CN109662727A - Fetal heart rate detection method and system based on fuzzy clustering algorithm - Google Patents
Fetal heart rate detection method and system based on fuzzy clustering algorithm Download PDFInfo
- Publication number
- CN109662727A CN109662727A CN201910085764.8A CN201910085764A CN109662727A CN 109662727 A CN109662727 A CN 109662727A CN 201910085764 A CN201910085764 A CN 201910085764A CN 109662727 A CN109662727 A CN 109662727A
- Authority
- CN
- China
- Prior art keywords
- fetal heart
- fuzzy clustering
- sound signal
- template library
- heart sound
- 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.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B7/00—Instruments for auscultation
- A61B7/02—Stethoscopes
- A61B7/04—Electric stethoscopes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Abstract
The present invention relates to medical electronics and fetal monitoring field, it is related to fetal heart rate detection method and system based on fuzzy clustering algorithm, method includes: acquisition primary fetal cardiechema signals；Signal Pretreatment is carried out to cardiechema signals；Cepstrum feature is extracted as characteristic parameter；Fuzzy clustering template library is trained using characteristic parameter；The optimal template that cardiechema signals to be measured are matched by fuzzy clustering template library, obtains the fetal heart frequency of cardiechema signals to be measured.The present invention extracts cepstrum feature using linear prediction residue error and is used as after characteristic parameter for training fuzzy clustering template library, obtain the corresponding instantaneous heart rate of fetal heart sound signal, more preferably template is generated by template library constantly training, it recycles optimal template matching to obtain which class Fetal Heart Rate cardiechema signals to be measured belong to, finally obtains the Fetal Heart Rate of heart sound to be measured.Fuzzy clustering algorithm can division by data set compared with " clearly demarcated ", tolerance and dynamic clustering can be realized well to cepstrum feature and parameter setting, detected more acurrate and effective.
Description
Technical field
The present invention relates to medical electronics and fetal monitoring field, in particular to a kind of fetus heart based on fuzzy clustering algorithm
Rate detection method and system.
Background technique
Cardiechema signals are the very typical biologic medical signals of human body, be can detecte out to a certain extent related to heart
Disease.Fetal heart monitoring is carried out to fetus in pregnant woman's body in stage perinatal period, it can be appreciated that the in utero situation of fetus is made pre-
The reason of preventing, and being diagnosed to be fetal distress, such as torsio funiculi umbilici, cord around neck, fetus anaemia, fetal anomaly etc. realize obstetrics
Clinical fetus intelligent monitor ensures the life security of pregnant woman and fetus, and therefore, most hospital is using fetal heart monitoring as fetus
Most basic detection means.The foundation of fetal heart monitoring evaluation mainly fetal heart frequency and in utero the two main indicators of pressure, therefore
The detection identification of fetal heart frequency is just particularly important.
It is currently main to the method for fetal heart frequency detection:
(1) instantaneous heart rate is calculated based on Fetal ECG signal, it is collected that this mode mainly passes through parent abdomen
Mixing electrocardiosignal carries out analytical calculation heart rate, but since collected signal is fetus and the overlapping electrocardiosignal of mother,
And it is mingled with various noise pollutions, so that the difficulty that faint Fetal ECG separates is bigger, error rate is higher.
(2) fetal heart frequency is extracted based on small wave converting method, because wavelet transformation analysis on high band temporal resolution
Can it is higher, low-frequency range can lower characteristic, be difficult precisely reflection to the information on certain Frequency points, obtained spectrogram compared with
Coarse, recognition effect is bad.
In conclusion currently lacking, a kind of effective mode is next accurately to detect fetal heart frequency.
Summary of the invention
Embodiments of the present invention aim to solve at least one of the technical problems existing in the prior art.For this purpose, of the invention
Embodiment need to provide a kind of fetal heart rate detection method and system based on fuzzy clustering algorithm.
