CN117171542A - UWB ranging data processing method in six-minute walking test - Google Patents
UWB ranging data processing method in six-minute walking test Download PDFInfo
- Publication number
- CN117171542A CN117171542A CN202311026351.5A CN202311026351A CN117171542A CN 117171542 A CN117171542 A CN 117171542A CN 202311026351 A CN202311026351 A CN 202311026351A CN 117171542 A CN117171542 A CN 117171542A
- Authority
- CN
- China
- Prior art keywords
- data
- item
- point
- points
- representing
- 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.)
- Granted
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 36
- 238000003672 processing method Methods 0.000 title claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 27
- 230000009467 reduction Effects 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000011947 six minute walk test Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 3
- 230000036391 respiratory frequency Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 8
- 230000000694 effects Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000036387 respiratory rate Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 208000011580 syndromic disease Diseases 0.000 description 3
- 230000002612 cardiopulmonary effect Effects 0.000 description 2
- 230000037080 exercise endurance Effects 0.000 description 2
- 230000037081 physical activity Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000004217 heart function Effects 0.000 description 1
- 230000004199 lung function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a UWB ranging data processing method in six-minute walking test, which comprises the following steps: acquiring various data in a six-minute walking test; acquiring all characteristic points in each item of data according to each item of data; acquiring sub-data segments of each item of data according to all characteristic points in each item of data; acquiring the overall correlation of all data according to the sub-data segments of each item of data; acquiring data points covered by each maximum value point in each item of data according to the maximum value point in each item of data; acquiring local correlation relations of all data according to data points covered by each maximum value point; obtaining a confusion coefficient from the overall correlation of all data and the local correlation of all data; and performing dimension reduction processing on each item of data according to the confusion coefficient to obtain dimension reduced data. The invention focuses on the change of local data and the change of whole data, so that the invention can achieve better effect when the data dimension reduction is carried out.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a UWB ranging data processing method in six-minute walking test.
Background
Six-minute walking test is a common physical activity assessment method for assessing exercise endurance and cardiopulmonary function of a person, in which a subject is required to walk as far as possible within six minutes at a normal walking speed, and then distance data of the subject is recorded by UWB ranging technology. UWB ranging (Ultra-wide ranging) is a ranging method based on Ultra-Wideband technology that uses very short pulse signals exchanged between transmitting and receiving devices to measure the distance between objects. The principle is that the distance between the object and the distance measuring device can be calculated according to the propagation speed of the signal by sending a high-speed pulse signal in a specific frequency range and measuring the time delay of the signal from the transmitter to the target object and back to the receiver. In the whole test process, not only distance data of the tested person but also data such as heart rate, respiratory rate, step number and the like are required to be monitored, and then the syndrome of the tested person is evaluated. Because the monitoring data have certain independence, the calculation amount is large when the multidimensional data are comprehensively analyzed, and therefore the obtained data need to be subjected to dimension reduction processing.
In the prior art, a plurality of dimension reduction algorithms are performed on data, wherein the t-SNE (t-Distributed Stochastic NeighborEmbedding) algorithm is a nonlinear dimension reduction algorithm and is commonly used for visualizing high-dimension data, and the high-dimension data can be mapped into a low-dimension space, usually two-dimensional or three-dimensional, so as to better understand the structure and similarity of the data. However, the t-SNE algorithm mainly focuses on the local similarity of the data in the data dimension reduction, but ignores the global structure, and in some cases, the t-SNE may present some global structure information as a local clustering phenomenon, so that interpretation of the result becomes difficult. While confusion is a key parameter of the t-SNE that is used to control the number of adjacent data points around each data point in the high-dimensional space. A larger confusion value may result in more global structure being preserved, but may also introduce excessive noise.
Disclosure of Invention
The invention provides a UWB ranging data processing method in six-minute walking test, which aims to solve the existing problems.
The UWB ranging data processing method in six-minute walking test adopts the following technical scheme:
one embodiment of the present invention provides a method for processing UWB ranging data in six-minute walk test, comprising the steps of:
acquiring various data in a six-minute walking test;
acquiring the possible degree of all data points in each item of data as characteristic points according to each item of data; acquiring all the characteristic points in each item of data according to the possible degree that all the data points in each item of data are characteristic points;
dividing each item of data according to the characteristic points in each item of data to obtain a plurality of sub-data segments of each item of data; acquiring the degree of correlation between each item of data according to the sub-data segment of each item of data; acquiring the overall correlation of all data according to the correlation degree among various data;
dividing all data points in each item of data according to the maximum value points in each item of data, and obtaining the data points covered by each maximum value point in each item of data; acquiring local correlation relations of all data according to data points covered by each maximum value point in each item of data; obtaining a confusion coefficient according to the overall correlation of all the data and the local correlation of all the data; and performing dimension reduction processing on each item of data according to the confusion coefficient to obtain dimension reduced data.
Preferably, the specific calculation formula included in the obtaining the degree of possibility that all data points in each item of data are feature points is as follows:
wherein p is l，i Representing the possibility degree that the ith data point in the first item data is a characteristic point;F i representing the magnitude of the ith data point in the first item of data; f (F) l，min Representing a minimum amplitude in the first item of data; k (k) l，i Representing the slope of the ith data point in the first item of data; sigma (sigma) l Representing the variance of the first item of data; sigma (sigma) l，(i±a) Representing the variance of all data from the i-a data point to the i+a data point in the data of the first term; wherein a is a preset time range; norm represents the normal normalization function.
Preferably, the step of acquiring all feature points in each item of data includes the following specific steps:
presetting a characteristic point threshold gamma; for the ith data point in the ith data, when the ith data point in the ith data is the probability degree p of the feature point l，i When the data is more than gamma, the ith data point in the first item of data is a characteristic point; the degree of probability p that the ith data point in the ith item of data is a feature point l，i And if the gamma is less than or equal to the gamma, the ith data point in the first item of data is not a characteristic point, and all the characteristic points in each item of data are acquired in a similar way.
Preferably, the obtaining the degree of correlation between the data includes the following specific calculation formula:
wherein K (l, h) represents a degree of correlation between the first item data and the h item data;representing the average value of all the amplitude values in the jth sub-data section in the first item of data; />Representing the average value of all the amplitude values in the jth sub-data segment in the h item of data; n is n l，j Representing the number of data points in the jth sub-data segment in the first item of data; n is n h,j Representing the number of data points in the jth sub-data segment in the h item of data; t is t l Representing the number of sub-data segments in the first item of data; t is t h Representing the number of sub-data segments in the h item of data;representing the magnitude of the qth data point in the jth sub-data segment in the ith item of data; />Representing the magnitude of the q data point in the j-th sub-data segment in the h-th item data; DTW () is a DTW distance; exp () represents an exponential function based on a natural constant.
Preferably, the step of obtaining the overall correlation of all the data includes the following specific steps:
recording the degree of correlation between the various data, and taking the degree of correlation between the various data into a set to be recorded as a degree of correlation set; the ratio of the mean value of all elements in the correlation degree set to the variance of all elements is taken as the overall correlation of all data.
Preferably, the dividing all the data points in each item of data according to the maximum value points in each item of data to obtain the data points covered by each maximum value point in each item of data comprises the following specific steps:
counting the number of data points at intervals between the ith data point in the ith data and all maximum points in the first data to obtain a plurality of data point numbers at intervals; taking a maximum value point corresponding to the minimum interval data point number in the interval data point numbers as a maximum value point Z covering the ith data point in the first item data, wherein the ith data point in the first item data is the data point covered by the maximum value point Z, and similarly, obtaining the maximum value point covering each data point in the first item data; and similarly, acquiring data points covered by each maximum value point.
Preferably, the obtaining the local correlation of all data includes the following specific calculation formula:
wherein Y represents the local correlation of all data; w represents the number of each item of data; b (B) l Representing the number of maximum points in the first item of data; a is that l，x Representing the number of data points covered by the xth maximum point in the first item of data;representing the magnitude of the x-th maximum point in the first item of data; f (F) lx，i Representing the amplitude of an ith data point covered by an xth maximum point in the first item of data; c (C) l Representing the number of data points in the first item of data; f (F) l，i Amplitude of the ith data point in the first item of data; f (F) l，(i+1) Representing the (i+1) th data point in the first item of data; f (F) l，(i-1) Representing the (i-1) th data point in the first item of data.
Preferably, the obtaining the confusion degree coefficient includes the following specific steps:
taking the product of the overall correlation of all data and the local correlation of all data as a confusion coefficient, and adopting a specific calculation formula as follows:
τ＝P×Y
where τ represents a confusion factor; p represents the overall correlation of all data; y represents the local correlation of all data.
Preferably, the step of acquiring each item of data in the six-minute walking test comprises the following specific steps:
the walking distance data of the testers are obtained through a UWB ranging method, and then the heart rate data, the respiratory frequency data and the step number data of the testers are obtained through portable heart rate monitoring equipment carried by the testers.
Preferably, the dimension reduction processing is performed on each item of data according to the confusion coefficient to obtain dimension reduced data, which comprises the following specific steps:
and according to the obtained confusion coefficient, performing dimension reduction processing on each item of data in the six-minute walking test by using a t-SNE algorithm to obtain dimension reduced data.
The technical scheme of the invention has the beneficial effects that: aiming at the problem that when the dimension reduction is carried out on data by the t-SNE algorithm, because the algorithm mainly focuses on the local similarity of the data and ignores the global structure, in some cases, the t-SNE can present some global structure information as a local clustering phenomenon, so that the interpretation of results becomes difficult.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart showing steps of a UWB ranging data processing method in a six-minute walk test according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description refers to specific implementation, structure, characteristics and effects of a UWB ranging data processing method in six-minute walking test 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 specifically describes a specific scheme of a UWB ranging data processing method in six-minute walking test provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a UWB ranging data processing method in a six-minute walking test according to an embodiment of the present invention is shown, the method comprising the steps of:
step S001: and collecting various data in the six-minute walking test, and sending the collected various data into a data processing system.
In the six-minute walking test, which is a common physical activity assessment method for assessing exercise endurance and cardiopulmonary function of a person, a tester is required to walk as far as possible within six minutes at a normal walking speed, and then distance data of the tester is recorded by UWB ranging technology. In the whole test process, not only distance data of the tested person but also data such as heart rate, respiratory rate, step number and the like are required to be monitored, and then the syndrome of the tested person is evaluated. Because the monitoring data have certain independence, the calculation amount is large when the multidimensional data are comprehensively analyzed, and therefore the obtained data need to be subjected to dimension reduction processing.
Specifically, the walking distance data of the testers are obtained through the UWB ranging method, and the UWB ranging method is a well-known technology, so that details are omitted in the embodiment, and then all data such as heart rate data, respiratory frequency data, step number data and the like of the testers are obtained through portable heart rate monitoring equipment carried by the testers; and transmitting all the obtained data to a data processing system in a wireless transmission mode, and processing the data such as distance, step number, heart rate, respiratory rate and the like.
Step S002: and acquiring all characteristic points in each item of data according to each item of data.
The main purpose of this embodiment is to perform dimension reduction processing on each item of data of a tester in a six-minute walk test; because the six-minute walking test is to record the walking distance of the tester in the six-minute walking test and evaluate the heart and lung functions of the tester in the central rate data, the respiratory rate data, the step number data and other data of the tester in the six-minute walking test; however, certain independence exists among various data of the testers in the six-minute walking test, and the overall correlation relation of all the data cannot be obtained directly through the various data of the testers in the six-minute walking test, so that the correlation among the various data needs to be analyzed, and then the obtained various data are subjected to dimension reduction according to the correlation existing among the various data.
It should be further noted that, in this embodiment, the dimension of each item of data is reduced based on the concept of t-SNE algorithm, and the t-SNE algorithm is a nonlinear dimension-reducing algorithm, which is commonly used for visualizing high-dimension data, and it can map the high-dimension data to a low-dimension space, so as to better understand the structure and correlation of the data; however, the traditional t-SNE algorithm mainly focuses on the local correlation of the data in the process of dimension reduction of the data, but ignores the global structure, and in the scene of six-minute walking test, the t-SNE may present certain global structure information as a local clustering phenomenon, so that interpretation of results becomes difficult. While confusion is a key parameter of the t-SNE that is used to control the number of adjacent data points around each data point in the high-dimensional space. A larger confusion value may result in more global structure being preserved, but may also introduce excessive noise. The present embodiment balances global structure and local correlation by adjusting the confusion factor, which represents the criterion that each data point selects a neighboring point, with lower confusion giving each point more attention to the correlation of its local neighborhood, while higher confusion increases the impact of the global structure. Therefore, correlation analysis is needed to be performed on multidimensional data first, and influence relations among the data are obtained.
Specifically, each item of collected data is arranged according to a time sequence, so that the change of each item of data along with time is obtained, each item of data along with time is projected into the same two-dimensional space, and the change of each item of data along with different time periods is obtained.
It should be noted that, in the whole exercise process of the six-minute walking test, the heart rate, the respiratory rate and other data of the testers are usually accelerated gradually along with the increase of the exercise distance of the testers, but in different exercise phases, the variation degree of each item of data is different, and meanwhile, in different time periods, the exercise phases of the testers are also different, so that the variation degree of each data point in each item of data needs to be obtained according to the variation of each item of data in different time periods.
The calculation formula for obtaining the change degree of the data points in each item of data according to the change of each item of data in different time periods is as follows:
wherein p is l，i Representing the possibility degree that the ith data point in the first item data is a characteristic point; f (F) i Representing the magnitude of the ith data point in the first item of data; f (F) l，min Representing a minimum amplitude in the first item of data; k (k) l，i Representing the slope of the ith data point in the first item of data; sigma (sigma) l Representing the variance of the first item of data; sigma (sigma) l，(i±a) Representing the variance of all data from the i-a data point to the i+a data point in the data of the first term; wherein a is a preset time range, the specific value of a can be set in combination with the actual situation, the hard requirement is not required in the embodiment, and in the embodiment, a=5 is used for calculation; norm represents the normal normalization function.
It should be further noted that (F) l，i -F l，mim ) Indicating the difference between the amplitude of the ith data point in the ith data and the minimum amplitude point in the first data, if the amplitude difference is larger, indicating that the monitoring data are changed to a larger extent under the movement amount at the moment; slope k of the ith data point in the ith data l，i The larger the variation degree of the ith data point in the ith data is, and the larger the overall variance of the amplitude values in the adjacent time periods of the ith data point in the ith data and the ith data amplitude is, the larger the monitoring data storage of the ith data point tester in the ith data isAt large fluctuations, it is therefore important to pay attention. The degree of probability p that the ith data point in the ith item of data is a feature point l，i The larger the data point is, the larger the fluctuation of the ith data point in the first item data is, the degree p of possibility that the ith data point in the first item data is taken as a characteristic point l，i And acquiring the characteristic points in the first item of data.
Specifically, by presetting a feature point threshold value γ, a specific value of γ may be set in combination with an actual situation, and the hard requirement is not made in this embodiment, and in this embodiment, γ=0.72 is described. The degree of probability p that the ith data point in the ith item of data is a feature point l，j When the data is more than gamma, the ith data point in the first item of data is a characteristic point; conversely, when the ith data point in the first item data is the probability p of the feature point l，i And if gamma is less than or equal to gamma, the ith data point in the first item of data is not a characteristic point.
Then, all feature points in the first item of data are acquired; and similarly, obtaining all characteristic points in each item of data.
So far, all characteristic points in each item of data are obtained.
Step S003: acquiring a plurality of sub-data segments of each item of data according to the characteristic points in each item of data; acquiring the degree of correlation between each item of data according to the sub-data segment of each item of data; and acquiring the overall correlation of all the data according to the correlation degree among the data.
1. And acquiring the degree of correlation between the various data according to all the characteristic points in the various data.
It should be noted that, because each item of data has a relationship with exercise intensity, each item of data changes to a certain extent as the six-minute walking test proceeds, and the data change between adjacent feature points in each item of data is small, so according to the feature points in each item of data, sub-data segments of each item of data are acquired, and because the data difference in each sub-data segment is small, and the data difference between each sub-data segment is large, the degree of correlation between each item of data is calculated according to each item of data and the sub-data segment of each item of data.
Specifically, firstly, according to the characteristic points in each item of data, each item of data is segmented to obtain a plurality of sub-data segments of each item of data, and according to the plurality of sub-data segments of each item of data, the correlation between each item of data is calculated, wherein a specific calculation formula is as follows:
wherein K (l, h) represents a degree of correlation between the first item data and the h item data;representing the average value of all the amplitude values in the jth sub-data section in the first item of data; />Representing the average value of all the amplitude values in the jth sub-data segment in the h item of data; n is n l，j Representing the number of data points in the jth sub-data segment in the first item of data; n is n h，j Representing the number of data points in the jth sub-data segment in the h item of data; t is t l Representing the number of sub-data segments in the first item of data; t is t h Representing the number of sub-data segments in the h item of data;representing the magnitude of the qth data point in the jth sub-data segment in the ith item of data; />Representing the magnitude of the q data point in the j-th sub-data segment in the h-th item data; DTW () is a DTW distance, and since the DTW distance is a well-known technique, description is not repeated in this embodiment, and DTW (l, h) represents the correlation between the first item of data and the h item of data calculated by the DTW algorithm; exp () represents an exponential function based on a natural constant.
It should be further noted that,characterization is the fluctuation of the first item of data; but->The characteristic is the fluctuation of the h item data, if the first item data is more relevant to the h item data, the fluctuation of the first item data is +.>Fluctuation conditions with the h item of data The ratio of (2) is more nearly 1, so when +.>The smaller the value of (a) the more relevant the first item data and the h item data are, whereas when + ∈)>The greater the value of (2), the less relevant the first item data and the h item data are; thus the present embodiment is for->The values of (c) are inversely normalized such that the greater the value of the degree of correlation K (l, h) between the first item of data and the h item of data, the more relevant the first item of data and the h item of data, whereas the smaller the value of the degree of correlation K (l, h) between the first item of data and the h item of data, the less relevant the first item of data and the h item of data.
So far, the degree of correlation K (l, h) between the first item of data and the h item of data is obtained, and the degree of correlation between the various items of data is obtained in a similar way.
2. And acquiring the overall correlation of all the data according to the correlation degree among the data.
It should be noted that, in this embodiment, since there are a plurality of items of data, and there are a plurality of combinations between the items of data, it is necessary to obtain the overall correlation of all the data according to all the combinations between the items of data.
Specifically, the degree of correlation between each item of data is recorded, the degree of correlation between each item of data is incorporated into a set and recorded as a degree of correlation set, and the overall correlation of all the data is obtained according to the degree of correlation set, wherein the specific calculation formula is as follows:
wherein P represents the overall correlation of all data; r represents the number of elements in the correlation degree set; k (K) v A value representing a v-th element in the set of degrees of correlation; σ represents the variance of all elements in the set of degrees of correlation.
It should be further noted that, if each element in the correlation degree set is the correlation degree between different items of data in the six-minute walking test, thenThe mean value of the degree of correlation between the data in the six-minute walk test is characterized by +.>The larger the overall correlation of all data in the six-minute walk test is, the higher the overall correlation of all data in the six-minute walk test is; the sigma represents the variance of the correlation degree among various data in the six-minute walking test, namely the difference degree of the correlation degree among various data in the six-minute walking test, and the larger the sigma is, the lower the overall correlation relation among all data in the six-minute walking test is; the greater P the overall correlation of all data in the six-minute walk test, the higher, whereas the smaller P the overall correlation of all data in the six-minute walk test, the lower.
So far, the whole correlation relation of all the data is obtained.
Step S004: acquiring local correlation relations of all data according to maximum value points in various data; and obtaining the confusion coefficient according to the overall correlation of all the data and the local correlation of all the data.
It should be noted that, because the confusion factor indicates a criterion that each data point selects a neighboring point, that is, an influence of its neighboring data on the current data point when the data is in the dimension reduction. Because redundant data points are mainly removed when the data dimension is reduced, important information in the data is kept as much as possible, and the dimension of the data is reduced, when the confusion degree is calculated, the relation of global data is required to be considered, and the change relation among neighborhood data points is also required to be considered.
Specifically, taking the ith data point in the first item of data as an example, counting the number of data points at intervals between the ith data point in the first item of data and all maximum points in the first item of data to obtain a plurality of data point numbers at intervals; taking a maximum value point corresponding to the minimum interval data point in the interval data point numbers as a maximum value point covering the ith data point; similarly, data points covered by each maximum value point in each item of data are obtained;
and then, according to the data points covered by each maximum value point in each item of data, acquiring the local correlation of all the data, wherein the specific calculation formula is as follows:
wherein Y represents the local correlation of all data; w represents the number of each item of data; b (B) l Representing the number of maximum points in the first item of data; a is that l，x Representing the number of data points covered by the xth maximum point in the first item of data;representing the magnitude of the x-th maximum point in the first item of data; f (F) lx，i Representing the amplitude of an ith data point covered by an xth maximum point in the first item of data; c (C) l Representing the number of data points in the first item of data; f (F) l，i Amplitude of the ith data point in the first item of data; f (F) l，(i+1) Representing the (i+1) th data point in the first item of data; f (F) l，(i-1) Representing the (i-1) th data point in the first item of data.
It should be noted that when there is only one data point and there is only one data point in the ith data point in the first item data, only one data point adjacent to the ith data point is selected.
So far, the local correlation of all the data is obtained.
And finally, taking the product of the overall correlation of all data and the local correlation of all data as a confusion coefficient, wherein a specific calculation formula is as follows:
τ＝P×Y
where τ represents a confusion factor; p represents the overall correlation of all data; y represents the local correlation of all data.
Thus, the confusion factor is obtained.
Step S005: and performing dimension reduction processing on each item of data according to the confusion coefficient to obtain dimension reduced data.
According to the obtained confusion degree coefficient, the dimension reduction processing is performed on each item of data in the six-minute walking test by using a t-SNE algorithm, and as the t-SNE algorithm is the prior known technology, the description is not repeated in the embodiment, the dimension reduced data are obtained, and then the syndrome of the tested person is evaluated according to the dimension reduced data.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. The UWB ranging data processing method in six-minute walking test is characterized by comprising the following steps:
acquiring various data in a six-minute walking test;
acquiring the possible degree of all data points in each item of data as characteristic points according to each item of data; acquiring all the characteristic points in each item of data according to the possible degree that all the data points in each item of data are characteristic points;
dividing each item of data according to the characteristic points in each item of data to obtain a plurality of sub-data segments of each item of data; acquiring the degree of correlation between each item of data according to the sub-data segment of each item of data; acquiring the overall correlation of all data according to the correlation degree among various data;
dividing all data points in each item of data according to the maximum value points in each item of data, and obtaining the data points covered by each maximum value point in each item of data; acquiring local correlation relations of all data according to data points covered by each maximum value point in each item of data; obtaining a confusion coefficient according to the overall correlation of all the data and the local correlation of all the data; and performing dimension reduction processing on each item of data according to the confusion coefficient to obtain dimension reduced data.
2. The method for processing UWB ranging data in six-minute walk test according to claim 1, wherein the obtaining the degree of possibility that all data points in each item of data are feature points comprises the following specific calculation formula:
wherein p is l，i Representing the possibility degree that the ith data point in the first item data is a characteristic point; f (F) i Representing the magnitude of the ith data point in the first item of data; f (F) l，min Representing a minimum amplitude in the first item of data; k (k) l，i Representing the slope of the ith data point in the first item of data; sigma (sigma) l Representing the variance of the first item of data; sigma (sigma) l，(i±a) Representing the variance of all data from the i-a data point to the i+a data point in the data of the first term; wherein a is a preset time range; norm represents the normal normalization function.
3. The method for processing UWB ranging data in six-minute walk test according to claim 1, wherein the step of acquiring all the feature points in each item of data comprises the steps of:
presetting a characteristic point threshold gamma; for the ith data point in the ith data, when the ith data point in the ith data is the probability degree p of the feature point l，j When the data is more than gamma, the ith data point in the first item of data is a characteristic point; the degree of probability p that the ith data point in the ith item of data is a feature point l，i And if the gamma is less than or equal to the gamma, the ith data point in the first item of data is not a characteristic point, and all the characteristic points in each item of data are acquired in a similar way.
4. The method for processing UWB ranging data in six-minute walk test according to claim 1, wherein the obtaining the degree of correlation between the data comprises the following specific calculation formula:
wherein K (l, h) represents a degree of correlation between the first item data and the h item data;representing the average value of all the amplitude values in the jth sub-data section in the first item of data; />Representing the average value of all the amplitude values in the jth sub-data segment in the h item of data; n is n l，j Representing the number of data points in the jth sub-data segment in the first item of data; n is n h，j Representing the number of data points in the jth sub-data segment in the h item of data; t is t l Representing the number of sub-data segments in the first item of data; t is t h Representing the number of sub-data segments in the h item of data; />Representing the magnitude of the qth data point in the jth sub-data segment in the ith item of data;/>representing the magnitude of the q data point in the j-th sub-data segment in the h-th item data; DTW () is a DTW distance; exp () represents an exponential function based on a natural constant.
5. The method for processing UWB ranging data in six minutes walking test according to claim 1, wherein the step of obtaining the overall correlation of all data comprises the steps of:
recording the degree of correlation between the various data, and taking the degree of correlation between the various data into a set to be recorded as a degree of correlation set; the ratio of the mean value of all elements in the correlation degree set to the variance of all elements is taken as the overall correlation of all data.
6. The method for processing UWB ranging data in six-minute walk test according to claim 1, wherein the dividing all data points in each item of data according to the maximum points in each item of data to obtain the data points covered by each maximum point in each item of data comprises the following specific steps:
counting the number of data points at intervals between the ith data point in the ith data and all maximum points in the first data to obtain a plurality of data point numbers at intervals; taking a maximum value point corresponding to the minimum interval data point number in the interval data point numbers as a maximum value point Z covering the ith data point in the first item data, wherein the ith data point in the first item data is the data point covered by the maximum value point Z, and similarly, obtaining the maximum value point covering each data point in the first item data; and similarly, acquiring data points covered by each maximum value point.
7. The method for processing UWB ranging data in six-minute walk test according to claim 1, wherein the obtaining of the local correlation of all data comprises the following specific calculation formula:
wherein Y represents the local correlation of all data; w represents the number of each item of data; b (B) l Representing the number of maximum points in the first item of data; a is that l，x Representing the number of data points covered by the xth maximum point in the first item of data;representing the magnitude of the x-th maximum point in the first item of data; f (F) lx，i Representing the amplitude of an ith data point covered by an xth maximum point in the first item of data; c (C) l Representing the number of data points in the first item of data; f (F) l，i Amplitude of the ith data point in the first item of data; f (F) l，(i+1) Representing the (i+1) th data point in the first item of data; f (F) l，(i-1) Representing the (i-1) th data point in the first item of data.
8. The method for processing UWB ranging data in six minutes walking test according to claim 1, wherein the obtaining the confusion factor comprises the specific steps of:
taking the product of the overall correlation of all data and the local correlation of all data as a confusion coefficient, and adopting a specific calculation formula as follows:
τ＝P×Y
where τ represents a confusion factor; p represents the overall correlation of all data; y represents the local correlation of all data.
9. The method for processing UWB ranging data in a six-minute walk test according to claim 1, wherein the step of acquiring each item of data in the six-minute walk test comprises the steps of:
the walking distance data of the testers are obtained through a UWB ranging method, and then the heart rate data, the respiratory frequency data and the step number data of the testers are obtained through portable heart rate monitoring equipment carried by the testers.
10. The method for processing UWB ranging data in six-minute walk test according to claim 1, wherein the step of performing the dimension reduction processing on each item of data according to the confusion factor to obtain the dimension reduced data comprises the following specific steps:
and according to the obtained confusion coefficient, performing dimension reduction processing on each item of data in the six-minute walking test by using a t-SNE algorithm to obtain dimension reduced data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311026351.5A CN117171542B (en) | 2023-08-15 | 2023-08-15 | UWB ranging data processing method in six-minute walking test |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311026351.5A CN117171542B (en) | 2023-08-15 | 2023-08-15 | UWB ranging data processing method in six-minute walking test |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117171542A true CN117171542A (en) | 2023-12-05 |
| CN117171542B CN117171542B (en) | 2024-06-28 |
Family
ID=88942156
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311026351.5A Active CN117171542B (en) | 2023-08-15 | 2023-08-15 | UWB ranging data processing method in six-minute walking test |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117171542B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103246702A (en) * | 2013-04-02 | 2013-08-14 | 大连理工大学 | Industrial sequential data missing filling method based on sectional state displaying |
| CN107992495A (en) * | 2016-10-26 | 2018-05-04 | 腾讯科技（深圳）有限公司 | Data analysing method and device |
| US20190347567A1 (en) * | 2018-03-13 | 2019-11-14 | Genetic Intelligence, Inc. | Methods for data segmentation and identification |
| CN111711633A (en) * | 2020-06-22 | 2020-09-25 | 中国科学技术大学 | Multi-stage fused encrypted traffic classification method |
| CN113192516A (en) * | 2021-04-22 | 2021-07-30 | 平安科技（深圳）有限公司 | Voice role segmentation method and device, computer equipment and storage medium |
| CN113780418A (en) * | 2021-09-10 | 2021-12-10 | 平安科技（深圳）有限公司 | Data screening method, system, equipment and storage medium |
| WO2022036616A1 (en) * | 2020-08-20 | 2022-02-24 | 中山大学 | Method and apparatus for generating inferential question on basis of low labeled resource |
| CN114492375A (en) * | 2020-10-26 | 2022-05-13 | 阿里巴巴集团控股有限公司 | Text processing method and device, electronic equipment and computer readable storage medium |
| CN116228176A (en) * | 2023-05-10 | 2023-06-06 | 安徽皖欣环境科技有限公司 | Sewage treatment data efficient management system based on data processing |
| CN116304779A (en) * | 2023-05-25 | 2023-06-23 | 济宁市健达医疗器械科技有限公司 | Intelligent measuring system for extracorporeal circulation temperature |
-
2023
- 2023-08-15 CN CN202311026351.5A patent/CN117171542B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103246702A (en) * | 2013-04-02 | 2013-08-14 | 大连理工大学 | Industrial sequential data missing filling method based on sectional state displaying |
| CN107992495A (en) * | 2016-10-26 | 2018-05-04 | 腾讯科技（深圳）有限公司 | Data analysing method and device |
| US20190347567A1 (en) * | 2018-03-13 | 2019-11-14 | Genetic Intelligence, Inc. | Methods for data segmentation and identification |
| CN111711633A (en) * | 2020-06-22 | 2020-09-25 | 中国科学技术大学 | Multi-stage fused encrypted traffic classification method |
| WO2022036616A1 (en) * | 2020-08-20 | 2022-02-24 | 中山大学 | Method and apparatus for generating inferential question on basis of low labeled resource |
| CN114492375A (en) * | 2020-10-26 | 2022-05-13 | 阿里巴巴集团控股有限公司 | Text processing method and device, electronic equipment and computer readable storage medium |
| CN113192516A (en) * | 2021-04-22 | 2021-07-30 | 平安科技（深圳）有限公司 | Voice role segmentation method and device, computer equipment and storage medium |
| CN113780418A (en) * | 2021-09-10 | 2021-12-10 | 平安科技（深圳）有限公司 | Data screening method, system, equipment and storage medium |
| CN116228176A (en) * | 2023-05-10 | 2023-06-06 | 安徽皖欣环境科技有限公司 | Sewage treatment data efficient management system based on data processing |
| CN116304779A (en) * | 2023-05-25 | 2023-06-23 | 济宁市健达医疗器械科技有限公司 | Intelligent measuring system for extracorporeal circulation temperature |
Non-Patent Citations (2)
| Title |
|---|
| JOHN A . LEE ET AL.: "Multi-scale similarities in stochastic neighbour embedding: Reducing dimensionality while preserving both local and global structure", NEUROCOMPUTING, 4 April 2015 (2015-04-04) * |
| 张 瑞，董庆兴: "基于 LDA-HMM 的知识流动模式发现研究", 情报科学, 30 June 2020 (2020-06-30) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117171542B (en) | 2024-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hsieh et al. | Deep learning-based indoor localization using received signal strength and channel state information | |
| US11902857B2 (en) | Handling concept drift in Wi-Fi-based localization | |
| Ding et al. | WiFi CSI-based human activity recognition using deep recurrent neural network | |
| CN108629380B (en) | Cross-scene wireless signal sensing method based on transfer learning | |
| Cheng et al. | Device-free indoor people counting using Wi-Fi channel state information for Internet of Things | |
| Yang et al. | Dense people counting using IR-UWB radar with a hybrid feature extraction method | |
| US10374902B2 (en) | Method for clustering wireless channel MPCs based on a KPD doctrine | |
| CN102404058B (en) | Electromagnetic wave discrimination device, electromagnetic wave discrimination method, and electromagnetic wave discrimination program | |
| Shih et al. | Occupancy estimation using ultrasonic chirps | |
| Kosba et al. | RASID: A robust WLAN device-free passive motion detection system | |
| CN106658590A (en) | Design and implementation of multi-person indoor environment state monitoring system based on WiFi channel state information | |
| CN113453180B (en) | Intelligent detection method and system for human body tumble and information data processing terminal | |
| CN111597991A (en) | Rehabilitation detection method based on channel state information and BilSTM-Attention | |
| CN110730473A (en) | Signal feature extraction method for WiFi activity recognition | |
| CN115291184B (en) | Attitude monitoring method combining millimeter wave radar and deep learning | |
| Tsai et al. | Refined autoencoder-based CSI hidden feature extraction for indoor spot localization | |
| Anderson et al. | A mathematical statistics formulation of the teleseismic explosion identification problem with multiple discriminants | |
| CN117171542B (en) | UWB ranging data processing method in six-minute walking test | |
| CN112364770B (en) | Commercial Wi-Fi-based human activity recognition and action quality evaluation method | |
| Wang et al. | Syncope detection in toilet environments using Wi-Fi channel state information | |
| CN104821854B (en) | A kind of many primary user's multidimensional frequency spectrum sensing methods based on random set | |
| Xu et al. | Cross-validation strategy for performance evaluation of machine learning algorithms in underwater acoustic target recognition | |
| CN114158004B (en) | Indoor passive moving target detection method based on graph convolution neural network | |
| CN106257302A (en) | A kind of cognitive radar target tracking method under clutter environment | |
| Cardenas et al. | Effects of antenna orientation in fall detection systems based on wifi signals |
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 |