CN111951948A - Nerve severe disease monitoring device - Google Patents
Nerve severe disease monitoring device Download PDFInfo
- Publication number
- CN111951948A CN111951948A CN202010838503.1A CN202010838503A CN111951948A CN 111951948 A CN111951948 A CN 111951948A CN 202010838503 A CN202010838503 A CN 202010838503A CN 111951948 A CN111951948 A CN 111951948A
- Authority
- CN
- China
- Prior art keywords
- simulation
- data
- monitoring
- sensing
- database
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012806 monitoring device Methods 0.000 title claims abstract description 8
- 210000005036 nerve Anatomy 0.000 title abstract description 12
- 201000010099 disease Diseases 0.000 title description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title description 2
- 238000012544 monitoring process Methods 0.000 claims abstract description 114
- 238000012545 processing Methods 0.000 claims abstract description 87
- 238000004088 simulation Methods 0.000 claims description 182
- 210000004556 brain Anatomy 0.000 claims description 97
- 239000011159 matrix material Substances 0.000 claims description 46
- 238000013527 convolutional neural network Methods 0.000 claims description 30
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 26
- 238000007917 intracranial administration Methods 0.000 claims description 26
- 238000001690 micro-dialysis Methods 0.000 claims description 26
- 229910052760 oxygen Inorganic materials 0.000 claims description 26
- 239000001301 oxygen Substances 0.000 claims description 26
- 230000008344 brain blood flow Effects 0.000 claims description 21
- 230000000926 neurological effect Effects 0.000 claims description 10
- 230000036285 pathological change Effects 0.000 claims description 4
- 231100000915 pathological change Toxicity 0.000 claims description 4
- 238000002567 electromyography Methods 0.000 claims description 2
- 239000000203 mixture Substances 0.000 claims 1
- 230000001537 neural effect Effects 0.000 claims 1
- 239000002994 raw material Substances 0.000 claims 1
- 238000000034 method Methods 0.000 description 17
- 238000005070 sampling Methods 0.000 description 12
- 238000012549 training Methods 0.000 description 7
- 230000002490 cerebral effect Effects 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 5
- 230000001360 synchronised effect Effects 0.000 description 5
- 230000003727 cerebral blood flow Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000003780 insertion Methods 0.000 description 3
- 230000037431 insertion Effects 0.000 description 3
- 210000003205 muscle Anatomy 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 230000017531 blood circulation Effects 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a severe nerve monitoring device which comprises a monitoring input channel, a monitoring analysis processing unit and a control unit, wherein the monitoring input channel is used for acquiring original multi-type sensing data and providing the data to the monitoring analysis processing unit as a basis for monitoring; the monitoring analysis processing unit is used for acquiring original multi-type sensing data from the monitoring input channel, analyzing the relation among the multi-type sensing data, acquiring more upper-level data according to the relation among the multi-type sensing data, and sending the more upper-level data to the monitoring feedback unit in an intermediate quantity form; the monitoring, analyzing and processing unit at least comprises an analog database, and the analog database is used for supporting the acquisition of higher-level data through the relation among the multi-type sensing data; the monitoring feedback output unit is used for analyzing the intermediate quantity into understandable data and displaying the result of the relation among the multi-type sensing data; the monitoring analysis processing unit is respectively connected with the monitoring input channel and the monitoring feedback output unit; the intermediate variable is in particular a data characteristic of a particular form.
Description
Technical Field
The invention relates to nerve severe monitoring, in particular to a nerve severe monitoring device.
Background
The technology in the field of nerve critical monitoring, for example, the nerve critical data acquisition equipment disclosed in chinese utility model CN 201621229538.0; the device comprises a rack, wherein a case is arranged on the rack, a data processing device is arranged in the case, and the data processing device is connected with a plug-in type access device; and the rack is also provided with a display device, and the display device is connected with the data processing device. The frame includes: a vertical rod is arranged on a supporting leg, and the display device is arranged at the top of the vertical rod; the case is fixed on the side wall of the upright rod. The plug-in access device comprises: an inlet, a plurality of plug-in component grooves and an outlet. A plurality of the insert grooves are respectively fixed with: the system comprises an intracranial pressure monitor signal conversion module and a bedside monitor signal conversion module. The side wall of the case is provided with an insertion opening, and the plurality of plug-in slots are installed in the insertion opening and face the insertion opening. According to the technical scheme, the plug-in type access device is arranged, so that connection of various sensors is realized. The nerve severe monitoring system disclosed in chinese utility model CN201621229680.5 comprises a machine body, a data processing device and a connecting device are installed in the machine body, the data processing device is connected with the connecting device, and the connecting device has a plurality of interfaces; the data processing device is connected with the display device and the networking equipment, and is also provided with an expansion interface; the data processing apparatus communicates with the server through a networking device. The plurality of interfaces have: the system comprises an intracranial pressure monitor signal interface, a bedside monitor signal interface, a transcranial Doppler signal interface, an electroencephalogram signal interface, a brain temperature module interface, a brain oxygen module interface, a brain microdialysis module interface and a brain blood flow module interface. The data processing device is also connected with a camera. The expansion interface is connected with a printer. The body includes: a display is installed on a base through a pole setting, a quick-witted case is installed to the lateral wall of pole setting, data processing device connecting device all installs in quick-witted incasement, data processing device with the display is connected. An operating platform is further installed on one side of the upright rod, and a handle is arranged on the operating platform. The display device is a touch screen.
According to the technical scheme, the problem that a monitoring system in the prior art cannot acquire data comprehensively is solved, and the data of various sensors is led into the data processing device through the connecting device with the plurality of sensor interfaces. The invention discloses a nerve intensive care system and a method for realizing synchronous monitoring of human body multi-parameter signals, which are disclosed by CN200610061231.9 in China, wherein the nerve intensive care system comprises a signal acquisition system and a processing/display system for processing and displaying the acquired signals, and the signal acquisition system is connected with the processing/display system through an interface; the signal acquisition system includes: the EEG module is used for acquiring EEG signals and/or the MP module is used for acquiring multi-parameter vital sign signals; the TCD module, the EEG module and the MP module respectively comprise at least one signal acquisition channel; the sampling and holding circuits are respectively connected with the output ends of the signal acquisition channels and synchronously sample the signals output by the acquisition channels; the input ends of the A/D converters are respectively connected with the output end of the sampling hold circuit and are used for converting analog signals output by sampling into digital signals; and the control module is in communication connection with the interface and is used for generating an A/D conversion control signal for controlling the A/D converter to perform analog-to-digital conversion and also generating a sampling control signal synchronous with the same clock pulse, wherein the sampling control signal is used for controlling each sampling hold circuit to synchronously acquire one sampling point of the TCD signal, the EEG signal and/or the MP signal. The method for realizing the synchronous monitoring of the human body multi-parameter signals comprises the following steps: collecting TCD signals and EEG signals and/or MP signals, and setting sampling control signals synchronous with a clock pulse; controlling each signal channel to synchronously sample the TCD signal, the EEG signal and the MP signal by using the sampling control signal, so that the sampling points of each signal channel are the same; carrying out A/D conversion on analog signal sampling points obtained by synchronous sampling to obtain digital signals and then caching and outputting the digital signals; the digital signal is processed and displayed on screen by a processing/display system. The technology aims at synchronously acquiring and displaying the TCD blood flow signal, the EEG electrophysiological signal and the MP vital sign signal on the same screen, synchronously monitoring the TCD blood flow signal, the EEG electrophysiological signal and the MP vital sign signal, providing comprehensive and valuable monitoring and diagnosis information for clinical nervous severe patients, and hopefully improving the monitoring quality and treatment level of the severe patients and reducing the death rate.
The above monitoring devices related to severe neurological conditions in the prior art are basically simple to expand the types of sensors and data acquisition ports of the sensors or synchronously acquire information of various sensors, and all of the devices are used for simply acquiring and reproducing severe neurological condition monitoring data; in fact, in the prior art, the data processing requirements for the sensors are even greater for obtaining more superior data processing for the links among multiple types of sensing data, and the fundamental purpose is to improve the intelligence and efficiency of monitoring, however, no technology can meet the requirements at present.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides the severe nerve monitoring device, which solves the problem that the data processing of the sensor in the prior art even the connection among multiple types of sensing data meets higher-level data processing requirements, and improves the intellectualization and high efficiency of monitoring.
The technical scheme adopted by the invention for solving the technical problems is as follows:
the nerve severe monitoring device comprises a monitoring input channel, a monitoring analysis processing unit and a plurality of monitoring input channels, wherein the monitoring input channel is used for acquiring original multi-type sensing data and providing the data to the monitoring analysis processing unit as a monitoring basis; the monitoring analysis processing unit is used for acquiring original multi-type sensing data from the monitoring input channel, analyzing the relation among the multi-type sensing data, acquiring more upper-level data according to the relation among the multi-type sensing data, and sending the more upper-level data to the monitoring feedback unit in an intermediate quantity form; the system is also used for acquiring original multi-type sensing data to complete updating; the monitoring, analyzing and processing unit at least comprises an analog database, and the analog database is used for supporting the acquisition of higher-level data through the relation among the multi-type sensing data; the monitoring feedback output unit is used for analyzing the intermediate quantity into understandable data and displaying the result of the relation among the multi-type sensing data; the monitoring analysis processing unit is respectively connected with the monitoring input channel and the monitoring feedback output unit; the intermediate parameter is specifically a data characterizing quantity in a specific form.
In a preferred or alternative embodiment, the multiple types of sensing include intracranial pressure monitor electrical signal sensing, transcranial doppler electrical signal sensing, electroencephalogram electrical signal sensing, brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing, brain electromyography sensing.
In a preferred or optional embodiment, the monitoring analysis processing unit includes an updating module and an analysis module, the updating module is configured to process original multi-type sensing data into an intermediate parameter, process meaning expression data of a monitored person mapped by the multi-type sensing data obtained through statistics into a second parameter, and characterize a data format of the intermediate parameter into matrix data and specifically into a matrix parameter group; processing matrix parameter groups of the intermediate parameters, distributing a numerical value to the intermediate parameters in each matrix parameter group, wherein the sum of all the intermediate parameters of each matrix parameter group is one, and dividing the matrix parameter groups into a simulation group and an identification group; said authentication group is labeled with a second parameter; the simulation database of the monitoring analysis processing unit is at least internally provided with a plurality of simulation sub-databases, and the analysis module is used for configuring basic parameters for the simulation database, then inputting the matrix parameter group into the simulation database and acquiring a second parameter; the updating module is also used for calculating in the simulation database by using the simulation group, changing the parameters of the simulation database and then identifying the simulation correct coefficient of the simulation database by using the identification group; then at least changing a parameter of a simulation sub-library, configuring a plurality of parameters of the simulation sub-library, namely obtaining a plurality of new simulation sub-libraries, identifying a simulation correct coefficient of each new simulation sub-library by using an identification group, selecting a new simulation sub-library with the highest correct coefficient to replace the original parameter-changed simulation sub-library, then identifying a simulation correct coefficient of the simulation database by using the identification group, judging whether the simulation correct coefficient is higher than the simulation correct coefficient of the last simulation database, if not, terminating the simulation, and if so, continuing the cycle simulation until obtaining the simulation database with the highest correct coefficient; the operation of the simulation group in the simulation database is to obtain the superior characteristics of the simulation group data by using the simulation database, change the parameters of the simulation database and actually map the superior characteristics of the simulation group data by using the parameters of the simulation database; the analysis module is also used for processing the original multi-type sensing data into intermediate parameters, inputting the intermediate parameters into the simulation database and then starting simulation to obtain second parameters corresponding to the intermediate variables.
In a preferred or optional embodiment, the simulation database is a convolutional neural network model database, and the simulation sub-library is a convolutional layer.
In a preferred or alternative embodiment, the processing of the raw multi-type sensing data into intermediate quantities comprises: for each unit of multi-type sensing data, the multi-type sensing data is digitalized, then a weighting coefficient is assigned to each type of sensing data, and all the digitalized sensing data are arranged into matrix data.
In a preferred or alternative embodiment, processing the raw multi-type sensing data into the intermediate quantities further comprises assigning a dynamic weighting factor to each type of sensing data.
In a preferred or alternative embodiment, processing the raw multi-type sensing data into the intermediate quantities further comprises changing an order of arrangement of the digitized sensing data in the matrix data.
In a preferred or alternative embodiment, the meaning expression data of the monitored person mapped by the statistically acquired multi-type sensing data is processed into a second parameter, wherein the second parameter is characterized by the meaning requirement of the monitored person.
In a preferred or alternative embodiment, the second parameter is also characteristic of the physical pathology and the need for first aid of the monitored person.
The invention has the beneficial effects that the method solves the problem that the processing of the data of the sensor in the prior art, even the relation between the multi-type sensing data, obtains higher-level data processing requirements, and improves the intellectualization and the high efficiency of monitoring. In the concrete implementation, the established simulation database can be practically used for acquiring more superior data of the relation among the multi-type sensing data, the original multi-type sensing data is processed into an intermediate parameter, the meaning expression data of the monitored person mapped by the multi-type sensing data acquired through statistics is processed into a second parameter, the data format of the intermediate parameter is represented as matrix data, and then the more superior data of the relation among the multi-type sensing data is acquired through processing the intermediate parameter, particularly through the simulation process. The simulation database is used for obtaining the superior characteristics of the simulation group data and changing the parameters of the simulation database, so that the simulation database can be optimized and iterated continuously, and the data processing is more accurate; the simulation database adopts a convolutional neural network model database, and the simulation sub-database adopts convolutional layers to improve the processing efficiency and maturity of data and reduce the cost.
Detailed Description
In specific implementation, the embodiment of the present application includes:
the monitoring input channel is used for acquiring original multi-type sensing data and providing the original multi-type sensing data to the monitoring analysis processing unit as a monitoring basis, and is also used for acquiring the original multi-type sensing data and providing the original multi-type sensing data to the monitoring analysis processing unit as an updating basis of the monitoring analysis unit;
the monitoring analysis processing unit is used for acquiring original multi-type sensing data from the monitoring input channel, analyzing the relation among the multi-type sensing data, acquiring more upper-level data according to the relation among the multi-type sensing data, and sending the more upper-level data to the monitoring feedback unit in an intermediate quantity form; the system is also used for acquiring original multi-type sensing data to complete updating;
the monitoring, analyzing and processing unit at least comprises an analog database, and the analog database is used for supporting the acquisition of higher-level data through the relation among the multi-type sensing data;
the monitoring feedback output unit is used for analyzing the intermediate quantity into understandable data and displaying the result of the relation among the multi-type sensing data;
the monitoring analysis processing unit is respectively connected with the monitoring input channel and the monitoring feedback output unit; the intermediate parameter is specifically a data characterizing quantity in a specific form.
In an implementation, the updating of the monitoring and analyzing unit is specifically that the monitoring input channel acquires original multi-type sensing data and provides the original multi-type sensing data to the monitoring and analyzing processing unit as a basis for updating the monitoring and analyzing unit, and then the monitoring and analyzing processing unit acquires the original multi-type sensing data to complete the updating.
The monitoring of the monitoring analysis processing unit is specifically that the monitoring input channel acquires original multi-type sensing data and provides the original multi-type sensing data to the monitoring analysis processing unit as a basis for monitoring, then the monitoring analysis processing unit acquires the original multi-type sensing data from the monitoring input channel and analyzes the relation among the multi-type sensing data, and acquires higher-level data from the relation among the multi-type sensing data (the simulation database of the monitoring analysis processing unit acquires higher-level data from the relation among the multi-type sensing data), and sends the higher-level data to the monitoring feedback unit in an intermediate quantity form; the monitoring feedback output unit analyzes the intermediate quantity into understandable data and displays the result of the relation between the multi-type sensing data.
The multiple types of sensors comprise intracranial pressure monitor electric signal sensing, transcranial Doppler electric signal sensing, electroencephalogram electric signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing and brain electromyographic signal sensing; therefore, in the specific implementation, the updating of the monitoring and analyzing unit is specifically that the monitoring input channel acquires the original electrical signal sensing of the intracranial pressure monitor, transcranial doppler electrical signal sensing, electroencephalogram electrical signal sensing, brain temperature sensing, cerebral oxygen sensing, brain microdialysis sensing, cerebral blood flow sensing and brain and electromyogram signal sensing data and provides the data to the monitoring and analyzing processing unit as the basis for updating the monitoring and analyzing unit, and then the monitoring and analyzing processing unit acquires the original electrical signal sensing of the intracranial pressure monitor, transcranial doppler electrical signal sensing, electroencephalogram electrical signal sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing and brain and electromyogram signal sensing data to complete the updating.
The monitoring of the monitoring analysis processing unit is specifically that the monitoring input channel acquires original intracranial pressure monitor electrical signal sensing, transcranial Doppler electrical signal sensing, electroencephalogram electrical signal sensing brain temperature sensing, cerebral oxygen sensing, brain microdialysis sensing, cerebral blood flow sensing and brain and muscle electrical signal sensing data and provides the data to the monitoring analysis processing unit as the basis for monitoring, and then the monitoring analysis processing unit acquires the original intracranial pressure monitor electrical signal sensing, transcranial Doppler electrical signal sensing, electroencephalogram electrical signal sensing brain temperature sensing, cerebral oxygen sensing, brain microdialysis sensing, cerebral blood flow sensing and brain and muscle electrical signal sensing data from the monitoring input channel and analyzes the intracranial pressure monitor electrical signal sensing, transcranial Doppler electrical signal sensing, electroencephalogram electrical signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing, brain and muscle electrical signal sensing data and analyzes the intracranial pressure monitor electrical signal sensing, transcranial Doppler electrical signal sensing, brain electrical signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis, The relation among the brain and electromyographic signal sensing data is obtained by the relation among an intracranial pressure monitor electric signal sensor, a transcranial Doppler electric signal sensor, an electroencephalogram electric signal sensor, a brain temperature sensor, a brain oxygen sensor, a brain microdialysis sensor, a brain blood flow sensor and the brain and electromyographic signal sensing data (the simulation database of the monitoring analysis processing unit obtains higher-level data by the relation among the intracranial pressure monitor electric signal sensor, the transcranial Doppler electric signal sensor, the electroencephalogram electric signal sensor, the brain oxygen sensor, the brain microdialysis sensor, the brain blood flow sensor and the brain and electromyographic signal sensing data), and the higher-level data is sent to the monitoring feedback unit in a medium quantity form; the monitoring feedback output unit analyzes the intermediate quantity into understandable data and displays the results of the relation among the intracranial pressure monitor electric signal sensing, transcranial Doppler electric signal sensing, electroencephalogram electric signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing and brain and electromyogram electric signal sensing data. The problem that the processing of data of the sensor in the prior art even the relation among the multi-type sensing data obtains more superior data processing requirements is solved, and the monitoring intelligence and the monitoring efficiency are improved.
In specific implementation, the monitoring analysis processing unit comprises an updating module and an analysis module, wherein the updating module is used for processing original multi-type sensing data into an intermediate parameter, processing the meaning expression data of the monitored person mapped by the multi-type sensing data obtained through statistics into a second parameter, and representing the data format of the intermediate parameter as matrix data and specifically as a matrix parameter group; processing matrix parameter groups of the intermediate parameters, distributing a numerical value to the intermediate parameters in each matrix parameter group, enabling the sum of all the intermediate parameters of each matrix parameter group to be 1, and dividing the matrix parameter groups into simulation groups and identification groups; said authentication group is labeled with a second parameter; the simulation database of the monitoring analysis processing unit is at least internally provided with a plurality of simulation sub-databases, and the analysis module is used for configuring basic parameters for the simulation database, then inputting the matrix parameter group into the simulation database and acquiring a second parameter; the updating module is also used for calculating in the simulation database by using the simulation group, changing the parameters of the simulation database and then identifying the simulation correct coefficient of the simulation database by using the identification group; then at least changing a parameter of a simulation sub-library, configuring a plurality of parameters of the simulation sub-library, namely obtaining a plurality of new simulation sub-libraries, identifying a simulation correct coefficient of each new simulation sub-library by using an identification group, selecting a new simulation sub-library with the highest correct coefficient to replace the original parameter-changed simulation sub-library, then identifying a simulation correct coefficient of the simulation database by using the identification group, judging whether the simulation correct coefficient is higher than the simulation correct coefficient of the last simulation database, if not, terminating the simulation, and if so, continuing the cycle simulation until obtaining the simulation database with the highest correct coefficient; the operation of the simulation group in the simulation database is to obtain the superior characteristics of the simulation group data by using the simulation database, change the parameters of the simulation database and actually map the superior characteristics of the simulation group data by using the parameters of the simulation database; the analysis module is also used for processing the original multi-type sensing data into intermediate parameters, inputting the intermediate parameters into the simulation database and then starting simulation to obtain second parameters corresponding to the intermediate variables;
establishing a simulation database of the monitoring analysis processing unit, at least the following steps:
the updating module processes original multi-type sensing data into intermediate parameters, processes the meaning expression data of the monitored person mapped by the multi-type sensing data obtained by statistics into second parameters, and represents the data format of the intermediate parameters into matrix data and specifically into a matrix parameter group;
the updating module processes the matrix parameter groups of the intermediate parameters, assigns a value to the intermediate parameters in each matrix parameter group, the sum of all the intermediate parameters of each matrix parameter group is 1, and divides the matrix parameter groups into a simulation group and an identification group:
said authentication group is labeled with a second parameter;
at least setting a plurality of simulation sub-databases in the established simulation database, configuring basic parameters for the simulation database, inputting the matrix parameter group into the simulation database and acquiring a second parameter;
the updating module uses the simulation group to operate in the simulation database and change the parameters of the simulation database, and then uses the identification group to identify the simulation correct coefficient of the simulation database; then at least changing a parameter of a simulation sub-library, configuring a plurality of parameters of the simulation sub-library, namely obtaining a plurality of new simulation sub-libraries, identifying a simulation correct coefficient of each new simulation sub-library by using an identification group, selecting a new simulation sub-library with the highest correct coefficient to replace the original parameter-changed simulation sub-library, then identifying a simulation correct coefficient of the simulation database by using the identification group, judging whether the simulation correct coefficient is higher than the simulation correct coefficient of the last simulation database, if not, terminating the simulation, and if so, continuing the cycle simulation until obtaining the simulation database with the highest correct coefficient; the operation of the simulation group in the simulation database is to obtain the superior characteristics of the simulation group data by using the simulation database, change the parameters of the simulation database and actually map the superior characteristics of the simulation group data by using the parameters of the simulation database; specifically, the simulation database adopts a convolutional neural network model database, and the simulation sub-database adopts convolutional layers.
Therefore, the convolutional neural network model database of the monitoring analysis processing unit is established by at least the following steps:
the updating module processes original intracranial pressure monitor electrical signal sensing, transcranial Doppler electrical signal sensing, electroencephalogram electrical signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing and brain electromyogram electrical signal sensing data into intermediate parameters, processes statistically acquired meaning expression data of a monitored person mapped by the intracranial pressure monitor electrical signal sensing, transcranial Doppler electrical signal sensing, electroencephalogram electrical signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing and brain electromyogram electrical signal sensing data into second parameters, and represents the data format of the intermediate parameters into matrix data and specifically represents the matrix parameter group;
the updating module processes the matrix parameter groups of the intermediate parameters, assigns a value to the intermediate parameters in each matrix parameter group, the sum of all the intermediate parameters of each matrix parameter group is 1, and divides the matrix parameter groups into a simulation group and an identification group:
said authentication group is labeled with a second parameter;
at least setting a plurality of convolution layers in the established convolutional neural network model database, configuring basic parameters for the convolutional neural network model database, inputting the matrix parameter group into the convolutional neural network model database and acquiring a second parameter;
the updating module uses the simulation group to operate in the convolutional neural network model database and changes the parameters of the convolutional neural network model database, and then uses the identification group to identify the simulation correct coefficient of the convolutional neural network model database; then at least changing the parameter of one convolution layer, configuring a plurality of parameters of the convolution layer, namely obtaining a plurality of new convolution layers, identifying the simulation correct coefficient of each new convolution layer by using an identification group, selecting a new convolution layer with the highest correct coefficient to replace the original convolution layer with the changed parameter, then identifying the simulation correct coefficient of the convolutional neural network model database by using the identification group, judging whether the simulation correct coefficient is higher than the simulation correct coefficient of the last convolutional neural network model database, if not, terminating the simulation, and if so, continuing the circular simulation until obtaining the convolutional neural network model database with the highest correct coefficient; the operation of the simulation group in the convolutional neural network model database is specifically to use the convolutional neural network model database to obtain the superior characteristics of the simulation group data and change the parameters of the convolutional neural network model database, and the parameters of the convolutional neural network model database actually map the superior characteristics of the simulation group data.
The simulation process described above is configured as a training learning of a convolutional neural network model database.
More specifically, the updating module uses the simulation group to operate in the convolutional neural network model database and changes the parameters of the convolutional neural network model database, and then uses the identification group to identify the correct training and learning coefficient of the convolutional neural network model database; then at least changing the parameter of one convolution layer, configuring a plurality of parameters of the convolution layer, namely obtaining a plurality of new convolution layers, identifying the correct training and learning coefficient of each new convolution layer by using an identification group, selecting a new convolution layer with the highest correct coefficient to replace the original convolution layer with the changed parameter, then identifying the correct training and learning coefficient of the convolutional neural network model database by using the identification group, judging whether the correct training and learning coefficient is higher than the correct training and learning coefficient of the last convolutional neural network model database, if not, terminating the simulation, if so, continuing the cyclic training and learning until obtaining the convolutional neural network model database with the highest correct coefficient; the operation of the simulation group in the convolutional neural network model database is specifically to use the convolutional neural network model database to obtain the superior characteristics of the simulation group data and change the parameters of the convolutional neural network model database, and the parameters of the convolutional neural network model database actually map the superior characteristics of the simulation group data.
The simulation database established in the above manner can be practically used for acquiring more superior data of the relation between the multi-type sensing data, and specifically, the original multi-type sensing data is processed into an intermediate parameter, the meaning expression data of the monitored person mapped by the multi-type sensing data acquired by statistics is processed into a second parameter, the data format of the intermediate parameter is represented as matrix data, and then the superior characteristics are acquired through the processing of the intermediate parameter, particularly through the simulation process, so that the more superior data of the relation between the multi-type sensing data is acquired.
Acquiring the upper features of the simulation group data by using a simulation database, changing parameters of the simulation database, and actually mapping the upper features of the simulation group data by using the parameters of the simulation database; the simulation database adopts a convolutional neural network model database, and the simulation sub-database adopts convolutional layers to improve the processing efficiency and maturity of data and reduce the cost.
In implementation, the processing of the original multi-type sensing data into the intermediate parameters includes: for multi-type sensing data of each unit, digitizing the multi-type sensing data, then assigning a weight coefficient to each type of sensing data, and arranging all digitized sensing data into matrix data; namely, the original intracranial pressure monitor electric signal sensing, transcranial Doppler electric signal sensing, electroencephalogram electric signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing and brain electromyogram electric signal sensing are processed into intermediate parameters, and the method comprises the following steps: for each unit of intracranial pressure monitor electrical signal sensing, transcranial Doppler electrical signal sensing, electroencephalogram electrical signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing, brain electromyogram signal sensing, intracranial pressure monitor electrical signal sensing, transcranial Doppler electrical signal sensing, electroencephalogram electrical signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing, brain electromyogram signal sensing are digitized, then a weight coefficient is distributed to each sensing data, all the digitized sensing data are arranged into matrix data, for example, the intracranial pressure monitor electrical signal sensing, transcranial electrical signal sensing, electroencephalogram electrical signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing, brain electromyogram signal sensing importance degree and relation degree of the brain electromyogram signal sensing and the brain electromyogram signal sensing are used as the intracranial pressure electrical signal sensing, transcranial Doppler sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing, brain electromyogram signal sensing, and brain electromyogram signal sensing, The transcranial Doppler electrical signal sensing, the electroencephalogram electrical signal sensing, the brain temperature sensing, the brain oxygen sensing, the brain microdialysis sensing, the brain blood flow sensing and the brain electromyographic signal sensing are distributed with weight coefficients from large to small, and the weight coefficients are used as the basis for digitizing the sensing data.
In the implementation, a dynamic weight coefficient is allocated to each sensing data; the dynamic weight coefficient is distributed to each intracranial pressure monitor electrical signal sensing, transcranial Doppler electrical signal sensing, electroencephalogram electrical signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing and brain electromyographic signal sensing data, and the intermediate parameter can be continuously optimized by configuring the weight coefficient as dynamic change.
In the implementation, the method further comprises the step of changing the arrangement sequence of the numerical sensing data in the matrix data; the arrangement sequence of digitized intracranial pressure monitor electrical signal sensing, transcranial Doppler electrical signal sensing, electroencephalogram electrical signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing and brain electromyogram electrical signal sensing data in matrix data is changed, and intermediate parameters can also be optimized.
In the implementation, the meaning expression data of the monitored person mapped by the multi-type sensing data obtained through statistics is processed into a second parameter, wherein the second parameter represents the idea requirement of the monitored person; the meaning expression data of the monitored person is mapped by statistically acquired electrical signal sensing of an intracranial pressure monitor, transcranial Doppler electrical signal sensing, electroencephalogram electrical signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing and brain electromyographic signal sensing data respectively, and is processed into second parameters, wherein the second parameters represent the meaning requirement of the monitored person, for example, certain determined multi-type sensing data expresses the monitored person to lie down, correspondingly, the meaning expression data of the monitored person is that the corresponding meaning requirement is to lie down, and the second parameters are data correspondingly marked as 'the monitored person is to lie down'.
More specifically, in the implementation, the second parameter further characterizes the physical and pathological changes and the need of first aid of the monitored person, and the second parameter is substantially the data corresponding to the mark "the physical and pathological changes of the monitored person specifically," the data of "the first aid of the monitored person specifically needs" and the data of the second parameter,
because the analysis module is used for processing original multi-type sensing data into intermediate parameters, inputting the intermediate parameters into the simulation database and then starting simulation to obtain second parameters corresponding to the intermediate variables, the analysis module processes the original intracranial pressure monitor electrical signal sensing, transcranial Doppler electrical signal sensing, electroencephalogram electrical signal sensing, cerebral oxygen sensing, cerebral microdialysis sensing, cerebral blood flow sensing and electroencephalogram electrical signal sensing data into the intermediate parameters in implementation, inputs the intermediate parameters into the simulation database and then starts simulation to obtain the second parameters corresponding to the intermediate variables, and the essence of the second parameters is data corresponding to the mark of ' the specific body pathological change of the monitored person ', the data of ' the specific emergency of the monitored person ', the specific need of the monitored person ', the data of the specific need of the monitored person, therefore, the upper-level data can be obtained according to the electrical signal sensing of the intracranial pressure monitor, the transcranial Doppler electrical signal sensing, the electroencephalogram electrical signal sensing, the brain temperature sensing, the brain oxygen sensing, the brain microdialysis sensing, the brain blood flow sensing and the brain electromyogram electrical signal sensing data.
Finally, it should be noted that the above examples are only used to illustrate the technical solutions of the present invention and not to limit the same; although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art will understand that: modifications to the specific embodiments of the invention or equivalent substitutions for parts of the technical features may be made; without departing from the spirit of the present invention, it is intended to cover all aspects of the invention as defined by the appended claims.
Claims (9)
1. The utility model provides a neural severe monitoring devices, characterized by: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the monitoring input channel is used for acquiring original multi-type sensing data and providing the data to the monitoring analysis processing unit as a monitoring basis, and is also used for acquiring the original multi-type sensing data and providing the data to the monitoring analysis processing unit as an updating basis of the monitoring analysis unit;
the monitoring analysis processing unit is used for acquiring original multi-type sensing data from the monitoring input channel, analyzing the relation among the multi-type sensing data, acquiring more upper-level data according to the relation among the multi-type sensing data, and sending the more upper-level data to the monitoring feedback unit in an intermediate quantity form; the system is also used for acquiring original multi-type sensing data to complete updating; the monitoring, analyzing and processing unit at least comprises an analog database, and the analog database is used for supporting the acquisition of higher-level data through the relation among the multi-type sensing data;
the monitoring feedback output unit is used for analyzing the intermediate quantity into understandable data and displaying the result of the relation among the multi-type sensing data; the monitoring analysis processing unit is respectively connected with the monitoring input channel and the monitoring feedback output unit; the intermediate parameter is specifically a data characterizing quantity in a specific form.
2. A neurological severe monitoring apparatus according to claim 1, wherein: the multiple types of sensors comprise intracranial pressure monitor electric signal sensing, transcranial Doppler electric signal sensing, electroencephalogram electric signal sensing brain temperature sensing, brain oxygen sensing, brain microdialysis sensing, brain blood flow sensing and brain electromyography electric signal sensing.
3. A neurological severe monitoring apparatus according to claim 1, wherein: the monitoring analysis processing unit comprises an updating module and an analysis module, wherein the updating module is used for processing original multi-type sensing data into intermediate parameters, processing the meaning expression data of a monitored person mapped by the multi-type sensing data obtained through statistics into second parameters, and representing the data format of the intermediate parameters into matrix data and specifically representing the matrix data into a matrix parameter group; processing matrix parameter groups of the intermediate parameters, distributing a numerical value to the intermediate parameters in each matrix parameter group, wherein the sum of all the intermediate parameters of each matrix parameter group is one, and dividing the matrix parameter groups into a simulation group and an identification group; said authentication group is labeled with a second parameter; the simulation database of the monitoring analysis processing unit is at least internally provided with a plurality of simulation sub-databases, and the analysis module is used for configuring basic parameters for the simulation database, then inputting the matrix parameter group into the simulation database and acquiring a second parameter; the updating module is also used for calculating in the simulation database by using the simulation group, changing the parameters of the simulation database and then identifying the simulation correct coefficient of the simulation database by using the identification group; then at least changing a parameter of a simulation sub-library, configuring a plurality of parameters of the simulation sub-library, namely obtaining a plurality of new simulation sub-libraries, identifying a simulation correct coefficient of each new simulation sub-library by using an identification group, selecting a new simulation sub-library with the highest correct coefficient to replace the original parameter-changed simulation sub-library, then identifying a simulation correct coefficient of the simulation database by using the identification group, judging whether the simulation correct coefficient is higher than the simulation correct coefficient of the last simulation database, if not, terminating the simulation, and if so, continuing the cycle simulation until obtaining the simulation database with the highest correct coefficient; the operation of the simulation group in the simulation database is to obtain the superior characteristics of the simulation group data by using the simulation database, change the parameters of the simulation database and actually map the superior characteristics of the simulation group data by using the parameters of the simulation database; the analysis module is also used for processing the original multi-type sensing data into intermediate parameters, inputting the intermediate parameters into the simulation database and then starting simulation to obtain second parameters corresponding to the intermediate variables.
4. A neurological severe monitoring apparatus according to claim 3, wherein: the simulation database adopts a convolutional neural network model database, and the simulation sub-database adopts convolutional layers.
5. A neurological severe monitoring apparatus according to claim 3, wherein: processing original multi-type sensing data into intermediate parameters, comprising: for each unit of multi-type sensing data, the multi-type sensing data is digitalized, then a weighting coefficient is assigned to each type of sensing data, and all the digitalized sensing data are arranged into matrix data.
6. A neurological severe monitoring apparatus according to claim 5, wherein: the processing of the raw multi-type sensing data into the intermediate parameter further comprises assigning a dynamic weighting factor to each type of sensing data.
7. A neurological severe monitoring apparatus according to claim 5, wherein: processing the raw multi-type sensing data into the intermediate parameter further includes changing an arrangement order of the digitized sensing data in the matrix data.
8. A neurological severe monitoring apparatus according to claim 3, wherein: and statistically processing the meaning expression data of the monitored person mapped by the multi-type sensing data into a second parameter, wherein the second parameter represents the idea requirement of the monitored person.
9. A neurological severe monitoring apparatus according to claim 3, wherein: the second parameter is also characteristic of the physical and pathological changes and the need for first aid of the monitored person.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010838503.1A CN111951948A (en) | 2020-08-19 | 2020-08-19 | Nerve severe disease monitoring device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010838503.1A CN111951948A (en) | 2020-08-19 | 2020-08-19 | Nerve severe disease monitoring device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111951948A true CN111951948A (en) | 2020-11-17 |
Family
ID=73359160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010838503.1A Pending CN111951948A (en) | 2020-08-19 | 2020-08-19 | Nerve severe disease monitoring device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111951948A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040077967A1 (en) * | 2001-02-13 | 2004-04-22 | Jordan Kenneth George | Automated realtime interpretation of brain waves |
| CN103857337A (en) * | 2011-10-12 | 2014-06-11 | 索尼公司 | PSG test headgear and PSG test device |
| US20160328642A1 (en) * | 2015-05-06 | 2016-11-10 | Indiana University Research And Technology Corporation | Sensor signal processing using an analog neural network |
| CN108776788A (en) * | 2018-06-05 | 2018-11-09 | 电子科技大学 | A kind of recognition methods based on brain wave |
| CN108874137A (en) * | 2018-06-15 | 2018-11-23 | 北京理工大学 | A kind of gesture motion based on EEG signals is intended to the universal model of detection |
| CN109925582A (en) * | 2019-03-20 | 2019-06-25 | 天津大学 | Bimodal brain-machine interactive movement neural feedback training device and method |
| CN110378394A (en) * | 2019-06-26 | 2019-10-25 | 广西大学 | More physiological data convergence analysis methods neural network based |
| CN110367976A (en) * | 2019-07-30 | 2019-10-25 | 腾讯科技（深圳）有限公司 | Eeg signal detection method, relevant device and storage medium |
| CN110841262A (en) * | 2019-12-06 | 2020-02-28 | 郑州大学体育学院 | Football training system based on wearable equipment |
| CN111317440A (en) * | 2018-12-13 | 2020-06-23 | 通用电气公司 | Early warning method for patient, monitoring device using the method and readable storage medium |
-
2020
- 2020-08-19 CN CN202010838503.1A patent/CN111951948A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040077967A1 (en) * | 2001-02-13 | 2004-04-22 | Jordan Kenneth George | Automated realtime interpretation of brain waves |
| CN103857337A (en) * | 2011-10-12 | 2014-06-11 | 索尼公司 | PSG test headgear and PSG test device |
| US20160328642A1 (en) * | 2015-05-06 | 2016-11-10 | Indiana University Research And Technology Corporation | Sensor signal processing using an analog neural network |
| CN108776788A (en) * | 2018-06-05 | 2018-11-09 | 电子科技大学 | A kind of recognition methods based on brain wave |
| CN108874137A (en) * | 2018-06-15 | 2018-11-23 | 北京理工大学 | A kind of gesture motion based on EEG signals is intended to the universal model of detection |
| CN111317440A (en) * | 2018-12-13 | 2020-06-23 | 通用电气公司 | Early warning method for patient, monitoring device using the method and readable storage medium |
| CN109925582A (en) * | 2019-03-20 | 2019-06-25 | 天津大学 | Bimodal brain-machine interactive movement neural feedback training device and method |
| CN110378394A (en) * | 2019-06-26 | 2019-10-25 | 广西大学 | More physiological data convergence analysis methods neural network based |
| CN110367976A (en) * | 2019-07-30 | 2019-10-25 | 腾讯科技（深圳）有限公司 | Eeg signal detection method, relevant device and storage medium |
| CN110841262A (en) * | 2019-12-06 | 2020-02-28 | 郑州大学体育学院 | Football training system based on wearable equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20030055356A1 (en) | Method and apparatus for displaying vital sign data | |
| CN100475131C (en) | Nerve intensive monitor system and method for realizing synchronous monitor of human multi-parameter signals | |
| EP3958275A1 (en) | Systems, methods and devices for sleep intervention quality estimation | |
| WO2022134242A1 (en) | Method for establishing automatic sleep staging and application thereof | |
| Maimon et al. | Single-channel EEG features during n-back task correlate with working memory load | |
| CN110782992A (en) | Intelligent implementation method and system for quantitative evaluation of rehabilitation effect based on electrocardiosignals | |
| CN107822628B (en) | Epileptic brain focus area automatic positioning device and system | |
| CN111951948A (en) | Nerve severe disease monitoring device | |
| CN113558640A (en) | Minimum consciousness state degree evaluation method based on electroencephalogram characteristics | |
| Hermanto et al. | Brain signal reference concept using cross correlation based for brain computer interface | |
| CN115944307B (en) | Epileptic brain electrical signal monitoring system and method based on space-time converter | |
| CN111481193A (en) | Fall risk assessment and early warning method and system | |
| CN1694646A (en) | System for adaptively deriving ECG chest lead signal data | |
| CN115474945A (en) | Multi-element global synchronization index method for multi-channel electroencephalogram and electromyographic coupling analysis | |
| Wei et al. | Mild cognitive impairment classification convolutional neural network with attention mechanism | |
| Pongsakornsathien et al. | Performance characterisation of wearable cardiac monitoring devices for aerospace applications | |
| Aurlien et al. | A new way of building a database of EEG findings | |
| CN114159062A (en) | Auxiliary mental state recognition device and method | |
| Sakamoto et al. | Differences in task-phase-dependent time-frequency patterns of local field potentials in the dorsal and ventral regions of the monkey lateral prefrontal cortex | |
| Nan et al. | Analysis of propagation of multi-channel EEG in the test of sustained attention | |
| Abbasi et al. | Fast calibration of a thirteen-command BCI by simulating SSVEPs from trains of transient VEPs-towards time-domain SSVEP BCI paradigms | |
| CN115394395B (en) | Method, system and device for neuropsychological assessment and intervention based on drawing creation | |
| CN113598791B (en) | Consciousness disturbance classification method based on time-space convolution neural network used by resting state electroencephalogram | |
| CN118078215B (en) | Vital sign monitoring method and system | |
| CN118216933B (en) | Electroencephalogram complexity measurement method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201117 |
|
| RJ01 | Rejection of invention patent application after publication |