A kind of fetal heart rate detection method based on fuzzy clustering algorithm of embodiment of the present invention, which is characterized in that packet
Include following steps:
Step 1, original fetal heart sound signal is acquired；
Step 2, Signal Pretreatment is carried out to cardiechema signals；
Step 3, to pretreated heart sound signal extraction cepstrum feature as characteristic parameter；
Step 4, fuzzy clustering template library is trained using characteristic parameter；
Step 5, the optimal template that fetal heart sound signal to be measured is matched by fuzzy clustering template library, obtains fetus to be measured
The fetal heart frequency of cardiechema signals.
In a kind of embodiment, step 2 include: low-pass filtering and bandpass filtering treatment first carried out to cardiechema signals, then into
Row filter and amplification and data normalized, obtain pretreated cardiechema signals.
In a kind of embodiment, step 3 includes: using linear prediction residue error to pretreated heart sound signal extraction
Cepstrum feature is as characteristic parameter.
In a kind of embodiment, step 4 includes: to utilize characteristic parameter according to the defined formula of preset template library model
Seek the optimal solution of estimation parameter until meeting termination condition by the iteration result of FCM Algorithms, obtains cost function
Convergent optimum point makes the fuzzy clustering template library generate satisfactory template.
In a kind of embodiment, the defined formula of template library model are as follows:
Wherein, θ and U meet constraint condition:
uij∈ [0,1], i=1 ..., N, j=1 ..., m
Cost function J is the function of fetal heart sound signal data collection X vector, and θ indicates vector to be estimated, θjIndicate jth
The expression of a cluster,U indicates N × m matrix, and (i, j) element representation in matrix is uj(xi), q table
Show ambiguity parameter, d (xi,θj) indicate xiAnd θjBetween dissimilarity, xiJth cluster in degree of membership and its in addition
(m-1) degree of membership in a cluster is related.
Embodiment of the present invention also proposes that a kind of fetal heart frequency detection system based on fuzzy clustering algorithm, feature exist
In, comprising:
Acquisition module, for acquiring original fetal heart sound signal；
Preprocessing module, for carrying out Signal Pretreatment to cardiechema signals；
Characteristic extracting module is used for pretreated heart sound signal extraction cepstrum feature as characteristic parameter；
Training module, for training fuzzy clustering template library using characteristic parameter；
Detection module is obtained for matching the optimal template of fetal heart sound signal to be measured by fuzzy clustering template library
The fetal heart frequency of fetal heart sound signal to be measured.
In a kind of embodiment, preprocessing module is specifically used for first carrying out at low-pass filtering and bandpass filtering cardiechema signals
Reason, then it is filtered amplification and data normalized, obtain pretreated cardiechema signals.
In a kind of embodiment, characteristic extracting module is specifically used for using linear prediction residue error to the pretreated heart
Sound signal extracts cepstrum feature as characteristic parameter.
In a kind of embodiment, training module is specifically used for the defined formula according to preset template library model, utilizes spy
Sign parameter seeks to estimate that the optimal solution of parameter up to meeting termination condition, obtains generation by the iteration result of FCM Algorithms
The optimum point of valence function convergence makes the fuzzy clustering template library generate satisfactory template.
In a kind of embodiment, the defined formula of template library model are as follows:
Wherein, θ and U meet constraint condition:
uij∈ [0,1], i=1 ..., N, j=1 ..., m
Cost function J is the function of fetal heart sound signal data collection X vector, and θ indicates vector to be estimated, θjIndicate jth
The expression of a cluster,U indicates N × m matrix, and (i, j) element representation in matrix is uj(xi), q table
Show ambiguity parameter, d (xi,θj) indicate xiAnd θjBetween dissimilarity, xiJth cluster in degree of membership and its in addition
(m-1) degree of membership in a cluster is related.
The fetal heart rate detection method and system based on fuzzy clustering algorithm of embodiment of the present invention, using linear prediction
Cepstrum coefficient extracts cepstrum feature as being used to train fuzzy clustering template library after characteristic parameter, and it is corresponding to obtain fetal heart sound signal
Instantaneous heart rate, more preferably template is generated by the continuous training of template library, optimal template matching is recycled to obtain heart sound to be measured
Which kind of Fetal Heart Rate signal belongs to, and finally obtains the Fetal Heart Rate of heart sound to be measured.Fuzzy clustering algorithm can by data set compared with " point
It is bright " division, cepstrum feature and parameter setting to extraction can tolerance well, and again with the process of dynamic clustering,
So that detection means is more accurate and effective.
The advantages of additional aspect of the invention, will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
The above-mentioned and/or additional aspect and advantage of embodiments of the present invention are from combination following accompanying drawings to embodiment
It will be apparent and be readily appreciated that in description, in which:
Fig. 1 is the flow diagram of the fetal heart rate detection method based on fuzzy clustering algorithm of embodiment of the present invention；
Fig. 2 is the composition schematic diagram of the fetal heart frequency detection system based on fuzzy clustering algorithm of embodiment of the present invention.
Specific embodiment
Embodiments of the present invention are described below in detail, the example of embodiment is shown in the accompanying drawings, wherein identical or class
As label indicate same or similar element or element with the same or similar functions from beginning to end.Below with reference to attached
The embodiment of figure description is exemplary, and can only be used to explain embodiments of the present invention, and should not be understood as to the present invention
Embodiment limitation.
Referring to Fig. 1, the fetal heart rate detection method based on fuzzy clustering algorithm of embodiment of the present invention, including it is following
Step:
Step 1, original fetal heart sound signal is acquired；
Step 2, Signal Pretreatment is carried out to cardiechema signals；
Step 3, to pretreated heart sound signal extraction cepstrum feature as characteristic parameter；
Step 4, fuzzy clustering template library is trained using characteristic parameter；
Step 5, the optimal template that fetal heart sound signal to be measured is matched by fuzzy clustering template library, obtains fetus to be measured
The fetal heart frequency of cardiechema signals.
Referring to Fig. 2, the fetal heart frequency detection system based on fuzzy clustering algorithm of embodiment of the present invention, comprising:
Acquisition module, for acquiring original fetal heart sound signal；
Preprocessing module, for carrying out Signal Pretreatment to cardiechema signals；
Characteristic extracting module is used for pretreated heart sound signal extraction cepstrum feature as characteristic parameter；
Training module, for training fuzzy clustering template library using characteristic parameter；
Detection module is obtained for matching the optimal template of fetal heart sound signal to be measured by fuzzy clustering template library
The fetal heart frequency of fetal heart sound signal to be measured.
In this embodiment, based on the fetal heart rate detection method of fuzzy clustering algorithm based on fuzzy clustering algorithm
Execution object of the fetal heart frequency detection system as step, or the execution object using the modules in system as step.
Specifically, execution object of the step 1 using acquisition module as step, execution object of the step 2 using preprocessing module as step,
Execution object of the step 3 using characteristic extracting module as step, execution object of the step 4 using training module as step, step 5
Execution object using detection module as step.
In step 1, acquisition module acquires original cardiechema signals and as to be tested using Doppler signal Acquisition Instrument
Cardiechema signals.Setting Y (n) indicates collected original signal, and S (n) indicates interference signal, X (n) indicate to go it is hot-tempered after fetal rhythm
Sound signal.
In step 2, specifically include: preprocessing module first carries out low-pass filtering and bandpass filtering treatment to cardiechema signals, then
It is filtered amplification and data normalized, obtains pretreated cardiechema signals.
Preprocessing module pre-processes collected signal, because original fetal heart sound signal contains a large amount of interference letter
Number, and original signal voltage is very low, normal cardiechema signals are divided into four parts of S1, S2, S3 and S4 heart sound, it is generally the case that
It is easier to listen to S1 and S2, and S3 and S4 are difficult to touch, wherein S1 and S2 heart sound concentrates on 20Hz~150Hz.Use low pass filtered
Wave device filters out the noise of the non-fetal cardiechema signals frequency range of aliasing in signal, can also there is some interference letters in cardiechema signals
Number, it is filtered with the bandpass filter that frequency band is 0Hz~250Hz, then to treated, signal is filtered amplification sum number
According to normalized, pretreated fetal heart sound signal is obtained.
