CN112043283A - Device and method for detecting movement of child in mother body - Google Patents
Device and method for detecting movement of child in mother body Download PDFInfo
- Publication number
- CN112043283A CN112043283A CN202010971497.7A CN202010971497A CN112043283A CN 112043283 A CN112043283 A CN 112043283A CN 202010971497 A CN202010971497 A CN 202010971497A CN 112043283 A CN112043283 A CN 112043283A
- Authority
- CN
- China
- Prior art keywords
- fetal movement
- data processing
- processing module
- acceleration
- movement
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1101—Detecting tremor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
- A61B5/7207—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal of noise induced by motion artifacts
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/02—Foetus
Abstract
The invention discloses a device and a method for detecting fetal movement of a child in a parent, wherein the device comprises an acceleration sensor and a microprocessor, the microprocessor comprises a data processing module and a storage module, the acceleration sensor is connected with the input end of the data processing module, and the output end of the data processing module is connected with the storage module; the acceleration sensor collects a fluctuation signal of the abdomen of the pregnant woman and sends the fluctuation signal to the data processing module, and the data processing module processes the fluctuation signal to remove a movement interference signal and identify a fetal movement signal; the storage module stores the fetal movement data identified by the data processing module. The method can accurately identify fetal movement and eliminate other movement interference, is scientific in method and accurate in result, and can be used for application scenes such as fetal monitoring of pregnant women in late pregnancy and products such as wearable fetal monitors.
Description
Technical Field
The invention belongs to the technology of monitoring fetal movement of a mother fetus, and particularly relates to a device and a method for detecting fetal movement of a mother fetus.
Background
Before the 20 th century, the stillbirth rate of developed countries has remained around 5%. Over the 30 s of the 20 th century, the rate of dead tires gradually decreased to 0.5%. However, in China, with the delay of marriage and childbearing age and the release of a second birth policy, the number of elderly high-risk puerperas is increased rapidly, and at present, more than 33% of pregnant women over 35 years old account for the new requirements for fetal monitoring. How to ensure the health development of the fetus in the pregnant woman is related to the happiness of ten million families, and the prenatal and postnatal care has an important effect on promoting the national quality. At present, two detection methods of fetal heart and fetal movement are mainly relied on. Fetal movement detection has a pre-warning time window more than one hour compared with fetal heart monitoring, and fetal abnormality can be found out in advance. Fetal movement occurs early in the fetus and becomes more complex with further perinatal progression. More than 60% of fetal movement is caused by fetal limb movement, and the fetus maintains about 5.7 seconds per fetal movement. The fetal movement reduction is the manifestation of fetal bad conditions, and researches show that the fetal movement times of healthy fetuses keep stable along with the deep perinatal period, but the fetal movement times of unhealthy fetuses have obvious swing in the perinatal period, so that the long-term continuous fetal movement monitoring is a very effective means for preventing bad fatalities in the late pregnancy period clinically.
The conventional ultrasonic imaging method in hospitals has high accuracy, but has the defects of high invasiveness and high cost. Moreover, the radiation has certain harm to the fetus and the pregnant woman, can not be used for a long time, and can not realize continuous non-invasive dynamic long-range fetal movement monitoring. Doctors recommend that pregnant women take an initiative in a quiet environment for several hours, one hour each morning, noon and evening, but studies have shown that pregnant women can only actively feel 36% of the effective fetal movements compared to the doppler method, which is the gold standard, which is very inaccurate. And for contemporary women, there is not necessarily enough free time to actually perform. The wearable passive fetal movement monitoring device collects and processes fetal movement signals in a manner that a mechanical sensor is attached to the abdomen of a pregnant woman, so that the accuracy can be greatly improved, and long-term monitoring can be realized. However, the detected signal is inevitably affected by the movement disturbance of the pregnant woman in daily life. The removal of motion disturbances is crucial to the performance of wearable fetal activity monitoring devices. The current method can only remove part of motion interference, has low accuracy and no universality, and greatly limits the application of fetal movement monitoring technology.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a device and a method for detecting fetal movement of a child in a mother body, which can accurately identify the fetal movement and eliminate other movement interferences.
The technical scheme is as follows: the invention discloses a device for detecting fetal movement of a mother inner tire, which comprises an acceleration sensor and a microprocessor, wherein the microprocessor comprises a data processing module and a storage module, the acceleration sensor is connected with the input end of the data processing module, and the output end of the data processing module is connected with the storage module; the acceleration sensor collects a fluctuation signal of the abdomen of the pregnant woman and sends the fluctuation signal to the data processing module, and the data processing module processes the fluctuation signal to remove a movement interference signal and identify a fetal movement signal; the storage module stores the fetal movement data identified by the data processing module.
The microprocessor also comprises a communication module, the communication module is connected with the output end of the data processing module, and the data processing module sends the processing result to external equipment through the communication module to realize wireless communication with the external equipment.
The invention also comprises a method for detecting the fetal movement of the child in the parent, which comprises the following steps:
(1) the signal acquisition module acquires an acceleration signal caused by fetal movement and an acceleration signal caused by movement interference in daily life of the pregnant woman and transmits the acquired data to the data processing module;
(2) the data processing module is used for segmenting the fetal movement acceleration data and the motion disturbance acceleration data respectively to obtain a plurality of windows;
(3) performing time-frequency signal analysis on the data subjected to segmentation processing to obtain a two-dimensional characteristic image;
(4) the data processing module performs data training on the two-dimensional characteristic images of the fetal movement signals by adopting a dictionary learning algorithm, and trains the two-dimensional characteristic images of movement interference in daily life of the pregnant woman by adopting the same method to obtain all atoms in the two sets of dictionaries;
(5) and the data processing module performs atomic decomposition on the original motion interference acceleration signal by a sparse representation method to finish motion interference removal and fetal movement signal identification.
In the step (2), the data processing module respectively performs segmentation processing on the fetal movement acceleration data and the motion disturbance acceleration data according to a fixed time interval to obtain a plurality of windows, and two adjacent windows are partially overlapped.
And (3) carrying out time-frequency signal analysis on the window with the fetal movement signal or the motion interference signal to obtain a two-dimensional characteristic image.
In the step (3), the time-frequency signal analysis determines the adopted method according to the comparison signal discrimination, and the adopted method is one of short-time Fourier change, continuous wavelet change, Wigner-Ville change and wavelet synchronous compression change methods.
In the step (4), the adopted dictionary learning algorithm is a singular value decomposition method.
In the step (5), performing atom decomposition on the original motion interference acceleration signal to obtain matched fetal movement atoms and motion interference atoms; if the matched fetal movement atoms exist and the acceleration is within the specified range, the fetal movement exists in the time window.
In the step (5), the sparse representation method adopted is an orthogonal matching pursuit method.
The number of the acceleration sensors is one or more, and when the number of the acceleration sensors is multiple, under the condition that signals detected by two or more acceleration sensors are completely the same, the acceleration signals are judged to be caused by the self-movement interference of the pregnant woman.
Has the advantages that: compared with the prior art, the invention has the beneficial effects that: the feature map and atoms of fetal movement or motion interference are extracted through a dictionary learning algorithm, and then matching is performed through a sparse representation algorithm, so that the fetal movement recognition method is more targeted, the fetal movement can be accurately recognized, other motion interference is eliminated, and the fetal movement recognition method is suitable for wearable fetal monitors.
Drawings
FIG. 1 is a block diagram of the detecting device according to the present invention;
FIG. 2 is a flow chart of the detection method of the present invention;
FIG. 3 is a diagram of raw acceleration signals collected by an acceleration sensor in the method of the present invention;
FIG. 4 is a schematic atomic diagram of a fetal activity dictionary in the method of the present invention;
FIG. 5 is a diagram of the original motion disturbance acceleration signal and its orthogonal matching tracking result in the method of the present invention.
Detailed Description
The invention is described in further detail below with reference to specific embodiments and the accompanying drawings.
As shown in figure 1, the maternal-fetal-movement detection device comprises an acceleration sensor and a microprocessor, and can be directly worn on the abdomen of a pregnant woman to receive mechanical signals. One or more acceleration sensors or arrays attached to the flexible circuit board are used for acquiring the abdomen fluctuation signals of the pregnant woman. The microprocessor comprises a data processing module, a storage module and a communication module, the acceleration sensor is connected to the input end of the data processing module, and the output end of the data processing module is respectively connected with the storage module and the communication module. The acceleration sensor collects a fluctuation signal of the abdomen of the pregnant woman and sends the fluctuation signal to the data processing module, and the data processing module processes the fluctuation signal to remove a movement interference signal and identify a fetal movement signal; the storage module stores the fetal movement data identified by the data processing module. And the data processing module sends the processing result to the external equipment through the communication module.
As shown in fig. 2, the invention further includes a method for detecting fetal movement of a mother inner tire, which specifically includes the following steps:
(1) as shown in fig. 3, the acceleration sensor collects acceleration signals caused by fetal movement, also collects acceleration signals caused by movement interference in daily life of the pregnant woman, and sends the data collected twice to the data processing module; in this embodiment, the signal acquisition module is an acceleration sensor attached to the abdomen of the pregnant woman; under the condition that the pregnant woman is completely still, a clean fetal movement signal is obtained through an acceleration sensor; when no fetal movement exists in the abdomen of the pregnant woman, motion interference signals of the pregnant woman such as respiration, laughing, cough, walking, waist turning, up and down steps, lying posture turning and the like are obtained through the acceleration sensor;
(2) the data processing module is used for segmenting fetal movement acceleration data and motion interference acceleration data respectively, and then performing time-frequency signal analysis on the segmented data to obtain a two-dimensional characteristic image; specifically, a data processing module in the microprocessor respectively divides a clean fetal movement signal and a motion interference signal into windows of about 5.7 seconds, and adjacent windows are overlapped with 1/4 or more.
(3) Carrying out short-time Fourier change, continuous wavelet change, Wigner-Ville change or synchronous wavelet compression change on a window with a clean fetal movement signal or motion interference signal to obtain a two-dimensional map through time-frequency signal analysis; the time frequency signal analysis adopts a method determined according to the comparison signal discrimination;
(4) as shown in fig. 4, the data processing module performs data training on the two-dimensional feature images of fetal movement signals by using singular value decomposition (K-SVD) or other dictionary training algorithms, and trains the two-dimensional feature images of movement interference in daily life of pregnant women by using the same method to obtain all atoms in two sets of dictionaries;
(5) as shown in fig. 5, the data processing module performs atomic decomposition on the original motion interference acceleration signal by Orthogonal Matching Pursuit (OMP) or other sparse representation methods to obtain matched fetal movement atoms and motion interference atoms; if the fetal movement atoms are matched and the acceleration range is 0.01 g-0.1 g, the fetal movement exists in the time window. If a plurality of acceleration sensors are arranged, if two or more acceleration sensors detect the same signals, the signals are judged to be caused by the self-movement interference of the pregnant woman, the false positives can be further reduced, and the detection accuracy rate is improved.
Claims (10)
1. The utility model provides a matrix inner tube child moves detection device which characterized in that: the device comprises an acceleration sensor and a microprocessor, wherein the microprocessor comprises a data processing module and a storage module, the acceleration sensor is connected to the input end of the data processing module, and the output end of the data processing module is connected with the storage module; the acceleration sensor collects a fluctuation signal of the abdomen of the pregnant woman and sends the fluctuation signal to the data processing module, and the data processing module processes the fluctuation signal to remove a movement interference signal and identify a fetal movement signal; the storage module stores the fetal movement data identified by the data processing module.
2. The matrix inner tire fetal movement detection apparatus of claim 1, wherein: the microprocessor also comprises a communication module, the communication module is connected with the output end of the data processing module, and the data processing module sends the processing result to external equipment through the communication module.
3. A method of detecting fetal movement in a mother's tire as claimed in claim 1 or 2, comprising the steps of:
(1) the acceleration sensor collects acceleration signals caused by fetal movement and acceleration signals caused by movement interference in daily life of the pregnant woman and sends the collected data to the data processing module;
(2) the data processing module is used for segmenting the fetal movement acceleration data and the motion disturbance acceleration data respectively to obtain a plurality of windows;
(3) performing time-frequency signal analysis on the data subjected to segmentation processing to obtain a two-dimensional characteristic image;
(4) the data processing module performs data training on the two-dimensional characteristic images of the fetal movement signals by adopting a dictionary learning algorithm, and trains the two-dimensional characteristic images of movement interference in daily life of the pregnant woman by adopting the same method to obtain all atoms in the two sets of dictionaries;
(5) and the data processing module performs atomic decomposition on the original motion interference acceleration signal by a sparse representation method to finish motion interference removal and fetal movement signal identification.
4. The method of detecting fetal movement in a mother's tire according to claim 3, wherein: in the step (2), the data processing module respectively performs segmentation processing on the fetal movement acceleration data and the motion disturbance acceleration data according to a fixed time interval to obtain a plurality of windows, and two adjacent windows are partially overlapped.
5. The method of detecting fetal movement in a mother's tire according to claim 4, wherein: and (3) carrying out time-frequency signal analysis on the window with the fetal movement signal or the motion interference signal to obtain a two-dimensional characteristic image.
6. The method of detecting fetal movement in a mother's tire according to claim 3, wherein: in the step (3), the time-frequency signal analysis determines the adopted method according to the comparison signal discrimination, and the adopted method is one of short-time Fourier change, continuous wavelet change, Wigner-Ville change and wavelet synchronous compression change methods.
7. The method of detecting fetal movement in a mother's tire according to claim 3, wherein: in the step (4), the adopted dictionary learning algorithm is a singular value decomposition method.
8. The method of detecting fetal movement in a mother's tire according to claim 3, wherein: in the step (5), performing atom decomposition on the original motion interference acceleration signal to obtain matched fetal movement atoms and motion interference atoms; if the matched fetal movement atoms exist and the acceleration is within the specified range, the fetal movement exists in the time window.
9. The method of detecting fetal movement in a mother's tire according to claim 3, wherein: in the step (5), the sparse representation method adopted is an orthogonal matching pursuit method.
10. The method of detecting fetal movement in a mother's tire according to claim 3, wherein: the number of the acceleration sensors is one or more, and when the number of the acceleration sensors is multiple, under the condition that signals detected by two or more acceleration sensors are completely the same, the acceleration signals are judged to be caused by the self-movement interference of the pregnant woman.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010971497.7A CN112043283A (en) | 2020-09-16 | 2020-09-16 | Device and method for detecting movement of child in mother body |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010971497.7A CN112043283A (en) | 2020-09-16 | 2020-09-16 | Device and method for detecting movement of child in mother body |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112043283A true CN112043283A (en) | 2020-12-08 |
Family
ID=73604757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010971497.7A Pending CN112043283A (en) | 2020-09-16 | 2020-09-16 | Device and method for detecting movement of child in mother body |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112043283A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113679354A (en) * | 2021-09-02 | 2021-11-23 | 上海贝瑞电子科技有限公司 | Fetal movement signal detection device and method and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWM490302U (en) * | 2014-08-11 | 2014-11-21 | Huai-De Chen | Fetal pulse detector with real-time data transmission |
| US20190261220A1 (en) * | 2016-11-08 | 2019-08-22 | Koninklijke Philips N.V. | Method for wireless data transmission range extension |
| US20190313929A1 (en) * | 2016-12-13 | 2019-10-17 | King Abdullah University Of Science And Technology | System and method for non-invasive extraction of fetal electrocardiogram signals |
-
2020
- 2020-09-16 CN CN202010971497.7A patent/CN112043283A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWM490302U (en) * | 2014-08-11 | 2014-11-21 | Huai-De Chen | Fetal pulse detector with real-time data transmission |
| US20190261220A1 (en) * | 2016-11-08 | 2019-08-22 | Koninklijke Philips N.V. | Method for wireless data transmission range extension |
| US20190313929A1 (en) * | 2016-12-13 | 2019-10-17 | King Abdullah University Of Science And Technology | System and method for non-invasive extraction of fetal electrocardiogram signals |
Non-Patent Citations (1)
| Title |
|---|
| 赵吕晨 等: "基于多加速度传感器的胎动信号检测方法", 《传感器与微系统》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113679354A (en) * | 2021-09-02 | 2021-11-23 | 上海贝瑞电子科技有限公司 | Fetal movement signal detection device and method and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106344005B (en) | A kind of removable electrocardiogram monitoring system | |
| CN111938613B (en) | Health monitoring device and method based on millimeter wave radar | |
| CN108416367B (en) | Sleep staging method based on multi-sensor data decision-level fusion | |
| CN110192862B (en) | Radar-based non-contact human body respiration detection method and device | |
| CN109528159B (en) | Human sleep and respiration monitoring system and method based on bed body | |
| Zhao et al. | An IoT-based wearable system using accelerometers and machine learning for fetal movement monitoring | |
| US20130102856A1 (en) | Non-invasive detection of fetal or maternal illness | |
| EP3803709A1 (en) | Detecting abnormalities in ecg signals | |
| CN107530015B (en) | Vital sign analysis method and system | |
| CN110236515A (en) | A kind of contactless heart rate detection method based on near-infrared video | |
| CN112263242A (en) | Respiration detection and mode classification method based on FMCW radar | |
| CN112971795B (en) | Electrocardiosignal quality evaluation method | |
| CN110960211A (en) | Embedded-based real-time electrocardio monitoring system | |
| CN115299899A (en) | Activity recognition and beat-to-beat blood pressure monitoring, analyzing and early warning system based on multiple sensors | |
| Delay et al. | Non invasive wearable device for fetal movement detection | |
| CN112043283A (en) | Device and method for detecting movement of child in mother body | |
| Liu et al. | Motion artifact detection in ppg signals based on gramian angular field and 2-d-cnn | |
| CN105708441B (en) | Wearable fingerstall and electrocardiogram and pulse-tracing collection terminal | |
| Iadarola et al. | A new method for sEMG envelope detection from reduced measurements | |
| Gaoan et al. | Heart rate measurement via smart phone acceleration sensor | |
| Lin et al. | Air-mattress system for ballistocardiogram-based heart rate and breathing rate estimation | |
| Liang et al. | Passive fetal movement signal detection system based on intelligent sensing technology | |
| CN113907765B (en) | Noninvasive fetal electrocardiosignal quality assessment method | |
| CN115770028A (en) | Blood pressure detection method, system, device and storage medium | |
| Quanyu | Pulse signal analysis based on deep learning network |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201208 |