CN117894491B - Physiological monitoring data processing method for assessing mental activities - Google Patents
Physiological monitoring data processing method for assessing mental activities Download PDFInfo
- Publication number
- CN117894491B CN117894491B CN202410296374.6A CN202410296374A CN117894491B CN 117894491 B CN117894491 B CN 117894491B CN 202410296374 A CN202410296374 A CN 202410296374A CN 117894491 B CN117894491 B CN 117894491B
- Authority
- CN
- China
- Prior art keywords
- data
- target component
- value
- component signals
- values
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003340 mental effect Effects 0.000 title claims abstract description 80
- 238000012544 monitoring process Methods 0.000 title claims abstract description 28
- 238000003672 processing method Methods 0.000 title claims abstract description 12
- 230000002159 abnormal effect Effects 0.000 claims abstract description 109
- 230000008859 change Effects 0.000 claims abstract description 95
- 230000005856 abnormality Effects 0.000 claims abstract description 18
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 6
- 230000000875 corresponding effect Effects 0.000 claims description 34
- 238000000034 method Methods 0.000 claims description 21
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000010606 normalization Methods 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 10
- 230000000739 chaotic effect Effects 0.000 claims description 8
- 108091026890 Coding region Proteins 0.000 claims description 4
- 230000002596 correlated effect Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 11
- 210000004556 brain Anatomy 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 230000000737 periodic effect Effects 0.000 description 6
- 230000001419 dependent effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 230000002996 emotional effect Effects 0.000 description 2
- 230000008921 facial expression Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 230000006996 mental state Effects 0.000 description 2
- 241000764238 Isis Species 0.000 description 1
- 206010027951 Mood swings Diseases 0.000 description 1
- 238000013019 agitation Methods 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000003183 myoelectrical effect Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Public Health (AREA)
- Psychology (AREA)
- Physics & Mathematics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Developmental Disabilities (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Child & Adolescent Psychology (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Hospice & Palliative Care (AREA)
- Social Psychology (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- Surgery (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Educational Technology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to the technical field of mental activity monitoring, in particular to a physiological monitoring data processing method for assessing mental activity. Firstly, physiological change time sequence data of a user to be detected is obtained, the physiological change time sequence data is decomposed by using an empirical mode decomposition algorithm, and a target component signal is screened out. The whole data characteristic and the continuous change characteristic of the target component signal are subjected to coding conversion to obtain coded data, so that the processing efficiency is improved. Since abnormal mental activities generally have complex data fluctuations, an abnormality factor is calculated to identify the data fluctuations and the complexity, and an abnormality characteristic value is obtained in combination with the data value distribution correlation between the target component signals. The characteristic value is based on the physiological change time sequence data of the individual, and can reflect the mental activity change of the individual more accurately. And finally, evaluating the mental activities of the user to be tested according to the abnormal characteristic values to obtain accurate and reliable monitoring results.
Description
Technical Field
The invention relates to the technical field of mental activity monitoring, in particular to a physiological monitoring data processing method for assessing mental activity.
Background
In modern life, assessment of mental activities is very important for many fields, such as clinical medicine, psychology, education, etc. Whereas changes in mental activities are often accompanied by specific physiological changes, these changes can be captured and analyzed by physiological monitoring data.
In the prior art, the threshold is directly set to judge whether the physiological monitoring data is abnormal or not, and differences among individuals and the connection and change characteristics among the data are ignored, so that misjudgment is caused on a large probability, the mental state of the individuals cannot be accurately represented, and the monitoring result is inaccurate.
Disclosure of Invention
In order to solve the technical problems that whether physiological monitoring data is abnormal or not is judged by directly setting a threshold value in the prior art, misjudgment is caused to a great extent by neglecting individual differences and the connection and change characteristics among the data, the mental state of an individual cannot be accurately represented, and the accuracy of a monitoring result is low, the invention aims to provide a physiological monitoring data processing method for assessing mental activities, and the adopted technical scheme is as follows:
Acquiring physiological change time sequence data of a user to be tested in a preset sampling period;
Decomposing the physiological change time sequence data based on a time-frequency analysis method to obtain all component signals; screening out target component signals according to the frequency characteristics of all the component signals; in any one target component signal, all data values are coded and converted according to the integral characteristic and the continuous change characteristic of data distribution to obtain coded data;
Obtaining an abnormal factor of the physiological change time sequence data according to the difference condition among the data values of all the target component signals, the arrangement sequence among the target component signals and the distribution disorder condition of the numerical values in the corresponding coded data; obtaining abnormal characteristic values of the physiological change time sequence data according to the data value distribution correlation conditions among all the target component signals and the abnormal factors of the physiological change time sequence data;
And evaluating the mental activities of the user to be tested according to the abnormal characteristic values to obtain mental activity monitoring results.
Further, in any one target component signal, according to the overall characteristic and the continuous variation characteristic of the data distribution, all the data values are coded and converted to obtain coded data, which includes:
in any one target component signal, calculating the average value of all data values as a reference value; encoding a data value larger than a reference value into 1, and encoding a data value smaller than or equal to the reference value into 0 to obtain a coding sequence of the target component signal;
In the coding sequence, starting from the coding value of the starting position to the third last coding value, taking each coding value as a value to be analyzed in sequence, and forming a binary sequence by the value to be analyzed and the two subsequent coding values;
and (3) obtaining all binary sequences, mapping each binary sequence into decimal numbers, and obtaining coded data composed of all decimal numbers.
