CN114679759B - Wearable electrocardiograph monitoring network switching method based on reinforcement learning - Google Patents

Wearable electrocardiograph monitoring network switching method based on reinforcement learning Download PDF

Info

Publication number
CN114679759B
CN114679759B CN202210323583.6A CN202210323583A CN114679759B CN 114679759 B CN114679759 B CN 114679759B CN 202210323583 A CN202210323583 A CN 202210323583A CN 114679759 B CN114679759 B CN 114679759B
Authority
CN
China
Prior art keywords
data
network
value
time
task
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.)
Active
Application number
CN202210323583.6A
Other languages
Chinese (zh)
Other versions
CN114679759A (en
Inventor
张羽
赵文娟
杨慧
亢羽童
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ningbo Research Institute of Northwestern Polytechnical University
Original Assignee
Ningbo Research Institute of Northwestern Polytechnical University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ningbo Research Institute of Northwestern Polytechnical University filed Critical Ningbo Research Institute of Northwestern Polytechnical University
Priority to CN202210323583.6A priority Critical patent/CN114679759B/en
Publication of CN114679759A publication Critical patent/CN114679759A/en
Application granted granted Critical
Publication of CN114679759B publication Critical patent/CN114679759B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/14—Reselecting a network or an air interface
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/25—Bioelectric electrodes therefor
    • A61B5/251—Means for maintaining electrode contact with the body
    • A61B5/256—Wearable electrodes, e.g. having straps or bands
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/25—Bioelectric electrodes therefor
    • A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
    • A61B5/28—Bioelectric electrodes therefor specially adapted for particular uses for electrocardiography [ECG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/332—Portable devices specially adapted therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/24—Reselection being triggered by specific parameters
    • H04W36/30—Reselection being triggered by specific parameters by measured or perceived connection quality data
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Public Health (AREA)
  • Animal Behavior & Ethology (AREA)
  • Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Veterinary Medicine (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Evolutionary Biology (AREA)
  • Cardiology (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

The invention discloses a wearable electrocardiograph monitoring network switching method based on reinforcement learning, which comprises the following steps: and (3) inputting an environment state, preprocessing data, using a Qlearning decision output action, receiving an environment feedback reward, updating a Qtable parameter, and executing network switching. Various factors in the wearable electrocardiograph monitoring environment can be comprehensively considered, the accuracy of the model is improved, meanwhile, the calculated amount of the model is guaranteed to be reduced as much as possible when a correct decision is made, the task of timely switching the wearable network is efficiently completed, and the method can be used as a model foundation for intelligent switching of the wearable electrocardiograph monitoring data transmission network.

Description

Wearable electrocardiograph monitoring network switching method based on reinforcement learning
Technical Field
The invention relates to the field of communication control, in particular to a wearable electrocardiograph monitoring network switching method based on reinforcement learning.
Background
Wearable electrocardiographic monitoring can improve the efficiency of healthcare. However, the current wearable devices relying on only a single wireless transmission technology do not guarantee that the patient can connect to the remote electrocardiographic healthcare center at any time and any place. For this reason, a vertical switching scheme sensitive to the health condition of the patient is proposed for remote wearable electrocardiographic monitoring applications under heterogeneous wireless networks. Vertical handover in heterogeneous networks refers to the process of migrating from one network to another without breaking a traffic link. Therefore, in the existing communication technology, the most appropriate technology must be selected according to factors such as power level, data rate, operation range, coexistence of multiple technologies and the like required by the wearable electrocardiograph data transmission, so as to reduce network switching delay time, thereby ensuring that electrocardiograph monitoring data can be transmitted in real time.
The prior art has the method for scanning Bluetooth communication or performing network switching by a cellular network according to the blacklist application of the terminal equipment so as to avoid the consumption of large flow, thereby providing good Internet surfing experience. However, the threshold condition set by the method is too complicated, and adds a lot of unnecessary calculation amount and energy consumption required by scanning. And selecting a network which meets the current service performance requirement and has highest reliability according to the time-space characteristics of the network connection of the mobile terminal so as to ensure that the transmission delay is small and the reliability is high. However, the method needs to collect information such as the position, time period, service type, network reliability and the like of each mobile terminal, needs a third-party server, has large calculation amount, and is not suitable for a physiological data real-time transmission system. Meanwhile, the method has the advantages that the network type is determined according to the use state of the network related function in the terminal and is switched to a matched high-power-consumption or low-power-consumption network, but the method does not consider the real-time transmission condition of the monitoring data of the wearable equipment, and the network type with high power consumption and low power consumption cannot be judged easily.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a wearable electrocardiograph monitoring network switching method based on reinforcement learning.
In order to achieve the aim of the invention, the invention adopts the following technical scheme:
a wearable electrocardiograph monitoring network switching method based on reinforcement learning comprises the following steps:
s1, receiving data returned by environment network monitoring equipment and an electrocardio data sensing module;
s2, preprocessing the data returned in the step S1, and obtaining a Q table about expected actions and corresponding expected action gain values by using a Q learning algorithm;
s3, classifying the data of the Q table preprocessed in the step S2 into clusters by using a subtractive clustering method, and calculating uncertain and inaccurate data to obtain an environment state matrix;
and S4, finding out the output with the maximum profit value from the Q table, sending the corresponding optimal action as output to an external task controller for execution, returning to the step S1 for continuous execution if the task is not completed after the action is executed, and ending the work if the task is completed.
Further, the data returned by the environmental network monitoring device in S1 includes the received signal strength RSSI of the bluetooth network of the wearable electrocardiograph monitoring device at time t t Throughput t Data transmission rate R t ；
The data returned by the electrocardio data sensing module comprises the frequency of electrocardio data at the moment t
Figure BDA0003570947500000021
/>
Further, the data preprocessing method in S2 is as follows:
s21, sampling the data returned in the step S1 at fixed intervals delta t, wherein each group of data comprises a plurality of samples;
s22, encoding the data sampled in the S21 into a data sequence to obtain a received signal strength data sequence RSSI of the current connection network in a time starting delta t interval Δt The Throughput data sequence of the current connection network in the delta t interval is started at the moment t Δt Data sequence R of current connection network data transmission rate in delta t interval is started at time t Δt And remove RSSI Δt 、Throughput Δt and RΔt Maximum and minimum values of (a);
s23, removing RSSI Δt 、Throughput Δt and RΔt The data sequence after the maximum value and the minimum value in the sequence is averaged to obtain the corresponding sequence average value
Figure BDA0003570947500000031
and />
Figure BDA0003570947500000032
And the obtained sequence average value and the current electrocardio data frequency at the time t are added>
Figure BDA0003570947500000033
Merging environmental statesMatrix S t 。
Further, the calculation method of the Q learning algorithm in S2 is as follows:
Figure BDA0003570947500000034
wherein ,Q(st ,a t ) Q table value, s at time t t For the environmental state matrix value at time t, a t Action at time t, S t Is an environmental state matrix, r t And alpha and gamma are constant parameters for the transmission rate of the current connection network at the moment t.
Further, the specific calculation mode of the subtractive clustering method in S3 is as follows:
Figure BDA0003570947500000035
wherein ,χi 、χ j Respectively the ith and the jth data in the Q table data after S2 pretreatment, r is the cluster radius, χ j -χ i For euclidean distances for the i and j data,
Figure BDA0003570947500000036
d is the data point with the highest density index j Data point χ i Density index of the location,/->
Figure BDA0003570947500000037
Is a two-norm square operation.
Further, the step S4 specifically includes the following steps:
s41, initializing Q (S, a), S ε S t A is E A, A is an action set, and an environment state matrix S is initialized according to the result after subtraction clustering t ；
S42, updating the environment state matrix S according to the network parameters of the connected network t And updating the Q table value;
s43, selecting and outputting the maximum Q value max (Q (S) t A) corresponding maximumOptimal action a' t And the task is executed by the external task control controller, and if the task is not completed after the execution, the step S1 is returned.
The invention has the following beneficial effects:
the invention creatively provides a heterogeneous network switching light reinforcement learning model construction method for wearable electrocardiograph monitoring equipment, and the adaptability of the model to perform rapid switching tasks in the wearable network environment is greatly improved by comprehensively considering network environment factors and ECG signal frequency characteristics of the wearable network switching; the invention also adopts the subtractive clustering technology to classify the switching measurement into the corresponding state, improves the accuracy of the Q table, can effectively reduce the calculated amount of the model, and is suitable for providing service for the wearable network in an embedded environment.
Drawings
Fig. 1 is a schematic flow chart of a wearable electrocardiographic monitoring network switching method based on reinforcement learning.
Fig. 2 is a schematic diagram of a network handover embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
A wearable electrocardiograph monitoring network switching method based on reinforcement learning, as shown in figure 1, comprises the following steps:
s1, receiving data returned by environment network monitoring equipment and an electrocardio data sensing module;
in this embodiment, the model receives as input data returned by the network environment state monitor, and environment state information such as the received signal strength RSSI of the bluetooth network of the wearable electrocardiograph monitoring device at time t t Throughput t Data transmission rate R t The method comprises the steps of carrying out a first treatment on the surface of the Receiving electrocardio frequency data returned by an electrocardio data sensing module as input, such as electrocardio data frequency at time t
Figure BDA0003570947500000051
S2, preprocessing the data returned in the step S1, and obtaining a Q table about expected actions and corresponding expected action gain values by using a Q learning algorithm;
as shown in fig. 2, the data preprocessing module mainly performs data sampling, and uses data obtained by sampling network condition monitor data and electrocardiographic data frequency at fixed intervals as output of the data preprocessing module, specifically, the method comprises the following steps:
s21, sampling the data returned in the step S1 at fixed intervals delta t, wherein each group of data comprises a plurality of samples;
s22, encoding the data sampled in the S21 into a data sequence to obtain a received signal strength data sequence RSSI of the current connection network in a time starting delta t interval Δt The Throughput data sequence of the current connection network in the delta t interval is started at the moment t Δt Data sequence R of current connection network data transmission rate in delta t interval is started at time t Δt And remove RSSI Δt 、Throughput Δt and RΔt Maximum and minimum values of (a);
s23, removing RSSI Δt 、Throughput Δt and RΔt The data sequence after the maximum value and the minimum value in the sequence is averaged to obtain the corresponding sequence average value
Figure BDA0003570947500000052
and />
Figure BDA0003570947500000053
And the obtained sequence average value and the current electrocardio data frequency at the time t are added>
Figure BDA0003570947500000054
Merging environmental state matrix S t 。
In the embodiment, as shown in fig. 2, a model adopts a Q learning algorithm (formula 1), and performs efficient learning and timely response on a network environment, namely, Q (s, a) takes action a to obtain a benefit expectation in a state of a certain moment, the environment feeds back corresponding rewards according to the action of a reagent, a state and an action are constructed into a q_table table to store a Q value, then the action capable of obtaining the maximum benefit is selected according to the Q value, so that an optimal decision is made, the defect of long time delay caused by network switching is overcome, and the frequency characteristic of electrocardiographic data is combined, the electrocardiographic data is subjected to layered coding according to the electrocardiographic sampling frequency, and is divided into a low-frequency ECG containing important cardiac condition details and a high-frequency ECG increasing the detail quantity of electrocardiographic signals, and then switching performance is evaluated from two aspects of energy efficiency and switching delay. The model judges whether the network switching condition is met according to the locally recorded historical information about the network transmission quality, dynamically determines that the network interface of the current wearable device autonomously performs network switching without information interaction with a receiving end, effectively avoids occurrence of network interruption events, and greatly reduces the time delay of network switching. In order to improve training efficiency and obtain a smaller Q table, a subtractive clustering technology (formula 2) is introduced to classify switching metrics into corresponding state intervals according to data distribution, and input indexes are classified into clusters, so that uncertain and inaccurate data are effectively processed, and the influence of reasoning on decisions is reduced to the greatest extent.
Figure BDA0003570947500000061
wherein ,Q(st ,a t ) Q table value, s at time t t For the environmental state matrix value at time t, a t Action at time t, S t Is an environmental state matrix, r t And alpha and gamma are constant parameters for the transmission rate of the current connection network at the moment t.
Figure BDA0003570947500000062
wherein ,χi 、χ j Respectively the ith and the jth data in the Q table data after S2 pretreatment, r is the cluster radius, χ j -χ i For euclidean distances for the i and j data,
Figure BDA0003570947500000063
d is the data point with the highest density index j Data point χ i Density index of the location,/->
Figure BDA0003570947500000064
Is a two-norm square operation.
S3, classifying the data of the Q table preprocessed in the step S2 into clusters by using a subtractive clustering method, and calculating uncertain and inaccurate data to obtain a new environment state matrix;
and S4, finding out the output with the maximum profit value from the Q table, sending the corresponding optimal action as output to an external task controller for execution, returning to the step S1 for continuous execution if the task is not completed after the action is executed, and ending the work if the task is completed.
Specifically, the method comprises the following steps:
the step S4 specifically comprises the following steps:
s41, initializing Q (S, a), S ε S t A is E A, A is an action set, and an environment state matrix S is initialized according to the result after subtraction clustering t ；
S42, updating the environment state matrix S according to the network parameters of the connected network t And updating the Q table value;
s43, selecting and outputting the maximum Q value max (Q (S) t The optimal action a 'corresponding to A)' t And the task is executed by the external task control controller, and if the task is not completed after the execution, the step S1 is returned.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principles and embodiments of the present invention have been described in detail with reference to specific examples, which are provided to facilitate understanding of the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Those of ordinary skill in the art will recognize that the embodiments described herein are for the purpose of aiding the reader in understanding the principles of the present invention and should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.

Claims (1)

1. A wearable electrocardiograph monitoring network switching method based on reinforcement learning is characterized by comprising the following steps:
s1, receiving data returned by environment network monitoring equipment and an electrocardiograph data sensing module, wherein the data returned by the environment network monitoring equipment comprises
Figure QLYQS_1
Received signal strength of Bluetooth network of wearable electrocardio monitoring equipment at moment +.>
Figure QLYQS_2
Throughput of
Figure QLYQS_3
Data transmission rate->
Figure QLYQS_4
；
The data returned by the electrocardio data sensing module comprises
Figure QLYQS_5
Time electrocardiographic data frequency->
Figure QLYQS_6
S2, preprocessing the data returned in the step S1, wherein the specific mode is as follows:
the data preprocessing mode is as follows:
s21, interval fixed time
Figure QLYQS_7
Sampling the data returned in the step S1, wherein each group of data comprises a plurality of samples;
s22, encoding the data sampled in the S21 into a data sequence to obtain a time beginning
Figure QLYQS_9
The currently connected network in the interval receives the signal strength data sequence +.>
Figure QLYQS_13
，/>
Figure QLYQS_15
Start of moment->
Figure QLYQS_10
Current connection network throughput data sequence within an interval
Figure QLYQS_12
，/>
Figure QLYQS_14
Start of moment->
Figure QLYQS_17
Data sequence of data transmission rate of current connection network in interval +.>
Figure QLYQS_8
And remove->
Figure QLYQS_11
、/>
Figure QLYQS_16
and />
Figure QLYQS_18
Maximum and minimum values of (a);
s23, removing
Figure QLYQS_20
、/>
Figure QLYQS_22
and />
Figure QLYQS_25
The data sequences after the maximum value and the minimum value in (1) are averaged to obtain the corresponding sequence average value +.>
Figure QLYQS_21
, />
Figure QLYQS_24
and />
Figure QLYQS_26
And averaging the obtained sequences and +.>
Figure QLYQS_27
The current electrocardiographic data frequency of the moment +.>
Figure QLYQS_19
Merging environmental state matrix->
Figure QLYQS_23
；
Obtaining a Q table about expected actions and return values corresponding to the expected actions by using a Q learning algorithm, wherein the Q learning algorithm is calculated in the following way:
Figure QLYQS_28
wherein ,
Figure QLYQS_29
q table value at time t +.>
Figure QLYQS_30
For the ambient state matrix value at time t +.>
Figure QLYQS_31
For action at time t->
Figure QLYQS_32
Is an environmental state matrix>
Figure QLYQS_33
For the transmission rate of the currently connected network at time t, < >>
Figure QLYQS_34
Is a constant parameter;
s3, classifying the data of the Q table preprocessed in the step S2 into clusters by using a subtractive clustering method, and calculating uncertain and inaccurate data to obtain an environment state matrix, wherein the subtractive clustering method comprises the following specific calculation modes:
Figure QLYQS_35
wherein ,
Figure QLYQS_36
respectively, i and j data in the Q table data after S2 pretreatment,/>
Figure QLYQS_37
For the radius of the cluster,
Figure QLYQS_38
euclidean distance for the ith and jth data,>
Figure QLYQS_39
for the data point with the highest density index, +.>
Figure QLYQS_40
Is data point->
Figure QLYQS_41
Density index of the location,/->
Figure QLYQS_42
Performing square operation for two norms;
s4, finding out the output with the biggest profit value in the Q table, sending the corresponding optimal action as output to an external task controller for execution, returning to the step S1 for continuous execution if the task is not completed after the action is executed, and ending the work if the task is completed, wherein the method specifically comprises the following steps:
s41, initializing
Figure QLYQS_43
，/>
Figure QLYQS_44
，/>
Figure QLYQS_45
，/>
Figure QLYQS_46
For action set, and initializing environmental state matrix according to subtraction clustered result>
Figure QLYQS_47
；
S42, updating the environment state matrix according to the network parameters of the connected network
Figure QLYQS_48
And updating the Q table value;
s43, according to the updated Q table value
Figure QLYQS_49
Selecting the optimal action corresponding to the maximum Q value>
Figure QLYQS_50
And the task is executed by the external task control controller, and if the task is not completed after the execution, the step S1 is returned. />
CN202210323583.6A 2022-03-29 2022-03-29 Wearable electrocardiograph monitoring network switching method based on reinforcement learning Active CN114679759B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210323583.6A CN114679759B (en) 2022-03-29 2022-03-29 Wearable electrocardiograph monitoring network switching method based on reinforcement learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210323583.6A CN114679759B (en) 2022-03-29 2022-03-29 Wearable electrocardiograph monitoring network switching method based on reinforcement learning

Publications (2)

Publication Number Publication Date
CN114679759A CN114679759A (en) 2022-06-28
CN114679759B true CN114679759B (en) 2023-06-09

Family

ID=82075786

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210323583.6A Active CN114679759B (en) 2022-03-29 2022-03-29 Wearable electrocardiograph monitoring network switching method based on reinforcement learning

Country Status (1)

Country Link
CN (1) CN114679759B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110809306A (en) * 2019-11-04 2020-02-18 电子科技大学 Terminal access selection method based on deep reinforcement learning
WO2021055595A1 (en) * 2019-09-18 2021-03-25 Bioxcel Therapeutics, Inc. Systems and methods for detection and prevention of emergence of agitation
CN112863653A (en) * 2021-03-01 2021-05-28 武汉中旗生物医疗电子有限公司 Electrocardio data compression method and device

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11138503B2 (en) * 2017-03-22 2021-10-05 Larsx Continuously learning and optimizing artificial intelligence (AI) adaptive neural network (ANN) computer modeling methods and systems
US20220054850A1 (en) * 2020-08-24 2022-02-24 West Affum Holdings Corp. Wearable cardioverter defibrillator care system with health and emotional companion accessory

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021055595A1 (en) * 2019-09-18 2021-03-25 Bioxcel Therapeutics, Inc. Systems and methods for detection and prevention of emergence of agitation
CN110809306A (en) * 2019-11-04 2020-02-18 电子科技大学 Terminal access selection method based on deep reinforcement learning
CN112863653A (en) * 2021-03-01 2021-05-28 武汉中旗生物医疗电子有限公司 Electrocardio data compression method and device

Also Published As

Publication number Publication date
CN114679759A (en) 2022-06-28

Similar Documents

Publication Publication Date Title
CN108545556B (en) Information processing unit neural network based and method
CN111314473A (en) Environmental monitoring system based on artificial intelligence
CN113423081B (en) Wireless energy transmission method and device, computer equipment and storage medium
JP2018124852A (en) Information processing system, information processing method, and program
TWI684139B (en) System and method of learning-based prediction for anomalies within a base station
CN114781439B (en) Model acquisition system, gesture recognition method, gesture recognition device, apparatus and storage medium
JP2020068473A (en) Sensor data compression system, sensor terminal, model building device, and program
CN114039870B (en) Deep learning-based real-time bandwidth prediction method for video stream application in cellular network
CN111030850B (en) SCADA system data acquisition period control method and device
CN115065728B (en) Multi-strategy reinforcement learning-based multi-target content storage method
CN113869482A (en) Intelligent street lamp self-adaptive energy-saving control method and system based on deep reinforcement learning
CN103974112B (en) A kind of TV set control method and device
CN114679759B (en) Wearable electrocardiograph monitoring network switching method based on reinforcement learning
CN117154844A (en) Energy supply control method and device for energy storage system
CN114521023A (en) SWIPT-assisted NOMA-MEC system resource allocation modeling method
CN117077870B (en) Water resource digital management method based on artificial intelligence
CN116225102B (en) Mobile energy storage communication temperature rise automatic monitoring system and device
CN113490248B (en) Multi-mode terminal switching method and device
CN116993240A (en) Logistics system control method, device, equipment and storage medium
KR101052332B1 (en) Wildlife Location Tracking System and Method
CN116416545A (en) Behavior detection method, apparatus, device and computer readable storage medium
AU2021105964A4 (en) Self-adaptive Energy-saving Control Method and System for Smart Street Lamps Based on Deep Reinforcement Learning
CN117748733A (en) Power grid information control method based on digital twin model
CN115718536B (en) Frequency modulation method and device, electronic equipment and readable storage medium
CN112422627B (en) Internet of things node control method and device, intelligent terminal and storage medium

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