In step 3, characteristic extracting module is using linear prediction residue error to pretreated heart sound signal extraction cepstrum
Feature is as characteristic parameter.Linear prediction residue error LPCC ((Linear Prediction CepstrumCoefficient)
The basic thought for carrying out linear prediction analysis to signal is: the sampling of a signal can use the line of several signal samplings in the past
Property combination to approach.By make linear prediction to sampling actual signal sampling is approached in least mean-square error meaning, can be with
Seek one group of unique predictive coefficient.Here predictive coefficient is exactly weighting coefficient used in linear combination.It is this linear pre-
It surveys analytical technology and is also often called LPC for short, LPCC is the cepstrum parameter of LPC.
Characteristic extracting module extracts the characteristic parameter of signal using linear prediction residue error, can reflect time signal
Frequency response and spectrum envelope can better describe the feature of cardiechema signals.
Wherein cepstrum recurrence formula are as follows:
WhereinThe cepstrum of original cardiechema signals x (n) is indicated, further from linear forecasting parameter aiIt is acquired to fall
Spectrum, obtains cnWith akRelationship:
c0=a1
In above-mentioned recurrence relation, akFor LPC coefficient, p is LPC order, and k is the order of LPCC, CkFor LPCC parameter, c0Table
Show the DC component of signal, and cepstrum feature c (n) is to carry out inverse Fourier transform meter on its log-magnitude spectrum to sequence x (n)
It calculates, is exactly striked characteristic parameter, so as to subsequent trained fuzzy clustering algorithm template library.
Step 4 includes: defined formula of the training module according to preset template library model, is passed through using characteristic parameter fuzzy
The iteration result of C mean algorithm seeks to estimate the optimal solution of parameter that acquisition cost function is convergent most until meeting termination condition
Advantage makes the fuzzy clustering template library generate satisfactory template.
Wherein, training module obtains the cepstrum feature c (n) of each part of signal, Lai Xunlian fuzzy clustering mould by step 3
Plate library, the defined formula of preset template library model are as follows:
Wherein, θ and U meet constraint condition:
uij∈ [0,1], i=1 ..., N, j=1 ..., m
Cost function J is the function of fetal heart sound signal data collection X vector, here using unknown number vector θ as parameter, training
Essence be estimation θ so that the data set X of fetal heart sound signal obtains optimal cluster.θjIndicate the expression of j-th of cluster,U indicates N × m matrix, and (i, j) element representation in matrix is uj(xi), q (> 1) indicates ambiguity
Parameter, d (xi,θj) indicate xiAnd θjBetween dissimilarity, xiDegree of membership in jth cluster and it is a poly- in addition (m-1)
Degree of membership in class is related.
In order to acquire Jq(θ, U) is minimized, and selects θj(0) it is used as θj, the initial estimate of j=1 ..., m, utilization
Following iterative algorithm obtains the estimated value of U and θ:
FCM algorithm is also fuzzy C-mean algorithm (Fuzzy C-means) algorithm, is that the fuzzy clustering based on objective function is calculated
Method is mainly used for the clustering of data.Its thought be exactly so as to be divided between the object of same cluster similarity maximum,
And the similarity between different clusters is minimum.FCM Algorithms are the improvement of common C mean algorithm, common C mean algorithm for
The division of data is rigid, and FCM Algorithms are then a kind of fuzzy divisions flexible.Common C mean algorithm is being classified
Shi Youyi rigid standard, is divided, classification results one or the other according to the standard.And FCM Algorithms more value person in servitude
Category degree, i.e., closer to which side, degree of membership is higher, and similarity is higher.
In present embodiment, θ is acquired with FCM Algorithmsj(t):
It solves
I=1 ..., N, j=1 ..., m are enabled, above-mentioned equation is recycled, for each θj, enable θjIt (t) is all non trivial solution, so
U is fixed, updates θ value and θ is fixed, updates U value in every single-step iteration afterwards, until meeting termination condition | | θ (t)-θ
(t-1) | | < ε, wherein ε is the constant of the very little of definition.Required iteration result is obtained by FCM Algorithms or certain
Iterative step in converge on the stable point of cost function and obtain fetus so that characteristic sequence converges on stable cost function
The instantaneous heart rate of heart sound constantly round-robin algorithm can make library is trained to generate more preferably template, be used for subsequent fetal heart sound in this way
Signal detection Fetal Heart Rate.
