CN118010165B - Automatic induction temperature early warning method and system for hair straightening comb - Google Patents
Automatic induction temperature early warning method and system for hair straightening comb Download PDFInfo
- Publication number
- CN118010165B CN118010165B CN202410410756.7A CN202410410756A CN118010165B CN 118010165 B CN118010165 B CN 118010165B CN 202410410756 A CN202410410756 A CN 202410410756A CN 118010165 B CN118010165 B CN 118010165B
- Authority
- CN
- China
- Prior art keywords
- independent component
- signal
- component signal
- temperature
- independent
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000006698 induction Effects 0.000 title claims abstract description 10
- 238000001914 filtration Methods 0.000 claims abstract description 68
- 230000008859 change Effects 0.000 claims abstract description 39
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 230000000739 chaotic effect Effects 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims description 39
- 230000006870 function Effects 0.000 claims description 13
- 238000012880 independent component analysis Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000006185 dispersion Substances 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010438 heat treatment Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 230000005670 electromagnetic radiation Effects 0.000 description 3
- 210000001520 comb Anatomy 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 210000004761 scalp Anatomy 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Landscapes
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Indication And Recording Devices For Special Purposes And Tariff Metering Devices (AREA)
Abstract
The invention relates to the technical field of data cleaning, in particular to an automatic induction temperature early warning method and system for a hair straightening comb. The method comprises the steps of obtaining independent characteristic values of each independent component signal of an original temperature signal, and obtaining the difference degree between the independent component signals according to the amplitude difference of data points in any two independent component signals and the independent characteristic value difference; combining the discrete degree of the slope between adjacent data points in the independent component signal and the chaotic degree and the independent characteristic value of the amplitude average change rate of the local signal section of the independent component signal, and adjusting the difference degree to obtain the filtering intensity value of the independent component signal; filtering the independent component signals by using a filtering algorithm based on the filtering intensity value to obtain a denoising temperature signal; and pre-warning the temperature of the hair straightening comb according to the amplitude difference of the data points in the signal of the temperature and the normal temperature. The invention adaptively acquires the filtering intensity value of the independent component signal, improves the denoising effectiveness of the original temperature signal, and increases the accuracy of temperature early warning of the hair straightening comb.
Description
Technical Field
The invention relates to the technical field of data cleaning, in particular to an automatic induction temperature early warning method and system for a hair straightening comb.
Background
Hair straightening combs are widely used as a hair waving tool, and the high temperature generated in the use process of the hair straightening combs can damage the hair and scalp of a user or even cause potential safety hazards due to improper use or equipment faults and the like. Therefore, it is important to perform temperature warning on the hair straightening comb.
Through the temperature change on the surface of the hair straightening comb of real-time perception of the infrared sensor who installs on the hair straightening comb, there is the noise in the temperature signal that leads to the sensor to gather easily because of factors such as ambient temperature change and electromagnetic radiation, leads to the temperature signal inaccurate. The method comprises the steps of separating signals into component signals, denoising each component signal through a filtering algorithm, wherein the difference exists between the types of noise and the strengths of noise contained in different component signals, so that the difference exists between the required filtering strengths of different component signals, parameters in the filtering algorithm are specified in advance in the prior art, if the parameter setting in the filtering algorithm is unreasonable, the situation that the noise in the component signals cannot be effectively removed and the signals are distorted is caused, the denoising effect of temperature signals is further poor, and the accuracy of temperature early warning of a hair straightening comb is reduced.
Disclosure of Invention
In order to solve the technical problems that the temperature signal denoising effect is poor and the temperature early warning of the hair straightening comb is error due to unreasonable parameter setting in a filtering algorithm when filtering a component signal, the invention aims to provide an automatic induction temperature early warning method and an automatic induction temperature early warning system for the hair straightening comb, and the adopted technical scheme is as follows:
In a first aspect, an embodiment of the present invention provides a method for automatically sensing a temperature of a hair straightening comb, the method comprising:
Respectively acquiring an original temperature signal of the hair straightening comb in a current working time period and a normal temperature signal of the hair straightening comb in a historical working time period;
Independent component analysis is carried out on the original temperature signals to obtain independent component signals; obtaining an independent characteristic value of each independent component signal according to the kurtosis value and the period degree of each independent component signal;
obtaining the difference degree between the independent component signals according to the difference between the amplitude difference of the data points in any two independent component signals and the independent characteristic value;
Dividing each independent component signal into different local signal segments, and obtaining the amplitude average change rate of each local signal segment; combining the discrete degree of the slope between adjacent data points in each independent component signal, the chaotic degree of the amplitude average change rate of the local signal section of each independent component signal and the independent characteristic value to obtain the noise membership degree of each independent component signal;
The noise membership degree is utilized to adjust the difference degree, and a filtering intensity value of each independent component signal is obtained; filtering the independent component signals of the original temperature signals by using a filtering algorithm based on the filtering intensity values to obtain denoising temperature signals;
And (3) early warning the temperature of the hair straightening comb based on the amplitude difference of the data points in the denoising temperature signal and the normal temperature signal.
Further, the method for obtaining the independent characteristic value of each independent component signal according to the kurtosis value and the period degree of each independent component signal comprises the following steps:
For each independent component signal, establishing a two-dimensional coordinate system by taking time as a horizontal axis and taking a temperature value as a vertical axis, and mapping the independent component signals into the two-dimensional coordinate system to obtain a signal curve segment; selecting any inflection point except the last inflection point in the signal curve segment as an analysis point, taking the next inflection point adjacent to the analysis point as a characteristic point of the analysis point, and respectively taking a vertical line of a transverse axis of the two-dimensional coordinate system as a characteristic line by passing through each characteristic point; enclosing the signal curve section, the two characteristic lines and the transverse axis into an analysis area taking the area as an analysis point; calculating the area of the analysis area as a characteristic area value of the analysis point;
according to the difference between the characteristic area values of any two inflection points except the last inflection point in the signal curve segment corresponding to the independent component signal, obtaining the cycle significance of the independent component signal;
Obtaining the kurtosis value of each independent component signal; and combining the difference between the kurtosis value of each independent component signal and the kurtosis value of the standard Gaussian curve and the period significance to obtain the independent characteristic value of each independent component signal.
Further, the calculation formula of the independent characteristic value of each independent component signal is as follows:
; wherein F is the independent eigenvalue of each independent component signal; k is the kurtosis value of each independent component signal; y is the kurtosis value of a standard Gaussian curve; m is the total number of inflection points in the signal curve segment corresponding to each independent component signal; /(I) The characteristic area value of a u-th inflection point in the signal curve segment corresponding to each independent component signal is obtained; /(I)The characteristic area value of the v inflection point in the signal curve segment corresponding to each independent component signal; /(I)-Said period significance for each individual component signal; /(I)As a function of absolute value; /(I)Is a preset positive number.
Further, the calculation formula of the degree of difference between the independent component signals is as follows:
; in the/> Is the degree of difference between the independent component signals; n is the total number of independent component signals; /(I)The independent eigenvalue for the n1 st independent component signal; /(I)The independent eigenvalues for the n2 nd independent component signal; /(I)Total number of data points in the n1 st independent component signal; The amplitude of the a-th data point in the n 1-th independent component signal; /(I) Total number of data points for the n2 nd independent component signal; /(I)The amplitude of the b data point in the n2 independent component signal; /(I)As a function of absolute value.
Further, the method for obtaining the amplitude average change rate of each local signal segment comprises the following steps of;
For each local signal segment of each independent component signal, taking the absolute value of the difference between the amplitude of each data point in the local signal segment and the amplitude of the next adjacent data point as the local amplitude difference of each data point in the local signal segment; counting the sum of the local amplitude differences of the rest data points except the last data point in the local signal section to be used as the comprehensive amplitude difference of the local signal section;
Taking the time interval between the corresponding moments of the data points of the two end points of the local signal section as the duration of the local signal section;
and taking the ratio of the comprehensive amplitude difference of the local signal section to the duration as the amplitude average change rate of the local signal section.
Further, the method for obtaining the noise membership degree of each independent component signal comprises the following steps:
Acquiring the slope between each data point in each independent component signal and the next adjacent data point as the slope value of each data point in each independent component signal; calculating the variance of the inclination values of the rest data points except the last data point in each independent component signal as the burr saliency of each independent component signal;
acquiring information entropy of the amplitude average change rate of the local signal segment of each independent component signal as the change rate confusion of each independent component signal;
According to the independent characteristic value of each independent component signal, the burr significance and the change rate confusion degree are obtained, and the noise membership degree of each independent component signal is obtained; and the independent characteristic value and the noise membership degree are in a negative correlation relationship, and the burr significance degree and the change rate confusion degree are in a positive correlation relationship with the noise membership degree.
Further, the method for obtaining the filtering intensity value of each independent component signal includes:
And weighting the difference degree by using the noise membership degree of each independent component signal to obtain a filtering intensity value of each independent component signal.
Further, the method for filtering the independent component signal of the original temperature signal by using a filtering algorithm based on the filtering intensity value to obtain a denoising temperature signal comprises the following steps:
The filtering intensity value of each independent component signal is used as the standard deviation of a Gaussian filtering algorithm for filtering each independent component signal, and the filtering component signal of each independent component signal is obtained;
Reconstructing the filtered component signals of all independent component signals of the original temperature signal to obtain the denoising temperature signal.
Further, the method for performing early warning heating on the temperature of the hair straightening comb based on the amplitude difference of the data points in the denoising temperature signal and the normal temperature signal comprises the following steps:
Taking the denoising temperature signal and the normal temperature signal as analysis signals, and calculating the variance of the amplitude of the data points in the analysis signals as the amplitude dispersion of the analysis signals;
normalizing the absolute value of the difference between the amplitude dispersion of the denoising temperature signal and the normal temperature signal to obtain a temperature difference;
When the temperature difference is smaller than a preset difference threshold, the temperature of the hair straightening comb is in a normal state; when the temperature difference is greater than or equal to a preset difference threshold, the temperature of the hair straightening comb is in an abnormal state.
In a second aspect, another embodiment of the present invention provides an automatic sensing temperature warning system for a hair straightening comb, the system comprising: a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of any one of the methods described above when executing the computer program.
The invention has the following beneficial effects:
In the embodiment of the invention, an independent component signal of an original temperature signal is obtained, the maximum non-Gaussian property exists among independent components, the kurtosis value and the periodic degree of the independent component signal reflect whether the independent component signal has the Gaussian property from the direct aspect and the side surface respectively, and the independent characteristic value is determined by analyzing the degree of the Gaussian property of the independent component signal; the difference of the amplitude values and the difference of the independent characteristic values of the data points between the independent component signals respectively show the independence between the independent component signals from the whole amplitude condition of the signals and the independent characteristic of the single signal, and the independence between the signals can be accurately reflected by combining the difference degree between the independent component signals obtained by the two factors; the discrete degree of the slope between adjacent data points presents the characteristic strength of the burr on the surface of the signal, the chaotic degree of the amplitude average change rate of the local signal section of the independent component signal reflects the stable state of the signal in a certain time, and the acquired noise membership degree can accurately reflect the noise degree existing in the independent component signal by combining the independent characteristic value; the filtering strength of each independent component signal, namely the filtering strength value, is adaptively adjusted through the noise membership degree, namely the parameters in a filtering algorithm for filtering the independent component signals are adaptively adjusted, so that the filtering effect of the independent component signals with more noise components is better, the condition that the independent component signals with less noise components are not distorted is ensured, the noise components of the original temperature signals are effectively removed, and the signal stability is improved; and then, based on the amplitude difference of the data points of the denoising temperature signal and the normal temperature signal, the judgment of the current working temperature state of the hair straightening comb is more accurate, and the accuracy of the temperature early warning of the hair straightening comb is improved.
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 illustrating steps of a method for automatically sensing temperature of a hair straightening comb according to an embodiment of the present invention.
FIG. 2 is a schematic diagram of a portion of an original temperature signal according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an analysis area according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to the specific implementation, structure, characteristics and effects of an automatic sensing temperature early warning method and system for a hair straightening comb according to the invention by combining the accompanying drawings and the preferred embodiment. 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 invention aims at the specific scene: a plurality of sensors are arranged on the hair straightening comb and are used for monitoring and sensing the temperature change of the hair straightening comb in real time; the infrared sensor is mainly used for sensing the temperature of the surface of the hair straightening comb in a non-contact mode, and can measure the surface temperature of an object with high precision. In the process of automatically sensing temperature, factors such as temperature change of surrounding environment, electromagnetic radiation and the like may cause unstable sensor signals, thereby affecting the accuracy of temperature early warning.
The invention provides a method and a system for automatically sensing temperature for a hair straightening comb.
Referring to fig. 1, a flowchart of steps of a method for automatically sensing temperature of a hair straightening comb according to an embodiment of the present invention is shown, where the method includes:
Step S1: the original temperature signal of the hair straightening comb in the current working period and the normal temperature signal of the hair straightening comb in the historical working period are respectively obtained.
Specifically, the infrared sensor is arranged on the side surface of the hair straightening comb, so that the infrared sensor can be aligned with the heating part of the hair straightening comb, and the infrared sensor can accurately sense the surface temperature of the hair straightening comb; the signals collected by the infrared sensor are analog signals, and the analog signals are converted into digital signals by utilizing an analog-to-digital converter; and transmitting the temperature signal acquired by the infrared sensor to a microprocessor so as to display the surface temperature of the hair straightening comb in real time.
In order to judge whether the current working temperature of the hair straightening comb is in an abnormal temperature state, firstly, respectively acquiring temperature signals of the hair straightening comb in a current working time period as original temperature signals and temperature signals in a historical working time period as normal temperature signals; then, the embodiment of the invention determines whether the hair straightening comb is in an abnormal temperature state in the current state by comparing the difference degree between the original temperature signal and the normal temperature signal. The horizontal axis of the coordinate system where the original temperature signal and the normal temperature signal are located is time, and the vertical axis is a temperature value; fig. 2 is a schematic diagram of a portion of an original temperature signal according to an embodiment of the present invention, as shown in fig. 2, a horizontal axis of a coordinate system in fig. 2 is time T, and a vertical axis is a temperature value W.
The starting time of the current working time period is the starting time of the hair straightening comb in the current working time, and the ending time is the current time of the hair straightening comb working; the historical working time period is the working time period of the hair straightening comb in the normal temperature state of certain historical work, and the working time period of the hair straightening comb in the normal temperature state of certain historical work is selected randomly as the historical working time period because the temperature signals of the hair straightening comb in the normal temperature state are similar.
In the process of automatically monitoring the surface temperature of the hair straightening comb by utilizing the infrared sensor, noise is easily caused in the temperature signal due to factors such as ambient temperature change, electromagnetic radiation and the like, so that the temperature signal is unstable.
Step S2: independent component analysis is carried out on the original temperature signals to obtain independent component signals; and obtaining the independent characteristic value of each independent component signal according to the kurtosis value and the period degree of each independent component signal.
In the embodiment of the invention, the independent component analysis is utilized to acquire each independent component signal of the original temperature signal, the independent component signals are uncorrelated, different independent components possibly have different signal characteristics and noise characteristics, and the independent processing can better keep the effective information of the signals. The analysis of the independent components is known to those skilled in the art, and will not be described herein.
The rule that the maximum non-Gaussian property exists among independent components belongs to independent component analysis is that the independent component signal has the Gaussian degree, and the independent characteristic, namely the independent characteristic value, of the independent component signal is determined. The kurtosis value of the independent component signal directly reflects whether the independent component signal has gaussian property; the periodicity degree of the independent component signals reflects whether the independent component signals have Gaussian property from the side surface, and the smaller the periodicity degree is, the more obvious is Gao Sixing; and the kurtosis value and the period degree of the independent component signals are combined for analysis, so that the accuracy of the independent characteristic values is improved.
Preferably, the specific acquisition method of the independent characteristic value of the independent component signal is as follows: for each independent component signal, establishing a two-dimensional coordinate system by taking time as a horizontal axis and taking a temperature value as a vertical axis, and mapping the independent component signals into the two-dimensional coordinate system to obtain a signal curve segment; selecting any inflection point except the last inflection point in the signal curve segment as an analysis point, taking the next inflection point adjacent to the analysis point as a characteristic point of the analysis point, and respectively making a perpendicular line of a transverse axis of a two-dimensional coordinate system through each characteristic point as a characteristic line; the signal curve section, the two characteristic lines and the transverse axis are surrounded to form an area as an analysis area of an analysis point; calculating the area of the analysis area as a characteristic area value of the analysis point; according to the difference between the characteristic area values of any two inflection points except the last inflection point in the signal curve segment corresponding to the independent component signal, acquiring the cycle significance of the independent component signal; obtaining the kurtosis value of each independent component signal; and combining the difference between the kurtosis value of each independent component signal and the kurtosis value of the standard Gaussian curve and the period significance to obtain the independent characteristic value of each independent component signal.
FIG. 3 is a schematic diagram of an analysis area according to an embodiment of the present invention, as shown in FIG. 3, a horizontal axis of a coordinate system in FIG. 3 is time T, a vertical axis is temperature W, a curve in FIG. 3 is a partial signal curve segment of an independent component signal in a two-dimensional coordinate system, and two gray points d1 and d2 on the curve are two adjacent inflection points in the signal curve segment; the crossing point d1 is a perpendicular to the transverse axis of the two-dimensional coordinate system, and the intersection point of the perpendicular and the transverse axis is a point d3; the passing point d2 is a perpendicular to the transverse axis of the two-dimensional coordinate system, and the intersection point of the perpendicular and the transverse axis is a point d4; the analysis area of the point d1 is defined by the area surrounded by the curve segment between the points d1 and d2, the line segment between the points d2 and d4, the line segment between the points d4 and d3, and the line segment between the points d3 and d 1.
It should be noted that, the method for calculating the kurtosis value of the signal and the method for obtaining the kurtosis value of the standard gaussian curve are both known techniques, and the method for obtaining the inflection point on the curve and the area of the analysis region are both common mathematical knowledge, and are not described herein.
The calculation formula of the independent characteristic value of each independent component signal is as follows:
wherein F is an independent characteristic value of each independent component signal; k is the kurtosis value of each independent component signal; y is the kurtosis value of a standard Gaussian curve; m is the total number of inflection points in the signal curve segment corresponding to each independent component signal; characteristic area values of a u-th inflection point in a signal curve segment corresponding to each independent component signal; /(I) Characteristic area values of a v-th inflection point in a signal curve segment corresponding to each independent component signal; /(I)A period saliency for each individual component signal; /(I)As a function of absolute value; /(I)The empirical value of 0.1 is taken for the preset positive number, and the function is to prevent the denominator from being 0 to cause meaningless.
It should be noted that the number of the substrates,Reflecting the difference between the independent component signal and the standard Gaussian distribution characteristics, when/>The smaller the independent component signal has stronger Gao Sixing, the worse the independence of the independent component signal with stronger gaussian property, the smaller the independent eigenvalue F. /(I)Reflecting the difference between the areas of the analysis areas of inflection points in the signal curve segments corresponding to the independent component signals, namely the characteristic area values; when cycle saliency/>The smaller the area of the analysis area of the inflection point in the signal curve segment of the independent component signal is, the more obvious the periodicity of the independent component signal is; the periodicity reflects whether the independent component signal has gaussian property from the side, and the more obvious the periodicity of the independent component signal is due to the fact that the standard gaussian distribution does not have periodicity, the more obvious the characteristic of non-gaussian property of the independent component signal is, so that the more obvious the independent characteristic of the independent component signal is, the larger the independent characteristic value F is.
Step S3: and obtaining the difference degree between the independent component signals according to the difference between the amplitude difference of the data points in any two independent component signals and the difference between the independent characteristic values.
Specifically, the independent components are independent of each other, and the independent components are generally distributed in a non-Gaussian manner, and the two characteristics belong to the rule of the independent component analysis method. The difference of the amplitude values and the difference of the independent characteristic values of the data points between the independent component signals respectively show the independence between the independent component signals from the whole amplitude condition of the signals and the independent characteristic of the single signal, and the independence between the signals can be accurately reflected by combining the difference degree between the independent component signals obtained by the two factors.
And obtaining the difference degree between the independent component signals according to the difference between the amplitude difference of the data points in any two independent component signals and the difference between the independent characteristic values. The calculation formula of the degree of difference between the independent component signals is as follows:
In the method, in the process of the invention, Is the degree of difference between the independent component signals; n is the total number of independent component signals; /(I)Independent characteristic values of the (n 1) th independent component signal; /(I)Independent eigenvalues for the n2 nd independent component signal; /(I)Total number of data points in the n1 st independent component signal; /(I)The amplitude of the a-th data point in the n 1-th independent component signal; /(I)Total number of data points for the n2 nd independent component signal; /(I)The amplitude of the b data point in the n2 independent component signal; /(I)As a function of absolute value.
It should be noted that, the reason why the independent features of the independent components are generated is that the independent components all include part of the features of the original signal, which results in a difference between the independent components; when (when)The larger the independence characteristic between the n1 independent component signal and the n2 independent component signal is, the more the independence characteristic accords with the mutual independence rule between independent components; Presenting the difference in the magnitudes of the data points in the n1 st and n2 nd independent component signals when When the difference is larger, the larger the overall amplitude difference of the data points in the two independent component signals is, the more the independent characteristics between the two independent component signals accord with the rule of mutual independence between independent components; the independence between two independent component signals is comprehensively presented, and the average value/>, of the independence between the two independent component signals is used for The independence between independent component signals is measured, and the worse the independence between the independent component signals is, the degree of difference/>The smaller the signal, the greater the likelihood of noise components being present in the independent component signal.
Since the core idea of independent component analysis is to separate independent component signals from each other, if the degree of independence between the independent component signals is low, it is stated that the independent component signals contain shared information, which is an indication of noise, instead of independent information. Therefore, in the embodiment of the invention, the difference degree between the independent component signals is taken as the noise intensity in the original temperature signal.
Step S4: dividing each independent component signal into different local signal segments, and obtaining the amplitude average change rate of each local signal segment; and combining the discrete degree of the slope between adjacent data points in each independent component signal, the chaotic degree of the amplitude average change rate of the local signal section of each independent component signal and the independent characteristic value to obtain the noise membership degree of each independent component signal.
For accurate analysis of each independent component signal, each independent component signal is uniformly divided into L local signal segments. It should be noted that, the time periods corresponding to the different local signal periods are equal in duration. In the embodiment of the invention, L takes an experience value of 10, and an implementer can set the L according to specific conditions.
The specific acquisition method of the amplitude average change rate of the local signal segment comprises the following steps: for each local signal segment of each independent component signal, taking the absolute value of the difference between the amplitude of each data point in the local signal segment and the amplitude of the next adjacent data point as the local amplitude difference of each data point in the local signal segment; counting the sum of local amplitude differences of other data points except the last data point in the local signal section to be used as the comprehensive amplitude difference of the local signal section; taking the time interval between the corresponding moments of the data points of the two end points of the local signal section as the duration of the local signal section; and taking the ratio of the comprehensive amplitude difference and the duration of the local signal segment as the amplitude average change rate of the local signal segment. The rate of change of the amplitude average reflects the average rate of change of the amplitude of the data points in the local signal segment.
In the process of analyzing the original temperature signal by using the independent component analysis, since the core idea of the independent component analysis is to separate components independent of each other, noise generally has low energy for the signal, that is, there is some tiny "burr" on the surface of the independent component signal originally having the maximum non-gaussian property, so that the independent component signal has a certain gaussian property, and the distribution characteristics of the independent component signal are broken. Thus, it is necessary to acquire the degree of noise present in the independent component signal, i.e., the degree of noise membership.
The discrete degree of the slope between adjacent data points in the independent component signal presents the characteristic strength of the surface burrs of the signal, the chaotic degree of the amplitude average change rate of the local signal section of the independent component signal reflects the stable state of the signal in a certain time, and the acquired noise membership degree can accurately reflect the noise degree existing in the independent component signal by combining the independent characteristic value.
Preferably, the specific acquisition method of the noise membership degree is as follows: acquiring the slope between each data point in each independent component signal and the next adjacent data point as the slope value of each data point in each independent component signal; calculating the variance of the inclination values of the rest data points except the last data point in each independent component signal as the burr significance of each independent component signal; acquiring the information entropy of the amplitude average change rate of the local signal segment of each independent component signal as the change rate confusion of each independent component signal; according to the independent characteristic value of each independent component signal, the burr significance and the change rate confusion degree are obtained, and the noise membership degree of each independent component signal is obtained; the independent characteristic value and the noise membership degree are in a negative correlation relationship, and the burr significance degree and the change rate confusion degree are in a positive correlation relationship with the noise membership degree.
It should be noted that, in the embodiment of the present invention, the binary group of the data points in the independent component signal is constructed, if the binary group of the 1 st data point in the independent component signal is x1= (r 1, s 1), and the binary group of the 2 nd data point is x2= (r 2, s 2); wherein r1 is the time of the 1 st data point in the independent component signal, s1 is the amplitude of the 1 st data point in the independent component signal, r2 is the time of the 2 nd data point in the independent component signal, s2 is the amplitude of the 2 nd data point in the independent component signal; the 1 st data point in the independent component signal has a slope value of. According to the above method, the tilt value of each of the remaining data points in each of the independent component signals except for the last data point is calculated. The specific calculation mode of the information entropy is known in the art.
The calculation formula of the noise membership degree of each independent component signal is specifically exemplified as follows:
Wherein R is the noise membership degree of each independent component signal; f is an independent characteristic value of each independent component signal; HL is the rate of change confusion of each independent component signal; c is the total number of data points in each independent component signal; a tilt value for the remaining c-th data point in each independent component signal except for the last data point; /(I) Mean of tilt values for remaining data points in each independent component signal except for the last data point; /(I)A spur saliency for each individual feature value; norm is the normalization function; /(I)The empirical value of 0.1 is taken for the preset positive number, and the function is to prevent the denominator from being 0 to cause meaningless.
When (when)When the noise intensity contained in the independent component signal is relatively larger, the noise membership degree R is larger. Rate of change clutter/>, of independent component signalsReflecting the steady state of the independent component signal at a certain time, when/>The larger the difference is, the larger the variation rate of the amplitude of the data point in different local time periods in the independent component signal is, and the signal usually keeps a relatively stable state in a certain time period, and the noise component can destroy the stability of the signal in a certain time period; thus, when/>The larger the independent component signal is, the worse the stable state of the independent component signal at a certain time is, and the larger the noise intensity contained in the independent component signal is, the larger the noise membership degree R is. When the independent characteristic value F is larger, the non-Gaussian characteristic of the independent component signal is more obvious, the probability that the signal is separated into noise in the original temperature signal when the signal is separated is smaller, and the noise intensity contained in the independent component signal is smaller, so that the noise membership degree R is smaller.
Step S5: the noise membership degree is utilized to adjust the difference degree, and a filtering intensity value of each independent component signal is obtained; and filtering the independent component signals of the original temperature signals by using a filtering algorithm based on the filtering intensity values to obtain denoising temperature signals.
Since the core idea of independent component analysis is to separate independent component signals from each other, if the degree of independence between the independent component signals is low, it is stated that the independent component signals contain shared information, which is an indication of noise, instead of independent information. Therefore, in the embodiment of the present invention, the degree of difference between the independent component signals acquired in step S3 is taken as the noise intensity in the original temperature signal. And simultaneously, the noise intensity in the original temperature signal is adjusted through the noise degree contained in the independent separation signal, so that the filtering intensity value of the independent component signal is obtained.
And weighting the difference degree by using the noise membership degree of each independent component signal to obtain the filtering strength value of each independent component signal. The calculation formula of the filter intensity value of each independent component signal is as follows:
In the method, in the process of the invention, A filtered intensity value for the q-th independent component signal; /(I)Noise membership for the q-th independent component signal; /(I)Is the degree of difference between the independent component signals.
It should be noted that when the noise membership degreeThe larger the q-th independent component signal contains, the larger the noise intensity, and in order to ensure the denoising intensity of the independent component signal, the larger the filtering intensity is needed to remove the noise component contained in the independent component signal, and the filtering intensity value/>The larger. When the noise membership/>The smaller the q-th independent component signal contains, the smaller the noise intensity, and in order to avoid distortion of the signal caused by excessive filtering intensity, the smaller the filtering intensity needs to be used for removing the noise component contained in the independent component signal, and the filtering intensity value/>The smaller.
The application selects the Gaussian filter algorithm to carry out filtering treatment on the independent component signals, and the filter has wider response range due to larger standard deviation, so that the effect of smoothing images or signals is stronger, and the blurring degree is higher; conversely, a smaller standard deviation results in a smaller range of influence of the filter, weaker smoothing and lower blurring. Therefore, in the embodiment of the application, the filtering intensity value of each independent component signal is used as the standard deviation of a Gaussian filtering algorithm for filtering each independent component signal to obtain the filtering component signal of each independent component signal; reconstructing the filtered component signals of all independent component signals of the original temperature signal to obtain a denoising temperature signal.
It should be noted that in the embodiment of the present invention, the filtered component signals of all the independent component signals are reconstructed by using independent component analysis. The gaussian filtering algorithm is a well known technique for those skilled in the art, and will not be described herein.
By taking the filtering intensity value of each independent component signal as the standard deviation of the Gaussian filtering algorithm for filtering each independent component signal, the independent component signal with higher noise component has a larger filtering effect, and the independent component signal with higher noise component can better retain the effective information in the original signal. By independently denoising each independent component signal, the noise in each independent component signal can be reduced in a targeted manner, after the denoised independent component signal, namely the filtered component signal, is reconstructed, the information of the original temperature signal can be reserved to the greatest extent, the information loss is reduced, and the quality and the definition of the whole reconstructed signal, namely the denoised temperature signal, are improved.
Step S6: and (3) early warning the temperature of the hair straightening comb based on the amplitude difference of the data points in the denoising temperature signal and the normal temperature signal.
If the distribution characteristics between the denoising temperature signal and the normal temperature signal are similar, the temperature of the hair straightening comb in the current working time period is indicated to be normal temperature change; if the distribution characteristics between the denoising temperature signal and the normal temperature signal have larger difference, the temperature of the hair straightening comb in the current working time period is indicated to belong to abnormal temperature change. The difference condition between the distribution characteristics of the denoising temperature signal and the normal temperature signal is measured through the amplitude difference of the data points in the denoising temperature signal and the normal temperature signal in the embodiment.
Taking the denoising temperature signal and the normal temperature signal as analysis signals, and calculating the variance of the amplitude of the data points in the analysis signals as the amplitude dispersion of the analysis signals; normalizing the absolute value of the difference between the amplitude dispersion of the denoising temperature signal and the normal temperature signal to obtain the temperature difference; when the temperature difference is smaller than a preset difference threshold, the temperature of the hair straightening comb is in a normal state, and the temperature of the hair straightening comb is normal in the current working time period; when the temperature difference is greater than or equal to a preset difference threshold, the temperature of the hair straightening comb is in an abnormal state, the hair straightening comb can trigger a system alarm at the current moment, and the system automatically stops the heating function of the hair straightening comb so as to avoid damage caused by overhigh temperature.
It should be noted that, in the embodiment of the present invention, the preset difference threshold takes an empirical value of 0.7, and an implementer can set the preset difference threshold according to specific situations; normalization functions are used to normalize absolute values of differences between amplitude dispersion of the denoising temperature signal and the normal temperature signal, and normalization methods such as function conversion, maximum and minimum normalization, sigmoid function and the like can be selected in the embodiment of the invention, so that the method is not limited.
The present invention has been completed.
In summary, in the embodiment of the present invention, the independent characteristic value of each independent component signal of the original temperature signal is obtained, and the difference degree between the independent component signals is obtained according to the difference of the amplitude values of the data points in any two independent component signals and the difference of the independent characteristic values; combining the discrete degree of the slope between adjacent data points in the independent component signal and the chaotic degree and the independent characteristic value of the amplitude average change rate of the local signal section of the independent component signal, and adjusting the difference degree to obtain the filtering intensity value of the independent component signal; filtering the independent component signals by using a filtering algorithm based on the filtering intensity value to obtain a denoising temperature signal; and pre-warning the temperature of the hair straightening comb according to the amplitude difference of the data points in the signal of the temperature and the normal temperature. The invention adaptively acquires the filtering intensity value of the independent component signal, improves the denoising effectiveness of the original temperature signal, and increases the accuracy of temperature early warning of the hair straightening comb.
Based on the same inventive concept as the embodiment of the method, the embodiment of the invention also provides an automatic sensing temperature early warning system of a hair straightening comb, which comprises: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the steps in the embodiment of the automatic induction temperature pre-warning method for the hair straightening comb are realized when the processor executes the computer program, for example, the steps shown in fig. 1. The automatic sensing temperature early warning method for the hair straightening comb is described in detail in the above embodiments, and will not be repeated.
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.
The foregoing description of the preferred embodiments of the present invention is not intended to be limiting, but rather, any modifications, equivalents, improvements, etc. that fall within the principles of the present invention are intended to be included within the scope of the present invention.
Claims (7)
1. An automatic induction temperature early warning method for a hair straightening comb is characterized by comprising the following steps:
Respectively acquiring an original temperature signal of the hair straightening comb in a current working time period and a normal temperature signal of the hair straightening comb in a historical working time period;
Independent component analysis is carried out on the original temperature signals to obtain independent component signals; obtaining an independent characteristic value of each independent component signal according to the kurtosis value and the period degree of each independent component signal;
obtaining the difference degree between the independent component signals according to the difference between the amplitude difference of the data points in any two independent component signals and the independent characteristic value;
Dividing each independent component signal into different local signal segments, and obtaining the amplitude average change rate of each local signal segment; combining the discrete degree of the slope between adjacent data points in each independent component signal, the chaotic degree of the amplitude average change rate of the local signal section of each independent component signal and the independent characteristic value to obtain the noise membership degree of each independent component signal;
The noise membership degree is utilized to adjust the difference degree, and a filtering intensity value of each independent component signal is obtained; filtering the independent component signals of the original temperature signals by using a filtering algorithm based on the filtering intensity values to obtain denoising temperature signals;
Based on the amplitude difference of data points in the denoising temperature signal and the normal temperature signal, pre-warning the temperature of the hair straightening comb;
The method for obtaining the independent characteristic value of each independent component signal according to the kurtosis value and the period degree of each independent component signal comprises the following steps:
For each independent component signal, establishing a two-dimensional coordinate system by taking time as a horizontal axis and taking a temperature value as a vertical axis, and mapping the independent component signals into the two-dimensional coordinate system to obtain a signal curve segment; selecting any inflection point except the last inflection point in the signal curve segment as an analysis point, taking the next inflection point adjacent to the analysis point as a characteristic point of the analysis point, and respectively taking a vertical line of a transverse axis of the two-dimensional coordinate system as a characteristic line by passing through each characteristic point; enclosing the signal curve section, the two characteristic lines and the transverse axis into an analysis area taking the area as an analysis point; calculating the area of the analysis area as a characteristic area value of the analysis point;
according to the difference between the characteristic area values of any two inflection points except the last inflection point in the signal curve segment corresponding to the independent component signal, obtaining the cycle significance of the independent component signal;
Obtaining the kurtosis value of each independent component signal; combining the difference between the kurtosis value of each independent component signal and the kurtosis value of the standard Gaussian curve and the period significance to obtain the independent characteristic value of each independent component signal;
the calculation formula of the independent characteristic value of each independent component signal is as follows:
; wherein F is the independent eigenvalue of each independent component signal; k is the kurtosis value of each independent component signal; y is the kurtosis value of a standard Gaussian curve; m is the total number of inflection points in the signal curve segment corresponding to each independent component signal; /(I) The characteristic area value of a u-th inflection point in the signal curve segment corresponding to each independent component signal is obtained; /(I)The characteristic area value of the v inflection point in the signal curve segment corresponding to each independent component signal; /(I)-Said period significance for each individual component signal; /(I)As a function of absolute value; /(I)Is a preset positive number;
The calculation formula of the difference degree between the independent component signals is as follows:
; in the/> Is the degree of difference between the independent component signals; n is the total number of independent component signals; /(I)The independent eigenvalue for the n1 st independent component signal; /(I)The independent eigenvalues for the n2 nd independent component signal; /(I)Total number of data points in the n1 st independent component signal; /(I)The amplitude of the a-th data point in the n 1-th independent component signal; /(I)Total number of data points for the n2 nd independent component signal; /(I)The amplitude of the b data point in the n2 independent component signal; /(I)As a function of absolute value.
2. The method for automatically sensing temperature for a hair straightening comb according to claim 1, wherein the method for obtaining the amplitude average change rate of each local signal segment comprises the following steps of;
For each local signal segment of each independent component signal, taking the absolute value of the difference between the amplitude of each data point in the local signal segment and the amplitude of the next adjacent data point as the local amplitude difference of each data point in the local signal segment; counting the sum of the local amplitude differences of the rest data points except the last data point in the local signal section to be used as the comprehensive amplitude difference of the local signal section;
Taking the time interval between the corresponding moments of the data points of the two end points of the local signal section as the duration of the local signal section;
and taking the ratio of the comprehensive amplitude difference of the local signal section to the duration as the amplitude average change rate of the local signal section.
3. The method for automatically sensing temperature for a hair straightening comb according to claim 1, wherein the method for obtaining the noise membership degree of each independent component signal comprises the following steps:
Acquiring the slope between each data point in each independent component signal and the next adjacent data point as the slope value of each data point in each independent component signal; calculating the variance of the inclination values of the rest data points except the last data point in each independent component signal as the burr saliency of each independent component signal;
acquiring information entropy of the amplitude average change rate of the local signal segment of each independent component signal as the change rate confusion of each independent component signal;
According to the independent characteristic value of each independent component signal, the burr significance and the change rate confusion degree are obtained, and the noise membership degree of each independent component signal is obtained; and the independent characteristic value and the noise membership degree are in a negative correlation relationship, and the burr significance degree and the change rate confusion degree are in a positive correlation relationship with the noise membership degree.
4. The method for automatically sensing temperature for a hair straightening comb according to claim 1, wherein the method for obtaining the filtering intensity value of each independent component signal comprises the following steps:
And weighting the difference degree by using the noise membership degree of each independent component signal to obtain a filtering intensity value of each independent component signal.
5. The method for automatically sensing temperature early warning of a hair straightening comb according to claim 1, wherein the method for filtering independent component signals of an original temperature signal by using a filtering algorithm based on the filtering intensity value to obtain a denoising temperature signal comprises the following steps:
The filtering intensity value of each independent component signal is used as the standard deviation of a Gaussian filtering algorithm for filtering each independent component signal, and the filtering component signal of each independent component signal is obtained;
Reconstructing the filtered component signals of all independent component signals of the original temperature signal to obtain the denoising temperature signal.
6. The automatic induction temperature pre-warning method for a hair straightening comb according to claim 1, wherein the pre-warning heating method for the temperature of the hair straightening comb based on the amplitude difference between the data points in the denoising temperature signal and the normal temperature signal comprises the following steps:
Taking the denoising temperature signal and the normal temperature signal as analysis signals, and calculating the variance of the amplitude of the data points in the analysis signals as the amplitude dispersion of the analysis signals;
normalizing the absolute value of the difference between the amplitude dispersion of the denoising temperature signal and the normal temperature signal to obtain a temperature difference;
When the temperature difference is smaller than a preset difference threshold, the temperature of the hair straightening comb is in a normal state; when the temperature difference is greater than or equal to a preset difference threshold, the temperature of the hair straightening comb is in an abnormal state.
7. An automatic induction temperature pre-warning system for a hair straightening comb, which is characterized by comprising: a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of a method for automatically sensing temperature for a hair straightening comb as claimed in any one of the preceding claims 1 to 6 when the computer program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410410756.7A CN118010165B (en) | 2024-04-08 | 2024-04-08 | Automatic induction temperature early warning method and system for hair straightening comb |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410410756.7A CN118010165B (en) | 2024-04-08 | 2024-04-08 | Automatic induction temperature early warning method and system for hair straightening comb |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118010165A CN118010165A (en) | 2024-05-10 |
| CN118010165B true CN118010165B (en) | 2024-06-11 |
Family
ID=90952784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410410756.7A Active CN118010165B (en) | 2024-04-08 | 2024-04-08 | Automatic induction temperature early warning method and system for hair straightening comb |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118010165B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07160508A (en) * | 1993-12-10 | 1995-06-23 | Fujitsu Ltd | Filter coefficient deciding method for adaptive filter |
| EP1384604A1 (en) * | 2002-07-24 | 2004-01-28 | The Goodyear Tire & Rubber Company | Method for processing information in a tire pressure monitoring system |
| CN102628356A (en) * | 2012-03-22 | 2012-08-08 | 中国石油天然气股份有限公司 | Method for inhibiting temperature monitoring noise of heavy oil thermal production well |
| CN104688220A (en) * | 2015-01-28 | 2015-06-10 | 西安交通大学 | Method for removing ocular artifacts in EEG signals |
| CN108646296A (en) * | 2018-05-16 | 2018-10-12 | 吉林大学 | Desert seismic signal noise reduction methods based on Adaptive spectra kurtosis filter |
| CN109001703A (en) * | 2018-08-10 | 2018-12-14 | 南京信息工程大学 | A kind of sea clutter denoising method based on the processing of wavelet packet multi-threshold |
| CN111982302A (en) * | 2020-08-24 | 2020-11-24 | 广东工业大学 | Temperature measurement method with noise filtering and environment temperature compensation |
| CN113092114A (en) * | 2021-04-08 | 2021-07-09 | 陕西科技大学 | Bearing fault diagnosis method and device and storage medium |
| CN113780056A (en) * | 2021-07-22 | 2021-12-10 | 山东科技大学 | Rolling bearing fault diagnosis method based on vibration signal |
| CN114658645A (en) * | 2022-03-15 | 2022-06-24 | 中国石油化工股份有限公司 | Multi-source signal fusion early warning method for reciprocating compressor |
| CN116049632A (en) * | 2022-11-14 | 2023-05-02 | 苏州城市学院 | Wind power main shaft bearing fault diagnosis method, device and application |
| CN116451029A (en) * | 2023-06-15 | 2023-07-18 | 深圳瑞福来智能科技股份有限公司 | Dehumidifier working state early warning method |
| WO2024027246A1 (en) * | 2022-08-05 | 2024-02-08 | 深圳Tcl新技术有限公司 | Sound signal processing method and apparatus, and electronic device and storage medium |
-
2024
- 2024-04-08 CN CN202410410756.7A patent/CN118010165B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07160508A (en) * | 1993-12-10 | 1995-06-23 | Fujitsu Ltd | Filter coefficient deciding method for adaptive filter |
| EP1384604A1 (en) * | 2002-07-24 | 2004-01-28 | The Goodyear Tire & Rubber Company | Method for processing information in a tire pressure monitoring system |
| CN102628356A (en) * | 2012-03-22 | 2012-08-08 | 中国石油天然气股份有限公司 | Method for inhibiting temperature monitoring noise of heavy oil thermal production well |
| CN104688220A (en) * | 2015-01-28 | 2015-06-10 | 西安交通大学 | Method for removing ocular artifacts in EEG signals |
| CN108646296A (en) * | 2018-05-16 | 2018-10-12 | 吉林大学 | Desert seismic signal noise reduction methods based on Adaptive spectra kurtosis filter |
| CN109001703A (en) * | 2018-08-10 | 2018-12-14 | 南京信息工程大学 | A kind of sea clutter denoising method based on the processing of wavelet packet multi-threshold |
| CN111982302A (en) * | 2020-08-24 | 2020-11-24 | 广东工业大学 | Temperature measurement method with noise filtering and environment temperature compensation |
| CN113092114A (en) * | 2021-04-08 | 2021-07-09 | 陕西科技大学 | Bearing fault diagnosis method and device and storage medium |
| CN113780056A (en) * | 2021-07-22 | 2021-12-10 | 山东科技大学 | Rolling bearing fault diagnosis method based on vibration signal |
| CN114658645A (en) * | 2022-03-15 | 2022-06-24 | 中国石油化工股份有限公司 | Multi-source signal fusion early warning method for reciprocating compressor |
| WO2024027246A1 (en) * | 2022-08-05 | 2024-02-08 | 深圳Tcl新技术有限公司 | Sound signal processing method and apparatus, and electronic device and storage medium |
| CN116049632A (en) * | 2022-11-14 | 2023-05-02 | 苏州城市学院 | Wind power main shaft bearing fault diagnosis method, device and application |
| CN116451029A (en) * | 2023-06-15 | 2023-07-18 | 深圳瑞福来智能科技股份有限公司 | Dehumidifier working state early warning method |
Non-Patent Citations (2)
| Title |
|---|
| Jes ú s Manuel J áquez-Muñoz.Frequency Analysis of Transients in Electrochemical Noise of Superalloys Waspaloy and Ultimet.metals.2021,全文. * |
| 王晓卫，王雪，王毅钊，张志华，梁振锋 .基于图像信息熵与多元变分模态分解的电缆局放信号去噪方法.电工技术学报.2023,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118010165A (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109117730B (en) | Real-time electrocardiogram atrial fibrillation judgment method, device and system and storage medium | |
| US9042973B2 (en) | Apparatus and method for measuring physiological signal quality | |
| US8041136B2 (en) | System and method for signal processing using fractal dimension analysis | |
| CN110547783A (en) | non-contact heart rate detection method, system, equipment and storage medium | |
| EP2777485B1 (en) | Signal processor, signal processing method, and signal processing program | |
| US9848784B2 (en) | Method for determining the physical and/or psychological state of a subject | |
| CN104523265B (en) | Abnormal electrocardiogram data judgment method and device | |
| CN110840443B (en) | Electrocardiosignal processing method, electrocardiosignal processing device and electronic equipment | |
| WO2019216378A1 (en) | Calculation device, detection device, calculation method, and computer program | |
| CN117649357A (en) | Ultrasonic image processing method based on image enhancement | |
| CN112494001B (en) | PPG signal quality evaluation method and device, wearable device and storage medium | |
| CN117235652B (en) | Steel wire processing environment supervision method and system based on big data | |
| CN111860102A (en) | Apparatus and method for analyzing state of system in noisy environment | |
| CN116269355A (en) | Safety monitoring system based on figure gesture recognition | |
| CN118010165B (en) | Automatic induction temperature early warning method and system for hair straightening comb | |
| CN117807551B (en) | Heart rate abnormality capturing method and system based on intelligent ring | |
| KR101483756B1 (en) | Method for detecting PPG signal | |
| CN109002758B (en) | Face feature point positioning method, device, equipment and storage medium | |
| JP2018020018A (en) | Biological signal processor, abnormality determination method, and program | |
| CN113057655A (en) | Recognition method, recognition system and detection system for electroencephalogram signal interference | |
| CN113768499A (en) | Blood oxygen saturation detection device, system and storage medium | |
| CN109567750B (en) | Sleep stage determination method and device and computer equipment | |
| CN117115174B (en) | Automatic detection method and system for appearance of pliers | |
| CN110674681A (en) | Identity verification method and device based on attention mechanism | |
| CN114403889B (en) | NN interval signal acquisition device, NN interval signal acquisition system and storage medium |
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 |