CN116130046A - Fuzzy memristor calculation method and system for hierarchical quantification of blood pressure - Google Patents

Fuzzy memristor calculation method and system for hierarchical quantification of blood pressure Download PDF

Info

Publication number
CN116130046A
CN116130046A CN202310190917.1A CN202310190917A CN116130046A CN 116130046 A CN116130046 A CN 116130046A CN 202310190917 A CN202310190917 A CN 202310190917A CN 116130046 A CN116130046 A CN 116130046A
Authority
CN
China
Prior art keywords
fuzzy
blood pressure
memristor
rule
data set
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
Application number
CN202310190917.1A
Other languages
Chinese (zh)
Other versions
CN116130046B (en
Inventor
李亚
纪少军
戴青云
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.)
Guangdong Polytechnic Normal University
Original Assignee
Guangdong Polytechnic Normal 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 Guangdong Polytechnic Normal University filed Critical Guangdong Polytechnic Normal University
Priority to CN202310190917.1A priority Critical patent/CN116130046B/en
Publication of CN116130046A publication Critical patent/CN116130046A/en
Application granted granted Critical
Publication of CN116130046B publication Critical patent/CN116130046B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/021—Measuring pressure in heart or blood vessels
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7232—Signal processing specially adapted for physiological signals or for diagnostic purposes involving compression of the physiological signal, e.g. to extend the signal recording period
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/15—Correlation function computation including computation of convolution operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • 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
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The invention discloses a fuzzy memristor calculation method and a system for blood pressure grading quantization, comprising the following steps: acquiring a blood pressure related data set based on a big data method, and carrying out preprocessing such as normalization and the like on the blood pressure related data set according to a threshold high pressure judging method to obtain definition and classification of blood pressure levels in the data set; establishing a fuzzy semantic set according to a judging result of hypertension in a blood pressure data set, generating an input variable based on the fuzzy semantic set, and leading the input variable into a memristor fuzzy logic circuit to determine a membership function; determining fuzzy rules through membership functions, obtaining fuzzy rule weights, converting the fuzzy rules stored in a rule base into mapping relations among fuzzy sets, obtaining final output results of memristor fuzzy logic circuits, and determining hierarchical quantization results of blood pressure data. According to the real-time intelligent fuzzy calculation method, the blood pressure data of the wearer are analyzed in real time, the blood pressure grading condition is analyzed, and the real-time efficient intelligent fuzzy calculation method is provided for health monitoring of the wearable equipment.