Further, the obtaining the abnormal factor of the physiological change time sequence data according to the difference condition among the data values of all the target component signals, the arrangement sequence among the target component signals and the distribution disorder condition of the numerical values in the corresponding coded data comprises the following steps:
for any one target component signal, calculating the difference between each data value and a corresponding reference value, and obtaining a deviation factor of each data value according to the difference factor of each data value and the variances of all data values, wherein the deviation factor and the difference factor are positively correlated, and the deviation factor and the variances of all data values are negatively correlated; taking the average value of the deviation factors of all the data values as the deviation degree value of the target component signal;
For any one target component signal, in the coded data corresponding to the target component signal, the same value is used as a similar value, the information entropy of the coded data is calculated according to the occurrence probability of each type of value, the information entropy is used as a chaotic degree value of the target component signal, a difference value between a preset constant and a sequence number value of the target component signal is used as an adjustment factor, and the ratio of the chaotic degree value and the adjustment factor is subjected to normalization operation to obtain a complex degree value of the target component signal; wherein the preset constant is greater than the total number of target component signals;
and normalizing the sum of the offset degree value and the complexity degree value of all the target component signals to obtain an abnormal factor of the physiological change time sequence data.
Further, the obtaining the abnormal characteristic value of the physiological change time sequence data according to the data value distribution correlation condition among all the target component signals and the abnormal factor of the physiological change time sequence data includes:
Combining any two target component signals in all target component signals to obtain all non-repeated signal combinations;
For any one signal combination, calculating correlation coefficients of all data values in two target component signals based on the pearson correlation coefficients, and obtaining abnormal parameters of the two target component signals in the signal combination according to the distribution of the data values in the two target component signals and the correlation coefficients corresponding to the two target component signals, wherein the values of the abnormal parameters are normalized values;
And normalizing the product of the average value of the abnormal parameters corresponding to all the signal combinations and the abnormal factor of the physiological change time sequence data to obtain an abnormal characteristic value of the physiological change time sequence data.
Further, the formula model of the abnormal parameter is:
Wherein, Represents the/>Abnormal parameters of two target component signals in the signal combination; /(I)Represents the/>Correlation coefficients between two target component signals in the respective signal combinations; /(I)Represents the/>The/>, in the target component signal 1, of the signal combinationsA data value; /(I)Represents the/>A reference value corresponding to the target component signal 1 in the signal combinations; /(I)Represents the/>The/>, in the target component signal 2, of the signal combinationsA data value; /(I)Represents the/>A reference value corresponding to the target component signal 2 in the signal combinations; Representing the total number of data values; /(I) Represents the/>The variances of all data values in the target component signal 1 in the individual signal combinations; /(I)Represents the/>The variances of all data values in the target component signal 2 in the individual signal combinations; /(I)Representing a preset first parameter; representing the normalization function.
Further, the time-frequency analysis method is used for decomposing the physiological change time sequence data to obtain all component signals, and the method comprises the following steps:
and decomposing the physiological change time sequence data based on an empirical mode decomposition algorithm to obtain all component signals.
Further, the step of evaluating the mental activities of the user to be tested according to the abnormal characteristic value to obtain a mental activity monitoring result includes:
when the abnormal characteristic value is larger than or equal to a preset judgment threshold value, mental activity abnormality early warning is needed;
And when the abnormal characteristic value is smaller than a preset judgment threshold value, the abnormal mental activity early warning is not needed.
Further, the preset judgment threshold value is set to 0.6.
Further, the preset number is set to be one-half of the total number of all the component signals and rounded up.
The invention has the following beneficial effects:
The invention firstly acquires the physiological change time sequence data of the user to be detected, and the physiological change time sequence data usually comprises a plurality of frequency components and complex nonlinear characteristics, so that the physiological change time sequence data can be decomposed into a plurality of component signals for deeply analyzing the characteristics of the data, thereby analyzing the component signals. Because abnormal mental activities often cause the data to have frequency difference with normal data, the target component signals can be screened out according to the frequency, which is beneficial to reducing the data dimension and increasing the pertinence of data analysis. And then, for each target component signal, the target component signal can be coded and converted according to the integral characteristic and the continuous change characteristic of the data to obtain coded data, so that the data redundancy is reduced to a certain extent, and the data processing efficiency is improved. Further, since abnormal mental activities tend to cause fluctuations in data and become more complex than normal mental activities, and such characteristics may reflect differences between data values in the target component signal and the degree of confusion in the distribution of the values of the encoded data, an abnormality factor of the physiological change time series data is calculated based on this. Then, because the abnormality of the data can represent a specific mode or trend in different component signals, based on the characteristic, the numerical distribution correlation between the target component signals is calculated, and the obtained abnormality factors are combined to obtain the abnormal characteristic value of the physiological change time sequence data, the abnormal characteristic value at the moment is calculated based on the data characteristic in the physiological change time sequence data of the individual, so that the change of the mental activity of the individual in a preset period can be more accurately represented, and finally, the mental activity of the user to be tested is evaluated based on the obtained abnormal characteristic value, and the obtained mental activity monitoring result is more accurate and has higher reliability.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a physiological monitoring data processing method for assessing mental activities according to one embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects of the present invention for achieving the intended purpose, the following detailed description refers to a specific implementation, structure, characteristics and effects of a physiological monitoring data processing method for assessing mental activities according to the present invention, with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific embodiment of a physiological monitoring data processing method for assessing mental activities according to the present invention.
Referring now to FIG. 1, a method flow diagram of a physiological monitoring data processing method for assessing mental activities is provided, the method comprising the steps of:
Step S1: and acquiring physiological change time sequence data of the user to be tested in a preset sampling period.
In today's fast paced life, assessment of mental activities is very important for many fields, such as clinical medicine, psychology, education, etc. Mental activities include emotional changes such as tension, panic, excitement, agitation, fatigue, low-lying, and the like, which can be reflected according to facial expression changes of an individual, but for special cases, such as the individual actively suppressing the emotional expression, so that the individual is not characterized on the face, and the mental activities are caught and the elbows are seen only by relying on the facial expression to evaluate the mental activities; however, the change of mental activities is often accompanied by specific physiological changes, so the change of mental activities can be captured and analyzed by physiological monitoring data, such as heart rate, blood pressure, brain electrical activity, myoelectrical activity and the like.
In the prior art, when analyzing physiological change data of an individual, a preset threshold value is usually set, and when the value of the physiological change data exceeds the threshold value, the mental activity is considered to be abnormal; however, because of the differences between individuals, the error rate of judging whether the mental activities are abnormal or not by directly setting the threshold is higher, so in the embodiment of the invention, the self-adaptive judgment on whether the mental activities of the individuals are abnormal or not is realized by analyzing the characteristics and the relations between the data in the physiological change data of the individuals, and the accuracy of the monitoring result is effectively improved.
In this embodiment of the present invention, brain wave data of a user to be measured is taken as an example of analyzed physiological change time series data, because: brain wave is a direct reaction of brain neuron activity, is closely related to individual mental activities such as cognition, emotion, consciousness and the like, and has higher time resolution and frequency resolution, so that the brain wave data can be analyzed to more directly and accurately know the mental activity state of a user to be tested. The acquisition method can be as follows: physiological change time sequence data of a user to be detected in a preset sampling period is obtained by using an electroencephalograph (EEG) or a portable EEG, wherein a horizontal axis is a time axis, each point corresponds to one sampling moment, and a data value of a vertical axis generally represents the amplitude or voltage value of brain waves. And then preprocessing the obtained physiological change time sequence data, namely filtering, noise reduction and other processes are carried out, so that the quality of the data is improved.
It should be noted that, the preset sampling period is set to 5 minutes before the current time, and the specific sampling period can be adjusted according to the implementation scenario, which is not limited herein; in the embodiment of the invention, the abnormal mental activities are compared with the state of the individual without the mood swings, so that the fear, the tension, the excitement and the like can be regarded as abnormal mental activities.
Thus, physiological change time sequence data of the user to be detected can be obtained and used in the subsequent analysis process.
Step S2: decomposing the physiological change time sequence data based on a time-frequency analysis method to obtain all component signals; screening out target component signals according to the frequency characteristics of all the component signals; in any one target component signal, all data values are coded and converted according to the integral characteristic and the continuous change characteristic of data distribution, so as to obtain coded data.
Physiological change timing data typically contains a variety of frequency components and complex nonlinear characteristics. Through time-frequency analysis, these complex signals can be decomposed into multiple component signals, each representing a different frequency component or time-frequency variation pattern. To facilitate in-depth understanding and analysis of essential features in the data.
Preferably, in one embodiment of the present invention, the decomposing the physiological change time sequence data based on a time-frequency analysis method to obtain all component signals includes:
The empirical mode decomposition algorithm can adaptively decompose proper component signals according to the characteristics of the data, so that the physiological change characteristics on different scales can be known, and the physiological change time sequence data is decomposed by the empirical mode decomposition algorithm, so that all the component signals are obtained.
It should be noted that, the empirical mode decomposition algorithm is a technical means well known to those skilled in the art, and will not be described herein in detail; and the sampling moments in all the component signals are in one-to-one correspondence, namely the total number of the data values is the same.
After all the component signals are acquired, since the residual component and noise information tend to be in a low frequency part compared to the useful information, the target component signal containing more useful information is filtered out according to the frequency.
Preferably, in one embodiment of the present invention, filtering the target component signal according to frequency characteristics of all component signals includes:
Based on the foregoing analysis, the component signals are obtained by an empirical mode decomposition algorithm, so the component signals at this time are arranged in a frequency from high to low, so the previous preset number of component signals are taken as target component signals, and the preset number is set to be one-half of the total number of component signals and rounded up.
After the high-frequency component signal, namely the target component signal, is obtained, the high-frequency component signal can be subjected to coding conversion so as to remove detail characteristics, retain main information carried by the target component signal, macroscopically analyze the integral characteristics of data, and improve the calculation efficiency.
Preferably, in one embodiment of the present invention, in any one of the target component signals, all data values are coded and converted according to the overall feature and the continuously variable feature of the data distribution, so as to obtain coded data, including:
For any one target component signal, calculating the average value of all data values in the target component signal, taking the average value as a reference value, wherein the reference value represents the average characteristic of all data values in the target component signal, then encoding the data value larger than the reference value as 1, encoding the data value smaller than or equal to the reference value as 0, and obtaining the encoding sequence of the target component signal, wherein the encoding sequence is helpful for capturing the main trend and the periodic structure in the signal, and preparing for the abnormal situation of the follow-up reflection of mental activities to a certain extent. The reason is that: the data generated by normal mental activities often have repetitive periodic changes or smooth fluctuation characteristics, and thus appear as continuous 0 or continuous 1 in the code sequence, compared with physiological changes generated by abnormal mental activities, which are more disordered in value, usually do not present the continuous modes, and often appear as random 0 and 1 distribution.
And then, in the code sequence, starting from the code value at the starting position to the third code value at the last position, taking each code value as a value to be analyzed, and forming a binary sequence by the value to be analyzed and the two subsequent code values, so as to obtain all the binary sequences. And finally, mapping each binary sequence into decimal numbers to obtain coded data composed of all decimal numbers. At this time, the range of each decimal value in the encoded data is 0-7, and each decimal value reflects the interrelation between three continuous encoded values in the encoded sequence and also carries the information of three continuous data points in the target component signal, so that the change trend and the periodic structure of the data in the target component signal can be represented, and the subsequent extraction of the data features is facilitated. The process of acquiring encoded data is illustrated: if the code sequence is 00111, the sequence numbers of the code values are 1, 2, 3, 4 and 5, when the continuous three code values are formed into a binary sequence, the code values with the sequence numbers of 1, 2 and 3 are sequentially used as the values to be analyzed, then the code values with the sequence numbers of 1, 2 and 3 form a binary sequence, namely 001, the code values with the sequence numbers of 2, 3 and 4 form a binary sequence, namely 011, and the code values with the sequence numbers of 3, 4 and 5 form a binary sequence, namely 111.
By means of code conversion, information data are effectively simplified, key features are extracted macroscopically, periodic changes and abnormal fluctuation modes in target component signals are highlighted, and subsequent analysis of whether mental activities are abnormal is facilitated.
Step S3: obtaining an abnormal factor of the physiological change time sequence data according to the difference condition among the data values of all the target component signals, the arrangement sequence among the target component signals and the distribution disorder condition of the numerical values in the corresponding coded data; and obtaining abnormal characteristic values of the physiological change time sequence data according to the data value distribution correlation conditions among all the target component signals and the abnormal factors of the physiological change time sequence data.
Taking brain wave data in the embodiment of the invention as an example, when the mental activities of a user to be detected are in a normal condition, the brain wave data generally shows a relatively stable fluctuation mode, and the data value distribution is relatively uniform and periodic; when the mental activities are abnormal, the brain wave data can be characterized by irregular waveforms, abnormal data fluctuation and the like.
The irregular distribution and abnormal fluctuation of the data values can be quantified according to the difference between the data values and the degree of disturbance of the distribution, so that the abnormal factors of the physiological change time sequence data are obtained based on the difference condition between the data values of all the target component signals and the disturbance condition of the distribution of the numerical values in the coded data corresponding to the target component signals.
Preferably, in one embodiment of the present invention, obtaining the anomaly factor of the physiological change time series data according to the difference condition between the values of all the target component signals, the arrangement sequence between the target component signals, and the distribution disorder condition of the values in the corresponding encoded data includes:
For any one target component signal, the average value of all data values in each target component signal is calculated in the step S2 and is used as a reference value, and the reference value represents the average characteristic of all data values in the target component signal, so that the difference between each data value and the reference value is calculated and used as a difference factor of each data value, and then the difference factor of each data value and the variance of all data values are obtained according to the difference factor of each data value and the variance of all data values, wherein the difference factor and the difference factor are in positive correlation, the variance of the difference factor and the variance of all data values are in negative correlation, the positive correlation represents that a dependent variable increases along with the increase of the independent variable, the dependent variable decreases along with the decrease of the independent variable, and the specific relation can be a multiplication relation, an addition relation, power of an exponential function and the like, and is determined by practical application; the negative correlation indicates that the dependent variable decreases with increasing independent variable, and the dependent variable increases with decreasing independent variable, which may be a subtraction relationship, a division relationship, or the like, and is determined by the actual application. The mean value of the deviation factors of all the data values is then taken as the deviation degree value of the target component signal. The formula model of the offset value may specifically be, for example:
Wherein, Represents the/>Offset degree values of the individual target component signals; /(I)Representing the total number of data values; /(I)Represents the/>The/>, in the individual target component signalsA data value; /(I)Represents the/>Reference values corresponding to the target component signals; /(I)Represent the firstVariance of all data values in the individual target component signals; /(I)Representing a preset second parameter.
In the formula model of the offset degree value, for any one target component signal, the difference between each data value and the reference value is calculated to obtain a difference factorThe larger the value is, the larger the offset between the average level represented by the data value and the whole data values is, and the data fluctuation condition in the target component signal can be represented to a certain extent; because the variance of the data can represent the overall fluctuation condition of the data, the variance of all the data values is combined with the difference factor calculated by each data value, the difference factor is taken as a molecular part, the variance of all the data values is taken as a denominator part, and the deviation factor/>, corresponding to each data value, is obtainedAt this time, the deviation factor indicates the ratio of the deviation amount of each data value in the overall fluctuation condition, the larger the deviation factor is, the larger the value is, the larger the fluctuation degree of the data value is represented, then the deviation factors of all the data values are integrated, and the average value is calculated as the deviation degree value of the target component signal.
In the step S2, the information data is simplified through the code conversion, and the periodic variation and the abnormal fluctuation mode in the target component signal are highlighted, so that the numerical value in the code data corresponding to the target component signal can be analyzed to a chaotic degree, thereby representing the abnormal fluctuation condition in the target component signal. For any one target component signal, taking the same value as the same kind of value in encoded data corresponding to the target component signal, then calculating the information entropy of the encoded data according to the occurrence probability of each kind of value in the encoded data, taking the information entropy as a chaotic degree value of the target component signal, taking a difference value between a preset constant and a sequence number value of the target component signal as an adjustment factor, and taking a value obtained by normalizing the ratio of the chaotic degree value and the adjustment factor as a complex degree value of the target component signal, wherein the preset constant is larger than the total number of the target component signal. The formula model of the complexity value is:
Wherein, Represents the/>Complexity values of the individual target component signals; /(I)Represents the/>The number of kinds of values in the coded data corresponding to the target component signals; /(I)Represents the/>Probability of occurrence of class values; /(I)Representing a preset constant; /(I)Represents the/>Sequence number values of the individual target component signals; /(I)Representing a base 2 logarithmic function; /(I)Representing the normalization function.
In a formula model of a complexity level value, the value of entropy of a molecular part represents the disorder level of data, and the larger the value is, the more disorder of numerical distribution is indicated, and the data value in a target component signal can be regarded as abnormal fluctuation at the moment, so that the data value deviates from a normal condition; then, since the component signal with larger sequence number value usually corresponds to the lower frequency component in the empirical mode decomposition process, it usually reflects the global feature or long-term trend of the signal, and although the fluctuation of the component signal with higher frequency is slower, the component signal also contains valuable information, and in order to improve the comprehensiveness and accuracy of information acquisition, the adjustment factor is calculated according to the sequence number value of the target component signalAt this time, when the sequence number of the target component signal is larger, the value of the adjustment factor is smaller, and based on the analysis, the sequence number of the target component signal is larger, that is, the sequence number is lower in frequency, and the occupied weight of the target component signal should be increased, so that the adjustment factor corresponding to the target component signal is used as a denominator part, the chaotic degree value is used as a numerator part, and a formula model of the complex degree value is constructed.
Based on the above process, the offset degree value and the complexity degree value of each target component signal can be obtained, then the offset degree value and the complexity degree value of all the target component signals are integrated to obtain an accumulated value, and the accumulated value is normalized to obtain an abnormal factor of the physiological change time sequence data. The formula model of the anomaly factor is:
Wherein, Representing an anomaly factor; /(I)Represents the/>Complexity values of the individual target component signals; /(I)Represent the firstOffset degree values of the individual target component signals; /(I)Representing the total number of target component signals; /(I)Representing the normalization function.
In the formula model of the anomaly factor, based on the analysis, the larger the offset degree value of the target component signal is, the more the fluctuation degree of the data value is, the more anomaly is likely to occur, and the larger the complexity degree value of the target component signal is, the more the distribution of the data value is disordered, and the more anomaly fluctuation is likely to occur; and accumulating the offset degree values and the complexity degree values of all the target component signals, and normalizing the accumulated sum to obtain an abnormal factor, wherein the larger the value of the abnormal factor is, the more likely abnormal fluctuation of the physiological change time sequence data of the user to be tested is.
The preset constant isIs not unique and varies depending on the total number of target component signals, for example, if the total number of target component signals is 4, the range of the preset constant is (4, + -infinity), however, in order to avoid excessive values, in this embodiment of the invention, a constant/>, is presetSetting as the total number of the target component signals plus one, wherein specific numerical values can be adjusted according to implementation scenes, and the method is not limited herein; presetting a second parameter/>The function of (2) is to prevent the denominator from being 0, and the value can be 0.001, and the specific value can be adjusted according to the implementation scene, and is not limited herein.
So far, by analyzing each target component signal obtained by decomposing the physiological time sequence change data, the abnormal factor representing the abnormal condition of the physiological time sequence change data is obtained and can be used in the subsequent analysis process.
When the mental activities are abnormal, the physiological time sequence change data can change, so that the component signals obtained by decomposing the physiological time sequence change data can have consistent change characteristics, namely, certain correlation exists among the component signals, and the correlation is more obvious as the component signals are closer. Based on this feature, by analyzing the relationship between the component signals, the data change caused by abnormal mental activities can be more effectively identified. Therefore, the distribution correlation condition of the data values among the target component signals is analyzed, and the abnormal characteristic values of the physiological change time sequence data are obtained by combining the abnormal factors of the physiological change data.
Preferably, in one embodiment of the present invention, obtaining the abnormal characteristic value of the physiological change time series data according to the numerical distribution correlation condition among all the target component signals and the abnormal factor of the physiological change time series data includes:
in order to analyze the relation between the target component signals, any two target component signals may be combined in all target component signals, so as to obtain all non-repeated signal combinations, for example, the total number of target component signals is 4, and the total number is respectively denoted as 1,2, 3 and 4, and then all non-repeated signal combinations are (1, 2), (1, 3), (1, 4), (2, 3), (2, 4) and (3, 4).
For any one signal combination, calculating the correlation coefficients of all data values in the two target component signals by using the pearson correlation coefficients, and then obtaining the abnormal parameters of the two target component signals in the signal combination according to the distribution of the data values in the two target component signals and the correlation coefficients corresponding to the two target component signals. The formula model of the abnormal parameters is as follows:
Wherein, Represents the/>Abnormal parameters of two target component signals in the signal combination; /(I)Represents the/>Correlation coefficients between two target component signals in the respective signal combinations; /(I)Represents the/>The/>, in the target component signal 1, of the signal combinationsA data value; /(I)Represents the/>A reference value corresponding to the target component signal 1 in the signal combinations; /(I)Represents the/>The/>, in the target component signal 2, of the signal combinationsA data value; /(I)Represents the/>A reference value corresponding to the target component signal 2 in the signal combinations; Representing the total number of data values; /(I) Represents the/>The variances of all data values in the target component signal 1 in the individual signal combinations; /(I)Represents the/>The variances of all data values in the target component signal 2 in the individual signal combinations; /(I)Representing a preset first parameter; representing the normalization function.
In the formula model of the abnormal parameter, for any one signal combination, calculating the difference between each data value in each target component signal in the signal combination and the reference value of the target component signal to obtainAndWhen the difference value is larger, the data value at the same sampling time is larger in the target component signals than the average level of the whole data, and the difference corresponding to the data value at the sampling time is multiplied by the two target component signals in the signal combination, when/>When the value of (2) is larger, the correlation condition between two target component signals can be reflected to a certain extent while the abnormal fluctuation of the data is represented, and then the/>, corresponding to all the data values, is reflectedAccumulating to obtain/>The data fluctuation condition under the existence of a correlation between target component signals is characterized, and the larger the value is, the more abnormal the value is; and taking the value as a molecular part, multiplying the variance of the data values of the two target component signals in the signal combination as a denominator part, and representing the integral fluctuation condition of the two target component signals to obtain/>The larger the value, the larger the proportion of the data fluctuation in the correlation between the target component signals to the overall fluctuation, the more likely an abnormality will occur. Finally, the correlation coefficient/>, between two target component signals in the signal combinationAs a conditioning parameter, in this embodiment of the invention, only the correlation between the component signals is analyzed, and the positive and negative correlations are not distinguished, so that the correlation number is added to the absolute value and then to/>Multiplying, when/>The higher the value, the stronger the correlation between the two target component signals is, which can be regarded as/>, which is obtained by analyzing abnormal fluctuation under the correlationThe value of (2) is more reliable, and the product of the two is normalized, so that the abnormal parameter/>And the larger the value of the anomaly parameter, the higher the anomaly probability of the two target component signals in the signal combination.
Based on the method, the abnormal parameters of the two target component signals in each signal combination can be obtained, and the value obtained by normalizing the product of the average value of the abnormal parameters corresponding to all the signal combinations and the abnormal factor of the physiological change time sequence data is used as the abnormal characteristic value of the physiological change time sequence data. The formula model of the abnormal characteristic value is as follows:
Wherein, Representing an abnormal characteristic value; /(I)Representing an anomaly factor; /(I)Representing the total number of signal combinations; /(I)Represent the firstAbnormal parameters of two target component signals in the signal combination; /(I)Representing the normalization function.
In the formula model of the abnormal characteristic value, based on the analysis process, when the abnormal factor is knownThe larger the value of (2) is, the more likely abnormality occurs in the physiological change time sequence data, and the larger the abnormality parameters of the two target component signals in the signal combination are, the more likely abnormality occurs in the data, so that the average value of the abnormality parameters corresponding to all the signal combinations is obtained, and the average value/>Multiplying the physiological change time sequence data by an abnormality factor and carrying out normalization processing to obtain an abnormality characteristic value of the physiological change time sequence data.
It should be noted that, the calculation process of the pearson correlation coefficient is an operation process well known to those skilled in the art, and will not be described herein in detail; presetting a first parameterThe function of (2) is to prevent the denominator from being 0, and the value can be 0.001, and the specific value can be adjusted according to the implementation scene, and is not limited herein.
So far, the self-adaptive judgment of whether the mental activities of the user to be tested are abnormal or not is realized by analyzing the characteristics and the relations among the data in the physiological change time sequence data of the user to be tested, the abnormal characteristic value is obtained, and the mental activities can be monitored based on the abnormal characteristic value in the subsequent process.
Step S4: and evaluating the mental activities of the user to be tested according to the abnormal characteristic values to obtain mental activity monitoring results.
Based on the above steps, when the abnormal characteristic value of the physiological change time sequence data of the user to be tested is larger, it is indicated that the user to be tested is more likely to have a change of mental activities, that is, abnormal changes occur compared with normal and stable mental activities, so that the mental activities of the individual can be monitored according to the abnormal characteristic value.
Preferably, in one embodiment of the present invention, the evaluation of mental activities of the user to be tested according to the abnormal characteristic value, to obtain a mental activity monitoring result, includes:
When the abnormal characteristic value is larger than or equal to a preset judgment threshold value, the mental activity of the user to be tested is compared with the normal steady state, namely, the mental activity is changed, and the mental activity abnormality early warning is needed; otherwise, when the abnormal characteristic value is smaller than the preset judgment threshold value, the mental activity of the user to be tested is in a normal stable state, and mental activity abnormal early warning is not needed, wherein the preset judgment threshold value is set to be 0.6.
It should be noted that, in other embodiments of the present invention, the preset determination threshold may also be set to a value obtained by normalizing the average value of the data values in the time-series data of physiological changes when the mental activities of the user to be tested are in a normal steady state. The specific method for setting the judgment threshold may be adjusted according to the implementation scenario, and is not limited herein.
In summary, in the embodiment of the present invention, firstly, physiological change time sequence data of a user to be measured is obtained, and since the physiological change time sequence data generally includes multiple frequency components and complex nonlinear features, the physiological change time sequence data can be decomposed into multiple component signals for further analyzing the features of the data, so as to analyze the component signals. Because abnormal mental activities often cause the data to have frequency difference with normal data, the target component signals can be screened out according to the frequency, which is beneficial to reducing the data dimension and increasing the pertinence of data analysis. And then, for each target component signal, the target component signal can be coded and converted according to the integral characteristic and the continuous change characteristic of the data to obtain coded data, so that the data redundancy is reduced to a certain extent, and the data processing efficiency is improved. Further, since abnormal mental activities tend to cause fluctuations in data and become more complex than normal mental activities, and such characteristics may reflect differences between data values in the target component signal and the degree of confusion in the distribution of the values of the encoded data, an abnormality factor of the physiological change time series data is calculated based on this. Then, because the abnormality of the data can represent a specific mode or trend in different component signals, based on the characteristic, the numerical distribution correlation between the target component signals is calculated, and the obtained abnormality factors are combined to obtain the abnormal characteristic value of the physiological change time sequence data, the abnormal characteristic value at the moment is calculated based on the data characteristics contained in the physiological change time sequence data of the individual, so that the change of the mental activity of the individual in a preset period can be more accurately represented, the mental activity of the user to be tested is finally evaluated based on the obtained abnormal characteristic value, and the obtained mental activity monitoring result is more accurate and has higher reliability.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (4)
1. A physiological monitoring data processing method for assessing mental activity, the method comprising:
Acquiring physiological change time sequence data of a user to be tested in a preset sampling period;
Decomposing the physiological change time sequence data based on a time-frequency analysis method to obtain all component signals; screening out target component signals according to the frequency characteristics of all the component signals; in any one target component signal, all data values are coded and converted according to the integral characteristic and the continuous change characteristic of data distribution to obtain coded data;
Obtaining an abnormal factor of the physiological change time sequence data according to the difference condition among the data values of all the target component signals, the arrangement sequence among the target component signals and the distribution disorder condition of the numerical values in the corresponding coded data; obtaining abnormal characteristic values of the physiological change time sequence data according to the data value distribution correlation conditions among all the target component signals and the abnormal factors of the physiological change time sequence data;
According to the abnormal characteristic value, the mental activities of the user to be tested are evaluated, and a mental activity monitoring result is obtained;
the time-frequency analysis method is based on decomposing the physiological change time sequence data to obtain all component signals, wherein the method comprises the following steps:
decomposing the physiological change time sequence data based on an empirical mode decomposition algorithm to obtain all component signals;
The screening the target component signal according to the frequency characteristics of all the component signals comprises the following steps:
Taking the pre-preset number of component signals as target component signals;
In any one target component signal, all data values are coded and converted according to the integral characteristic and the continuous change characteristic of data distribution to obtain coded data, which comprises the following steps:
in any one target component signal, calculating the average value of all data values as a reference value; encoding a data value larger than a reference value into 1, and encoding a data value smaller than or equal to the reference value into 0 to obtain a coding sequence of the target component signal;
In the coding sequence, starting from the coding value of the starting position to the third last coding value, taking each coding value as a value to be analyzed in sequence, and forming a binary sequence by the value to be analyzed and the two subsequent coding values;
Obtaining all binary sequences, mapping each binary sequence into decimal numbers, and obtaining coded data composed of all decimal numbers;
Obtaining an anomaly factor of the physiological change time sequence data according to the difference condition among the data values of all the target component signals, the arrangement sequence among the target component signals and the distribution disorder condition of the numerical values in the corresponding coded data, wherein the anomaly factor comprises the following components:
For any one target component signal, calculating the difference between each data value and a corresponding reference value, and obtaining a deviation factor of each data value according to the difference factor of each data value and the variances of all data values, wherein the deviation factor and the difference factor are positively correlated, and the deviation factor and the variances of all data values are negatively correlated; taking the average value of the deviation factors of all the data values as the deviation degree value of the target component signal; the formula model of the offset degree value includes:
Wherein, Represents the/>Offset degree values of the individual target component signals; /(I)Representing the total number of data values; /(I)Represents the/>The/>, in the individual target component signalsA data value; /(I)Represents the/>Reference values corresponding to the target component signals; /(I)Represents the/>Variance of all data values in the individual target component signals; /(I)Representing a preset second parameter; /(I)Represents the/>The/>, in the individual target component signalsA difference factor for each data value; /(I)Represents the/>The/>, in the individual target component signalsDeviation factors for the individual data values;
for any one target component signal, in the coded data corresponding to the target component signal, the same value is used as a similar value, the information entropy of the coded data is calculated according to the occurrence probability of each type of value, the information entropy is used as a chaotic degree value of the target component signal, a difference value between a preset constant and a sequence number value of the target component signal is used as an adjustment factor, and the ratio of the chaotic degree value and the adjustment factor is subjected to normalization operation to obtain a complex degree value of the target component signal; wherein the preset constant is greater than the total number of target component signals; the formula model of the complexity value comprises:
Wherein, Represents the/>Complexity values of the individual target component signals; /(I)Represents the/>The number of kinds of values in the coded data corresponding to the target component signals; /(I)Represents the/>Probability of occurrence of class values; /(I)Representing a preset constant; /(I)Represents the/>Sequence number values of the individual target component signals; /(I)Representing a base 2 logarithmic function; /(I)Representing a normalization function; Represents the/> Adjustment factors for the individual target component signals; /(I)Represents the/>A value of degree of confusion for each target component signal;
Normalizing the sum of the offset degree value and the complexity degree value of all the target component signals to obtain an abnormal factor of the physiological change time sequence data;
The obtaining the abnormal characteristic value of the physiological change time sequence data according to the data value distribution correlation condition among all the target component signals and the abnormal factors of the physiological change time sequence data comprises the following steps:
Combining any two target component signals in all target component signals to obtain all non-repeated signal combinations;
For any one signal combination, calculating correlation coefficients of all data values in two target component signals based on the pearson correlation coefficients, and obtaining abnormal parameters of the two target component signals in the signal combination according to the distribution of the data values in the two target component signals and the correlation coefficients corresponding to the two target component signals, wherein the values of the abnormal parameters are normalized values;
the value obtained by normalizing the product of the average value of the abnormal parameters corresponding to all the signal combinations and the abnormal factor of the physiological change time sequence data is used as the abnormal characteristic value of the physiological change time sequence data;
The formula model of the abnormal parameters is as follows:
; wherein/> Represents the/>Abnormal parameters of two target component signals in the signal combination; /(I)Represents the/>Correlation coefficients between two target component signals in the respective signal combinations; Represents the/> The/>, in the target component signal 1, of the signal combinationsA data value; /(I)Represents the/>A reference value corresponding to the target component signal 1 in the signal combinations; /(I)Represents the/>The/>, in the target component signal 2, of the signal combinationsA data value; /(I)Represents the/>A reference value corresponding to the target component signal 2 in the signal combinations; /(I)Representing the total number of data values; /(I)Represents the/>The variances of all data values in the target component signal 1 in the individual signal combinations; /(I)Represents the/>The variances of all data values in the target component signal 2 in the individual signal combinations; /(I)Representing a preset first parameter; /(I)Representing the normalization function.
2. The method for processing physiological monitor data for assessing mental activities according to claim 1, wherein the assessing mental activities of the user to be tested according to the abnormal characteristic value to obtain mental activity monitoring results comprises:
when the abnormal characteristic value is larger than or equal to a preset judgment threshold value, mental activity abnormality early warning is needed;
And when the abnormal characteristic value is smaller than a preset judgment threshold value, the abnormal mental activity early warning is not needed.
3. A physiological monitor data processing method for assessing a mental activity according to claim 2, wherein said preset decision threshold is set to 0.6.
4. A physiological monitor data processing method for assessing a mental activity according to claim 1, wherein said preset number is set to be one-half of the total number of all component signals and rounded up.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410296374.6A CN117894491B (en) | 2024-03-15 | 2024-03-15 | Physiological monitoring data processing method for assessing mental activities |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410296374.6A CN117894491B (en) | 2024-03-15 | 2024-03-15 | Physiological monitoring data processing method for assessing mental activities |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117894491A CN117894491A (en) | 2024-04-16 |
| CN117894491B true CN117894491B (en) | 2024-06-11 |
Family
ID=90641506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410296374.6A Active CN117894491B (en) | 2024-03-15 | 2024-03-15 | Physiological monitoring data processing method for assessing mental activities |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117894491B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118436347B (en) * | 2024-04-26 | 2025-04-11 | 苏州大学 | EEG signal emotion recognition system based on adaptive data structure optimization |
| CN118177830B (en) * | 2024-05-15 | 2024-08-09 | 济南宝林信息技术有限公司 | Heart function real-time monitoring data optimization processing method based on artificial intelligence |
| CN118500538B (en) * | 2024-07-18 | 2024-11-01 | 茌平鲁环汽车散热器有限公司 | Method for monitoring working condition of automobile radiating fin |
| CN118571491A (en) * | 2024-08-01 | 2024-08-30 | 江苏盖睿健康科技有限公司 | Health monitoring and early warning system based on wearable equipment |
| CN118839285B (en) * | 2024-08-05 | 2025-03-18 | 洛阳莱普生信息科技有限公司 | Livestock biological asset supervision method and system based on intelligent ear tags |
| CN119108104B (en) * | 2024-11-06 | 2025-03-04 | 樊文星 | Physical sign physiological data monitoring method and system for nephrology department patient and medical equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1049791A (en) * | 1996-08-05 | 1998-02-20 | Nippon Telegr & Teleph Corp <Ntt> | Time series signal processing method and apparatus |
| CN111528838A (en) * | 2020-05-19 | 2020-08-14 | 中国电子科技集团公司第三十八研究所 | Abnormal electroencephalogram signal detection device and detection method |
| CN114027847A (en) * | 2021-11-17 | 2022-02-11 | 湖南万脉医疗科技有限公司 | Electrocardiosignal analysis method based on time-frequency analysis |
| WO2022210072A1 (en) * | 2021-03-29 | 2022-10-06 | 川崎重工業株式会社 | Robot malfunction sign detection device and robot malfunction sign detection method |
| CN115414044A (en) * | 2022-09-27 | 2022-12-02 | 河南大学 | Human mental state management system, method and equipment based on electroencephalogram analysis |
| WO2022257459A1 (en) * | 2021-06-10 | 2022-12-15 | 平安科技（深圳）有限公司 | User behavior anomaly analysis method and apparatus, device, and storage medium |
| CN115860260A (en) * | 2022-12-28 | 2023-03-28 | 国网河南省电力公司经济技术研究院 | A Residential Air Conditioning Load Forecasting Model Considering Eigendecomposition of Frequency Domain Data |
| CN116866129A (en) * | 2023-08-21 | 2023-10-10 | 王梅 | Wireless communication signal detection method |
| CN117349781A (en) * | 2023-12-06 | 2024-01-05 | 东莞市郡嘉电子科技有限公司 | Intelligent diagnosis method and system for faults of transformer |
-
2024
- 2024-03-15 CN CN202410296374.6A patent/CN117894491B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1049791A (en) * | 1996-08-05 | 1998-02-20 | Nippon Telegr & Teleph Corp <Ntt> | Time series signal processing method and apparatus |
| CN111528838A (en) * | 2020-05-19 | 2020-08-14 | 中国电子科技集团公司第三十八研究所 | Abnormal electroencephalogram signal detection device and detection method |
| WO2022210072A1 (en) * | 2021-03-29 | 2022-10-06 | 川崎重工業株式会社 | Robot malfunction sign detection device and robot malfunction sign detection method |
| WO2022257459A1 (en) * | 2021-06-10 | 2022-12-15 | 平安科技（深圳）有限公司 | User behavior anomaly analysis method and apparatus, device, and storage medium |
| CN114027847A (en) * | 2021-11-17 | 2022-02-11 | 湖南万脉医疗科技有限公司 | Electrocardiosignal analysis method based on time-frequency analysis |
| CN115414044A (en) * | 2022-09-27 | 2022-12-02 | 河南大学 | Human mental state management system, method and equipment based on electroencephalogram analysis |
| CN115860260A (en) * | 2022-12-28 | 2023-03-28 | 国网河南省电力公司经济技术研究院 | A Residential Air Conditioning Load Forecasting Model Considering Eigendecomposition of Frequency Domain Data |
| CN116866129A (en) * | 2023-08-21 | 2023-10-10 | 王梅 | Wireless communication signal detection method |
| CN117349781A (en) * | 2023-12-06 | 2024-01-05 | 东莞市郡嘉电子科技有限公司 | Intelligent diagnosis method and system for faults of transformer |
Non-Patent Citations (3)
| Title |
|---|
| Time-Frequency Analysis of Seismic Data Using Synchrosqueezing Transform;Ping Wang等;IEEE Geoscience and Remote Sensing Letters;20140502;第11卷(第12期);第2042 - 2044页 * |
| 基于Hilbert-Huang变换的第一心音信号时频分析;杜寿昌等;云南民族大学学报(自然科学版);20040410(第02期);第95-98，115页 * |
| 基于可视化图方法的体征时间序列数据分类分析研究;焦晓宇等;世界科学技术-中医药现代化;20160430;第18卷(第4期);第664-670页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117894491A (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117894491B (en) | Physiological monitoring data processing method for assessing mental activities | |
| US8204583B2 (en) | System for seizure monitoring and detection | |
| CN101272733B (en) | Monitoring method and apparatus | |
| US6725074B1 (en) | Quality indicator for measurement signals, in particular, for medical measurement signals such as those used in measuring oxygen saturation | |
| US20250025060A1 (en) | Heart rate monitoring method, device and apparatus | |
| US9042973B2 (en) | Apparatus and method for measuring physiological signal quality | |
| US9924870B2 (en) | Monitoring physiological parameters | |
| JP2005021450A (en) | Device and method for analyzing state of organism | |
| CN115862877B (en) | Method, system and device for detecting, quantifying and assisting in intervention of sleep sustainability | |
| CN115910351B (en) | Method, system and device for sleep periodic detection quantification and auxiliary intervention | |
| CN115715684B (en) | Heart detection evaluation method, system, storage medium and device | |
| US8805484B2 (en) | System, apparatus and method for diagnosing seizures | |
| John et al. | A generalized signal quality estimation method for IoT sensors | |
| JP2023099043A (en) | Systems and methods for seizure detection based on changes in electroencephalogram (eeg) non-linearities | |
| CN115429292B (en) | Device and system for detecting quality of electroencephalogram signal based on spectrum analysis | |
| KR102342106B1 (en) | Non-contact biosignal analysis system for body condition determination | |
| KR20200143873A (en) | Method and apparatus for automatic detection of epileptic seizure waveform based on feature extraction with probabilistic model and machine learning using coefficient in multi-frequency bands from electroencephalogram signals | |
| CN117874689A (en) | A method for intelligent processing of heart rate monitoring data | |
| Sabor et al. | BHI-Net: Brain-heart interaction-based deep architectures for epileptic seizures and firing location detection | |
| CN116035536A (en) | Method, system and device for detecting and quantifying sleep activity level | |
| CN118648883B (en) | Dual-mode blood pressure calculation method, device, equipment and storage medium | |
| Aminifar et al. | Recognoise: Machine-learning-based recognition of noisy segments in electrocardiogram signals | |
| Wang et al. | Exploration of instantaneous amplitude and frequency features for epileptic seizure prediction | |
| CN118398214A (en) | Psychological analysis and memory integration method of AI | |
| CN117807551B (en) | Heart rate abnormality capturing method and system based on intelligent ring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |