CN117617921A - Intelligent blood pressure monitoring system and method based on Internet of things - Google Patents
Intelligent blood pressure monitoring system and method based on Internet of things Download PDFInfo
- Publication number
- CN117617921A CN117617921A CN202410089090.XA CN202410089090A CN117617921A CN 117617921 A CN117617921 A CN 117617921A CN 202410089090 A CN202410089090 A CN 202410089090A CN 117617921 A CN117617921 A CN 117617921A
- Authority
- CN
- China
- Prior art keywords
- blood pressure
- training
- natural mode
- time sequence
- mode function
- 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
- 230000036772 blood pressure Effects 0.000 title claims abstract description 273
- 238000012544 monitoring process Methods 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 35
- 239000013598 vector Substances 0.000 claims abstract description 109
- 206010005746 Blood pressure fluctuation Diseases 0.000 claims abstract description 41
- 230000002159 abnormal effect Effects 0.000 claims abstract description 39
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 39
- 238000012300 Sequence Analysis Methods 0.000 claims abstract description 15
- 230000006870 function Effects 0.000 claims description 170
- 238000012549 training Methods 0.000 claims description 118
- 238000004458 analytical method Methods 0.000 claims description 20
- 238000010606 normalization Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 11
- 230000004927 fusion Effects 0.000 claims description 10
- 238000013135 deep learning Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 3
- 230000006855 networking Effects 0.000 claims description 2
- 230000002526 effect on cardiovascular system Effects 0.000 abstract description 12
- 208000026106 cerebrovascular disease Diseases 0.000 abstract description 11
- 208000024172 Cardiovascular disease Diseases 0.000 abstract description 10
- 201000010099 disease Diseases 0.000 abstract description 7
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 7
- 230000008859 change Effects 0.000 description 13
- 230000036541 health Effects 0.000 description 12
- 238000009826 distribution Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000011282 treatment Methods 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 4
- 230000036996 cardiovascular health Effects 0.000 description 3
- 230000005802 health problem Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 206010020772 Hypertension Diseases 0.000 description 2
- 208000001953 Hypotension Diseases 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000036543 hypotension Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000011269 treatment regimen Methods 0.000 description 2
- 208000027796 Blood pressure disease Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009530 blood pressure measurement Methods 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 210000000748 cardiovascular system Anatomy 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003860 sleep quality Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Abstract
The application discloses an intelligent blood pressure monitoring system and method based on the Internet of things, which relate to the technical field of intelligent blood pressure monitoring and are used for acquiring a blood pressure time sequence of a monitored object acquired by an intelligent blood pressure meter; transmitting the blood pressure time sequence to a cloud server; at the cloud server, performing empirical mode decomposition and time sequence analysis on the blood pressure time sequence to obtain a blood pressure global natural mode function semantic coding feature vector; and determining whether the blood pressure fluctuation of the monitored object is abnormal or not based on the semantic coding feature vector of the blood pressure global natural mode function. Therefore, abnormal fluctuation conditions of blood pressure of the monitored object can be learned and identified, and effective technical support is provided for preventing and treating cardiovascular and cerebrovascular diseases and other diseases.
Description
Technical Field
The application relates to the technical field of intelligent blood pressure monitoring, in particular to an intelligent blood pressure monitoring system and method based on the Internet of things.
Background
Blood pressure is one of the most important indicators used in the assessment of cardiovascular health of a patient. Abnormal fluctuations in blood pressure may suggest the presence of cardiovascular and cerebrovascular diseases or other abnormalities in the human body. Thus, real-time monitoring and analysis of blood pressure is an effective means of preventing and treating these diseases.
At present, the intelligent sphygmomanometer on the market can conveniently collect and record blood pressure data of a user, but analysis and diagnosis of the blood pressure data also need to depend on judgment of a professional doctor, so that the burden of medical resources is increased, and the experience and satisfaction of the user are reduced.
Therefore, an intelligent blood pressure monitoring system and method based on the internet of things are expected.
Disclosure of Invention
In order to overcome the defects, the application provides an intelligent blood pressure monitoring system and method based on the Internet of things.
The application also provides an intelligent blood pressure monitoring system based on the internet of things, which comprises:
the blood pressure time sequence acquisition module is used for acquiring a blood pressure time sequence of the monitored object acquired by the intelligent sphygmomanometer;
the data transmission module is used for transmitting the blood pressure time sequence to a cloud server;
the empirical mode decomposition and time sequence analysis module is used for performing empirical mode decomposition and time sequence analysis on the blood pressure time sequence at the cloud server to obtain a blood pressure global intrinsic mode function semantic coding feature vector;
the blood pressure fluctuation judging module of the monitored object is used for determining whether the blood pressure fluctuation of the monitored object is abnormal or not based on the semantic coding feature vector of the blood pressure global natural mode function;
Wherein, the empirical mode decomposition and timing analysis module comprises: the data normalization unit is used for performing data normalization on the blood pressure time sequence to obtain a normalized blood pressure time sequence; a sequence decomposition unit, configured to process the normalized blood pressure time sequence using an empirical mode decomposition algorithm to decompose the normalized blood pressure time sequence into a plurality of intrinsic mode functions, where each of the plurality of intrinsic mode functions is a subsequence that includes different frequencies and amplitudes; the coding unit is used for coding each natural mode function in the plurality of natural mode functions by utilizing a deep learning network model so as to obtain a plurality of natural mode function semantic feature vectors; the fusion unit is used for fusing the plurality of natural mode function semantic feature vectors to obtain the blood pressure global natural mode function semantic coding feature vector.
In the intelligent blood pressure monitoring system based on the internet of things, the deep learning network model is a feature extractor based on a one-dimensional convolution layer.
In the intelligent blood pressure monitoring system based on the internet of things, the encoding unit is configured to: encoding each of the plurality of natural mode functions using the one-dimensional convolutional layer-based feature extractor to obtain the plurality of natural mode function semantic feature vectors.
In the above intelligent blood pressure monitoring system based on the internet of things, the fusion unit includes: and the projection subunit is used for fusing the plurality of natural mode function semantic feature vectors by using a projection layer to obtain the blood pressure global natural mode function semantic coding feature vector.
In the intelligent blood pressure monitoring system based on the internet of things, the projection subunit is configured to: fusing the plurality of natural mode function semantic feature vectors by using a projection formula to obtain the blood pressure global natural mode function semantic coding feature vector; wherein, the projection formula is:
；
wherein,semantically encoding feature vectors for the global natural mode function of blood pressure,>is->Semantic feature vectors of the intrinsic mode functions, < ->Representing cascade,/->Representing a projection mapping of the vector.
In the intelligent blood pressure monitoring system based on the internet of things, the blood pressure fluctuation judging module of the monitored object is configured to: and the semantic coding feature vector of the global natural mode function of the blood pressure is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the blood pressure fluctuation of the monitored object is abnormal or not.
The intelligent blood pressure monitoring system based on the Internet of things further comprises a training module for training the feature extractor based on the one-dimensional convolution layer, the projection layer and the classifier.
In the intelligent blood pressure monitoring system based on the internet of things, the training module comprises: the training data acquisition unit is used for acquiring training data, wherein the training data comprises a training blood pressure time sequence and a true value of whether the blood pressure fluctuation of the monitored object is abnormal or not; the training data normalization unit is used for performing data normalization on the training blood pressure time sequence at the cloud server to obtain a training normalized blood pressure time sequence; the training sequence decomposition unit is used for processing the training standardized blood pressure time sequence by using an empirical mode decomposition algorithm to decompose the training standardized blood pressure time sequence into a plurality of training natural mode functions, wherein each training natural mode function in the plurality of training natural mode functions is a training subsequence containing different frequencies and amplitudes; the training encoding unit is used for encoding each training natural mode function in the training natural mode functions by using the feature extractor based on the one-dimensional convolution layer so as to obtain semantic feature vectors of the training natural mode functions; the training fusion unit is used for fusing the plurality of training natural mode function semantic feature vectors by using the projection layer to obtain training blood pressure global natural mode function semantic coding feature vectors; the training classification unit is used for enabling the training blood pressure global natural mode function semantic coding feature vector to pass through a classifier to obtain a classification loss function value; and the training unit is used for training the feature extractor based on the one-dimensional convolution layer, the projection layer and the classifier by using the classification loss function value, wherein in each iteration of the training, the semantic coding feature vector of the global natural mode function of the training blood pressure is corrected.
The application also provides an intelligent blood pressure monitoring method based on the Internet of things, which comprises the following steps:
acquiring a blood pressure time sequence of a monitored object acquired by an intelligent sphygmomanometer;
transmitting the blood pressure time sequence to a cloud server;
at the cloud server, performing empirical mode decomposition and time sequence analysis on the blood pressure time sequence to obtain a blood pressure global natural mode function semantic coding feature vector;
determining whether the blood pressure fluctuation of the monitored object is abnormal or not based on the semantic coding feature vector of the blood pressure global natural mode function;
the cloud server performs empirical mode decomposition and time sequence analysis on the blood pressure time sequence to obtain a blood pressure global natural mode function semantic coding feature vector, and the method comprises the following steps:
data normalization is carried out on the blood pressure time sequence to obtain a normalized blood pressure time sequence;
processing the normalized blood pressure time series by using an empirical mode decomposition algorithm to decompose the normalized blood pressure time series into a plurality of natural mode functions, wherein each natural mode function in the plurality of natural mode functions is a subsequence containing different frequencies and amplitudes;
Coding each natural mode function in the plurality of natural mode functions by using a deep learning network model to obtain a plurality of natural mode function semantic feature vectors;
and fusing the plurality of natural mode function semantic feature vectors to obtain the blood pressure global natural mode function semantic coding feature vector.
Compared with the prior art, the intelligent blood pressure monitoring system and method based on the Internet of things, provided by the application, acquire the blood pressure time sequence of the monitored object acquired by the intelligent sphygmomanometer; transmitting the blood pressure time sequence to a cloud server; at the cloud server, performing empirical mode decomposition and time sequence analysis on the blood pressure time sequence to obtain a blood pressure global natural mode function semantic coding feature vector; and determining whether the blood pressure fluctuation of the monitored object is abnormal or not based on the semantic coding feature vector of the blood pressure global natural mode function. Therefore, abnormal fluctuation conditions of blood pressure of the monitored object can be learned and identified, and effective technical support is provided for preventing and treating cardiovascular and cerebrovascular diseases and other diseases.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
Fig. 1 is a block diagram of an intelligent blood pressure monitoring system based on the internet of things provided in an embodiment of the present application.
Fig. 2 is a flowchart of an intelligent blood pressure monitoring method based on the internet of things provided in an embodiment of the present application.
Fig. 3 is a schematic diagram of a system architecture of an intelligent blood pressure monitoring method based on the internet of things provided in an embodiment of the present application.
Fig. 4 is an application scenario diagram of an intelligent blood pressure monitoring system based on the internet of things provided in an embodiment of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings. The illustrative embodiments of the present application and their description are presented herein to illustrate the application and not to limit the application.
Unless defined otherwise, all technical and scientific terms used in the examples of this application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application.
In the description of the embodiments of the present application, unless otherwise indicated and defined, the term "connected" should be construed broadly, and for example, may be an electrical connection, may be a communication between two elements, may be a direct connection, or may be an indirect connection via an intermediary, and it will be understood by those skilled in the art that the specific meaning of the term may be understood according to the specific circumstances.
It should be noted that, the term "first\second\third" in the embodiments of the present application merely distinguishes similar objects, and does not represent a specific order for the objects, and it is understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that the embodiments of the present application described herein may be implemented in sequences other than those illustrated or described herein.
Blood pressure is one of the important indicators for measuring cardiovascular health, reflecting the strength of heart pumping and the resistance of blood vessels. A normal blood pressure range may help assess whether a person's cardiovascular system is functioning properly, and abnormal blood pressure fluctuations may suggest the presence of cardiovascular and cerebrovascular disease or other health problems. Monitoring and analyzing blood pressure in real time can provide important information about the cardiovascular condition of a patient, helping to prevent and treat related diseases.
Conventional blood pressure meters are a common tool for measuring blood pressure via cuffs and audio or digital displays, which require a professional to make the measurement, and typically provide only a single measurement, and not continuous blood pressure change information. There are many automatic blood pressure monitoring devices on the market today that can be conveniently used for blood pressure measurements at home, which devices typically comprise an electronic sphygmomanometer and a cuff that can be automatically inflated and released to measure blood pressure and display the results. Some devices may also transmit data to a smart phone or computer via bluetooth or wireless connection for long term monitoring and analysis. The 24-hour dynamic blood pressure monitoring is a more comprehensive blood pressure monitoring method, can continuously measure and record the blood pressure change of a patient, and the patient wears a portable sphygmomanometer device which can automatically measure the blood pressure in different time intervals of a day and record data for subsequent analysis.
The intelligent sphygmomanometer on the market can conveniently collect and record the blood pressure data of the user, but the analysis and diagnosis of the blood pressure data do need to depend on the judgment of a professional doctor, and the situation not only increases the burden of medical resources, but also can reduce the experience and satisfaction of the user. To address this problem, some intelligent blood pressure meters and health monitoring devices began to incorporate algorithms based on artificial intelligence and machine learning to provide more intelligent data analysis and diagnostic functions that automatically analyze blood pressure data, identify abnormal patterns, and provide preliminary evaluations and advice.
For example, smart sphygmomanometers may use machine learning algorithms to learn and identify characteristics of different blood pressure patterns, such as hypertension, hypotension, blood pressure fluctuations, etc., which may gradually increase the accuracy and sensitivity to abnormal conditions by training a large amount of blood pressure data. In addition, the intelligent sphygmomanometer can also be combined with other health data, such as heart rate, exercise record, sleep quality and the like for comprehensive analysis. By comprehensively considering multiple health indicators, the algorithm may provide more comprehensive health assessments and recommendations. Therefore, the algorithm of the intelligent sphygmomanometer can be used as an auxiliary tool to help a user to better know the blood pressure condition of the user, and the user can seek advice and guidance of a professional doctor when the user needs the advice and guidance, so that the burden of medical resources can be reduced, and the experience and satisfaction of the user are improved.
The internet of things refers to the connection of various physical devices through the internet, so that information exchange and communication are realized. The internet of things technology is widely applied in the medical field, can improve the quality and efficiency of medical service and reduce medical cost and risk.
The application provides an intelligent blood pressure monitoring system based on thing networking, this system comprises three parts: intelligent sphygmomanometer, high in the clouds server and mobile terminal. The intelligent sphygmomanometer can automatically measure the blood pressure of a user and send data to the cloud server through a wireless network.
The cloud server can store, analyze and process the data, generate blood pressure reports and suggestions, and feed back the blood pressure reports and suggestions to the user through the mobile terminal. The mobile terminal can enable the user to check the blood pressure condition of the user at any time and any place, and can also carry out remote consultation and diagnosis with doctors. The system has the following advantages: firstly, the user can conveniently monitor the blood pressure of the user at any time and any place, and the health consciousness and self-management capacity of the user are improved; secondly, intelligent analysis and processing are carried out on the data by utilizing a cloud computing technology, so that the accuracy and the reliability of the data are improved; third, realize the real-time interaction between doctor and the user, have improved timeliness and effectiveness of the medical service.
In one embodiment of the present application, fig. 1 is a block diagram of an intelligent blood pressure monitoring system based on the internet of things provided in the embodiment of the present application. As shown in fig. 1, an intelligent blood pressure monitoring system 100 based on the internet of things according to an embodiment of the present application includes: a blood pressure time series acquisition module 110 for acquiring a blood pressure time series of a monitored subject acquired by the intelligent sphygmomanometer; the data transmission module 120 is configured to transmit the blood pressure time sequence to a cloud server; the empirical mode decomposition and time sequence analysis module 130 is configured to perform empirical mode decomposition and time sequence analysis on the blood pressure time sequence at the cloud server to obtain a semantic coding feature vector of a global intrinsic mode function of blood pressure; the blood pressure fluctuation judging module 140 of the monitored object is configured to determine whether the blood pressure fluctuation of the monitored object is abnormal based on the semantic coding feature vector of the global natural mode function of the blood pressure.
In the blood pressure time series acquisition module 110, blood pressure time series data of the monitored subject is acquired from the smart sphygmomanometer. In practical applications, accuracy and reliability of the sphygmomanometer are ensured, as well as a method and operation for correctly using the sphygmomanometer. The module is used for acquiring blood pressure time series data, so that the blood pressure condition of a monitored object can be monitored in real time, and continuous blood pressure data is provided for subsequent analysis and judgment.
In the data transmission module 120, the blood pressure time series data is transmitted to a cloud server. In the transmission process, the security and privacy protection of the data are ensured, and proper encryption and authentication measures are adopted. Through the data transmission module, the blood pressure data can be transmitted to the cloud server in real time, remote monitoring and analysis are realized, and doctors or professionals can conveniently further process and diagnose the blood pressure data.
In the empirical mode decomposition and timing analysis module 130, the time series of blood pressure is subjected to empirical mode decomposition and timing analysis to obtain a global intrinsic mode function semantic coding feature vector of blood pressure. During the analysis, appropriate decomposition methods and parameters are selected, as well as the correct handling of noise and outliers that may be present. Through an empirical mode decomposition and time sequence analysis module, the blood pressure time sequence can be decomposed into different intrinsic mode functions, and the characteristic vector of the blood pressure can be extracted. Therefore, the change mode and trend of the blood pressure can be better understood, and a more accurate basis is provided for the subsequent judgment of the fluctuation of the blood pressure.
In the blood pressure fluctuation judging module 140, it is judged whether or not there is abnormality in the blood pressure fluctuation of the monitored subject based on the global natural mode function semantic coding feature vector of the blood pressure. In the judging process, a proper fluctuation judging model is established, and a reasonable threshold or standard is set to distinguish normal fluctuation from abnormal fluctuation. The abnormal fluctuation condition of the blood pressure of the monitored object can be timely found through the blood pressure fluctuation judging module, early warning and intervention are facilitated, and necessary measures are timely taken to avoid or alleviate the risk of cardiovascular and cerebrovascular diseases.
The modules respectively bear important functions and tasks in the intelligent blood pressure monitoring system, and can provide more accurate and timely blood pressure monitoring and early warning by accurately acquiring blood pressure time sequence data, safely transmitting the data, performing empirical mode decomposition and time sequence analysis and judging whether blood pressure fluctuation is abnormal or not, thereby helping users and doctors to better manage and control cardiovascular health.
Aiming at the technical problems, the technical concept of the application is to collect and store the blood pressure time sequence of the monitored object by utilizing the internet of things technology, and extract and capture the blood pressure fluctuation characteristics and the change modes contained in the blood pressure time sequence by utilizing an intelligent algorithm, so that the abnormal fluctuation condition of the blood pressure of the monitored object is learned and identified. Thus, the preparation method provides effective technical support for preventing and treating cardiovascular and cerebrovascular diseases and other diseases.
Through the internet of things technology, the blood pressure time sequence can be acquired and transmitted to the cloud server in real time to realize remote monitoring and management, so that doctors or professionals can access and analyze blood pressure data of a monitored object at any time, abnormal fluctuation can be found in time, and personalized guidance and intervention measures are provided. The intelligent algorithm can extract and capture the characteristics of blood pressure fluctuation from the blood pressure time sequence, such as amplitude, frequency, time domain, frequency domain characteristics and the like, and the characteristics can help to know the change mode and trend of the blood pressure, so that a basis is provided for identifying and judging abnormal fluctuation.
By learning and identifying abnormal fluctuations in the blood pressure time sequence, abnormal conditions of blood pressure can be found in time, the abnormal fluctuations can be early indications of hypertension, hypotension or other cardiovascular and cerebrovascular diseases, and the early finding can prompt doctors or professionals to take corresponding treatment measures, so that potential health risks are reduced. By analyzing fluctuation characteristics and change modes in the blood pressure time sequence, personalized prevention and treatment strategies can be provided for each monitored object, and a targeted health management plan can be formulated according to individual characteristics and historical data, including medication, life style change, regular follow-up and the like, so that the risk of cardiovascular and cerebrovascular diseases is reduced. Through the internet of things technology and an intelligent algorithm, a large amount of blood pressure time series data can be accumulated, and a recognition and prediction model of abnormal blood pressure fluctuation is continuously optimized and improved by combining machine learning and data analysis methods, so that health management becomes more data-driven, and the accuracy and effect of prevention and treatment are improved.
That is, the blood pressure time sequence is acquired and stored by utilizing the internet of things technology, and the blood pressure fluctuation characteristics and the change modes are extracted and captured by combining an intelligent algorithm, so that effective technical support can be provided for preventing and treating diseases such as cardiovascular and cerebrovascular diseases, and the like.
Based on the above, in the technical scheme of the application, firstly, acquiring a blood pressure time sequence of a monitored object acquired by an intelligent sphygmomanometer; and transmitting the blood pressure time sequence to a cloud server. Here, the real-time blood pressure value of the monitored subject can be accurately measured by the intelligent sphygmomanometer and recorded to form a blood pressure time sequence. These data are important bases for understanding the blood pressure status of the monitored subject. The blood pressure time sequence is transmitted to the cloud server, so that centralized storage of data can be realized, and risks of data loss and damage are avoided. The cloud server has larger storage capacity and high reliability, and can safely store a large amount of blood pressure data.
In one embodiment of the present application, the empirical mode decomposition and timing analysis module includes: the data normalization unit is used for performing data normalization on the blood pressure time sequence to obtain a normalized blood pressure time sequence; a sequence decomposition unit, configured to process the normalized blood pressure time sequence using an empirical mode decomposition algorithm to decompose the normalized blood pressure time sequence into a plurality of intrinsic mode functions, where each of the plurality of intrinsic mode functions is a subsequence that includes different frequencies and amplitudes; the coding unit is used for coding each natural mode function in the plurality of natural mode functions by utilizing a deep learning network model so as to obtain a plurality of natural mode function semantic feature vectors; the fusion unit is used for fusing the plurality of natural mode function semantic feature vectors to obtain the blood pressure global natural mode function semantic coding feature vector.
And then, at the cloud server, carrying out data standardization on the blood pressure time sequence to obtain a standardized blood pressure time sequence. That is, the scale difference between the individual values in the blood pressure time series is eliminated by the data normalization process to ensure that all the data are on the same scale. More specifically, there may be a large difference in the blood pressure value ranges of different monitored subjects. If the data is not normalized, the original blood pressure time series is directly used for analysis and comparison, and the time series characteristics of the blood pressure can be misinterpreted due to scale difference. By normalizing the blood pressure time series, the data can be converted into a relatively consistent scale, thereby facilitating subsequent analysis and comparison.
Given that standardized blood pressure time series often have complex non-linear and non-stationary properties, it is not possible to directly analyze them with conventional linear methods. In the technical solution of the present application, it is desirable to process the normalized blood pressure time series using an empirical mode decomposition algorithm to decompose the normalized blood pressure time series into a plurality of intrinsic mode functions. Wherein each of the plurality of natural mode functions is a subsequence comprising different frequencies and amplitudes. In particular, the empirical mode decomposition algorithm (Empirical Mode Decomposition, EMD) is an algorithm for analyzing non-stationary time series data. It can decompose a complex time series into a plurality of natural mode functions (Intrinsic Mode Function, IMF). The natural mode function is a sub-sequence with different frequencies and amplitudes that can be used to represent different modes in a time sequence. That is, the empirical mode decomposition algorithm decomposes the normalized blood pressure time series into a series of intrinsic mode functions, each of which contains subsequences of different scales and frequencies for characterizing blood pressure time series variation characteristic information expressed by the normalized blood pressure time series. To a certain extent, each natural mode function can be understood as a specific mode of variation. By carrying out feature extraction and mode recognition on each natural mode function, the periodic change, trend change, emergency and the like in the blood pressure time sequence can be further analyzed, so that richer information is extracted for recognizing abnormal fluctuation of blood pressure.
Further, each of the plurality of natural mode functions is encoded using a feature extractor based on a one-dimensional convolution layer to obtain a plurality of natural mode function semantic feature vectors. That is, a feature extractor is constructed using a one-dimensional convolution layer to capture temporal semantic feature information in each of the natural mode functions, characterizing and characterizing the intrinsic characteristics of each of the natural mode functions.
In a specific embodiment of the present application, the deep learning network model is a feature extractor based on a one-dimensional convolution layer.
More specifically, the encoding unit is configured to: encoding each of the plurality of natural mode functions using the one-dimensional convolutional layer-based feature extractor to obtain the plurality of natural mode function semantic feature vectors.
The intrinsic mode function is a method capable of effectively representing signal characteristics, multi-mode information can be extracted and captured by encoding a plurality of intrinsic mode functions, each intrinsic mode function represents components of a signal on different frequencies and amplitudes, and more comprehensive and rich signal characteristics can be obtained by encoding the components. By encoding the plurality of natural mode functions, semantic feature vectors of the plurality of natural mode functions can be obtained for personalized analysis and identification, and individual blood pressure abnormal fluctuation judgment and classification are carried out according to different feature vectors, so that personalized health management and treatment strategies are provided, and the health requirements of each monitored object are better met.
The feature extractor based on the one-dimensional convolution layer can learn the features with local perceptibility, can extract local features by carrying out convolution operation on the inherent mode function, and can combine and compress the features by pooling operation to obtain higher-level semantic feature representation so as to capture the time domain and frequency domain features of the inherent mode function, thereby being beneficial to better understanding and analyzing the mode and trend of blood pressure fluctuation. By using the feature extractor based on the one-dimensional convolution layer, the feature representation with good generalization capability and robustness can be learned to be applicable to different data sets and application scenes, and the feature extractor has certain anti-interference capability on noise and interference, so that the feature vector after the inherent mode function coding can be widely applied to different blood pressure monitoring tasks.
In other words, the feature extractor based on the one-dimensional convolution layer is used for encoding a plurality of natural mode functions, so that rich feature representation can be obtained, the data dimension and complexity are reduced, the generalization capability and the robustness are good, personalized analysis and identification are supported, and the method can provide effective technical support for analysis and prediction of blood pressure fluctuation and promote prevention and treatment of cardiovascular and cerebrovascular diseases.
And then fusing the plurality of natural mode function semantic feature vectors by using a projection layer to obtain a blood pressure global natural mode function semantic coding feature vector. That is, feature information respectively representing and describing different specific change modes is fused, so that the model is helped to better understand the blood pressure change trend and fluctuation mode of the monitored object. More specifically, the projection layer maps each of the eigenmode function semantic feature vectors into a common feature space through a shared projection layer to map each of the eigenmode function semantic feature vectors to the same dimension so that they can be directly fused. That is, the projection layer converts the feature distribution expressing different variation modes into the same representation form by using the same projection layer, so that the difference between feature expressions under different modes is eliminated, and the process of feature fusion has high consistency.
In a specific embodiment of the present application, the fusion unit includes: and the projection subunit is used for fusing the plurality of natural mode function semantic feature vectors by using a projection layer to obtain the blood pressure global natural mode function semantic coding feature vector.
Further, the projection subunit is configured to: fusing the plurality of natural mode function semantic feature vectors by using a projection formula to obtain the blood pressure global natural mode function semantic coding feature vector; wherein, the projection formula is:
；
wherein,semantically encoding feature vectors for the global natural mode function of blood pressure,>is->Semantic feature vectors of the intrinsic mode functions, < ->Representing cascade,/->Representing a projection mapping of the vector.
And then, the blood pressure global natural mode function semantic coding feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the blood pressure fluctuation of the monitored object is abnormal or not.
In a specific embodiment of the present application, the blood pressure fluctuation determining module of the monitored object is configured to: and the semantic coding feature vector of the global natural mode function of the blood pressure is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the blood pressure fluctuation of the monitored object is abnormal or not.
By using the classifier to classify the blood pressure fluctuation, automatic fluctuation judgment can be realized, subjectivity and error of manual judgment are reduced, the classifier can learn the characteristics of different fluctuation modes, and new blood pressure fluctuation is classified according to the characteristics. The blood pressure fluctuation is judged by the classifier, so that abnormal fluctuation conditions can be timely found, the abnormal fluctuation conditions can be early indications of blood pressure diseases or other health problems, and early detection can prompt a user to take appropriate measures, such as medical treatment or life style adjustment, so as to prevent or treat potential health problems.
The classification result can be subjected to personalized monitoring and early warning according to the health condition and the historical data of the individual, and a personalized monitoring and early warning strategy can be provided for each monitored object according to the characteristics and the historical data of the individual by establishing a classification model of blood pressure fluctuation so as to better meet the health management requirements of the monitored object. The blood pressure fluctuation is judged by using the classifier, so that the judging efficiency and accuracy can be improved, and the classifier can process a large amount of blood pressure fluctuation data in a short time and give out corresponding classification results, thereby helping doctors or professionals to make diagnosis and treatment decisions more quickly and accurately.
In one embodiment of the present application, the intelligent blood pressure monitoring system based on the internet of things further includes a training module for training the feature extractor based on the one-dimensional convolution layer, the projection layer and the classifier. The training module comprises: the training data acquisition unit is used for acquiring training data, wherein the training data comprises a training blood pressure time sequence and a true value of whether the blood pressure fluctuation of the monitored object is abnormal or not; the training data normalization unit is used for performing data normalization on the training blood pressure time sequence at the cloud server to obtain a training normalized blood pressure time sequence; the training sequence decomposition unit is used for processing the training standardized blood pressure time sequence by using an empirical mode decomposition algorithm to decompose the training standardized blood pressure time sequence into a plurality of training natural mode functions, wherein each training natural mode function in the plurality of training natural mode functions is a training subsequence containing different frequencies and amplitudes; the training encoding unit is used for encoding each training natural mode function in the training natural mode functions by using the feature extractor based on the one-dimensional convolution layer so as to obtain semantic feature vectors of the training natural mode functions; the training fusion unit is used for fusing the plurality of training natural mode function semantic feature vectors by using the projection layer to obtain training blood pressure global natural mode function semantic coding feature vectors; the training classification unit is used for enabling the training blood pressure global natural mode function semantic coding feature vector to pass through a classifier to obtain a classification loss function value; and the training unit is used for training the feature extractor based on the one-dimensional convolution layer, the projection layer and the classifier by using the classification loss function value, wherein in each iteration of the training, the semantic coding feature vector of the global natural mode function of the training blood pressure is corrected.
In the technical scheme of the application, the plurality of natural mode functions express sub-distribution modes of time sequence distribution of the training blood pressure time sequence based on different frequencies and amplitudes, so that each training natural mode function semantic feature vector in the plurality of training natural mode function semantic feature vectors expresses corresponding time sequence associated features under different sub-distribution modes. However, in consideration of the imbalance of the expression of each individual frequency and amplitude to the overall time sequence distribution of the training blood pressure time sequence, the plurality of training natural mode function semantic feature vectors also have cross-mode time sequence associated feature distribution information differences, so that the plurality of training natural mode function semantic feature vectors are mapped into the same high-dimensional feature space by using a projection layer, but the respective corresponding local feature distribution of the plurality of training natural mode function semantic feature vectors in the high-dimensional space still enables the training blood pressure global natural mode function semantic coding feature vectors to have abnormal distribution time sequence information game discretization, and the training blood pressure global natural mode function semantic coding feature vectors are influenced by classification training of a classifier.
Based on this, the applicant of the present application preferably corrects the training blood pressure global natural mode function semantic coding feature vector every time the training blood pressure global natural mode function semantic coding feature vector is iteratively trained by a classifier, specifically expressed as: correcting the training blood pressure global natural mode function semantic coding feature vector in each round of iteration of training by using the following optimization formula to obtain a corrected training blood pressure global natural mode function semantic coding feature vector; wherein, the optimization formula is:
；
wherein,is the characteristic value of the semantic coding characteristic vector of the global natural mode function of the training blood pressure,/I>Is the +.sup.th of the semantic coding feature vector of the global natural mode function of the training blood pressure>Characteristic value of individual position, and->Is a scale superparameter,/->Is the characteristic value of the semantic coding characteristic vector of the global natural mode function of the correction training blood pressure,a logarithmic function with a base of 2 is shown.
Specifically, when the training blood pressure global natural mode function semantic coding feature vector is iteratively trained by the classifier, the weight matrix of the classifier acts on the training blood pressure global natural mode function semantic coding feature vector during training, because of the compact characteristic of the weight matrix, the abnormal distribution time sequence information game between the feature values of each position of the training blood pressure global natural mode function semantic coding feature vector can be discretized to generate a large-scale information game, so that a classification solution can not be converged to Nash equilibrium on the basis of the game, and especially under the condition that large-scale imperfect game discretization information based on the time sequence feature distribution of the training blood pressure global natural mode function semantic coding feature vector exists, the training blood pressure global natural mode function semantic coding feature vector is subjected to equivalent convergence of information game equalization by the vector information automatic control equalization neighborhood based on the training blood pressure global natural mode function semantic coding feature vector, and the self-convergence of the feature values in the local neighborhood can be promoted, so that the training blood pressure global natural mode function semantic coding feature vector can be improved through the training effect of the classifier.
In summary, the intelligent blood pressure monitoring system 100 based on the internet of things according to the embodiment of the application is illustrated, which uses the internet of things technology to collect and store the blood pressure time sequence of the monitored object, and uses the intelligent algorithm to extract and capture the blood pressure fluctuation characteristics and the change modes contained in the blood pressure time sequence, so as to learn and identify the abnormal fluctuation condition of the blood pressure of the monitored object. Thus, the preparation method provides effective technical support for preventing and treating cardiovascular and cerebrovascular diseases and other diseases.
As described above, the intelligent blood pressure monitoring system 100 based on the internet of things according to the embodiment of the present application may be implemented in various terminal devices, for example, a server for intelligent blood pressure monitoring based on the internet of things, and the like. In one example, the intelligent blood pressure monitoring system 100 based on the internet of things according to the embodiments of the present application may be integrated into the terminal device as one software module and/or hardware module. For example, the intelligent blood pressure monitoring system 100 based on the internet of things may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the intelligent blood pressure monitoring system 100 based on the internet of things can be one of numerous hardware modules of the terminal device.
Alternatively, in another example, the intelligent blood pressure monitoring system 100 based on the internet of things and the terminal device may be separate devices, and the intelligent blood pressure monitoring system 100 based on the internet of things may be connected to the terminal device through a wired and/or wireless network and transmit the interaction information according to the agreed data format.
Fig. 2 is a flowchart of an intelligent blood pressure monitoring method based on the internet of things provided in an embodiment of the present application. Fig. 3 is a schematic diagram of a system architecture of an intelligent blood pressure monitoring method based on the internet of things provided in an embodiment of the present application. As shown in fig. 2 and fig. 3, an intelligent blood pressure monitoring method based on the internet of things includes: 210, acquiring a blood pressure time sequence of a monitored object acquired by an intelligent sphygmomanometer; 220, transmitting the blood pressure time sequence to a cloud server; 230, at the cloud server, performing empirical mode decomposition and time sequence analysis on the blood pressure time sequence to obtain a blood pressure global natural mode function semantic coding feature vector; 240, determining whether the blood pressure fluctuation of the monitored object is abnormal or not based on the semantic coding feature vector of the blood pressure global natural mode function.
It will be appreciated by those skilled in the art that the specific operation of each step in the above-described intelligent blood pressure monitoring method based on the internet of things has been described in detail in the above description of the intelligent blood pressure monitoring system based on the internet of things with reference to fig. 1, and thus, a repetitive description thereof will be omitted.
Fig. 4 is an application scenario diagram of an intelligent blood pressure monitoring system based on the internet of things provided in an embodiment of the present application. As shown in fig. 4, in this application scenario, first, a blood pressure time series of a monitored subject acquired by a smart sphygmomanometer is acquired (C as illustrated in fig. 4); then, the acquired blood pressure time sequence of the monitored object is input into a server (S as illustrated in fig. 4) deployed with an intelligent blood pressure monitoring algorithm based on the internet of things, wherein the server can process the blood pressure time sequence of the monitored object based on the intelligent blood pressure monitoring algorithm of the internet of things to determine whether the blood pressure fluctuation of the monitored object is abnormal or not.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present application and are not meant to limit the scope of the invention, but to limit the scope of the invention.
Claims (9)
1. Intelligent blood pressure monitored control system based on thing networking, its characterized in that includes:
the blood pressure time sequence acquisition module is used for acquiring a blood pressure time sequence of the monitored object acquired by the intelligent sphygmomanometer;
the data transmission module is used for transmitting the blood pressure time sequence to a cloud server;
the empirical mode decomposition and time sequence analysis module is used for performing empirical mode decomposition and time sequence analysis on the blood pressure time sequence at the cloud server to obtain a blood pressure global intrinsic mode function semantic coding feature vector;
the blood pressure fluctuation judging module of the monitored object is used for determining whether the blood pressure fluctuation of the monitored object is abnormal or not based on the semantic coding feature vector of the blood pressure global natural mode function;
wherein, the empirical mode decomposition and timing analysis module comprises:
the data normalization unit is used for performing data normalization on the blood pressure time sequence to obtain a normalized blood pressure time sequence;
a sequence decomposition unit, configured to process the normalized blood pressure time sequence using an empirical mode decomposition algorithm to decompose the normalized blood pressure time sequence into a plurality of intrinsic mode functions, where each of the plurality of intrinsic mode functions is a subsequence that includes different frequencies and amplitudes;
The coding unit is used for coding each natural mode function in the plurality of natural mode functions by utilizing a deep learning network model so as to obtain a plurality of natural mode function semantic feature vectors;
the fusion unit is used for fusing the plurality of natural mode function semantic feature vectors to obtain the blood pressure global natural mode function semantic coding feature vector.
2. The intelligent blood pressure monitoring system based on the internet of things according to claim 1, wherein the deep learning network model is a feature extractor based on a one-dimensional convolution layer.
3. The intelligent blood pressure monitoring system based on the internet of things according to claim 2, wherein the encoding unit is configured to:
encoding each of the plurality of natural mode functions using the one-dimensional convolutional layer-based feature extractor to obtain the plurality of natural mode function semantic feature vectors.
4. The intelligent blood pressure monitoring system based on the internet of things of claim 3, wherein the fusion unit comprises:
and the projection subunit is used for fusing the plurality of natural mode function semantic feature vectors by using a projection layer to obtain the blood pressure global natural mode function semantic coding feature vector.
5. The intelligent blood pressure monitoring system based on the internet of things of claim 4, wherein the projection subunit is configured to:
fusing the plurality of natural mode function semantic feature vectors by using a projection formula to obtain the blood pressure global natural mode function semantic coding feature vector; wherein, the projection formula is:
；
wherein,semantically encoding feature vectors for the global natural mode function of blood pressure,>is->Semantic feature vectors of the intrinsic mode functions, < ->Representing cascade,/->Representing a projection mapping of the vector.
6. The intelligent blood pressure monitoring system based on the internet of things according to claim 5, wherein the blood pressure fluctuation judging module of the monitored object is configured to:
and the semantic coding feature vector of the global natural mode function of the blood pressure is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the blood pressure fluctuation of the monitored object is abnormal or not.
7. The internet of things-based intelligent blood pressure monitoring system of claim 6, further comprising a training module for training the one-dimensional convolutional layer-based feature extractor, the projection layer, and the classifier.
8. The intelligent blood pressure monitoring system based on the internet of things of claim 7, wherein the training module comprises:
the training data acquisition unit is used for acquiring training data, wherein the training data comprises a training blood pressure time sequence and a true value of whether the blood pressure fluctuation of the monitored object is abnormal or not;
the training data normalization unit is used for performing data normalization on the training blood pressure time sequence at the cloud server to obtain a training normalized blood pressure time sequence;
the training sequence decomposition unit is used for processing the training standardized blood pressure time sequence by using an empirical mode decomposition algorithm to decompose the training standardized blood pressure time sequence into a plurality of training natural mode functions, wherein each training natural mode function in the plurality of training natural mode functions is a training subsequence containing different frequencies and amplitudes;
the training encoding unit is used for encoding each training natural mode function in the training natural mode functions by using the feature extractor based on the one-dimensional convolution layer so as to obtain semantic feature vectors of the training natural mode functions;
The training fusion unit is used for fusing the plurality of training natural mode function semantic feature vectors by using the projection layer to obtain training blood pressure global natural mode function semantic coding feature vectors;
the training classification unit is used for enabling the training blood pressure global natural mode function semantic coding feature vector to pass through a classifier to obtain a classification loss function value;
and the training unit is used for training the feature extractor based on the one-dimensional convolution layer, the projection layer and the classifier by using the classification loss function value, wherein in each iteration of the training, the semantic coding feature vector of the global natural mode function of the training blood pressure is corrected.
9. An intelligent blood pressure monitoring method based on the Internet of things is characterized by comprising the following steps:
acquiring a blood pressure time sequence of a monitored object acquired by an intelligent sphygmomanometer;
transmitting the blood pressure time sequence to a cloud server;
at the cloud server, performing empirical mode decomposition and time sequence analysis on the blood pressure time sequence to obtain a blood pressure global natural mode function semantic coding feature vector;
determining whether the blood pressure fluctuation of the monitored object is abnormal or not based on the semantic coding feature vector of the blood pressure global natural mode function;
The cloud server performs empirical mode decomposition and time sequence analysis on the blood pressure time sequence to obtain a blood pressure global natural mode function semantic coding feature vector, and the method comprises the following steps:
data normalization is carried out on the blood pressure time sequence to obtain a normalized blood pressure time sequence;
processing the normalized blood pressure time series by using an empirical mode decomposition algorithm to decompose the normalized blood pressure time series into a plurality of natural mode functions, wherein each natural mode function in the plurality of natural mode functions is a subsequence containing different frequencies and amplitudes;
coding each natural mode function in the plurality of natural mode functions by using a deep learning network model to obtain a plurality of natural mode function semantic feature vectors;
and fusing the plurality of natural mode function semantic feature vectors to obtain the blood pressure global natural mode function semantic coding feature vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410089090.XA CN117617921B (en) | 2024-01-23 | 2024-01-23 | Intelligent blood pressure monitoring system and method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410089090.XA CN117617921B (en) | 2024-01-23 | 2024-01-23 | Intelligent blood pressure monitoring system and method based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117617921A true CN117617921A (en) | 2024-03-01 |
| CN117617921B CN117617921B (en) | 2024-03-26 |
Family
ID=90035835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410089090.XA Active CN117617921B (en) | 2024-01-23 | 2024-01-23 | Intelligent blood pressure monitoring system and method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117617921B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108319666A (en) * | 2018-01-19 | 2018-07-24 | 国网浙江省电力有限公司电力科学研究院 | A kind of electric service appraisal procedure based on multi-modal the analysis of public opinion |
| US20190175041A1 (en) * | 2017-12-11 | 2019-06-13 | Adaptive, Intelligent And Dynamic Brain Corporation (Aidbrain) | Method, module and system for analysis of physiological signal |
| US20200196875A1 (en) * | 2017-05-22 | 2020-06-25 | Adaptive, Intelligent And Dynamic Brain Corporation (Aidbrain) | Method, module and system for analysis of physiological signals |
| US20200229774A1 (en) * | 2019-01-17 | 2020-07-23 | Grant Hocking | Method to Quantify Hypertension, Aging Status and Vascular Properties in Vivo from Arterial Optical Plethysmograph Waveform Measurements |
| CN112818912A (en) * | 2021-02-24 | 2021-05-18 | 南京信息工程大学 | Lightning early warning method based on integrated empirical mode decomposition and extreme gradient lifting |
| CN116864112A (en) * | 2023-07-18 | 2023-10-10 | 湘南学院 | User data intelligent management system and method for human body chip |
-
2024
- 2024-01-23 CN CN202410089090.XA patent/CN117617921B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200196875A1 (en) * | 2017-05-22 | 2020-06-25 | Adaptive, Intelligent And Dynamic Brain Corporation (Aidbrain) | Method, module and system for analysis of physiological signals |
| US20190175041A1 (en) * | 2017-12-11 | 2019-06-13 | Adaptive, Intelligent And Dynamic Brain Corporation (Aidbrain) | Method, module and system for analysis of physiological signal |
| CN108319666A (en) * | 2018-01-19 | 2018-07-24 | 国网浙江省电力有限公司电力科学研究院 | A kind of electric service appraisal procedure based on multi-modal the analysis of public opinion |
| US20200229774A1 (en) * | 2019-01-17 | 2020-07-23 | Grant Hocking | Method to Quantify Hypertension, Aging Status and Vascular Properties in Vivo from Arterial Optical Plethysmograph Waveform Measurements |
| CN112818912A (en) * | 2021-02-24 | 2021-05-18 | 南京信息工程大学 | Lightning early warning method based on integrated empirical mode decomposition and extreme gradient lifting |
| CN116864112A (en) * | 2023-07-18 | 2023-10-10 | 湘南学院 | User data intelligent management system and method for human body chip |
Non-Patent Citations (2)
| Title |
|---|
| YEH JIARONG，ET AL: "Investigating complex patterns of blocked intestinal artery blood pressure signals by empirical mode decomposition and linguistic analysis", PROCEEDINGS OF THE 2007 INTERNATIONAL SYMPOSIUM ON NONLINEAR DYNAMICS, vol. 96, 31 October 2007 (2007-10-31) * |
| 张畅，陈辉，郑秀娟: "基于优化脉搏波特征的无袖带血压检测方法", 电子测量技术, vol. 44, no. 24, 31 December 2021 (2021-12-31) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117617921B (en) | 2024-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230131876A1 (en) | Systems and methods of identity analysis of electrocardiograms | |
| AU2006325153B2 (en) | Residual-based monitoring of human health | |
| US10265029B2 (en) | Methods and systems for calculating and using statistical models to predict medical events | |
| JP2018524137A (en) | Method and system for assessing psychological state | |
| CN111613335A (en) | Health early warning system and method | |
| US11529105B2 (en) | Digital twin updating | |
| CN110993096B (en) | Sepsis early warning device, equipment and storage medium | |
| Shrestha et al. | ECG data analysis with IoT and machine learning | |
| CN117617921B (en) | Intelligent blood pressure monitoring system and method based on Internet of things | |
| CN116098595B (en) | System and method for monitoring and preventing sudden cardiac death and sudden cerebral death | |
| CN116978510A (en) | Nursing grading evaluation system for home cerebral apoplexy patient | |
| US20220254502A1 (en) | System, method and apparatus for non-invasive & non-contact monitoring of health racterstics using artificial intelligence (ai) | |
| AU2019204388A1 (en) | Residual-based monitoring of human health | |
| CN110911011B (en) | Sepsis early warning device, equipment and storage medium | |
| US20160228067A1 (en) | System and method for intelligent monitoring of patient vital signs | |
| US20240013877A1 (en) | Method for calculating a degree of fatigue | |
| US20230178200A1 (en) | Direct medical treatment predictions using artificial intelligence | |
| CN117542474A (en) | Remote nursing monitoring system and method based on big data | |
| Yu et al. | DESIGN OF CUSTOMIZED HEALTH CARE SYSTEM BASED ON BIG DATA | |
| CN117158938A (en) | Health monitoring method and device applied to intelligent watch and electronic equipment | |
| WO2023214957A1 (en) | Machine learning models for estimating physiological biomarkers | |
| WO2023214956A1 (en) | Systems, devices, and methods for biomarker detection and tracking | |
| Ganesh et al. | An IoT Enabled Computational Model and Application Development for Monitoring Cardiovascular Risks | |
| KR20230161131A (en) | Method for diagnosing skin based on artificial intelligence | |
| EP4244869A1 (en) | Clinical warning score system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |