CN111667916A - Machine learning-based antenatal uterine contraction judging system - Google Patents
Machine learning-based antenatal uterine contraction judging system Download PDFInfo
- Publication number
- CN111667916A CN111667916A CN202010518019.0A CN202010518019A CN111667916A CN 111667916 A CN111667916 A CN 111667916A CN 202010518019 A CN202010518019 A CN 202010518019A CN 111667916 A CN111667916 A CN 111667916A
- Authority
- CN
- China
- Prior art keywords
- uterine contraction
- uterine
- user
- information
- contraction
- 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
- 208000036029 Uterine contractions during pregnancy Diseases 0.000 title claims abstract description 177
- 238000010801 machine learning Methods 0.000 title claims abstract description 39
- 238000004891 communication Methods 0.000 claims abstract description 20
- 238000012544 monitoring process Methods 0.000 claims abstract description 8
- 210000001015 abdomen Anatomy 0.000 claims abstract description 4
- 230000008602 contraction Effects 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 26
- 238000000034 method Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 5
- 239000012567 medical material Substances 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 12
- 210000003754 fetus Anatomy 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000017531 blood circulation Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 210000004291 uterus Anatomy 0.000 description 2
- 208000008035 Back Pain Diseases 0.000 description 1
- 208000008930 Low Back Pain Diseases 0.000 description 1
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000000220 Panda oleosa Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 208000010515 dystocia Diseases 0.000 description 1
- 230000035558 fertility Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 210000000754 myometrium Anatomy 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Bioethics (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The uterine contraction state of the antenatal user is accurately judged, so that unnecessary medical material pressure and time and risk cost of the antenatal user are reduced. The invention provides a machine learning-based antenatal uterine contraction judging system which comprises a uterine contraction signal acquisition device, a server device and a client terminal. The uterine contraction signal acquisition device is fixed on the abdomen of the user, acquires the uterine contraction original information of the labor user and generates a corresponding uterine contraction signal; the server device receives the uterine contraction signals in a wireless communication mode and distributes the processed uterine contraction state information to the address information through the trained machine learning model; the client terminal calls the uterine contraction state information stored in the server device by enabling the on-production user to access the address information, so that the real-time monitoring of the uterine contraction state of the on-production user is completed, and whether the on-production user is suitable for production or not is judged.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence, relates to medical instruments for monitoring and early warning, and particularly relates to a temporary labor contraction judging system based on machine learning.
Background
With the comprehensive implementation of the two-fetus policy, China is coming to a new cycle of birth peak, people pay more and more attention to the health conditions of pregnant women and fetuses, and the realization of 'prenatal and postnatal care' is very important for modern families. Uterine contraction (uterine contraction) is an important physiological characteristic of pregnant women and is also a very important clinical obstetrical examination parameter. Before delivery, the uterine contraction of the pregnant woman becomes regular, becomes strong from weak, and gradually weakens until disappearance after a certain time, which is directly manifested as the hardening of the skin from soft. During this period, if the monitoring is not performed effectively, the uterine contraction pressure may be too high to affect the blood circulation and flow in the uterus, so as to cause the fetus to be lack of oxygen, and the morbidity and mortality of the fetus and the mother are high, and the monitoring reminding through the medical instrument is particularly important in order to protect the physical health of the pregnant woman and the healthy development of the fetus.
The pregnant woman needs to go to a hospital regularly for obstetrical examination according to the advice of doctors, so that the safety of the pregnant woman and a fetus is ensured to a certain extent, and the tension of the pregnant woman is relieved. However, during the edd period of 37 weeks, the frequency of contractions of the pregnant woman increases, and regular contractions and the antenatal condition may occur at any time during this period. But the pregnant woman is difficult to judge the regular degree of the uterine contraction, and is easy to worry about even frequent medical treatment as soon as the uterine contraction occurs. At the moment, traffic jam on roads is unnecessary, walking is inconvenient, queuing and registration are carried out, the time cost of the pregnant women is greatly increased, in addition, many pregnant women are generally married at night, the fertility experience is lacked, the uterine contraction situation is not well understood, the uterine contraction situation at the moment is found after hospital examination and is not suitable for parturient, the examination needs to be carried out for several days, the medical resources of the hospital are occupied, the pregnant women wait for the parturient examination in the hospital, the doctor-patient contradiction is easy to happen, and meanwhile, the back-and-forth running is not beneficial to the rest of the pregnant women during the parturient. Modern medical research shows that early arrival in a hospital for parturient can greatly increase the risk of dystocia due to the nervous mind of the pregnant woman during the waiting period.
From the perspective of medical data, due to the height and body type of many patients and the like, the data difference between different patients is large, and in the face of mass data, the error of the output result of the traditional algorithm increases along with the increase of the data processing amount, so that the uterine contraction states of different patients are difficult to be accurately judged.
If complex monitoring equipment is adopted to detect the uterine contraction state of a patient, although the precision of judging the uterine contraction state can be guaranteed, the cost is too high, the size is large, and the realization of household use is not practical.
Disclosure of Invention
In order to solve the problems, a temporary labor contraction judging system based on machine learning is provided.
The invention adopts the following technical scheme:
the invention relates to a machine learning-based antenatal uterine contraction judging system, which comprises: uterine contraction signal acquisition device, server device and client terminal. The uterine contraction signal acquisition device is fixed on the abdomen of the user and used for acquiring the uterine contraction original information of the user and processing the information to generate a uterine contraction signal; the server device is used for receiving the uterine contraction signals, distinguishing the uterine contraction signals through a uterine contraction distinguishing model trained in advance so as to generate uterine contraction state information reflecting the uterine contraction state of the user, and distributing the uterine contraction state information to the address information through a web application framework which uses the same operation language as the uterine contraction distinguishing model; and the client terminal acquires the uterine contraction state information through accessing the address information and displays the uterine contraction state information to a user, wherein the training method of the uterine contraction judging model comprises the following steps: acquiring a uterine contraction signal for training and a corresponding uterine contraction state label; carrying out merging processing and default value processing on the training uterine contraction signals through a data analysis module to be used as signals to be processed; extracting appropriate feature engineering from the signal to be processed; and inputting the characteristic engineering into the uterine contraction judging model, and realizing training of the uterine contraction judging model by a support vector machine algorithm based on the uterine contraction state label so as to obtain the uterine contraction judging model.
The machine learning-based antenatal uterine contraction judging system provided by the invention also has the technical characteristics that the uterine contraction signal acquisition device comprises: the acquisition unit is fixed at the uterine bottom of a user and used for acquiring uterine contraction original information; the circuit unit is connected with the acquisition unit and used for filtering and amplifying the uterine contraction original information and generating amplified uterine contraction information; the processor unit is connected with the circuit unit, receives the amplified uterine contraction information and processes the information into uterine contraction signals; the wireless communication unit is connected with the processor unit and is used for outputting the uterine contraction signal to the server device; the Bluetooth unit is connected with the acquisition unit and is used for being in communication connection with the user terminal; and the power supply unit is connected with each unit in the uterine contraction signal acquisition device and is used for providing energy for all units of the uterine contraction signal acquisition device.
The machine learning-based antenatal uterine contraction judging system provided by the invention has the technical characteristics that the acquisition unit is fixed by a patch type shell, and the uterine fundus of a user is installed by a bridle.
The machine learning-based labor contraction judging system provided by the invention has the technical characteristics that the acquisition units are pressure sensors output by millivolt voltage and touch force sensors output by millivolt voltage.
The machine learning-based real-time labor contraction judging system provided by the invention also has the technical characteristics that: and the database unit is used for storing the uterine contraction signals, the training uterine contraction signals, the uterine contraction state labels, the characteristic engineering, the signals to be processed, the uterine contraction state information and the address information.
The machine learning-based real-time labor contraction judging system provided by the invention has the technical characteristics that the web application framework is used for sending the contraction state information to the client terminal when the client terminal logs in the address information.
Action and Effect of the invention
According to the machine learning-based antenatal uterine contraction judging system, the machine learning model trained in advance is used for judging uterine contraction information, compared with the traditional judging method, the uterine contraction state judging accuracy is greatly improved, medical material pressure caused by misjudgment can be relieved, and time cost and risk cost of a user are reduced. Meanwhile, the machine learning model and the web application framework adopt a unified operation language, so that later development and maintenance are facilitated. In addition, the uterine contraction signal acquisition device is simple in structure and convenient to carry, can be used as an auxiliary judgment device carried by a user, and achieves real-time monitoring of the user.
Drawings
FIG. 1 is a block diagram of a machine learning-based real-time labor contraction determination system according to an embodiment of the present invention;
FIG. 2 is a block diagram of the uterine contraction signal acquisition device in the embodiment of the present invention;
FIG. 3 is a block diagram of a server apparatus in the embodiment of the present invention;
FIG. 4 is a schematic diagram of a training uterine contraction signal in an embodiment of the present invention;
FIG. 5 is a flow diagram of pre-training of a machine learning model in an embodiment of the invention; and
fig. 6 is a flowchart of the work flow of the machine learning-based real-time labor contraction judging system in the embodiment of the present invention.
Detailed Description
In order to make the technical means, creation features, achievement purposes and effects of the present invention easy to understand, the present invention will be described in detail with reference to the following embodiments and accompanying drawings.
< example >
Fig. 1 is a block diagram of a machine learning-based real-time labor contraction judging system in an embodiment of the present invention.
As shown in fig. 1, a machine learning-based real-time labor contraction judging system 100 includes a contraction signal collecting device 101, a server device 102, a client terminal 103, and a communication network 104.
Among them, the communication network 104 includes: bluetooth wireless communication 104A and WIFI wireless communication 104B. The uterine contraction signal acquisition device 101 is in communication connection with the user terminal 103 through Bluetooth wireless communication 104A, the uterine contraction signal acquisition device 101 is in communication connection with the server device 102 through WIFI wireless communication 104B, and the server device 102 is in communication connection with the user terminal 103 through WIFI wireless communication 104B.
In this embodiment, the uterine contraction signal acquisition device 101 is fixed to the abdomen of the user, and is configured to acquire the uterine contraction original information of the user and process the information to generate a uterine contraction signal.
Fig. 2 is a structural block diagram of the uterine contraction signal acquisition device in the embodiment of the invention.
As shown in fig. 2, the uterine contraction signal acquisition device 101 includes: the device comprises an acquisition unit 11, a circuit unit 12, a processor unit 13, a wireless communication unit 14, a Bluetooth unit 15 and a power supply unit 16.
The acquisition unit 11 is a pressure sensor and a touch force sensor which are fixed on the uterine fundus of the user through a patch type shell, and can acquire pressure information and touch force information of the uterine fundus of the user as uterine contraction original information.
In this embodiment, the pressure sensor and the touch force sensor used by the acquisition unit 11 are output voltage in millivolt in the FSS series.
The circuit unit 12 is an amplifying circuit connected to the acquisition unit 11, and is configured to filter and amplify the uterine contraction original information and use the information as amplified uterine contraction information.
The processor unit 13 is a single chip connected to the circuit unit 12, and is used for receiving and amplifying the uterine contraction information and processing the information into a uterine contraction signal.
In this embodiment, the single chip microcomputer adopted by the processor unit 13 develops the board stm32f103c8t6 for the smallest stm 32.
The wireless communication unit 14 is used for exchanging data between the uterine contraction signal acquisition device 101 and the server device 102.
In this embodiment, the wireless communication unit 14 is a WIFI module connected to the processor unit 13. When the processor unit 13 generates a uterine contraction signal, the wireless communication unit 14 outputs the uterine contraction signal to the server apparatus 102.
The bluetooth unit 15 is an HC-06 bluetooth module connected to the acquisition unit 11, and the bluetooth unit 15 is used for performing wireless communication connection between the uterine contraction signal acquisition device 101 and the client terminal 103. When the client terminal 103 sends a working signal to the bluetooth unit 15 in the uterine contraction signal collecting device 101, the signal is sent to start the collecting unit 11.
The power supply unit 16 is connected to all the units to ensure that the units are powered.
Fig. 3 is a block diagram of a server apparatus in the embodiment of the present invention.
As shown in fig. 3, the server apparatus 102 includes a database unit 21, a contraction judgment model 22, and an access feedback unit 23.
The database unit 21 is used for storing the uterine contraction signal received by the server device 102,
in this embodiment, the database unit 21 further stores training contraction signals for training and intermediate information generated in the training process, such as: the system comprises a uterine contraction state label, a characteristic project, a signal to be processed, uterine contraction state information and address information required by an access feedback process.
In this embodiment, the sampling rate of the uterine contraction data is 5Hz, and 2100 pieces of data collected by each sample are classified into three types: regular uterine contractions, pseudouterine contractions, and no uterine contractions.
Fig. 4 is a schematic diagram of a uterine contraction signal for training in the embodiment of the present invention.
As shown in part a of fig. 4, a schematic diagram of regular contractions in the uterine contraction signal for training in this embodiment is shown. Regular uterine contraction is a temporary labor sign, and is developed to a state that the uterine contraction is performed once every 2-3 minutes after the development, lasts for about 30 seconds, and is directly manifested as the skin becomes soft and hard, the lumbago is obviously aggravated, and a small part of people have painless uterine contraction.
As shown in part B of fig. 4, a diagram of a pseudo uterine contraction in the training uterine contraction signal in the present embodiment is shown. Pseudouterine contractions are irregular contractions of the uterus that occur several weeks before delivery and when the uterine muscles are more sensitive, manifested by short duration and weak strength.
As shown in part C of fig. 4, a non-uterine contraction diagram of the training uterine contraction signal in the present embodiment is shown. The no uterine contraction data is used to distinguish the case of no uterine contraction.
The uterine contraction judging model 22 is a model obtained by training a machine learning model in advance, and is used for judging a uterine contraction signal so as to generate uterine contraction state information reflecting the uterine contraction state of the user.
FIG. 5 is a flow chart of pre-training of a machine learning model in an embodiment of the invention
As shown in fig. 5, the pre-training of the machine learning model in this embodiment includes the following steps:
step U1, the machine learning model obtains the training uterine contraction signal and the corresponding uterine contraction state label from the database unit 21, and then step U2 is performed;
step U2, merging the training uterine contraction signals through a pandas data analysis module and processing the training uterine contraction signals with default values to be used as signals to be processed, and then entering step U3;
step U3, extracting appropriate feature engineering from the signal to be processed obtained in the step U2, and then entering the step U4;
and step U4, inputting the characteristic engineering obtained in the step U3 into a machine learning model, training the machine learning model by a support vector machine algorithm based on the uterine contraction state label to obtain a uterine contraction judging model, and entering an ending state.
In this embodiment, the machine learning model classifies the uterine contraction signals by LIBSVM.
The access feedback unit 23 is configured to assign the uterine contraction state information to a URL. In this embodiment, the access feedback unit 23 is a flash lightweight web application framework using the same operation language (python) as the uterine contraction judging model 22.
The client terminal 103 is a user operation terminal, and the user calls the uterine contraction state information in the server apparatus 102 by performing a predetermined operation on the client terminal 103.
In this embodiment, the client terminal is a small program loaded on the mobile phone of the user, when the user accesses the URL through the small program, the access feedback unit 23 sends the uterine contraction state information to the client terminal 103, and the user checks the uterine contraction state information allocated to the URL through the small program of the mobile phone, thereby determining whether the user is suitable for the temporary production.
In this embodiment, the uterine contraction state information is a view function generated based on the uterine contraction signal and image information corresponding to regular uterine contraction, pseudo uterine contraction, and no uterine contraction, respectively.
Fig. 6 is a flowchart of the work flow of the machine learning-based real-time labor contraction judging system in the embodiment of the present invention.
As shown in fig. 6, the working flow of the machine learning-based real-time labor contraction judging system 100 is as follows:
step S1, the uterine contraction signal acquisition device 101 acquires the original uterine contraction information through the acquisition unit 11, and then step S2 is performed;
step S2, the uterine contraction signal collecting device 101 performs filtering and amplification processing on the original uterine contraction information generated in step S1 through the circuit unit 12 to generate amplified uterine contraction information, and then the process goes to step S3;
step S3, the uterine contraction signal collecting device 101 receives the amplified uterine contraction information generated in step S2 through the processor unit 13 and processes the information into a uterine contraction signal, and then proceeds to step S4;
step S4, the uterine contraction signal collecting device 101 outputs the uterine contraction signal obtained in step S3 to the server device 102 through the wireless communication unit 14, and then proceeds to step S5;
step S5, the server apparatus 102 discriminates the uterine contraction signal by the uterine contraction discrimination model 22 to generate uterine contraction state information reflecting the uterine contraction state of the user, and then proceeds to step S6;
in step S6, the server apparatus 102 assigns the contraction status information generated in step S5 to a URL in the server through the web application framework, and then proceeds to step S7;
in step S7, the client terminal 103 accesses the URL in step S6, and the server apparatus 102 transmits the contraction state information assigned in the URL to the client terminal 103 through the web application framework, and displays it to the user through the applet, and then enters an end state.
Examples effects and effects
According to the machine learning-based antenatal uterine contraction judging system provided by the embodiment, as the pre-trained machine learning model is used for judging uterine contraction information, compared with the traditional judging method, the uterine contraction state judging accuracy is greatly improved, the medical material pressure caused by misjudgment can be relieved, and the time cost and the risk cost of a user are reduced. Meanwhile, the machine learning model and the web application framework adopt a unified operation language, so that later development and maintenance are facilitated. In addition, the uterine contraction signal acquisition device is simple in structure and convenient to carry, can be used as an auxiliary judgment device carried by a user, and can realize real-time monitoring of the user.
In the embodiment, the pressure sensor and the touch force sensor used by the acquisition unit are output by millivolt voltage in FSS series, so that the acquired signal precision is high, and the uterine contraction original information obtained after proper filtering and amplifying is more accurate.
In the embodiment, because the processor unit adopts the stm32 singlechip, the singlechip has high working speed and needs few peripheral elements, the installation difficulty of the processor unit can be reduced, and the processing efficiency is improved.
In the embodiment, the machine learning model is trained by using a support vector machine algorithm and the uterine contraction data is classified by using the LIBSVM, so that compared with the traditional learning-only method, the identification precision is higher, and the identification accuracy of the system is correspondingly improved.
In the embodiment, the user accesses the address information by logging in the mobile phone preloading small program and obtains the uterine contraction state information distributed at the corresponding address information in an image form, so that the operation of the user is convenient and fast, and the learning cost is low.
The above-described embodiments are merely illustrative of specific embodiments of the present invention, and the present invention is not limited to the description of the above-described embodiments.
In the above embodiment, the uterine contraction state information is output to the client terminal only when the user accesses the address information through the applet. In other schemes of the invention, the generated uterine contraction state information is output to the client terminal, stored in the mobile phone and used for generating a function view based on the stored uterine contraction state information.
Claims (6)
1. A temporary labor contraction judging system based on machine learning is used for monitoring the contraction state of a user to be delivered and judging whether the temporary labor is suitable or not, and is characterized by comprising the following steps:
the uterine contraction signal acquisition device is fixed on the abdomen of the user and used for acquiring the uterine contraction original information of the user and processing the information to generate a uterine contraction signal;
the server device is used for receiving the uterine contraction signals and distinguishing the uterine contraction signals through a uterine contraction distinguishing model trained in advance so as to generate uterine contraction state information reflecting the uterine contraction state of the user, and the server device distributes the uterine contraction state information to address information through a web application framework which uses the same operation language as the uterine contraction distinguishing model; and
the client terminal acquires the uterine contraction state information by accessing the address information and displays the uterine contraction state information to the user,
the training method of the uterine contraction judging model comprises the following steps:
acquiring a uterine contraction signal for training and a corresponding uterine contraction state label;
carrying out merging processing and default value processing on the training uterine contraction signals through a data analysis module to be used as signals to be processed;
extracting appropriate feature engineering from the signal to be processed;
inputting the characteristic engineering into a uterine contraction judging model, and realizing training of the uterine contraction judging model by a support vector machine algorithm based on the uterine contraction state label so as to obtain the uterine contraction judging model.
2. The machine learning-based real-time labor contraction judging system according to claim 1, wherein:
wherein, the uterine contraction signal acquisition device comprises:
the acquisition unit is fixed at the uterine bottom of the user and used for acquiring the uterine contraction original information;
the circuit unit is connected with the acquisition unit and used for filtering and amplifying the uterine contraction original information and generating amplified uterine contraction information;
the processor unit is connected with the circuit unit, receives the amplified uterine contraction information and processes the information into uterine contraction signals; and
and the wireless communication unit is connected with the processor unit and used for outputting the uterine contraction signal to the server device.
3. The machine learning-based real-time labor contraction judging system according to claim 2, wherein:
wherein, the acquisition unit is fixed with SMD shell, through the band installation the user the palace bottom.
4. The machine learning-based real-time labor contraction judging system according to claim 2, wherein:
the acquisition unit is a pressure sensor which outputs millivolt voltage and a touch force sensor which outputs millivolt voltage.
5. The machine learning-based real-time labor contraction judging system according to claim 1, wherein:
wherein the server apparatus further includes:
and the database unit is used for storing the uterine contraction signal, the training uterine contraction signal, the uterine contraction state label, the characteristic engineering, the signal to be processed, the uterine contraction state information and the address information.
6. The machine learning-based real-time labor contraction judging system according to claim 1, wherein:
the web application framework is used for sending the uterine contraction state information to the client terminal when the client terminal logs in the address information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010518019.0A CN111667916A (en) | 2020-06-09 | 2020-06-09 | Machine learning-based antenatal uterine contraction judging system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010518019.0A CN111667916A (en) | 2020-06-09 | 2020-06-09 | Machine learning-based antenatal uterine contraction judging system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111667916A true CN111667916A (en) | 2020-09-15 |
Family
ID=72386289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010518019.0A Pending CN111667916A (en) | 2020-06-09 | 2020-06-09 | Machine learning-based antenatal uterine contraction judging system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111667916A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1879551A (en) * | 2005-06-17 | 2006-12-20 | 中国科学院上海微系统与信息技术研究所 | A wireless medical monitoring method and device |
| CN101564287A (en) * | 2008-04-23 | 2009-10-28 | 财团法人工业技术研究院 | System and method for real-time monitoring and communication of housebound pregnant woman |
| CN202537484U (en) * | 2011-12-14 | 2012-11-21 | 北京理工大学 | Premature delivery prediction instrument |
| TW201509382A (en) * | 2013-09-10 | 2015-03-16 | Univ Southern Taiwan Sci & Tec | Uterine contraction monitoring device |
| CN207804229U (en) * | 2017-04-10 | 2018-09-04 | 杭州电子科技大学 | A kind of uterine contraction signal acquisition Transmission system based on Android |
| CN108550399A (en) * | 2018-03-20 | 2018-09-18 | 深圳大学 | A kind of fetal monitoring early warning system and method |
| CN109875556A (en) * | 2019-03-05 | 2019-06-14 | 广州爱听贝科技有限公司 | A kind of intelligence just before giving birth monitors system |
| CN109998478A (en) * | 2018-01-05 | 2019-07-12 | 广州莲印医疗科技有限公司 | A kind of shared fetal monitoring data processing method and device |
| CN110136819A (en) * | 2018-02-02 | 2019-08-16 | 南京九圣生物科技股份有限公司 | One kind is based on Internet of Things intelligence fetus fetal rhythm monitoring system and monitoring method |
| CN110931125A (en) * | 2019-12-11 | 2020-03-27 | 北京深睿博联科技有限责任公司 | Discrimination signal identification method and device for cerebral apoplexy |
-
2020
- 2020-06-09 CN CN202010518019.0A patent/CN111667916A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1879551A (en) * | 2005-06-17 | 2006-12-20 | 中国科学院上海微系统与信息技术研究所 | A wireless medical monitoring method and device |
| CN101564287A (en) * | 2008-04-23 | 2009-10-28 | 财团法人工业技术研究院 | System and method for real-time monitoring and communication of housebound pregnant woman |
| CN202537484U (en) * | 2011-12-14 | 2012-11-21 | 北京理工大学 | Premature delivery prediction instrument |
| TW201509382A (en) * | 2013-09-10 | 2015-03-16 | Univ Southern Taiwan Sci & Tec | Uterine contraction monitoring device |
| CN207804229U (en) * | 2017-04-10 | 2018-09-04 | 杭州电子科技大学 | A kind of uterine contraction signal acquisition Transmission system based on Android |
| CN109998478A (en) * | 2018-01-05 | 2019-07-12 | 广州莲印医疗科技有限公司 | A kind of shared fetal monitoring data processing method and device |
| CN110136819A (en) * | 2018-02-02 | 2019-08-16 | 南京九圣生物科技股份有限公司 | One kind is based on Internet of Things intelligence fetus fetal rhythm monitoring system and monitoring method |
| CN108550399A (en) * | 2018-03-20 | 2018-09-18 | 深圳大学 | A kind of fetal monitoring early warning system and method |
| CN109875556A (en) * | 2019-03-05 | 2019-06-14 | 广州爱听贝科技有限公司 | A kind of intelligence just before giving birth monitors system |
| CN110931125A (en) * | 2019-12-11 | 2020-03-27 | 北京深睿博联科技有限责任公司 | Discrimination signal identification method and device for cerebral apoplexy |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102781323A (en) | Body parameter sensor and monitor interface | |
| CN203749393U (en) | Personal health intelligent wristband system | |
| WO2018160446A1 (en) | Systems and methods for fetal monitoring | |
| CN1088422A (en) | The diagnostic equipment of labor and method | |
| CN109171686B (en) | Wearable medical equipment of intelligence and portable real-time supervision system of family | |
| CN103654858A (en) | Portable stroke early-warning monitor | |
| CN107997743A (en) | Portable uterine contraction monitoring system based on body surface uterine myoelectricity | |
| CN110123338A (en) | Intelligent fetal activity monitoring system | |
| CN111667916A (en) | Machine learning-based antenatal uterine contraction judging system | |
| CN204047553U (en) | A kind of cow oestrus automated watch-keeping facility | |
| CN105726016B (en) | Electrocardio output method and device | |
| CN110522436A (en) | Pulse signal acquisition system | |
| CN106709260A (en) | Understanding doctor type doctor-patient online interactive method | |
| CN103519791A (en) | System and method for collecting human body temperature | |
| CN110420021A (en) | 12 lead electrocardio-data collection and synchronous display system and method | |
| CN113425278B (en) | Method for monitoring fetal heart through data collected by wearable equipment | |
| CN203873785U (en) | Fetal heart rate remote monitoring system based on mobile network | |
| CN108937917A (en) | A kind of wearable ECG collection device and its acquisition method based on single lead | |
| CN205864399U (en) | A kind of wireless network signal for medical treatment bracelet receives device | |
| CN109589137A (en) | Method, apparatus, terminal and the computer readable storage medium of movement of the foetus identification | |
| CN211022740U (en) | Wireless heart sound signal acquisition device | |
| CN210843027U (en) | Pulse signal acquisition device | |
| CN202027574U (en) | Portable fetus ECG gatherer | |
| HU200272B (en) | Method and instrument for external measuring of uterus retractions | |
| CN110123296A (en) | One kind is fetal monitoring system and its wearing clothing based on Internet of Things |
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: 20200915 |