In step 5, detection module matches fetal heart sound signal to be measured by the fuzzy clustering template library of training and belongs to
Which kind of cardiechema signals template, and then obtain the fetus rate of fetal heart sound signal to be measured.
It is used as after characteristic parameter in conclusion the present invention extracts cepstrum feature using linear prediction residue error for training
Fuzzy clustering template library obtains the corresponding instantaneous heart rate of fetal heart sound signal, is generated more preferably by the continuous training of template library
Template recycles optimal template matching to obtain which kind of Fetal Heart Rate cardiechema signals to be measured belong to, and finally obtains the tire of heart sound to be measured
Heart rate.Fuzzy clustering algorithm can division by data set compared with " clearly demarcated ", can be very to the cepstrum feature and parameter setting of extraction
Tolerance well, and again with the process of dynamic clustering, so that detection means is more accurate and effective.
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (10)
1. a kind of fetal heart rate detection method based on fuzzy clustering algorithm, which comprises the following steps:
Step 1, original fetal heart sound signal is acquired；
Step 2, Signal Pretreatment is carried out to cardiechema signals；
Step 3, to pretreated heart sound signal extraction cepstrum feature as characteristic parameter；
Step 4, fuzzy clustering template library is trained using characteristic parameter；
Step 5, the optimal template that fetal heart sound signal to be measured is matched by fuzzy clustering template library, obtains fetal heart sound to be measured
The fetal heart frequency of signal.
2. as described in claim 1 based on the fetal heart rate detection method of fuzzy clustering algorithm, which is characterized in that step 2 includes:
Low-pass filtering and bandpass filtering treatment are first carried out to cardiechema signals, then are filtered amplification and data normalized, is obtained pre-
Treated cardiechema signals.
3. as claimed in claim 2 based on the fetal heart rate detection method of fuzzy clustering algorithm, which is characterized in that step 3 includes:
Using linear prediction residue error to pretreated heart sound signal extraction cepstrum feature as characteristic parameter.
4. as claimed in claim 3 based on the fetal heart rate detection method of fuzzy clustering algorithm, which is characterized in that step 4 includes:
According to the defined formula of preset template library model, seek to estimate by the iteration result of FCM Algorithms using characteristic parameter
The optimal solution of parameter is counted until meeting termination condition, obtains the convergent optimum point of cost function generate fuzzy clustering template library
Satisfactory template.
5. as claimed in claim 4 based on the fetal heart rate detection method of fuzzy clustering algorithm, which is characterized in that template library model
Defined formula are as follows:
Wherein, θ and U meet constraint condition:
uij∈ [0,1], i=1 ..., N, j=1 ..., m
Cost function J is the function of fetal heart sound signal data collection X vector, and θ indicates vector to be estimated, θjIndicate j-th of cluster
Expression,U indicates N × m matrix, and (i, j) element representation in matrix is uj(xi), q indicates fuzzy
Property parameter, d (xi,θj) indicate xiAnd θjBetween dissimilarity, xiDegree of membership in jth cluster and it is a in addition (m-1)
Degree of membership in cluster is related.
6. a kind of fetal heart frequency detection system based on fuzzy clustering algorithm characterized by comprising
Acquisition module, for acquiring original fetal heart sound signal；
Preprocessing module, for carrying out Signal Pretreatment to cardiechema signals；
Characteristic extracting module is used for pretreated heart sound signal extraction cepstrum feature as characteristic parameter；
Training module, for training fuzzy clustering template library using characteristic parameter；
Detection module obtains to be measured for matching the optimal template of fetal heart sound signal to be measured by fuzzy clustering template library
The fetal heart frequency of fetal heart sound signal.
7. the fetal heart frequency detection system based on fuzzy clustering algorithm as claimed in claim 6, which is characterized in that preprocessing module
Specifically for first carrying out low-pass filtering and bandpass filtering treatment to cardiechema signals, then it is filtered at amplification and data normalization
Reason, obtains pretreated cardiechema signals.
8. the fetal heart frequency detection system based on fuzzy clustering algorithm as claimed in claim 7, which is characterized in that feature extraction mould
Block is specifically used for using linear prediction residue error to pretreated heart sound signal extraction cepstrum feature as characteristic parameter.
9. the fetal heart frequency detection system based on fuzzy clustering algorithm as claimed in claim 8, which is characterized in that training module tool
Body is used for the defined formula according to preset template library model, the iteration result for passing through FCM Algorithms using characteristic parameter
Seek the optimal solution of estimation parameter until meeting termination condition, obtains the convergent optimum point of cost function to make fuzzy clustering template
Library generates satisfactory template.
10. the fetal heart frequency detection system based on fuzzy clustering algorithm as claimed in claim 9, which is characterized in that template library mould
The defined formula of type are as follows:
Wherein, θ and U meet constraint condition:
uij∈ [0,1], i=1 ..., N, j=1 ..., m
Cost function J is the function of fetal heart sound signal data collection X vector, and θ indicates vector to be estimated, θjIndicate j-th of cluster
Expression,U indicates N × m matrix, and (i, j) element representation in matrix is uj(xi), q indicates fuzzy
Property parameter, d (xi,θj) indicate xiAnd θjBetween dissimilarity, xiDegree of membership in jth cluster and it is a in addition (m-1)
Degree of membership in cluster is related.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910085764.8A CN109662727A (en) | 2019-01-29 | 2019-01-29 | Fetal heart rate detection method and system based on fuzzy clustering algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910085764.8A CN109662727A (en) | 2019-01-29 | 2019-01-29 | Fetal heart rate detection method and system based on fuzzy clustering algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109662727A true CN109662727A (en) | 2019-04-23 |
Family
ID=66151094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910085764.8A Pending CN109662727A (en) | 2019-01-29 | 2019-01-29 | Fetal heart rate detection method and system based on fuzzy clustering algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109662727A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113192629A (en) * | 2021-05-08 | 2021-07-30 | 清华大学 | Method and apparatus for automatic fetal heart interpretation |
| CN114398493A (en) * | 2021-12-29 | 2022-04-26 | 中国人民解放军92728部队 | Unmanned aerial vehicle type spectrum construction method based on fuzzy clustering and cost-effectiveness value |
| CN117807551A (en) * | 2024-02-29 | 2024-04-02 | 深圳市魔样科技有限公司 | Heart rate abnormality capturing method and system based on intelligent ring |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120032157A (en) * | 2010-09-28 | 2012-04-05 | 한국전기연구원 | Apparatus and method for measuring pulse condition using fuzzy theory |
| CN102940485A (en) * | 2012-10-10 | 2013-02-27 | 广州三瑞医疗器械有限公司 | Algorithm for automatically recognizing fetal heart rate baseline |
| CN105845140A (en) * | 2016-03-23 | 2016-08-10 | 广州势必可赢网络科技有限公司 | Speaker confirmation method and speaker confirmation device used in short voice condition |
| CN105962915A (en) * | 2016-06-02 | 2016-09-28 | 安徽大学 | Non-contact type human body respiration rate and heart rate synchronous measuring method and system |
| CN106491085A (en) * | 2016-10-31 | 2017-03-15 | 广东工业大学 | A kind of fetal heart sound instantaneous heart rate detection recognition method and device |
| CN108875604A (en) * | 2018-05-31 | 2018-11-23 | 中国地质大学（武汉） | Higher-order of oscillation rhythm and pace of moving things detection method based on fuzzy clustering optimization gauss mixed model |
-
2019
- 2019-01-29 CN CN201910085764.8A patent/CN109662727A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120032157A (en) * | 2010-09-28 | 2012-04-05 | 한국전기연구원 | Apparatus and method for measuring pulse condition using fuzzy theory |
| CN102940485A (en) * | 2012-10-10 | 2013-02-27 | 广州三瑞医疗器械有限公司 | Algorithm for automatically recognizing fetal heart rate baseline |
| CN105845140A (en) * | 2016-03-23 | 2016-08-10 | 广州势必可赢网络科技有限公司 | Speaker confirmation method and speaker confirmation device used in short voice condition |
| CN105962915A (en) * | 2016-06-02 | 2016-09-28 | 安徽大学 | Non-contact type human body respiration rate and heart rate synchronous measuring method and system |
| CN106491085A (en) * | 2016-10-31 | 2017-03-15 | 广东工业大学 | A kind of fetal heart sound instantaneous heart rate detection recognition method and device |
| CN108875604A (en) * | 2018-05-31 | 2018-11-23 | 中国地质大学（武汉） | Higher-order of oscillation rhythm and pace of moving things detection method based on fuzzy clustering optimization gauss mixed model |
Non-Patent Citations (4)
| Title |
|---|
| 张文英: "基于LabVIEW的心音信号分类识别系统设计", 《中国优秀硕士学位论文全文数据库（电子期刊）信息科技辑》 * |
| 张文英等: "改进的高斯混合模型在心音信号分类识别中应用", 《振动与冲击》 * |
| 蔡静颖: "《模糊聚类算法及应用》", 1 August 2015, 冶金工业出版社 * |
| 钟丽莎: "基于GMM的心音信号生物识别方法研究", 《中国医疗器械杂志》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113192629A (en) * | 2021-05-08 | 2021-07-30 | 清华大学 | Method and apparatus for automatic fetal heart interpretation |
| CN114398493A (en) * | 2021-12-29 | 2022-04-26 | 中国人民解放军92728部队 | Unmanned aerial vehicle type spectrum construction method based on fuzzy clustering and cost-effectiveness value |
| CN117807551A (en) * | 2024-02-29 | 2024-04-02 | 深圳市魔样科技有限公司 | Heart rate abnormality capturing method and system based on intelligent ring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cömert et al. | Fetal hypoxia detection based on deep convolutional neural network with transfer learning approach | |
| CN100418480C (en) | Heart disease automatic classification system based on heart sound analysis and heart sound segmentation method | |
| CN109662727A (en) | Fetal heart rate detection method and system based on fuzzy clustering algorithm | |
| CN110598676B (en) | Deep learning gesture electromyographic signal identification method based on confidence score model | |
| CN104887224A (en) | Epileptic feature extraction and automatic identification method based on electroencephalogram signal | |
| CN112487945B (en) | Pulse condition identification method based on double-path convolution neural network fusion | |
| CN111407315A (en) | Quality evaluation method for ultrasonic Doppler fetal heart signals | |
| CN112869716B (en) | Pulse feature identification system and method based on two-channel convolutional neural network | |
| CN110123304A (en) | Dynamic electrocardiogram noise filtering method based on multi-template matching and correlation matrix | |
| CN111783715B (en) | Identity recognition method based on pulse signal feature extraction | |
| CN112971799A (en) | Non-stimulation fetal heart monitoring classification method based on machine learning | |
| Gao et al. | Real time ECG characteristic point detection with randomly selected signal pair difference (RSSPD) feature and random forest classifier | |
| CN107045624B (en) | Electroencephalogram signal preprocessing and classifying method based on maximum weighted cluster | |
| CN112137620A (en) | Ultra-wideband radar-based human body weak respiration signal detection method | |
| CN113796873B (en) | Wearable dynamic electrocardiosignal classification method and system | |
| CN110070013A (en) | A kind of ECG signal noise pollution degree and classification intelligent evaluation method | |
| CN116807496A (en) | Method, device, equipment and medium for positioning epileptic interval brain wave abnormal signals | |
| CN110200624A (en) | Based on convolutional neural networks-Recognition with Recurrent Neural Network-support vector machines mixed model disease identification algorithm | |
| CN111209816B (en) | Non-contact fatigue driving detection method based on regular extreme learning machine | |
| Yang et al. | Unsupervised clustering and analysis of contraction-dependent fetal heart rate segments | |
| Lu et al. | Pulse waveform analysis for pregnancy diagnosis based on machine learning | |
| CN115089139A (en) | Personalized physiological parameter measuring method combining biological characteristic identification | |
| CN112617761A (en) | Sleep stage staging method for self-adaptive multipoint generation | |
| Raghav et al. | Fractal feature based ECG arrhythmia classification | |
| CN109784279A (en) | X-ray high voltage power supply method for diagnosing faults based on multi-wavelet analysis and SVM |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190423 |
|
| RJ01 | Rejection of invention patent application after publication |