Description

Fuzzy memristor calculation method and system for hierarchical quantification of blood pressure
Technical Field
The invention relates to the technical field of blood pressure grading, in particular to a fuzzy memristor calculation method and system for blood pressure grading quantization.
Background
Wearable devices play an increasingly important role in health monitoring. Currently, wearable devices suffer from volume, power consumption and battery size, requiring more reliable real-time computing power. However, most of the algorithm calculation is run on a computer, and in this implementation manner, the calculation and storage functions are separated, so that the calculation speed of the algorithm calculation is limited, and the problem of high energy consumption of modern wearable equipment is indirectly caused.
In the real-time health monitoring process, the problems of nature, ambiguity or uncertainty of natural language form description exist. Therefore, the fuzzy logic has good application prospect in a health scene. Fuzzy logic is highly valued by the scientific community because of its ability to circumvent the limitations of traditional probabilistic models requiring precise mathematical modeling and the strong processing of fuzzy uncertainty problems arising from extensive uncertainty of the system concept. In particular, in the process of accurate hierarchical quantization of health states, the fuzzy logic can solve various uncertain problems which cannot be solved by binary logic by means of the membership function concept. Therefore, in a scene of utilizing the wearable equipment to monitor blood pressure in daily life, the memristor fuzzy logic circuit is applied to the wearable blood pressure monitoring classification quantification, blood pressure data of a wearer is analyzed in real time, blood pressure classification condition early warning is carried out, and a real-time efficient intelligent hardware processing system is provided for the wearable blood pressure monitoring classification quantification application, so that the problem which cannot be solved yet is urgent at present.
Disclosure of Invention
In order to solve the technical problems, the invention provides a fuzzy memristor calculation method and a fuzzy memristor calculation system for blood pressure grading quantization.
The first aspect of the invention provides a fuzzy memristor calculation method for blood pressure grading quantification, which comprises the following steps:
acquiring a blood pressure related data set based on a big data method, and preprocessing the blood pressure related data set according to a threshold high pressure judging method to obtain definition and classification of blood pressure levels in the data set;
normalizing the preprocessed blood pressure data by using a linear function, and scaling the blood pressure data in an equal proportion;
establishing a fuzzy semantic set according to a judging result of hypertension in a blood pressure data set, generating an input variable based on the fuzzy semantic set, and leading the input variable into a memristor fuzzy logic circuit to determine a membership function;
determining fuzzy rules through membership functions, obtaining fuzzy rule weights, converting the fuzzy rules stored in a rule base into mapping relations among fuzzy sets, obtaining final output results of memristor fuzzy logic circuits, determining hierarchical quantization results of blood pressure data, and performing precision evaluation on the hierarchical quantization results;
the memristor fuzzy logic circuit comprises a fuzzification circuit module, a rule base circuit module and an inference engine circuit module.
In the scheme, a blood pressure related data set is obtained based on a big data method, and is preprocessed according to a threshold high pressure judging method to obtain definition and classification of blood pressure levels in the data set, specifically:
setting retrieval constraints through a preset age group and medical indexes, acquiring preset quantity of data information based on the retrieval constraints by utilizing a big data means, and constructing a blood pressure related data set;
screening systolic pressure, diastolic pressure and hypertension diagnosis results in the blood pressure related data set, determining systolic pressure and diastolic pressure thresholds according to a threshold hypertension judging method, and obtaining blood pressure levels of data in the blood pressure related data set according to comparison, wherein the hypertension diagnosis results comprise: normal, pre-hypertension and hypertension;
and determining the classification of the blood pressure data in the data set through the blood pressure level, setting a class label according to the classification result, and marking the blood pressure data in the blood pressure related data set.
In the scheme, the preprocessed blood pressure related data is normalized by using a linear function, and the blood pressure related data is scaled in equal proportion, specifically:
normalizing blood pressure data in a blood pressure related data set by using a linear function normalization method, and converting the blood pressure data into a range of [0,1] to realize the equal-proportion scaling of the blood pressure data;
the normalization processing formula of the blood pressure data is as follows:
Figure SMS_1
；
wherein ,
Figure SMS_2
representing normalized blood pressure data, +.>
Figure SMS_3
Representing blood pressure data->
Figure SMS_4
，/>
Figure SMS_5
Respectively represent the maximum value and the minimum value of the blood pressure data.
In the scheme, a fuzzy semantic set is constructed according to the judgment result of hypertension in a blood pressure data set, an input variable is generated based on the fuzzy semantic set, and the input variable is imported into a memristor fuzzy logic circuit to determine a membership function, specifically:
dividing blood pressure data into three fuzzy semantic sets according to hypertension diagnosis results and category labels in blood pressure related data sets: in (a)
Figure SMS_6
High->
Figure SMS_7
High->
Figure SMS_8
；
Determining each fuzzy semantic set membership function corresponding to the systolic pressure and the diastolic pressure according to the triangular membership functions, and storing the fuzzy semantic set membership functions in each row of a memristor array recorded in a fuzzification circuit module, wherein memristors in the memristor array are subjected to pre-parallel programming through pulse voltages to obtain resistance information of each memristor;
the memristor array is composed of two groups of parallel wires which are mutually perpendicular, one memristor is connected with two cross wires at each cross point, and the calculation expression for programming the resistance value of the memristor according to the membership function is as follows:
Figure SMS_9
；
wherein ,
Figure SMS_10
representing the resistance of the corresponding memristor on vertical conductor j, +.>
Figure SMS_11
Representing the feedback resistance of the operational amplifier,
Figure SMS_12
representing the triangle membership function at the point +.>
Figure SMS_13
Membership degree of (3);
and taking the systolic pressure and the diastolic pressure as inputs of the memristor fuzzy circuit, wherein each input corresponds to three membership functions, and acquiring corresponding membership degrees through a fuzzy circuit module.
In the scheme, a fuzzy rule is determined through a membership function, and a fuzzy rule weight is obtained, specifically:
the membership degree output by a fuzzification circuit module in the memristor fuzzy circuit is used as the input of a rule base circuit module, and 9 fuzzy rules are generated based on the middle, higher and higher semantic fuzzy sets corresponding to the systolic pressure and the diastolic pressure;
generating a fuzzy rule table according to the fuzzy rule and a division rule of hypertension in a blood pressure related data set, and generating a memristor fuzzy circuit IF-THEN rule base according to the fuzzy rule table;
and obtaining a weight value corresponding to the fuzzy rule according to the ratio of the membership product of the single fuzzy rule to the accumulated sum of all membership products of the fuzzy rule.
In the scheme, the fuzzy rules stored in the rule base are converted into the mapping relation among fuzzy sets, and the final output result of the memristor fuzzy logic circuit is obtained, specifically:
obtaining a weighted average sum of input variables according to the posterior parameters and posterior parameter weights in the fuzzy rule in the fuzzy reasoning circuit module, and obtaining a final output result of the memristor fuzzy logic circuit based on the weighted average sum of the input variables and the fuzzy rule weights, wherein the calculation formula is as follows:
Figure SMS_14
；
wherein ,
Figure SMS_15
represent the firstkWeight value of bar rule +.>
Figure SMS_16
Representing a weighted average sum of the input variables +.>
Figure SMS_17
Representing the weight of the back-piece parameter, i.e. the weight of each input variable, +.>
Figure SMS_18
Representing the dimension of the input variable ∈>
Figure SMS_19
Indicating the final output result of the memristive fuzzy logic.
In the scheme, the output precision reaches the preset standard by adjusting the weight of the parameters of the back-part in the fuzzy inference circuit module, and the method specifically comprises the following steps:
acquiring 2 back-piece parameters corresponding to each fuzzy rule, and selecting normalized data in the blood pressure related data set to train the weight of the back-piece parameters;
the method comprises the steps that a back-piece parameter weight unit is formed by two memristors which are connected in opposite directions and a single-pole double-throw switch, and programming or calculation of the parameter weight unit is realized by the single-pole double-throw switch;
when the accuracy of the output signal of the reasoning engine circuit module reaches a preset threshold value, stopping training to obtain an optimal solution of the parameter weight of the back-part, opening a PMOS transistor, closing an NMOS transistor, enabling the parameter weight unit of the back-part to enter a programming process, otherwise, closing the PMOS transistor, and opening the NMOS transistor to continue calculation training;
and setting a memristor fuzzy logic circuit through the optimal solution of the back part parameter weight, and carrying out blood pressure grading quantization of the target user by utilizing the fuzzy logic circuit with the precision meeting the preset standard.
The second aspect of the present invention also provides a fuzzy memristor computing system for hierarchical quantification of blood pressure, the system comprising: the device comprises a memory and a processor, wherein the memory comprises a fuzzy memristor calculation method program for blood pressure grading quantization, and the fuzzy memristor calculation method program for blood pressure grading quantization realizes the following steps when being executed by the processor:
acquiring a blood pressure related data set based on a big data method, and preprocessing the blood pressure related data set according to a threshold high pressure judging method to obtain definition and classification of blood pressure levels in the data set;
normalizing the preprocessed blood pressure data by using a linear function, and scaling the blood pressure data in an equal proportion;
establishing a fuzzy semantic set according to a judging result of hypertension in a blood pressure data set, generating an input variable based on the fuzzy semantic set, and leading the input variable into a memristor fuzzy logic circuit to determine a membership function;
determining fuzzy rules through membership functions, obtaining fuzzy rule weights, converting the fuzzy rules stored in a rule base into mapping relations among fuzzy sets, obtaining final output results of memristor fuzzy logic circuits, determining hierarchical quantization results of blood pressure data, and performing precision evaluation on the hierarchical quantization results;
the memristor fuzzy logic circuit comprises a fuzzification circuit module, a rule base circuit module and an inference engine circuit module.
The invention discloses a fuzzy memristor calculation method and a system for blood pressure grading quantization, comprising the following steps: acquiring a blood pressure related data set based on a big data method, and carrying out preprocessing such as normalization and the like on the blood pressure related data set according to a threshold high pressure judging method to obtain definition and classification of blood pressure levels in the data set; establishing a fuzzy semantic set according to a judging result of hypertension in a blood pressure data set, generating an input variable based on the fuzzy semantic set, and leading the input variable into a memristor fuzzy logic circuit to determine a membership function; determining fuzzy rules through membership functions, obtaining fuzzy rule weights, converting the fuzzy rules stored in a rule base into mapping relations among fuzzy sets, obtaining final output results of memristor fuzzy logic circuits, and determining hierarchical quantization results of blood pressure data. According to the real-time intelligent fuzzy calculation method, the blood pressure data of the wearer are analyzed in real time, the blood pressure grading condition is analyzed, and the real-time efficient intelligent fuzzy calculation method is provided for health monitoring of the wearable equipment.
Drawings
FIG. 1 shows a flow chart of a fuzzy memristor calculation method for hierarchical quantification of blood pressure in accordance with the present invention;
FIG. 2 shows a schematic diagram of memristive fuzzy logic circuit for blood pressure hierarchical quantification of the present invention;
FIG. 3 shows a schematic circuit diagram of a memristor programming single pole double throw switch of the present disclosure;
FIG. 4 illustrates a flow chart of a method of the present invention for adjusting the weight of a back-piece parameter;
FIG. 5 shows a schematic circuit diagram of a back-piece parameter weighting unit of the present invention;
FIG. 6 illustrates a block diagram of a fuzzy memristive computing system for hierarchical quantification of blood pressure in accordance with the present invention;
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
FIG. 1 shows a flow chart of a fuzzy memristor calculation method for hierarchical quantification of blood pressure in accordance with the present invention.
As shown in fig. 1, the first aspect of the present invention provides a fuzzy memristor calculation method for hierarchical quantification of blood pressure, including:
s102, acquiring a blood pressure related data set based on a big data method, and preprocessing the blood pressure related data set according to a threshold high pressure judging method to obtain definition and classification of blood pressure levels in the data set;
s104, carrying out normalization processing on the preprocessed blood pressure data by using a linear function, and carrying out equal proportion scaling on the blood pressure data;
s106, constructing a fuzzy semantic set according to a judgment result of hypertension in the blood pressure data set, generating an input variable based on the fuzzy semantic set, and leading the input variable into a memristor fuzzy logic circuit to determine a membership function;
s108, determining fuzzy rules through membership functions, obtaining fuzzy rule weights, converting the fuzzy rules stored in a rule base into mapping relations among fuzzy sets, obtaining final output results of a memristor fuzzy logic circuit, determining hierarchical quantization results of blood pressure data, and evaluating the hierarchical quantization results in precision.
It should be noted that, the memristor ambiguity logic circuit includes an ambiguity circuit module, a rule base circuit module and an inference engine circuit module, and the memristor ambiguity logic circuit is shown in fig. 2. Setting retrieval constraints through a preset age group and medical indexes, acquiring preset quantity of data information based on the retrieval constraints by utilizing a big data means, and constructing a blood pressure related data set; screening systolic pressure, diastolic pressure and hypertension diagnosis results in the blood pressure related data set, determining systolic pressure and diastolic pressure thresholds according to a threshold hypertension judging method, and obtaining blood pressure levels of data in the blood pressure related data set according to comparison, wherein the hypertension diagnosis results comprise: normal, pre-hypertension and hypertension; and determining the classification of the blood pressure data in the data set through the blood pressure level, setting a class label according to the classification result, and marking the blood pressure data in the blood pressure related data set.
Normalizing blood pressure data in a blood pressure related data set by using a linear function normalization method, and converting the blood pressure data into a range of [0,1] to realize the equal-proportion scaling of the blood pressure data;
the normalization processing formula of the blood pressure data is as follows:
Figure SMS_20
；
wherein ,
Figure SMS_21
representing normalized blood pressure data, +.>
Figure SMS_22
Representing blood pressure data->
Figure SMS_23
，/>
Figure SMS_24
Respectively represent the maximum value and the minimum value of the blood pressure data.
It should be noted that, according to the hypertension diagnosis result and the category label in the blood pressure related data set, the blood pressure data is divided into three fuzzy semantic sets: in (a)
Figure SMS_25
High->
Figure SMS_26
High->
Figure SMS_27
The method comprises the steps of carrying out a first treatment on the surface of the According to the membership function form and expert experience, a triangle function is selected to determine each fuzzy semantic set membership function corresponding to the systolic pressure and the diastolic pressure, and each fuzzy semantic set membership function is stored in each row of a memristor array recorded in a fuzzification circuit module, wherein memristors in the memristor array are recorded in each row of the fuzzification circuit moduleThe memristor carries out pre-parallel programming through pulse voltage to obtain resistance information of each memristor;
according to FIG. 3, a single-pole double-throw switch composed of the source of an NMOS transistor and the drain of a PMOS transistor is preset in the blurring circuit module, the threshold voltages of the NMOS transistor and the PMOS transistor are respectively
Figure SMS_29
and />
Figure SMS_32
；/>
Figure SMS_33
Control the single pole double throw switch to open or not, when +.>
Figure SMS_30
The PMOS transistor is turned on, and the input voltage of the circuit is +.>
Figure SMS_31
Programming voltage
Figure SMS_34
Programming the memristor applied at both ends; when->
Figure SMS_35
The NMOS transistor is turned on, and the input voltage of the circuit is
Figure SMS_28
The circuit enters a calculation process;
the memristor array is composed of two groups of parallel wires which are mutually perpendicular, one memristor is connected with two cross wires at each cross point, and the calculation expression for programming the resistance value of the memristor according to the membership function is as follows:
Figure SMS_36
；
wherein ,
Figure SMS_37
representing saggingResistance value of corresponding memristor on straight conductor j, +.>
Figure SMS_38
Representing the feedback resistance of the operational amplifier,
Figure SMS_39
representing the triangle membership function at the point +.>
Figure SMS_40
Membership degree of (3);
and taking the systolic pressure and the diastolic pressure as inputs of a memristor fuzzy circuit, wherein each input corresponds to three membership functions, and acquiring corresponding membership degrees according to a preprogrammed memristor resistance value through a fuzzy circuit module.
The membership degree output by a fuzzification circuit module in the memristor fuzzy circuit is used as the input of a rule base circuit module, the rule circuit module consists of an operational amplifier, a resistor, a multiplier and a divider, and 9 fuzzy rules are generated based on three semantic fuzzy sets of middle, higher and higher corresponding to the systolic pressure and the diastolic pressure;
generating a fuzzy rule table according to the fuzzy rule and a division rule of hypertension in a blood pressure related data set, and generating a memristor fuzzy circuit IF-THEN rule base according to the fuzzy rule table;
Figure SMS_41
；
Figure SMS_42
；
wherein in the front part (IF)
Figure SMS_43
and />
Figure SMS_44
Input signals respectively representing memristive fuzzy logic circuits, M, LH and H representing fuzzy semantic sets of the memristive fuzzy logic system, +.>
Figure SMS_45
Output of rule back-part (THEN) representing inference engine, < >>
Figure SMS_46
Representing rule back-piece parameter weights;
and obtaining a weight value corresponding to the fuzzy rule according to the ratio of the membership product of the single fuzzy rule to the accumulated sum of all membership products of the fuzzy rule, wherein the calculation expression of the rule base circuit module is as follows:
Figure SMS_47
；
wherein
Figure SMS_48
Indicating that the membership function corresponding to the input information is at +.>
Figure SMS_49
Bar fuzzy rule pair input->
Figure SMS_50
Membership of->
Figure SMS_51
Is a membership product representing k rules>
Figure SMS_52
Represent the firstkWeight value of bar rule +.>
Figure SMS_53
Representing the total number of rules.
It should be noted that, in the fuzzy inference circuit module, a weighted average sum of input variables is obtained according to the posterior parameters and the posterior parameter weights in the fuzzy rule, and a final output result of the memristor fuzzy logic circuit is obtained based on the weighted average sum of the input variables and the fuzzy rule weights, and the calculation formula is as follows:
Figure SMS_54
；
wherein ,
Figure SMS_55
represent the firstkWeight value of bar rule +.>
Figure SMS_56
Representing a weighted average sum of the input variables +.>
Figure SMS_57
Representing the weight of the back-piece parameter, i.e. the weight of each input variable, +.>
Figure SMS_58
Representing the dimension of the input variable ∈>
Figure SMS_59
Indicating the final output result of the memristive fuzzy logic.
Fig. 4 shows a flow chart of a method of the invention for adjusting the weight of a back-piece parameter.
According to the embodiment of the invention, the output precision reaches the preset standard by adjusting the weight of the back-part parameter in the fuzzy inference circuit module, and the method specifically comprises the following steps:
s402, acquiring 2 back-piece parameters corresponding to each fuzzy rule, and selecting normalized data in a blood pressure related data set to train the weight of the back-piece parameters;
s404, forming a back-piece parameter weight unit through two memristors which are connected in opposite directions and a single-pole double-throw switch, and programming or calculating the parameter weight unit through the single-pole double-throw switch;
s406, when the accuracy of the output signal of the reasoning engine circuit module reaches a preset threshold value, stopping training to obtain an optimal solution of the back-piece parameter weight, opening a PMOS transistor, closing an NMOS transistor, enabling a back-piece parameter weight unit to enter a programming process, otherwise, closing the PMOS transistor, and opening the NMOS transistor to continue calculation training;
s408, setting a memristor fuzzy logic circuit through the optimal solution of the back-part parameter weight, and defining the range of blood pressure hierarchical diagnosis for the output of the circuit to obtain a hierarchical quantification result.
As shown in FIG. 5, the definition is that
Figure SMS_60
and />
Figure SMS_61
For the conductance values of two memristors, the reasoning engine circuit module is programmed, and the conductance value of the memristor is +.>
Figure SMS_62
and />
Figure SMS_63
Difference between->
Figure SMS_64
The values of (2) may be positive and negative; the expression of the calculation performed by the reasoning engine circuit module is as follows:
Figure SMS_65
；
wherein ,
Figure SMS_66
，/>
Figure SMS_67
representing the feedback resistance of the operational amplifier, +.>
Figure SMS_68
The input signal is represented by a signal representative of the input signal,
Figure SMS_69
representing the output signal;
and comparing and calculating the accuracy according to the theoretical result and the grading quantization result of the blood pressure data in the blood pressure related database, grading and quantizing the blood pressure of the target user by using a fuzzy logic circuit with the accuracy meeting the preset standard, and early warning according to the grading and quantizing of the blood pressure.
FIG. 6 illustrates a block diagram of a fuzzy memristive computing system for hierarchical quantification of blood pressure in accordance with the present invention.
The second aspect of the present invention also provides a fuzzy memristive computation system 6 for hierarchical quantification of blood pressure, the system comprising: the memory 61, the processor 62, include a kind of fuzzy memristance calculation method procedure used for blood pressure grading quantification in the said memory, the said a kind of fuzzy memristance calculation method procedure used for blood pressure grading quantification realizes the following steps when being executed by the said processor:
acquiring a blood pressure related data set based on a big data method, and preprocessing the blood pressure related data set according to a threshold high pressure judging method to obtain definition and classification of blood pressure levels in the data set;
normalizing the preprocessed blood pressure data by using a linear function, and scaling the blood pressure data in an equal proportion;
establishing a fuzzy semantic set according to a judging result of hypertension in a blood pressure data set, generating an input variable based on the fuzzy semantic set, and leading the input variable into a memristor fuzzy logic circuit to determine a membership function;
determining fuzzy rules through membership functions, obtaining fuzzy rule weights, converting the fuzzy rules stored in a rule base into mapping relations among fuzzy sets, obtaining final output results of memristor fuzzy logic circuits, determining hierarchical quantization results of blood pressure data, and performing precision evaluation on the hierarchical quantization results;
the memristor fuzzy logic circuit comprises a fuzzification circuit module, a rule base circuit module and an inference engine circuit module.
It is to be noted that, setting retrieval constraints through preset age groups and medical indexes, acquiring preset quantity of data information based on the retrieval constraints by utilizing big data means, and constructing a blood pressure related data set; screening systolic pressure, diastolic pressure and hypertension diagnosis results in the blood pressure related data set, determining systolic pressure and diastolic pressure thresholds according to a threshold hypertension judging method, and obtaining blood pressure levels of data in the blood pressure related data set according to comparison, wherein the hypertension diagnosis results comprise: normal, pre-hypertension and hypertension; and determining the classification of the blood pressure data in the data set through the blood pressure level, setting a class label according to the classification result, and marking the blood pressure data in the blood pressure related data set.
Normalizing blood pressure data in a blood pressure related data set by using a linear function normalization method, and converting the blood pressure data into a range of [0,1] to realize the equal-proportion scaling of the blood pressure data;
the normalization processing formula of the blood pressure data is as follows:
Figure SMS_70
；
wherein ,
Figure SMS_71
representing normalized blood pressure data, +.>
Figure SMS_72
Representing blood pressure data->
Figure SMS_73
，/>
Figure SMS_74
Respectively represent the maximum value and the minimum value of the blood pressure data.
It should be noted that, according to the hypertension diagnosis result and the category label in the blood pressure related data set, the blood pressure data is divided into three fuzzy semantic sets: in (a)
Figure SMS_75
High->
Figure SMS_76
High->
Figure SMS_77
The method comprises the steps of carrying out a first treatment on the surface of the According to the membership function form and expert experience, a triangle function is selected to determine each fuzzy semantic set membership function corresponding to the systolic pressure and the diastolic pressure, and the fuzzy semantic set membership functions are stored in each row of a memristor array recorded in a fuzzification circuit module, and memristors in the memristor array are subjected to pre-parallel programming through pulse voltages to obtain resistance information of each memristor;
presetting a single-pole double-throw switch formed by connecting a source electrode of an NMOS transistor and a drain electrode of a PMOS transistor, wherein threshold voltages of the NMOS transistor and the PMOS transistor are respectively
Figure SMS_78
and />
Figure SMS_82
；/>
Figure SMS_84
Control the single pole double throw switch to open or not when
Figure SMS_80
The PMOS transistor is turned on, and the input voltage of the circuit is +.>
Figure SMS_81
Programming voltage->
Figure SMS_83
Programming the memristor applied at both ends; when->
Figure SMS_85
The NMOS transistor is turned on, and the input voltage of the circuit is +.>
Figure SMS_79
The circuit enters a calculation process;
the memristor array is composed of two groups of parallel wires which are mutually perpendicular, one memristor is connected with two cross wires at each cross point, and the calculation expression for programming the resistance value of the memristor according to the membership function is as follows:
Figure SMS_86
；
wherein ,
Figure SMS_87
representing the resistance of the corresponding memristor on vertical conductor j, +.>
Figure SMS_88
Representing the feedback resistance of the operational amplifier,
Figure SMS_89
representing the triangle membership function at the point +.>
Figure SMS_90
Membership degree of (3);
and taking the systolic pressure and the diastolic pressure as inputs of a memristor fuzzy circuit, wherein each input corresponds to three membership functions, and acquiring corresponding membership degrees according to a preprogrammed memristor resistance value through a fuzzy circuit module.
The membership degree output by a fuzzification circuit module in the memristor fuzzy circuit is used as the input of a rule base circuit module, the rule circuit module consists of an operational amplifier, a resistor, a multiplier and a divider, and 9 fuzzy rules are generated based on three semantic fuzzy sets of middle, higher and higher corresponding to the systolic pressure and the diastolic pressure;
generating a fuzzy rule table according to the fuzzy rule and a division rule of hypertension in a blood pressure related data set, and generating a memristor fuzzy circuit IF-THEN rule base according to the fuzzy rule table;
Figure SMS_91
；
Figure SMS_92
；
wherein in the front part (IF)
Figure SMS_93
and />
Figure SMS_94
Input signals respectively representing memristive fuzzy logic circuits, M, LH and H representing fuzzy semantic sets of the memristive fuzzy logic system, +.>
Figure SMS_95
Output of rule back-part (THEN) representing inference engine, < >>
Figure SMS_96
Representing rule back-piece parameter weights;
and obtaining a weight value corresponding to the fuzzy rule according to the ratio of the membership product of the single fuzzy rule to the accumulated sum of all membership products of the fuzzy rule, wherein the calculation expression of the rule base circuit module is as follows:
Figure SMS_97
；
wherein
Figure SMS_98
Indicating that the membership function corresponding to the input information is at +.>
Figure SMS_99
Bar fuzzy rule pair input->
Figure SMS_100
Membership of->
Figure SMS_101
Is a membership product representing k rules>
Figure SMS_102
Represent the firstkWeight value of bar rule +.>
Figure SMS_103
Representing the total number of rules.
It should be noted that, in the fuzzy inference circuit module, a weighted average sum of input variables is obtained according to the posterior parameters and the posterior parameter weights in the fuzzy rule, and a final output result of the memristor fuzzy logic circuit is obtained based on the weighted average sum of the input variables and the fuzzy rule weights, and the calculation formula is as follows:
Figure SMS_104
；
wherein ,
Figure SMS_105
represent the firstkWeight value of bar rule +.>
Figure SMS_106
Representing a weighted average sum of the input variables +.>
Figure SMS_107
Representing the weight of the back-piece parameter, i.e. the weight of each input variable, +.>
Figure SMS_108
Representing the dimension of the input variable ∈>
Figure SMS_109
Indicating the final output result of the memristive fuzzy logic.
It should be noted that, acquiring 2 back-piece parameters corresponding to each fuzzy rule, and selecting normalized data in the blood pressure related data set to train the weight of the back-piece parameters; the method comprises the steps that a back-piece parameter weight unit is formed by two memristors which are connected in opposite directions and a single-pole double-throw switch, and programming or calculation of the parameter weight unit is realized by the single-pole double-throw switch; when the accuracy of the output signal of the reasoning engine circuit module reaches a preset threshold value, stopping training to obtain an optimal solution of the parameter weight of the back-part, opening the PMOS transistor, closing the NMOS transistor, enabling the parameter weight unit of the back-part to enter a programming process, otherwise, closing the PMOS transistor, and opening the NMOS transistor to continue calculation training.
Definition of the definition
Figure SMS_110
and />
Figure SMS_111
For the conductance values of two memristors, the reasoning engine circuit module is programmed, and the conductance value of the memristor is +.>
Figure SMS_112
and />
Figure SMS_113
Difference between->
Figure SMS_114
The values of (2) may be positive and negative; the expression of the calculation performed by the reasoning engine circuit module is as follows:
Figure SMS_115
；
wherein ,
Figure SMS_116
，/>
Figure SMS_117
representing the feedback resistance of the operational amplifier, +.>
Figure SMS_118
The input signal is represented by a signal representative of the input signal,
Figure SMS_119
representing the output signal;
and setting a memristor fuzzy logic circuit through an optimal solution of the back part parameter weight, defining a blood pressure grading diagnosis range for the output of the circuit, obtaining a grading quantization result, comparing calculation precision according to a theoretical result of blood pressure data in a blood pressure related database and the grading quantization result, grading and quantizing the blood pressure of a target user by utilizing the fuzzy logic circuit with the precision meeting a preset standard, and carrying out corresponding early warning.
The third aspect of the present invention also provides a computer readable storage medium, including a fuzzy memristance calculating method program for blood pressure hierarchical quantization, where the steps of a fuzzy memristance calculating method for blood pressure hierarchical quantization according to any one of the above claims are implemented when the fuzzy memristance calculating method program for blood pressure hierarchical quantization is executed by a processor.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-only memory (ROM), a random access memory (RAM, randomAccessMemory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. The fuzzy memristor calculating method for blood pressure grading quantification is characterized by comprising the following steps of:
acquiring a blood pressure related data set based on a big data method, and preprocessing the blood pressure related data set according to a threshold high pressure judging method to obtain definition and classification of blood pressure levels in the data set;
normalizing the preprocessed blood pressure data by using a linear function, and scaling the blood pressure data in an equal proportion;
establishing a fuzzy semantic set according to a judging result of hypertension in a blood pressure data set, generating an input variable based on the fuzzy semantic set, and leading the input variable into a memristor fuzzy logic circuit to determine a membership function;
determining fuzzy rules through membership functions, obtaining fuzzy rule weights, converting the fuzzy rules stored in a rule base into mapping relations among fuzzy sets, obtaining final output results of memristor fuzzy logic circuits, determining hierarchical quantization results of blood pressure data, and performing precision evaluation on the hierarchical quantization results;
the memristor fuzzy logic circuit comprises a fuzzification circuit module, a rule base circuit module and an inference engine circuit module.
2. The fuzzy memristor computing method for blood pressure hierarchical quantization according to claim 1, wherein a blood pressure related data set is obtained based on a big data method, and the blood pressure related data set is preprocessed according to a threshold high pressure judging method to obtain definition and classification of blood pressure levels in the data set, specifically:
setting retrieval constraints through a preset age group and medical indexes, acquiring preset quantity of data information based on the retrieval constraints by utilizing a big data means, and constructing a blood pressure related data set;
screening systolic pressure, diastolic pressure and hypertension diagnosis results in the blood pressure related data set, determining systolic pressure and diastolic pressure thresholds according to a threshold hypertension judging method, and obtaining blood pressure levels of data in the blood pressure related data set according to comparison, wherein the hypertension diagnosis results comprise: normal, pre-hypertension and hypertension;
and determining the classification of the blood pressure data in the data set through the blood pressure level, setting a class label according to the classification result, and marking the blood pressure data in the blood pressure related data set.
3. The fuzzy memristor computing method for hierarchical quantization of blood pressure according to claim 1, wherein the preprocessed blood pressure related data is normalized by a linear function, and the blood pressure related data is scaled in equal proportion, specifically:
normalizing blood pressure data in a blood pressure related data set by using a linear function normalization method, and converting the blood pressure data into a range of [0,1] to realize the equal-proportion scaling of the blood pressure data;
the normalization processing formula of the blood pressure data is as follows:
Figure QLYQS_1
；
wherein ,
Figure QLYQS_2
representing normalized blood pressure data, +.>
Figure QLYQS_3
Representing blood pressure data->
Figure QLYQS_4
，/>
Figure QLYQS_5
Respectively represent the maximum value and the minimum value of the blood pressure data.
4. The fuzzy memristor computing method for hierarchical quantification of blood pressure according to claim 1, wherein a fuzzy semantic set is constructed according to a judgment result of hypertension in a blood pressure dataset, an input variable is generated based on the fuzzy semantic set, and the input variable is led into a memristor fuzzy logic circuit to determine membership functions, specifically:
dividing blood pressure data into three fuzzy semantic sets according to hypertension diagnosis results and category labels in blood pressure related data sets: in (a)
Figure QLYQS_6
High->
Figure QLYQS_7
High->
Figure QLYQS_8
；
Determining each fuzzy semantic set membership function corresponding to the systolic pressure and the diastolic pressure according to the triangular membership functions, and storing the fuzzy semantic set membership functions in each row of a memristor array recorded in a fuzzification circuit module, wherein memristors in the memristor array are subjected to pre-parallel programming through pulse voltages to obtain resistance information of each memristor;
the memristor array is composed of two groups of parallel wires which are mutually perpendicular, one memristor is connected with two cross wires at each cross point, and the calculation expression for programming the resistance value of the memristor according to the membership function is as follows:
Figure QLYQS_9
；
wherein ,
Figure QLYQS_10
representing the resistance of the corresponding memristor on vertical conductor j, +.>
Figure QLYQS_11
Representing the feedback resistance of the operational amplifier, +.>
Figure QLYQS_12
Representing the triangle membership function at the point +.>
Figure QLYQS_13
Membership degree of (3);
and taking the systolic pressure and the diastolic pressure as inputs of the memristor fuzzy circuit, wherein each input corresponds to three membership functions, and acquiring corresponding membership degrees through a fuzzy circuit module.
5. The fuzzy memristor computing method for hierarchical quantization of blood pressure according to claim 1, wherein the fuzzy rule is determined through membership functions, and the fuzzy rule weight is obtained, specifically:
the membership degree output by a fuzzification circuit module in the memristor fuzzy circuit is used as the input of a rule base circuit module, and 9 fuzzy rules are generated based on the middle, higher and higher semantic fuzzy sets corresponding to the systolic pressure and the diastolic pressure;
generating a fuzzy rule table according to the fuzzy rule and a division rule of hypertension in a blood pressure related data set, and generating a memristor fuzzy circuit IF-THEN rule base according to the fuzzy rule table;
and obtaining a weight value corresponding to the fuzzy rule according to the ratio of the membership product of the single fuzzy rule to the accumulated sum of all membership products of the fuzzy rule.
6. The fuzzy memristor computing method for hierarchical quantization of blood pressure according to claim 1, wherein the fuzzy rules stored in the rule base are converted into mapping relations among fuzzy sets, and final output results of the memristor fuzzy logic circuit are obtained, specifically:
obtaining a weighted average sum of input variables according to the posterior parameters and posterior parameter weights in the fuzzy rule in the fuzzy reasoning circuit module, and obtaining a final output result of the memristor fuzzy logic circuit based on the weighted average sum of the input variables and the fuzzy rule weights, wherein the calculation formula is as follows:
Figure QLYQS_14
；
wherein ,
Figure QLYQS_15
represent the firstkWeight value of bar rule +.>
Figure QLYQS_16
Representing a weighted average sum of the input variables +.>
Figure QLYQS_17
Representing the weight of the back-piece parameter, i.e. the weight of each input variable, +.>
Figure QLYQS_18
Representing the dimension of the input variable ∈>
Figure QLYQS_19
Indicating the final output result of the memristive fuzzy logic.
7. The fuzzy memristor computing method for hierarchical quantization of blood pressure according to claim 6, wherein the output precision is enabled to reach a preset standard by adjusting the weight of the back-piece parameter in the fuzzy reasoning circuit module, specifically:
acquiring 2 back-piece parameters corresponding to each fuzzy rule, and selecting normalized data in the blood pressure related data set to train the weight of the back-piece parameters;
the method comprises the steps that a back-piece parameter weight unit is formed by two memristors which are connected in opposite directions and a single-pole double-throw switch, and programming or calculation of the parameter weight unit is realized by the single-pole double-throw switch;
when the accuracy of the output signal of the reasoning engine circuit module reaches a preset threshold value, stopping training to obtain an optimal solution of the parameter weight of the back-part, opening a PMOS transistor, closing an NMOS transistor, enabling the parameter weight unit of the back-part to enter a programming process, otherwise, closing the PMOS transistor, and opening the NMOS transistor to continue calculation training;
and setting a memristor fuzzy logic circuit through the optimal solution of the back part parameter weight, and carrying out blood pressure grading quantization of the target user by utilizing the fuzzy logic circuit with the precision meeting the preset standard.
8. A fuzzy memristor computing system for hierarchical quantification of blood pressure, the system comprising: the device comprises a memory and a processor, wherein the memory comprises a fuzzy memristor calculation method program for blood pressure grading quantization, and the fuzzy memristor calculation method program for blood pressure grading quantization realizes the following steps when being executed by the processor:
acquiring a blood pressure related data set based on a big data method, and preprocessing the blood pressure related data set according to a threshold high pressure judging method to obtain definition and classification of blood pressure levels in the data set;
normalizing the preprocessed blood pressure data by using a linear function, and scaling the blood pressure data in an equal proportion;
establishing a fuzzy semantic set according to a judging result of hypertension in a blood pressure data set, generating an input variable based on the fuzzy semantic set, and leading the input variable into a memristor fuzzy logic circuit to determine a membership function;
determining fuzzy rules through membership functions, obtaining fuzzy rule weights, converting the fuzzy rules stored in a rule base into mapping relations among fuzzy sets, obtaining final output results of memristor fuzzy logic circuits, determining hierarchical quantization results of blood pressure data, and performing precision evaluation on the hierarchical quantization results;
the memristor fuzzy logic circuit comprises a fuzzification circuit module, a rule base circuit module and an inference engine circuit module.
9. The fuzzy memristor computing system for hierarchical quantification of blood pressure according to claim 8, wherein a fuzzy semantic set is constructed according to a judgment result of hypertension in a blood pressure dataset, and an input variable is generated based on the fuzzy semantic set to be imported into a memristor fuzzy logic circuit to determine membership functions, specifically:
dividing blood pressure data into three fuzzy semantic sets according to hypertension diagnosis results and category labels in blood pressure related data sets: in (a)
Figure QLYQS_20
High->
Figure QLYQS_21
High->
Figure QLYQS_22
；
Determining each fuzzy semantic set membership function corresponding to the systolic pressure and the diastolic pressure according to the triangular membership functions, and storing the fuzzy semantic set membership functions in each row of a memristor array recorded in a fuzzification circuit module, wherein memristors in the memristor array are subjected to pre-parallel programming through pulse voltages to obtain resistance information of each memristor;
the memristor array is composed of two groups of parallel wires which are mutually perpendicular, one memristor is connected with two cross wires at each cross point, and the calculation expression for programming the resistance value of the memristor according to the membership function is as follows:
Figure QLYQS_23
；
wherein ,
Figure QLYQS_24
representing the resistance of the corresponding memristor on vertical conductor j, +.>
Figure QLYQS_25
Representing the feedback resistance of the operational amplifier, +.>
Figure QLYQS_26
Representing the triangle membership function at the point +.>
Figure QLYQS_27
Membership degree of (3);
and taking the systolic pressure and the diastolic pressure as inputs of the memristor fuzzy circuit, wherein each input corresponds to three membership functions, and acquiring corresponding membership degrees through a fuzzy circuit module.
10. The fuzzy memristor computing system for hierarchical quantization of blood pressure according to claim 8, wherein the fuzzy rules stored in the rule base are converted into mapping relations among fuzzy sets, and final output results of the memristor fuzzy logic circuit are obtained, specifically:
obtaining a weighted average sum of input variables according to the posterior parameters and posterior parameter weights in the fuzzy rule in the fuzzy reasoning circuit module, and obtaining a final output result of the memristor fuzzy logic circuit based on the weighted average sum of the input variables and the fuzzy rule weights, wherein the calculation formula is as follows:
Figure QLYQS_28
；
wherein ,
Figure QLYQS_29
represent the firstkWeight value of bar rule +.>
Figure QLYQS_30
Representing a weighted average sum of the input variables +.>
Figure QLYQS_31
Representing the weight of the back-piece parameter, i.e. the weight of each input variable, +.>
Figure QLYQS_32
Representing the dimension of the input variable ∈>
Figure QLYQS_33
Indicating the final output result of the memristive fuzzy logic. />
CN202310190917.1A 2023-03-02 2023-03-02 Fuzzy memristor calculation method and system for hierarchical quantification of blood pressure Active CN116130046B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310190917.1A CN116130046B (en) 2023-03-02 2023-03-02 Fuzzy memristor calculation method and system for hierarchical quantification of blood pressure

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310190917.1A CN116130046B (en) 2023-03-02 2023-03-02 Fuzzy memristor calculation method and system for hierarchical quantification of blood pressure

Publications (2)

Publication Number Publication Date
CN116130046A true CN116130046A (en) 2023-05-16
CN116130046B CN116130046B (en) 2024-03-08

Family

ID=86295616

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310190917.1A Active CN116130046B (en) 2023-03-02 2023-03-02 Fuzzy memristor calculation method and system for hierarchical quantification of blood pressure

Country Status (1)

Country Link
CN (1) CN116130046B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013056319A1 (en) * 2011-10-21 2013-04-25 University Of Technology, Sydney A system and method for determining blood pressure
CN105551520A (en) * 2016-02-01 2016-05-04 福州大学 Programmable circuit based on memristor/metal-oxide-semiconductor field-effect transistor (MOSFET) and realization method thereof
CN107533668A (en) * 2016-03-11 2018-01-02 慧与发展有限责任合伙企业 For the hardware accelerator for the nodal value for calculating neutral net
KR20190114212A (en) * 2018-03-29 2019-10-10 국민대학교산학협력단 Single Column Memristor Crossbar and CMOS Activation Function Circuit for Binarized Neural Networks
US20200117539A1 (en) * 2018-10-12 2020-04-16 Western Digital Technologies, Inc. Storing deep neural network weights in non-volatile storage systems using vertical error correction codes
US20200218967A1 (en) * 2019-01-03 2020-07-09 Hewlett Packard Enterprise Development Lp Complex-Valued Neural Networks
CN113241196A (en) * 2021-05-17 2021-08-10 中国科学院自动化研究所 Remote medical treatment and grading monitoring system based on cloud-terminal cooperation
CN114819128A (en) * 2022-05-09 2022-07-29 清华大学 Variational reasoning method and device of Bayesian neural network based on memristor array
CN115345246A (en) * 2022-08-19 2022-11-15 广东技术师范大学 Intelligent liver cancer staging method and system based on T-S fuzzy semantics
CN115394444A (en) * 2022-09-06 2022-11-25 广东技术师范大学 Health condition hierarchical quantitative evaluation implementation method and system based on fuzzy theory

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013056319A1 (en) * 2011-10-21 2013-04-25 University Of Technology, Sydney A system and method for determining blood pressure
CN105551520A (en) * 2016-02-01 2016-05-04 福州大学 Programmable circuit based on memristor/metal-oxide-semiconductor field-effect transistor (MOSFET) and realization method thereof
CN107533668A (en) * 2016-03-11 2018-01-02 慧与发展有限责任合伙企业 For the hardware accelerator for the nodal value for calculating neutral net
KR20190114212A (en) * 2018-03-29 2019-10-10 국민대학교산학협력단 Single Column Memristor Crossbar and CMOS Activation Function Circuit for Binarized Neural Networks
US20200117539A1 (en) * 2018-10-12 2020-04-16 Western Digital Technologies, Inc. Storing deep neural network weights in non-volatile storage systems using vertical error correction codes
US20200218967A1 (en) * 2019-01-03 2020-07-09 Hewlett Packard Enterprise Development Lp Complex-Valued Neural Networks
CN113241196A (en) * 2021-05-17 2021-08-10 中国科学院自动化研究所 Remote medical treatment and grading monitoring system based on cloud-terminal cooperation
CN114819128A (en) * 2022-05-09 2022-07-29 清华大学 Variational reasoning method and device of Bayesian neural network based on memristor array
CN115345246A (en) * 2022-08-19 2022-11-15 广东技术师范大学 Intelligent liver cancer staging method and system based on T-S fuzzy semantics
CN115394444A (en) * 2022-09-06 2022-11-25 广东技术师范大学 Health condition hierarchical quantitative evaluation implementation method and system based on fuzzy theory

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
孙增圻: "基于T-S模型的模糊神经网络", 《清华大学学报（自然科学版）》, pages 76 - 80 *

Also Published As

Publication number Publication date
CN116130046B (en) 2024-03-08

Similar Documents

Publication Publication Date Title
Reddy et al. A deep neural networks based model for uninterrupted marine environment monitoring
CN107516110B (en) Medical question-answer semantic clustering method based on integrated convolutional coding
Jin et al. Pareto-based multiobjective machine learning: An overview and case studies
Bonissone A fuzzy sets based linguistic approach: theory and applications
Tuan et al. Dental diagnosis from X-ray images using fuzzy rule-based systems
Kulluk et al. Fuzzy DIFACONN-miner: A novel approach for fuzzy rule extraction from neural networks
Verikas et al. A general framework for designing a fuzzy rule-based classifier
Sarah et al. LSTM model to forecast time series for EC2 cloud price
Wang et al. Patient admission prediction using a pruned fuzzy min–max neural network with rule extraction
CN115394444A (en) Health condition hierarchical quantitative evaluation implementation method and system based on fuzzy theory
Binu et al. BFC: Bat algorithm based fuzzy classifier for medical data classification
Yedjour Extracting classification rules from artificial neural network trained with discretized inputs
CN116130046B (en) Fuzzy memristor calculation method and system for hierarchical quantification of blood pressure
Li et al. System identification of neural signal transmission based on backpropagation neural network
CN117009785A (en) Security monitoring method, device, server and system
Cao et al. Adopting improved Adam optimizer to train dendritic neuron model for water quality prediction
Anand et al. Hybrid data mining systems: the next generation
Pabian et al. Supervised Training of Siamese Spiking Neural Networks with Earth Mover's Distance
Xu et al. Deep multi-scale residual connected neural network model for intelligent athlete balance control ability evaluation
Kumar et al. A GA-based method for constructing TSK fuzzy rules from numerical data
Latha et al. Stock Price Prediction using HFTSF Algorithm
Xiong et al. A sparse connected long short-term memory with sharing weight for time series prediction
Tiwari et al. Leveraging Advanced Machine Learning Methods to Enhance Multilevel Fusion Score Level Computations
Goh et al. Fuzzy associative conjuncted maps network
Wu et al. An intelligent classification method with multiple time-scale analysis

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