplitude, mean, variance, skewness, kurtosis, etc. statistical parameters can be directly extracted from the time domain waveform of the brain wave signal; the frequency domain characteristics mainly focus on the energy distribution of the brain wave signal at different frequencies, such as power spectral density, frequency band energy, etc. These features are usually obtained by frequency domain analysis methods such as Fourier transform.

[0043] It can be understood that the space-time characteristics combine the variation characteristics of the brain wave signal in space and time. Among them, the spatial distribution is the brain wave signal characteristics at different electrode positions, such as the correlation between electrodes, spatial patterns (such as topographic maps), etc. The time dynamics is the trend of the brain wave signal changing with time, such as the latency of event-related potential (ERP), waveform change, etc. The space-time pattern is a feature that combines spatial distribution and time dynamics, such as the dynamic connection pattern of brain network.

[0044] It can be understood that in the correlation analysis of nonlinear characteristics, the correlation between different channels or different time periods of the brain wave signal is analyzed to reveal the functional connection between brain regions; complexity analysis such as sample entropy, approximate entropy, fuzzy entropy, etc. is used to quantify the complexity and irregularity of the brain wave signal.

[0045] It should be noted that in actual application, feature extraction usually needs to be selected and optimized according to specific tasks and targets. For example, in the detection of epileptic seizures, the frequency domain characteristics (such as energy changes in specific frequency bands) and space-time characteristics (such as the propagation pattern of epileptic discharges) may be focused on; while in cognitive task analysis, more attention may be paid to time domain characteristics (such as the waveform characteristics of ERP) and nonlinear characteristics (such as the complexity of brain activity).

[0046] It is worth noting that feature extraction is followed by feature selection and dimensionality reduction to reduce redundancy and improve model performance. Common feature selection and dimensionality reduction methods include principal component analysis, linear discriminant analysis, independent component analysis, etc. Feature extraction is an iterative and optimization process that requires continuous trial and adjustment to find the most suitable feature set for the current task and data.

[0047] Step S30, a linear phase harmonic filter is established according to the features.

[0048] It is worth noting that the linear phase harmonic filter is a special filter whose phase response is proportional to frequency, that is, the phase delay increases linearly with the increase of frequency. This characteristic makes the relative time relationship of each frequency component remain unchanged after the signal passes through the filter, thereby avoiding signal distortion. The main task of this step is to determine the order, cutoff frequency, passband attenuation and transition bandwidth of the filter. These parameters need to consider the requirements of signal processing tasks, system performance indicators, cost and actual application environment, etc.

[0049] The main parameter determination method of the linear phase harmonic filter is as follows: the harmonic order (the order of the filter) determines the suppression ability of the filter to harmonic signals. The higher the order, the better the suppression effect of the filter to harmonic signals, but at the same time, it will also increase the complexity and cost of the filter.

[0050] The cutoff frequency is the cutoff boundary of the filter to high frequency signals. The selection of the cutoff frequency depends on the requirements of the signal processing task, for example, if it is necessary to retain the signal components of higher frequencies, a lower cutoff frequency can be selected; conversely, if it is necessary to eliminate higher frequency interference, a higher cutoff frequency can be selected.

[0051] The passband attenuation determines the degree of attenuation of the filter to signals in the passband. The passband attenuation is usually determined according to the requirements of the signal processing task and the system performance indicators.

[0052] The transition bandwidth is the width of the filter near the cutoff frequency to the other side of the cutoff frequency. The selection of the transition bandwidth will affect the frequency response characteristics of the filter. Generally, the narrower the transition bandwidth, the steeper the frequency response change of the filter, the stronger the suppression ability to harmonics and clutter; conversely, the wider the transition bandwidth, the more gentle the frequency response change of the filter, the weaker the suppression ability to harmonics and clutter. In the design, the appropriate transition bandwidth can be determined according to the actual application requirements and system performance indicators.

[0053] Further, please refer to Figure 2 , Figure 2A flowchart of a feasible implementation of the step of establishing a linear phase harmonic filter according to the characteristics is provided for the first embodiment of the method for filtering power frequency interference of brain waves of the present application. In a feasible implementation, the step of establishing a linear phase harmonic filter according to the characteristics includes A10 and A20:

[0054] Step A10, based on the pre-processed brain wave signal characteristics, the order of the filter, the cutoff frequency, the passband attenuation and the transition bandwidth are obtained. Step A20, based on the order of the filter, the cutoff frequency, the passband attenuation and the transition bandwidth, a linear phase harmonic filter is built.

[0055] It can be understood that, as described above, the values of the order of the filter, the cutoff frequency, the passband attenuation and the transition bandwidth are sequentially changed according to the extracted pre-processed brain wave signal characteristics, and the optimal parameters are determined to be input into the linear phase harmonic filter.

[0056] In a feasible implementation, step A20 is followed by steps A30 to A60:

[0057] Step A30, a test signal is input into the linear phase harmonic filter, and a filtered test signal is obtained.

[0058] It should be noted that the test signal can be an analog EEG signal or a signal with known characteristics, and the filtered test signal is obtained by inputting the linear phase harmonic filter, and it is observed whether the filtered signal meets the expectation.

[0059] Step A40, based on the test signal and the filtered test signal, the quality of the filtered test signal is evaluated. Step A50, based on the quality of the filtered test signal, it is judged whether the filtering result of the linear phase harmonic filter is qualified. Step A60, if the filtering result of the linear phase harmonic filter is within the preset range, the linear phase harmonic filter is determined to be qualified.

[0060] It can be understood that the evaluation of the quality of the filtered test signal is a comprehensive process, which involves the use of multiple evaluation indexes and methods. It includes how to evaluate the frequency response, signal-to-noise ratio, harmonic distortion and signal stability of the filter, and the signals before and after filtering are compared through visualization and statistical analysis. When the filtered test signal is not distorted, the frequency response, signal-to-noise ratio, harmonic distortion and signal stability are within the preset range, and the current linear phase harmonic filter is determined to be qualified and can be put into use.

[0061] It should be noted that the preset range described above is not a specific standard range. Specifically, the frequency response is a description of the attenuation characteristics of the filter for signals of different frequencies, and it needs to be observed whether the desired signal is attenuated; the signal-to-noise ratio is an index for measuring the noise content in the signal. Theoretically, the signal-to-noise ratio should be improved after filtering; the harmonic distortion usually refers to the appearance of the integer multiple frequency components of the original frequency in the signal; and the signal stability can be evaluated in various ways, including observing whether the statistical quantities such as the mean, variance, and standard deviation of the signal change significantly over time.

[0062] In a possible implementation, after step A60, steps A70 and A80 are further included:

[0063] In step A70, if the filtering result of the linear phase harmonic filter is outside the preset range, it is determined that the linear phase harmonic filter is unqualified. In step A80, when the linear phase harmonic filter is unqualified, the order, cutoff frequency, passband attenuation, and transition bandwidth of the filter are obtained based on the preprocessed electroencephalogram signal features.

[0064] It can be understood that, as described above, if the filtering result is outside the preset range, it means that the linear phase harmonic filter is unqualified, and the parameters need to be selected again to build the linear phase harmonic filter.

[0065] It should be noted that when the operator manually sets a specific standard range as the preset range, the parameters of the filter can be adjusted adaptively according to the signal characteristics and the preset range by monitoring the electroencephalogram signal in real time, so that the filter can better adapt to the filtering requirements in different scenarios.

[0066] In this embodiment, the linear phase harmonic filter established based on the extracted features is iteratively optimized, and can be customized for the characteristics of the electroencephalogram signal. The linear phase characteristic ensures that the signal phase is not distorted during the filtering process, which is crucial for maintaining the time characteristics and phase relationship of the signal. The harmonic filter can effectively remove the interference components related to specific frequencies while retaining useful signal components, thereby further improving the quality of the signal and the accuracy of the analysis.

[0067] The above is only one possible implementation of step S30 provided by the present embodiment, and the present embodiment does not specifically limit the specific implementation of step S30.

[0068] In step S40, the preprocessed electroencephalogram signal is filtered by the linear phase harmonic filter.

[0069] It can be understood that when a suitable linear phase harmonic filter is built, the pre-processed electroencephalogram signal can be filtered to obtain a more accurate and high-quality electroencephalogram signal.

[0070] The embodiment provides a method for filtering out power frequency interference of an electroencephalogram, and the signal-to-noise ratio of the electroencephalogram signal is improved through a preprocessing step. Based on the high-quality signal, multi-directional features are extracted to more comprehensively and accurately reflect the complexity and dynamics of brain activity. The linear phase harmonic filter established based on the extracted features can be customized for the characteristics of the electroencephalogram signal, effectively removing interference components related to specific frequencies while retaining useful signal components. The filtering result is more optimal, thereby further improving the quality of the signal and the accuracy of anesthesia depth monitoring.

[0071] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as the above-mentioned first embodiment can be referred to the above introduction, and the subsequent will not be repeated. An application mode in anesthesia depth monitoring based on the filtered electroencephalogram signal of the first embodiment is proposed.

[0072] Specifically, after step S40, it further includes: extracting anesthesia depth features from the filtered electroencephalogram signal; using a machine learning or deep learning algorithm to perform pattern recognition on the extracted anesthesia depth features to determine the current anesthesia depth; and based on the current anesthesia depth, confirming the current anesthesia state of the patient.

[0073] It should be noted that the anesthesia depth features are extracted from the filtered electroencephalogram signal, which can be segmented by time window first, and each segment of signal is standardized for subsequent analysis. Then the feature extraction as described in the above embodiment is performed, including time domain features, frequency domain features, spatiotemporal features, and nonlinear features, etc. These features can reflect the characteristics of the electroencephalogram signal.

[0074] It can be understood that the selection of anesthesia depth features needs to be based on physiological and clinical knowledge of anesthesia depth, and the most relevant and representative features are selected, which usually include frequency features (such as median frequency MF, spectral edge frequency SEF), nonlinear features (such as bispectrum index BIS), etc. Feature selection or dimensionality reduction techniques may be required to reduce redundancy and improve model efficiency.

[0075] It should be noted that the construction of a machine learning or deep learning model requires selecting a suitable machine learning algorithm (such as SVM, random forest, decision tree) or deep learning model (such as CNN, RNN, LSTM, Transformer, etc.) according to the characteristics of the data and the complexity of the problem. The labeled anesthesia depth data (such as BIS value or other clinical evaluation criteria) is used to train the model, and the performance of the model is evaluated by cross-validation and other methods. The model parameters are adjusted by grid search, random search or Bayesian optimization to optimize the performance of the model.

[0076] It should be noted that the anesthesia depth judgment and state confirmation is achieved by deploying the trained model to a real-time system, processing the new brain wave signals in real time, and predicting the current anesthesia depth. Then, according to the predicted anesthesia depth, combined with clinical standards and doctor's experience, the anesthesia state of the patient (such as awake, light anesthesia, deep anesthesia, etc.) is confirmed. Finally, according to the real-time feedback of the anesthesia state, the dose and speed of the anesthetic drug are adjusted in time to ensure the safety and comfort of the patient.

[0077] It can be understood that the accuracy and reliability of the model are evaluated through clinical experiments and data analysis, and the feature extraction method, model structure and parameter setting are continuously optimized according to feedback and new research results to improve the overall performance of the system.

[0078] In this embodiment, by using machine learning or deep learning algorithm to recognize the extracted anesthesia depth features, combined with the filtering method of embodiment one, the accuracy of anesthesia depth monitoring is improved.

[0079] It should be noted that the above examples are only for understanding the present application and do not constitute a limitation on the method for filtering out the power frequency interference of brain waves of the present application. More forms of simple transformation based on this technical concept are within the protection scope of the present application.

[0080] The present application also provides a device for filtering out the power frequency interference of brain waves, please refer to Figure 3 The device for filtering out the power frequency interference of brain waves comprises: a collection module 10 for collecting brain wave signals and preprocessing; an identification module 20 for extracting features of the preprocessed brain wave signals; a filtering module 30 for establishing a linear phase harmonic filter according to the features; and further for filtering the preprocessed brain wave signals through the linear phase harmonic filter.

[0081] The device for filtering out power frequency interference of brain waves provided in the application adopts the method for filtering out power frequency interference of brain waves in the above embodiment, and can solve the technical problem of poor filtering result of brain wave signals in the prior art, which leads to the decrease of accuracy of anesthesia depth monitoring. Compared with the prior art, the device for filtering out power frequency interference of brain waves provided in the application has the same beneficial effects as the method for filtering out power frequency interference of brain waves provided in the above embodiment, and other technical features of the device for filtering out power frequency interference of brain waves are the same as the features disclosed in the above embodiment, which will not be repeated here.

[0082] The application provides a device for filtering out power frequency interference of brain waves, which comprises at least one processor and a memory connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method for filtering out power frequency interference of brain waves in the above embodiment one.

[0083] Reference will be made to the following description of the drawings Figure 4 which shows a structural schematic diagram of the device for filtering out power frequency interference of brain waves suitable for implementing the embodiments of the application. The device for filtering out power frequency interference of brain waves in the embodiments of the application can include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description), PMPs (Portable MediaPlayer), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 4 The device for filtering out power frequency interference of brain waves shown is only an example, and should not bring any limitation to the functions and use range of the embodiments of the application.

[0084] As Figure 4As shown, the device for filtering out power frequency interference of brain waves can include a processing device 1001 (for example, a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 to a random access memory (RAM) 1004. In the RAM 1004, various programs and data required for the operation of the device for filtering out power frequency interference of brain waves are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the device for filtering out power frequency interference of brain waves to communicate with other devices wirelessly or by wire to exchange data. Although the device for filtering out power frequency interference of brain waves with various systems is shown in the figure, it should be understood that all the systems shown are not required to be implemented or possessed. More or fewer systems can be alternatively implemented or possessed.

[0085] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program codes for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are executed.

[0086] The device for filtering out power frequency interference of brain waves provided in the present application adopts the method for filtering out power frequency interference of brain waves in the above-mentioned embodiments, and can solve the technical problem of poor filtering result of brain wave signals in the prior art, which leads to the decrease in accuracy of anesthesia depth monitoring. Compared with the prior art, the device for filtering out power frequency interference of brain waves provided in the present application has the same beneficial effects as the method for filtering out power frequency interference of brain waves provided in the above-mentioned embodiments, and other technical features in the device for filtering out power frequency interference of brain waves are the same as the features disclosed in the previous embodiment method, which will not be described here.

[0087] It should be understood that various aspects disclosed herein can be implemented in hardware, software, firmware, or any combination thereof. Various aspects disclosed herein can be implemented in any of the above described embodiments or examples, and combinations thereof. While various aspects of the present disclosure can be embodied in many different forms, the specific aspects described herein are shown and described by way of example only.

[0088] The above description is provided as an enabling teaching of the application. It is to be understood that the application is not limited to the specific details described herein. Any person skilled in the art would understand that the application could be implemented in other ways without departing from the spirit or the scope of the application. The described embodiments are to be considered in a descriptive sense only and not for purposes of limitation. Therefore, the scope of the application is defined not by the detailed description, but by the appended claims.

[0089] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e., computer program) for performing the method for filtering out power frequency interference of brain waves in the above-described embodiments.

[0090] The computer readable storage medium provided by the present application may, for example, be a U disk, but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more conductive wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present embodiment, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer readable storage medium can be transmitted in any suitable medium, including but not limited to electrical wire, optical cable, RF (Radio Frequency), etc., or any suitable combination thereof.

[0091] The above computer readable storage medium can be included in the device for filtering out power frequency interference of brain waves; or can exist separately without being assembled into the device for filtering out power frequency interference of brain waves.

[0092] The computer readable storage medium described above carries one or more programs, when the one or more programs are executed by the device for filtering power interference of brain waves, the device for filtering power interference of brain waves is caused to: collect brain wave signals and perform preprocessing, the preprocessing includes removing noise, impedance correction and amplifying signals; extract features of the preprocessed brain wave signals, the features include time domain features, frequency domain features, space-time features and nonlinear features; establish a linear phase harmonic filter according to the features; filter the preprocessed brain wave signals through the linear phase harmonic filter.

[0093] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0094] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a procedure, or a part of code, which comprises one or more executable instructions for implementing the specified functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in some cases, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations of blocks in the block diagrams and / or flow diagrams, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0095] The modules described in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the module itself.

[0096] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e., a computer program) for executing the method for filtering out power frequency interference of brain waves. The technical problem of poor filtering result of brain wave signal in the prior art, which leads to the decrease of accuracy of anesthesia depth monitoring, can be solved. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the method for filtering out power frequency interference of brain waves provided by the above embodiments, which will not be repeated here.

[0097] The present application also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for filtering out power frequency interference of brain waves as described above.

[0098] The computer program product provided by the present application can solve the technical problem of poor filtering result of brain wave signal in the prior art, which leads to the decrease of accuracy of anesthesia depth monitoring. Compared with the prior art, the computer program product provided by the present application has the same beneficial effects as the method for filtering out power frequency interference of brain waves provided by the above embodiments, which will not be repeated here.

[0099] The above only describes some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation, direct / indirect application in other related technical fields based on the technical concept of the present application, and the content of the specification and drawings are included in the patent protection scope of the present application.

Claims

1. A method for filtering out power frequency interference of brain waves, characterized by, The method comprises: Collecting and preprocessing electroencephalogram signals, the preprocessing including removing noise, impedance correction and amplifying signals; Extracting features of the preprocessed electroencephalogram signals, the features including time domain features, frequency domain features, time-space features and nonlinear features; Establishing a linear phase harmonic filter according to the features; Filtering the preprocessed electroencephalogram signals through the linear phase harmonic filter; The step of extracting features of the preprocessed electroencephalogram signals comprises: Plotting waveforms of the preprocessed electroencephalogram signals; Based on the waveforms, performing time domain analysis, frequency domain analysis, time-space analysis and nonlinear analysis on the preprocessed electroencephalogram signals, and obtaining analysis results; Performing feature selection and dimensionality reduction processing on the analysis results to screen out features of the preprocessed electroencephalogram signals; The step of establishing a linear phase harmonic filter according to the features comprises: Based on the features of the preprocessed electroencephalogram signals, obtaining the order, cutoff frequency, passband attenuation and transition bandwidth of the filter; Based on the order, cutoff frequency, passband attenuation and transition bandwidth of the filter, building a linear phase harmonic filter.

2. The method of claim 1, wherein, The step of building a linear phase harmonic filter based on the order, cutoff frequency, passband attenuation and transition bandwidth of the filter further comprises: Inputting a test signal through the linear phase harmonic filter to obtain a filtered test signal; Based on the test signal and the filtered test signal, evaluating the quality of the filtered test signal; Based on the quality of the filtered test signal, determining whether the filtering result of the linear phase harmonic filter is qualified; If the filtering result of the linear phase harmonic filter is within a preset range, the linear phase harmonic filter is determined to be qualified.

3. The method of claim 2, wherein, The step of determining that the linear phase harmonic filter is qualified if the filtering result of the linear phase harmonic filter is within a preset range further comprises: If the filtering result of the linear phase harmonic filter is outside the preset range, the linear phase harmonic filter is determined to be unqualified; When the linear phase harmonic filter is unqualified, the step of obtaining the order, cutoff frequency, passband attenuation and transition bandwidth of the filter based on the features of the preprocessed electroencephalogram signals is performed.

4. The method of claim 1, wherein, The step of filtering the preprocessed electroencephalogram signals through the linear phase harmonic filter further comprises: Extracting anesthesia depth features from the filtered electroencephalogram signals; Using a machine learning or deep learning algorithm to perform pattern recognition on the extracted anesthesia depth features to determine the current anesthesia depth; Based on the current anesthesia depth, confirming the current anesthesia state of the patient.

5. A device for filtering out power frequency interference of brain waves, characterized by comprising: The device comprises: A collection module for collecting and preprocessing electroencephalogram signals; An identification module for extracting features of the preprocessed electroencephalogram signals; A filtering module for establishing a linear phase harmonic filter according to the features, and further for filtering the preprocessed electroencephalogram signals through the linear phase harmonic filter. The identification module is further configured to draw a waveform of the preprocessed brain wave signal, perform time domain analysis, frequency domain analysis, time-space analysis and nonlinear analysis on the preprocessed brain wave signal based on the waveform, and obtain analysis results; and perform feature selection and dimension reduction processing on the analysis results to screen out preprocessed brain wave signal features. The filtering module is further configured to obtain an order, a cutoff frequency, a passband attenuation and a transition bandwidth of a filter based on the preprocessed brain wave signal features, and build a linear phase harmonic filter based on the order, the cutoff frequency, the passband attenuation and the transition bandwidth of the filter.

6. A device for filtering out power frequency interference of brain waves, characterized by, The device comprises a memory, a processor and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the method for filtering out power frequency interference of brain waves according to any one of claims 1 to 4.

7. A storage medium, characterized by The storage medium is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the method for filtering out power frequency interference of brain waves according to any one of claims 1 to 4.

8. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program is executed by the processor to implement the steps of the method for filtering out power frequency interference of brain waves according to any one of claims 1 to 4.

Images