CN102389307A - Delivery starting forecasting device based on uterine electromyography and method for extracting characteristic parameter - Google Patents
Delivery starting forecasting device based on uterine electromyography and method for extracting characteristic parameter Download PDFInfo
- Publication number
- CN102389307A CN102389307A CN201110165745XA CN201110165745A CN102389307A CN 102389307 A CN102389307 A CN 102389307A CN 201110165745X A CN201110165745X A CN 201110165745XA CN 201110165745 A CN201110165745 A CN 201110165745A CN 102389307 A CN102389307 A CN 102389307A
- Authority
- CN
- China
- Prior art keywords
- electrometrogram
- signal
- anemia
- pregnant woman
- predictor
- 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
Images
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention relates to a delivery starting forecasting device based on uterine electromyography and a method for extracting characteristic parameter. The device comprises a uterine electromyography signal acquisition system, a uterine electromyography digital signal processing system, an image-text display device for processing result and a sound forecasting device; the uterine electromyography signal acquisition system is connected with the uterine electromyography digital signal processing system; and the uterine electromyography digital signal processing system is connected with the image-text display device and the sound forecasting device. The method for extracting characteristic parameter processes the uterine electromyography signal by using method of wavelet transform and artificial neural network, extracts characteristic parameter, judges and reads the processing result. Using the device and the method, the delivery starting time can be objectively and accurately forecasted, the risk of delivery can be effectively reduced, and the disease incidence and death rate of newborn baby can be decreased; meanwhile, the obstetrician can be helped to timely take effective measures for reducing occurrence rate of premature delivery and retarded birth so as to reduce the risk of delivery and defect rate of newborn baby.
Description
Technical field
The present invention relates to perinatal stage anemia of pregnant woman monitoring technology, particularly a kind of childbirth based on electrometrogram is started predictor and is extracted method of characteristic parameters.
Background technology
Childbirth is a complex physical activity, and the essential condition that childbirth is started is the maturation of fetus and the preparation of parent, and the concrete reason that childbirth is started it be not immediately clear.Start the difference of time according to childbirth, childbirth can be divided into premature labor, term birth and retarded birth.The childbirth of gestation between full 28 thoughtful discontented 37 foot weeks is called premature labor, and term birth is claimed in the childbirth of gestation between full 37 thoughtful discontented 42 foot weeks, and retarded birth is claimed in full 42 weeks of gestation and subsequent childbirth.The incidence rate of premature labor is 5%-10%, and is different because of area, ethnic group etc., and in the non-lopsided neonatal death in one month of being born, 3/4 because of due to the premature labor, and premature labor can cause the serious bad newborn baby's of enclosing prognosis.Same, postterm pregnancy receives extensive attention because of enclosing sick rate of newborn baby and mortality rate apparently higher than normal full-term pregnancy.Therefore, in the obstetrics field, objective, the prediction childbirth time of starting has important practical significance exactly.
Prediction childbirth at present starts time method to comprise traditional reckoning, biochemistry detection, ultrasonic examination etc.The tradition projectional technique calculates expected date of confinement according to the date of last menstrual period, and the method for biochemistry detection is predicted childbirth through detecting all kinds of secretions, the prediction childbirths such as variation of ultrasonic examination through observing fetus, cervix uteri.It is not high that above method exists precision of prediction, perhaps needs shortcomings such as intrusive mood acquired signal.
Because when childbirth is started; Uterotonic intensity and persistent period etc. obviously increase; The uterine contraction of rhythmicity is directly driving the anemia of pregnant woman fetus is being excreted, and therefore can predict to give a birth and start that the method for measuring uterine contraction commonly used comprises the intrauterine pressure catheter and the piezometer of giving a birth through the measurement uterine contraction.But intrauterine pressure catheter has wound, and the childbirth piezometer need be entangled in anemia of pregnant woman's abdominal part with belt, and not only the anemia of pregnant woman can feel uncomfortable, and measures inaccurate.To start the time in order predicting to give a birth safer, exactly, to have proposed the measuring method of electrometrogram.Wherein, to the order of accuarcy of the direct impact prediction of correctness of electrometrogram processing method.
U.S. Pat 6823211B2 (application number US20020149422) has described a kind of device of predicting stages of labor; This device is portable composite set; Utilize the technical Analysis electrometrogram signal of fast Fourier transform, confirm the preparation in uterus, whether prediction will give a birth.U.S. Pat 6134466 (application number US19980123377) has been described a kind of device of diagnosing childbirth, and the average frequency of electrometrogram signal is diagnosed childbirth through the relation of analyzing this average frequency when calculating uterine contraction.Chinese patent CN101448455A (application number CN200780018702.0) has described the device of a kind of predict human or other mammalian labour onsets; Be based on uncomplicated date processing principle; Be used for device in family or other non-clinical uses; It is through calculating the electrometrogram peak value, the prediction labour onset.Disclosed device is through predicting stages of labor to the processing of uterus electromyogram signal in the above patent, and the order of accuarcy of prediction is not high.
Summary of the invention
The objective of the invention is to overcome the shortcoming of prior art, the utilization digital signal processing method, provide a kind of objective, prediction childbirth starts the childbirth based on electrometrogram of time to start predictor exactly.
Another object of the present invention is to provide the extraction method of characteristic parameters of starting predictor to realize by above-mentioned childbirth based on electrometrogram.
In order to achieve the above object, the present invention adopts following technical scheme:
Predictor is started in a kind of childbirth based on electrometrogram, comprising: the picture and eassay display device of electrometrogram signal acquiring system, electrometrogram digital information processing system, result and sound predictor; The electrometrogram signal acquiring system is connected with the electrometrogram digital information processing system, and the uterine myoelectricity digital information processing system is connected with the sound predictor with picture and eassay display device.
Preferably; Said electrometrogram signal acquiring system comprises: the electrode that is used to extract the anemia of pregnant woman's abdominal part signal of telecommunication that includes electrometrogram; Be used for preposition bioelectric amplifier with the undistorted amplification of the signal of telecommunication of extracting; The wave filter that is used for filtering interference signals is used for rearmounted bioelectric amplifier that signal is amplified once more, is used for amplified analog signal is converted to the analog/digital converter of digital signal; Said electrode, preposition bioelectric amplifier, analog filter, rearmounted bioelectric amplifier, analog/digital converter are linked in sequence successively.
Preferably, said wave filter filtering is above high-frequency signal and the following low frequency signal of 0.2HZ of 5HZ in anemia of pregnant woman's abdominal part signal of telecommunication.
Preferably, said preposition bioelectric amplifier and rearmounted bioelectric amplifier signal is amplified to analog/digital converter can perception and the order of magnitude of processing.
Preferably, being kept on the personal computer of electrometrogram handled, and the electrometrogram digital signal, is delivered on the personal computer and preserved processing in the corresponding program such as USB interface through the I/O interface; The preservation of electrometrogram also can be accomplished on embedded equipment, and the electrometrogram digital signal is is directly met and sent off to embedded equipment through the plate cascade of USB interface or printed circuit board (PCB) and preserved processing in the program accordingly.
The extraction method of characteristic parameters of utilizing above-mentioned childbirth based on electrometrogram to start predictor to realize comprises following basic step:
(1), extracts the signal of telecommunication that comprises the electrometrogram signal through electrode;
(2), utilize the analog filtering technology to eliminate noises such as anemia of pregnant woman's electrocardio, fetus electrocardio, power frequency interference and electromagnetic interference;
(3), use preconditioning techniques such as suppressing power frequency interference and elimination baseline drift that the electrometrogram digital signal is handled;
(4), the utilization wavelet analysis technology extracts the eigenvalue of electrometrogram signal; Utilization wavelet transform, wavelet package transforms or lifting wavelet transform method are decomposed the electrometrogram digital signal; It is resolved into each frequency band by identical frequency interval, signal on each frequency range is carried out eigenvalue calculation such as energy, power, average and frequency;
(5) if the electrometrogram signal extracts through the dynamic monitoring continuous acquisition; The technology that then maintenance data compares and peak value detects; The eigenvalue of each frequency band signals in more adjacent two days, and with the peak value of eigenvalue and anemia of pregnant woman the threshold value just before giving birth the time compares; If the electrometrogram signal extracts through single acquisition, then use the technological prediction childbirth of artificial neural network to start the time, artificial neural network is obtained by a plurality of anemia of pregnant woman's electrometrogram sample of signal training;
(6), electrometrogram and characteristic parameter thereof are exported with picture and eassay display device, start the predictive value of time to show childbirth, through the output that will predict the outcome of sound predictor.
Preferably, in the step (1), said electrometrogram signal adopts four path electrodes to extract; Electrode is placed on anemia of pregnant woman's abdomen body-surface position; Reference electrode is placed on anemia of pregnant woman's hip, extracts the differential signal of electrode, and extraction time is 20-40 minute; Can guarantee to obtain the accurate characteristic of uterine myoelectricity comprehensively, and can regulate extraction time voluntarily according to anemia of pregnant woman's comfort level.
Preferably; In the step (1); The collection of said electrometrogram signal realizes that through dynamic monitoring continuous acquisition or single the dynamic monitoring continuous acquisition is that the last fortnight in expected date of confinement begins, and in the identical time anemia of pregnant woman is carried out the collection of electrometrogram signal every day; Single acquisition is in arbitrary sky of the last fortnight of expected date of confinement the anemia of pregnant woman to be carried out the collection of an electrometrogram signal, can select wherein a kind of method to gather the electrometrogram signal according to anemia of pregnant woman's practical situation.
In the step (5), the sample training of said artificial neural network may further comprise the steps:
(51), expected date of confinement the last fortnight arbitrary day, gather a plurality of anemia of pregnant woman's electrometrogram signal in the time identical with the single acquisition signal;
(52), each frequency band of component of signal use wavelet transformation or Fourier transform method to decompose to(for) data;
(53) and after calculating the eigenvalues such as energy, power, average and frequency of each frequency band signal carry out normalization, with the input of the value after this normalization as artificial neural network;
(54), these anemia of pregnant woman of tracing observation, when it is given a birth, serve as the output valve of corresponding input with this date of parturition.As input, corresponding date of parturition is as output with the eigenvalue after the normalization, to the artificial neural network training, within 24 hours, so far accomplishes artificial neural network training up to the error of output valve.
Process result is shown through picture and eassay display device and sound predictor and is exported.
Compared with prior art, the present invention has the following advantages and beneficial effect:
1, the present invention is through analysis and processing to the electrometrogram of anemia of pregnant woman expected date of confinement; Utilization wavelet transformation and Artificial Neural Network model are handled the electrometrogram signal; Extract characteristic parameter, interpretation result, the time that ability is objective, prediction childbirth is accurately started; Can effectively reduce the childbirth risk, reduce neonatal disease and send out rate and mortality rate.
2, the invention provides utilization wavelet transform, wavelet package transforms or lifting wavelet transform method and decompose the electrometrogram digital signal; Extract method of characteristic parameters such as energy, power, frequency and average then on the frequency range in decomposition; And need not intrusive mood and gather the pregnant woman uterus electromyogram signal, the anemia of pregnant woman can choose suitable way according to the practical situation of self.
3, the present invention is noninvasive, handles body surface electrometrogram signal through utilization wavelet analysis and the bonded method of artificial neural network, and anemia of pregnant woman's feel more cooperates the artificial neural network that trains, and can within 24 hours, predict term labor.The present invention can help the obstetrician in time to adopt an effective measure, and reduces the incidence rate of premature labor and retarded birth, reduces childbirth risk and neonate ratio of defects.
Description of drawings
Fig. 1 is the block diagram of system of the present invention;
Fig. 2 is that electrode of the present invention is placed sketch map;
Fig. 3 is the collection sketch map of electrometrogram signal of the present invention;
Fig. 4 is electrometrogram single acquisition signal processing flow figure of the present invention;
Fig. 5 is a repeatedly acquired signal process chart of electrometrogram of the present invention.
The specific embodiment
Below in conjunction with embodiment and accompanying drawing, the present invention is described in further detail, but embodiment of the present invention is not limited thereto.
Embodiment 1
Predictor is started in a kind of childbirth based on electrometrogram as shown in Figure 1; Comprise: the picture and eassay display device of electrometrogram signal acquiring system, electrometrogram digital information processing system, result and sound predictor; The electrometrogram signal acquiring system is connected with the electrometrogram digital information processing system, and the electrometrogram digital information processing system is connected with the sound predictor with picture and eassay display device.
As shown in Figure 3; Said electrometrogram signal acquiring system comprises: the electrode that is used to extract the anemia of pregnant woman's abdominal part signal of telecommunication that includes electrometrogram; Be used for preposition bioelectric amplifier with the undistorted amplification of the signal of telecommunication of extracting; The analog filter that is used for filtering interference signals with the rearmounted bioelectric amplifier that signal amplifies once more, is used for amplified analog signal is converted to the analog/digital converter of digital signal; Said electrode, preposition bioelectric amplifier, analog filter, rearmounted bioelectric amplifier, analog/digital converter are linked in sequence successively.
Said analog filter filtering be the above high-frequency signal and the following low frequency signal of 0.2HZ of 5HZ in anemia of pregnant woman's abdominal part signal of telecommunication, prevent that anemia of pregnant woman's interfering signals such as abdominal part signal, the fetal brain signal of telecommunication from exerting an influence to the uterus electromyogram signal.
Said preposition bioelectric amplifier and rearmounted bioelectric amplifier with signal be amplified to analog/digital converter can perception and with the order of magnitude of handling, for example for 8 analog/digital converter, the voltage range that can change is 0-5V; The magnitude of voltage of each representative approximately is 5/256=0.02V so, and for the analogue signal less than 0.02V, the output valve of AD converter is 0; And abdominal part electrometrogram voltage of signals size is generally several mv; Even littler, thus need be with voltage amplification at least more than the 0.02V, actual in certainly precision; Can amplify manyly, such as being amplified to more than the 1V.
Electrometrogram signal through behind the digitized uses the digital signal corresponding handling procedure to carry out Treatment Analysis in personal computer or embedded equipment.If need on personal computer, handle, then the electrometrogram digital signal is delivered on the personal computer through USB interface and is preserved processing in the corresponding program; If handle through embedded equipment ARM; This embedded equipment also can be DSP, FPGA etc., and then the electrometrogram digital signal is preserved processing in the program accordingly through USB interface or direct meeting and sending off to embedded equipment through the plate cascade of printed circuit board (PCB).
A kind of childbirth launch device method of characteristic parameters of extracting electrometrogram as shown in Figure 4, the method for employing dynamic monitoring continuous acquisition electrometrogram comprises following basic step:
(1), arbitrary day from anemia of pregnant woman's expected date of confinement the last fortnight begins; Extract the anemia of pregnant woman's abdominal part signal that comprises the electrometrogram signal in the identical time through the electrode that is placed on anemia of pregnant woman's abdominal part every day; The electrode putting position is: E1 is placed on umbilicus left side 3.5cm, 1cm place, umbilicus below; E2 is placed on umbilicus the right 3.5cm, 1cm place, umbilicus below; E3 is placed on umbilicus left side 3.5cm, 8cm place, umbilicus below; E4 is placed on umbilicus the right 3.5cm, 1cm place, umbilicus below; Reference electrode is positioned over hip.Gather the electrometrogram signal of 30 minutes durations; Consider anemia of pregnant woman's comfortableness; Also can suitably shorten extraction time; Wherein one road signal of the difference of the difference of poor, the E1 signal of E1 signal and E2 signal and E3 signal or E3 signal and E4 signal is chosen for input signal, extracts the differential signal of electrode, extraction time is 20-40 minute;
(2), input signal is amplified the back and eliminate mother's electrocardio, fetus electrocardio, electromagnetic interference noise with the analog filtering technology, the signal that the following 5HZ of filtering 0.2HZ is above;
(3), analog signal conversion is become digital signal, use and suppress that power frequency is disturbed and the preconditioning technique of eliminating baseline drift is handled the electrometrogram digital signal;
(4), the technology of utilization wavelet analysis is extracted the eigenvalue of electrometrogram signal; Be that utilization wavelet transform, wavelet package transforms or lifting wavelet transform method are decomposed the electrometrogram digital signal, it is resolved into each frequency band by identical frequency interval;
(5), the technology that detects of maintenance data comparison and peak value, the eigenvalue of each frequency band signals in more adjacent two days, and with the peak value of eigenvalue and anemia of pregnant woman just before giving birth the time peak value of corresponding frequency band compare;
(6), electrometrogram is exported with picture and eassay display device, start the predictive value of time to show childbirth, through the output that will predict the outcome of sound predictor.
Embodiment 2
As shown in Figure 5, start predictor for above-mentioned a kind of childbirth based on electrometrogram, can also extract characteristic parameter through the method for single acquisition pregnant woman uterus electromyogram signal, it comprises following basic step:
(1), at the last fortnight of expected date of confinement, the anemia of pregnant woman is carried out the collection of an electrometrogram signal, the electrode putting position is: E1 is placed on umbilicus left side 3.5cm, umbilicus below 1cm place; E2 is placed on umbilicus the right 3.5cm, 1cm place, umbilicus below; E3 is placed on umbilicus left side 3.5cm, 8cm place, umbilicus below; E4 is placed on umbilicus the right 3.5cm, 1cm place, umbilicus below; Reference electrode is positioned over hip.Gather the electrometrogram signal of 30 minutes durations; Consider anemia of pregnant woman's comfortableness; Also can suitably shorten extraction time; Wherein one road signal of the difference of the difference of poor, the E1 signal of E1 signal and E2 signal and E3 signal or E3 and E4 signal is chosen for input signal, extracts the differential signal of electrode, extraction time is 20-40 minute;
(2), input signal is amplified the back and eliminate mother's electrocardio, fetus electrocardio, electromagnetic interference noise with the analog filtering technology, the signal that the following 5HZ of filtering 0.2HZ is above;
(3), analog signal conversion is become digital signal, use and suppress that power frequency is disturbed and the preconditioning technique of eliminating baseline drift is handled the electrometrogram digital signal;
(4), owing in full frequency band, the uterus electromyogram signal is carried out characteristic parameter extraction; Can cover the part useful information; The present invention uses wavelet transformation that the uterus electromyogram signal is carried out the decomposition at each frequency band, supposes for sample rate to be that the uterine myoelectricity signal of 2fs carries out 8 grades WAVELET PACKET DECOMPOSITION, and then the band width of each frequency band signals is fs/256; For the component of signal on each frequency band, parameters such as computation of characteristic values energy, power, frequency, average;
(5), the parameters such as energy, power, frequency, average that each frequency band got component of signal carry out normalization and handle, with the input of this normalized value as artificial neural network;
(6), the technology of utilization artificial neural network, normalized eigenvalue is imported well-drilled artificial neural network, prediction childbirth is started the time, artificial neural network is obtained by a plurality of anemia of pregnant woman's electrometrogram sample of signal training.
In the step (6), the training of said artificial neural network sample may further comprise the steps:
(61), expected date of confinement the last fortnight arbitrary day, gather a plurality of anemia of pregnant woman's electrometrogram signal in the time identical with the single acquisition signal;
(62), each frequency band of component of signal use wavelet transformation or Fourier transformation method to decompose to(for) data;
(63) and behind the calculating energy, power, average, frequency carry out normalization, with the input of the value after this normalization as artificial neural network;
(64), these anemia of pregnant woman of tracing observation; When it is given a birth, serve as the output valve of corresponding input with this date of parturition, with the eigenvalue after the normalization as input; Corresponding date of parturition is as output; To the artificial neural network training, within 24 hours, so far accomplish artificial neural network training up to the error of output valve.
The foregoing description is a preferred implementation of the present invention; But embodiment of the present invention is not restricted to the described embodiments; Other any do not deviate from change, the modification done under spirit of the present invention and the principle, substitutes, combination, simplify; All should be the substitute mode of equivalence, be included within protection scope of the present invention.
Claims (10)
1. predictor is started in the childbirth based on electrometrogram; It is characterized in that; Comprise: the picture and eassay display device of electrometrogram signal acquiring system, electrometrogram digital information processing system, result and sound predictor; The electrometrogram signal acquiring system is connected with the electrometrogram digital information processing system, and the electrometrogram digital information processing system is connected with the sound predictor with picture and eassay display device.
2. predictor is started in a kind of childbirth based on electrometrogram according to claim 1; It is characterized in that; Said electrometrogram signal acquiring system comprises: the electrode that is used to extract the anemia of pregnant woman's abdominal part signal of telecommunication that includes electrometrogram; Be used for preposition bioelectric amplifier with the undistorted amplification of the signal of telecommunication of extracting; The analog filter that is used for filtering interference signals with the rearmounted bioelectric amplifier that signal amplifies once more, is used for amplified analog signal is converted to the analog/digital converter of digital signal; Said electrode, preposition bioelectric amplifier, analog filter, rearmounted bioelectric amplifier, analog/digital converter are linked in sequence successively.
3. predictor is started in a kind of childbirth based on electrometrogram according to claim 2, it is characterized in that, said analog filter filtering be the above high-frequency signal and the following low frequency signal of 0.2HZ of 5HZ in anemia of pregnant woman's abdominal part signal of telecommunication.
4. predictor is started in a kind of childbirth based on electrometrogram according to claim 2; It is characterized in that, said preposition bioelectric amplifier and rearmounted bioelectric amplifier with signal be amplified to analog/digital converter can perception and with the order of magnitude of handling.
5. predictor is started in a kind of childbirth based on electrometrogram according to claim 1; It is characterized in that; Being kept on the personal computer of electrometrogram handled, and the electrometrogram digital signal is delivered on the personal computer through USB interface and preserved processing in the corresponding program.
6. predictor is started in a kind of childbirth based on electrometrogram according to claim 1; It is characterized in that; The preservation of electrometrogram is handled and on embedded equipment, is accomplished, and the electrometrogram digital signal is is directly met and sent off to embedded equipment through the plate cascade of USB interface or printed circuit board (PCB) and preserved processing in the program accordingly.
7. an extraction method of characteristic parameters of utilizing claim 1-6 each said childbirth based on electrometrogram starting predictor to realize is characterized in that, comprises following basic step:
(1), extracts the signal of telecommunication that comprises the electrometrogram signal through electrode;
(2), eliminate mother's electrocardio, fetus electrocardio, electromagnetic interference noise with the analog filtering technology;
(3), use the preconditioning technique that suppresses the power frequency interference and eliminate baseline drift that the electrometrogram digital signal is handled;
(4), the technology of utilization wavelet analysis is extracted the eigenvalue of electrometrogram signal; Be that utilization wavelet transform, wavelet package transforms or lifting wavelet transform method are decomposed the electrometrogram digital signal; It is resolved into each frequency band by identical frequency interval, decompose the characteristic parameter that extracts energy, power, frequency and average on the frequency range at each then;
(5) if the electrometrogram signal extracts through the dynamic monitoring continuous acquisition; The technology that then maintenance data compares and peak value detects; The eigenvalue of each frequency band signals in more adjacent two days, and with the peak value of eigenvalue and anemia of pregnant woman just before giving birth the time peak value of corresponding frequency band compare; If the electrometrogram signal extracts through single acquisition, then use the technological prediction childbirth of artificial neural network to start the time, artificial neural network is obtained by a plurality of anemia of pregnant woman's electrometrogram sample of signal training;
(6), electrometrogram is exported with picture and eassay display device, start the predictive value of time to show childbirth, through the output that will predict the outcome of sound predictor.
8. extraction method of characteristic parameters according to claim 7 is characterized in that, gathers the electrode of electrometrogram signal in the said step (1); All be placed on anemia of pregnant woman's abdominal part; Extract the differential signal of electrode, extraction time is 20-40 minute, and reference electrode is placed on anemia of pregnant woman's hip.
9. extraction method of characteristic parameters according to claim 7; It is characterized in that; The collection of uterus electromyogram signal realizes through dynamic monitoring continuous acquisition or single acquisition in the said step (1); The dynamic monitoring continuous acquisition is that the last fortnight in expected date of confinement begins, and in the identical time anemia of pregnant woman is carried out the collection of electrometrogram signal every day; Single acquisition is in arbitrary sky of the last fortnight of expected date of confinement the anemia of pregnant woman to be carried out the collection of single electrometrogram signal.
10. extraction method of characteristic parameters according to claim 7 is characterized in that, in the step (5), the sample training of said artificial neural network may further comprise the steps:
(51), expected date of confinement the last fortnight arbitrary day, gather a plurality of anemia of pregnant woman's electrometrogram signal in the time identical with the single acquisition signal;
(52), each frequency band of component of signal use wavelet transformation or Fourier transformation method to decompose to(for) data;
(53) and behind the calculating energy, power, average, frequency carry out normalization, with the input of the value after this normalization as artificial neural network;
(54), these anemia of pregnant woman of tracing observation; When it is given a birth, serve as the output valve of corresponding input with this date of parturition, with the eigenvalue after the normalization as input; Corresponding date of parturition is as output; To the artificial neural network training, within 24 hours, so far accomplish artificial neural network training up to the error of output valve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110165745.XA CN102389307B (en) | 2011-06-20 | 2011-06-20 | Delivery starting forecasting device based on uterine electromyography and method for extracting characteristic parameter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110165745.XA CN102389307B (en) | 2011-06-20 | 2011-06-20 | Delivery starting forecasting device based on uterine electromyography and method for extracting characteristic parameter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102389307A true CN102389307A (en) | 2012-03-28 |
| CN102389307B CN102389307B (en) | 2014-01-29 |
Family
ID=45856795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110165745.XA Active CN102389307B (en) | 2011-06-20 | 2011-06-20 | Delivery starting forecasting device based on uterine electromyography and method for extracting characteristic parameter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102389307B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488857A (en) * | 2012-06-15 | 2014-01-01 | 国家人口计生委科学技术研究所 | Spontaneous abortion risk prediction system and method for establishing system |
| CN107137080A (en) * | 2017-05-25 | 2017-09-08 | 中国科学院深圳先进技术研究院 | Chronic back pain patient muscle's active state determination methods and system |
| CN109614840A (en) * | 2017-11-28 | 2019-04-12 | 重庆交通大学 | Premature labor detection method based on deep learning network |
| CN109645996A (en) * | 2019-02-21 | 2019-04-19 | 广州爱听贝科技有限公司 | A kind of uterine contractions fatigue monitoring method, system, intelligent terminal and storage medium |
| CN109805930A (en) * | 2019-02-21 | 2019-05-28 | 广州爱听贝科技有限公司 | It is a kind of to drive the method and system for reminding puerpera to exert oneself based on puerpera's uterine contraction signal |
| CN110123484A (en) * | 2019-05-31 | 2019-08-16 | 乐山知行智能科技有限公司 | A kind of livestock childbirth detection method and device |
| CN113133771A (en) * | 2021-03-18 | 2021-07-20 | 浙江工业大学 | Uterine electromyographic signal analysis and early birth prediction method based on time-frequency domain entropy characteristics |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1251754A (en) * | 1999-11-17 | 2000-05-03 | 天津大学 | Uterus contraction monitor |
| WO2001045555A1 (en) * | 1999-12-21 | 2001-06-28 | Jopejo Limited | Device for prediction of human or mammalian labour |
| CN2703499Y (en) * | 2003-01-29 | 2005-06-08 | 广州三瑞医疗器械有限公司 | Apparatus for monitoring mother metryperkinesis and controlling delivery process |
| CN202154676U (en) * | 2011-06-20 | 2012-03-07 | 暨南大学 | Childbirth launch forecasting device based on uterine flesh report graph |
-
2011
- 2011-06-20 CN CN201110165745.XA patent/CN102389307B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1251754A (en) * | 1999-11-17 | 2000-05-03 | 天津大学 | Uterus contraction monitor |
| WO2001045555A1 (en) * | 1999-12-21 | 2001-06-28 | Jopejo Limited | Device for prediction of human or mammalian labour |
| CN2703499Y (en) * | 2003-01-29 | 2005-06-08 | 广州三瑞医疗器械有限公司 | Apparatus for monitoring mother metryperkinesis and controlling delivery process |
| CN202154676U (en) * | 2011-06-20 | 2012-03-07 | 暨南大学 | Childbirth launch forecasting device based on uterine flesh report graph |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488857A (en) * | 2012-06-15 | 2014-01-01 | 国家人口计生委科学技术研究所 | Spontaneous abortion risk prediction system and method for establishing system |
| CN107137080A (en) * | 2017-05-25 | 2017-09-08 | 中国科学院深圳先进技术研究院 | Chronic back pain patient muscle's active state determination methods and system |
| CN109614840A (en) * | 2017-11-28 | 2019-04-12 | 重庆交通大学 | Premature labor detection method based on deep learning network |
| CN109614840B (en) * | 2017-11-28 | 2022-03-18 | 重庆交通大学 | Premature delivery detection method based on deep learning network |
| CN109645996A (en) * | 2019-02-21 | 2019-04-19 | 广州爱听贝科技有限公司 | A kind of uterine contractions fatigue monitoring method, system, intelligent terminal and storage medium |
| CN109805930A (en) * | 2019-02-21 | 2019-05-28 | 广州爱听贝科技有限公司 | It is a kind of to drive the method and system for reminding puerpera to exert oneself based on puerpera's uterine contraction signal |
| CN109645996B (en) * | 2019-02-21 | 2022-04-08 | 广州爱听贝科技有限公司 | Uterine contraction debilitation monitoring method and system, intelligent terminal and storage medium |
| CN110123484A (en) * | 2019-05-31 | 2019-08-16 | 乐山知行智能科技有限公司 | A kind of livestock childbirth detection method and device |
| CN113133771A (en) * | 2021-03-18 | 2021-07-20 | 浙江工业大学 | Uterine electromyographic signal analysis and early birth prediction method based on time-frequency domain entropy characteristics |
| CN113133771B (en) * | 2021-03-18 | 2022-10-28 | 浙江工业大学 | Uterine electromyographic signal analysis and early birth prediction method based on time-frequency domain entropy characteristics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102389307B (en) | 2014-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10987047B2 (en) | System and method for analyzing progress of labor and preterm labor | |
| CN102389307B (en) | Delivery starting forecasting device based on uterine electromyography and method for extracting characteristic parameter | |
| CN1287729C (en) | System for detection and analysis of material uterine, material and fetal cardiac and fetal brain activity | |
| Schlembach et al. | Monitoring the progress of pregnancy and labor using electromyography | |
| Fele-Žorž et al. | A comparison of various linear and non-linear signal processing techniques to separate uterine EMG records of term and pre-term delivery groups | |
| US7333850B2 (en) | Maternal-fetal monitoring system | |
| Vlemminx et al. | Electrohysterography for uterine monitoring during term labour compared to external tocodynamometry and intra-uterine pressure catheter | |
| Mikkelsen et al. | Electrohysterography of labor contractions: propagation velocity and direction | |
| Garcia-González et al. | Characterization of EHG contractions at term labor by nonlinear analysis | |
| Diab et al. | Classification of uterine EMG signals using supervised classification method | |
| Benalcazar-Parra et al. | Electrohysterographic characterization of the uterine myoelectrical response to labor induction drugs | |
| Hao et al. | Development of electrohysterogram recording system for monitoring uterine contraction | |
| CN1273080C (en) | Method and device for monitoring contraction activities of mother womb and controlling childbirth process | |
| CN105266799B (en) | A kind of ecg amplifier auto gain control method based on blind separation technology | |
| Li et al. | A study of uterine inertia on the spontaneous of labor using uterine electromyography | |
| CN202154676U (en) | Childbirth launch forecasting device based on uterine flesh report graph | |
| Huber et al. | Potential use of electrohysterography in obstetrics: a review article | |
| Garfield et al. | Monitoring the onset and progress of labor with electromyography in pregnant women | |
| CN113133771B (en) | Uterine electromyographic signal analysis and early birth prediction method based on time-frequency domain entropy characteristics | |
| Eswaran et al. | Application of wavelet transform to uterine electromyographic signals recorded using abdominal surface electrodes | |
| Yang et al. | Estimation of intrauterine pressure from electrohysterography using hilbert phase slips and statistics method | |
| Snowden et al. | A digital system for recording the electrical activity of the uterus | |
| CN107157474B (en) | Portable multicytosis electrocardioscanner and monitoring method thereof | |
| Hu et al. | A wireless and wearable system for fetal heart rate monitoring | |
| Lyapina et al. | The patterns of changes in the electrohysterogram amplitude characteristics in healthy pregnant women during the third trimester |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |