CN104856666B - A kind of bioelectrical signals monitoring system based on LabVIEW - Google Patents
A kind of bioelectrical signals monitoring system based on LabVIEW Download PDFInfo
- Publication number
- CN104856666B CN104856666B CN201510204734.6A CN201510204734A CN104856666B CN 104856666 B CN104856666 B CN 104856666B CN 201510204734 A CN201510204734 A CN 201510204734A CN 104856666 B CN104856666 B CN 104856666B
- Authority
- CN
- China
- Prior art keywords
- bioelectrical signals
- signal
- function
- interface
- connection weight
- 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.)
- Expired - Fee Related
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
- A61B5/0004—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by the type of physiological signal transmitted
- A61B5/0006—ECG or EEG signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/25—Bioelectric electrodes therefor
- A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
- A61B5/291—Bioelectric electrodes therefor specially adapted for particular uses for electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
-
- 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
- A61B5/7221—Determining signal validity, reliability or quality
-
- 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
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- 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
Abstract
The invention discloses a kind of bioelectrical signals monitoring system based on LabVIEW, by the bioelectrical signals of the bioelectrical signals of bioelectrical signals extraction equipment extraction multichannel, then parallel processing multichannel, monitored person is monitored using bioelectrical signals observation interface.In specific configuration, the need for monitored person can be according to itself, by the built-in function prestored in signal transacting interface selective calling system, bioelectrical signals are handled in real time, finally shown again by the display box on signal transacting interface, complete the monitoring to being monitored person's physical signs.
Description
Technical field
The invention belongs to physiology monitoring technical field, more specifically, it is related to a kind of biological telecommunications based on LabVIEW
Number monitoring system.
Background technology
Bioelectrical signals are the key character parameter of health state, while also effectively reflecting the brain activity of people
Situation and human body moving situation.By the analysis and monitoring to human biological signal, the health of human body can be held exactly
State, more can realize the operation and control to external equipment by the feature recognition to different bioelectrical signals.
Bioelectrical signals analysis in the market is excessively single with monitoring system functional, and signal processing algorithm is more simple
It is single, and most homogeneous system programs do not possess good portability, the brain telecommunications that such as TI companies are designed based on ADS1299 chips
Number extraction module and god read the eeg sensor that science and technology is designed based on TGAM chips, and therefore, both the above equipment is difficult to effectively
Promoted in the market.
More specifically say, the EEG signals extraction module designed compared to TI companies based on ADS1299 chips, the present invention
With small volume, a variety of powering modes, heat power consumption is small, carries bioelectrical signals extraction element and more multi-functional software is shown
Advantage.The eeg sensor that science and technology is designed based on TGAM chips is read compared to god, the present invention has power consumption low, and communication is stable, many
The advantages of passage is gathered.
The content of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of bioelectrical signals prison based on LabVIEW
The bioelectrical signals collected are analyzed by examining system by signal processing algorithm, realize the real-time monitoring to body state.
For achieving the above object, the bioelectrical signals monitoring system of the invention based on LabVIEW, it is characterised in that
Including:
One bioelectrical signals extraction equipment, including electroencephalogramsignal signal collection equipment and multiple limbs signal collecting devices, two
Include spring steel plate, stretchy nylon band and dry electrode slice in collecting device, wherein, at least wrapped in electroencephalogramsignal signal collection equipment
Include 3 dry electrode slices;Dry electrode slice is attached by welding on corresponding spring steel plate, is set by wearing bioelectrical signals extraction
It is stuck in when standby on head and limbs, and welding position is corresponding with bioelectrical signals active regions;Stretchy nylon band is located at bullet
It on spring steel disc, can further strengthen the closeness of contact of dry electrode slice and human body, increase the stability of acquiring biological electric signals;
Extract bioelectrical signals when, bioelectrical signals extraction equipment is worn on head and each position of limbs, respectively extract brain and
Bioelectrical signals on each position of limbs, then PCB circuit collection is sent to by the electromagnetic shield signal line connected on collecting device
Into module;
A plurality of electromagnetic shield signal line, using the anti-tampering design of multilayer, wherein internal layer is signal transmssion line, and outer layer is rubber
Layer, is wire envelope in the periphery of signal transmssion line;
One PCB circuit integrated modules, including electromagnetic interface filter, preamplifier and analog-digital converter;For receiving biological electricity
The multichannel bioelectrical signals of data extraction device collection, and by the bioelectrical signals parallel processing of multichannel, it is then forwarded to zigbee
Group-net communication module;
PCB circuit integrated modules are received after bioelectrical signals, are first passed through electromagnetic interface filter and are filtered out the higher electricity of out-of-band frequency
Magnetic noise, filtered bioelectrical signals are input to analog-digital converter after preamplifier amplifies, and analog-digital converter again will
The bioelectrical signals of simulation are converted into the data signal for being easy to transmitting-receiving, and are sent to zigbee group-net communication modules;
One zigbee group-net communication modules contain multiple COM1s, and the transmission of PCB circuit integrated modules can be received parallel
Multichannel bioelectrical signals, relay to bioelectrical signals observation interface, realize and receive multiple network type communication more;
One signal process function storehouse, signal transacting interface handles function in function library by call signal, to biological telecommunications
Number handled, re-send to bioelectrical signals observation interface;
One bioelectrical signals observation interface, by the tab control on bioelectrical signals observation interface, selection enters letter
Number observation interface or signal transacting interface;
On signal monitoring interface, the communication between zigbee group-net communications module and bioelectrical signals observation interface can be set
Port, selection needs signalling channel during entering signal processing interface, and in communication, the signal quality of bioelectrical signals can be in instrument
Directly observed on dial plate, the relevant information of bioelectrical signals shows the biology on brain and limbs by 2-D display boxes respectively
Electric signal;
On signal transacting interface, the function that user can as needed in selective call signal processing function library, then
Function according to calling is configured, such as selection filter function, then sets out and filter out frequency range;Trap function is such as selected, then is set
Go out the Hz noise frequency range of trap function removal;Wavelet function is such as selected, then sets the female ripple type of small echo, selection wavelet decomposition
The number of plies;Neural network function is such as selected, then when calling the function, trains neural network classifier parameter;Bioelectrical signals are passed through
Cross after the completion of above-mentioned processing, its relevant information shows the bioelectrical signals on brain and limbs by 2-D display boxes respectively.
What the goal of the invention of the present invention was realized in:
Bioelectrical signals monitoring system of the invention based on LabVIEW, multichannel is extracted by bioelectrical signals extraction equipment
Bioelectrical signals, then parallel processing multichannel bioelectrical signals, monitored person is carried out using bioelectrical signals observation interface
Monitoring.In specific configuration, the need for monitored person can be according to itself, pass through signal transacting interface selective calling system
In the built-in function that prestores, bioelectrical signals are handled in real time, finally shown again by the display box on signal transacting interface,
Complete the monitoring to being monitored person's physical signs.
Meanwhile, the bioelectrical signals monitoring system of the invention based on LabVIEW also has the advantages that:
(1), in the present invention, bioelectrical signals extraction equipment is constituted based on spring steel, stretchy nylon band and dry electrode slice.
Bioelectrical signals are extracted using modes such as electrode cap, adhesive patches more than existing like product, compared with electrode cap, present invention tool
There are light weight, small volume, low cost and other advantages;Compared with adhesive patches, the present invention, which has can be repeated several times, to be used, with human body knot
Close tight ness rating adjustable, the advantages of conveniently dressing and remove;
(2), the bioelectrical signals of multiple passages can be observed simultaneously by bioelectrical signals observation interface, can also hand
Dynamic setting communication interface, while monitoring communication quality in real time;
(3), invention increases the design of built-in function;Multi-signal processing letter is prestored in signal process function storehouse
Number, user can be achieved to be handled in real time extracting obtained bioelectrical signals under all kinds of environment without programming;Secondly, signal
Processing function library can extend, and the signal process function that writeable access customer is voluntarily write meets all kinds of demands of user;
(4), in signal transacting interface, user can be as needed, function pair in selective call signal processing function library
Bioelectrical signals are handled, and operating process is simple.
Brief description of the drawings
Fig. 1 is bioelectrical signals monitoring system a kind of embodiment Organization Chart of the invention based on LabVIEW;
Fig. 2 is a kind of embodiment structure chart of bioelectrical signals extraction equipment shown in Fig. 1;
Fig. 3 is a kind of embodiment structure chart of bioelectrical signals observation interface shown in Fig. 1.
Embodiment
The embodiment to the present invention is described below in conjunction with the accompanying drawings, so as to those skilled in the art preferably
Understand the present invention.Requiring particular attention is that, in the following description, when known function and design detailed description perhaps
When can desalinate the main contents of the present invention, these descriptions will be ignored herein.
Embodiment
LabVIEW(Laboratory Virtual Instrumentation Engineering Workbench):It is real
Test room virtual instrument engineering platform;
Zigbee:Low-power consumption Personal Area Network agreement based on IEEE802.15.4 standards;
Fig. 1 is bioelectrical signals monitoring system a kind of embodiment Organization Chart of the invention based on LabVIEW.
In the present embodiment, as shown in figure 1, a kind of bioelectrical signals monitoring system based on LabVIEW of the present invention, bag
Include:Bioelectrical signals extraction equipment 1, electromagnetic shield signal line 2, PCB circuit integrated modules 3, zigbee group-net communications module 4,
Signal process function storehouse 5 and bioelectrical signals observation interface 6.
As shown in Fig. 2 bioelectrical signals extraction equipment 1 is again including electroencephalogramsignal signal collection equipment and multiple limbs signal acquisitions
Equipment, wherein, it is limbs signal collecting device on the right of electroencephalogramsignal signal collection equipment, Fig. 2 that Fig. 2 left sides, which are,.In two collecting devices
Include spring steel plate 1.1, stretchy nylon band 1.2 and dry electrode slice 1.3;Wherein, in electroencephalogramsignal signal collection equipment, dry electrode
At least 3 pieces of piece 1.3.Dry electrode slice 1.3 is attached by welding on corresponding spring steel plate 1.1, and head can be stuck in well
In portion and limbs, and welding position is corresponding with bioelectrical signals active regions;Stretchy nylon band 1.2 can further strengthen dry electricity
The closeness of contact of pole piece 1.3 and human body, increases the stability of acquiring biological electric signals;When extracting bioelectrical signals, by brain
Electrical signal collection equipment is worn on head, and multiple limbs signal collecting devices are worn on into wrist, big arm and small arm respectively
Deng position, the bioelectrical signals on brain and limbs are extracted respectively;An electromagnetic shielding is respectively connected with each collecting device end
Signal wire 2, the bioelectrical signals of collection are sent to PCB circuit integrated modules by electromagnetic shield signal line 2 again;
Electromagnetic shield signal line 2, using the anti-tampering design of multilayer, wherein internal layer is signal transmssion line, and outer layer is rubber layer,
It is wire envelope in the periphery of signal transmssion line, so as to realize electromagnetic shielding to a certain extent, enhances electric signal
Antijamming capability, increases effective propagation path;
PCB circuit integrated modules 3, including electromagnetic interface filter, preamplifier and analog-digital converter;For receiving biological electricity
The multichannel bioelectrical signals that data extraction device 1 is gathered, and the bioelectrical signals parallel processing of multichannel is handled, it is then forwarded to
Zigbee group-net communications module 4;
PCB circuit integrated modules 3 are received after bioelectrical signals, and first passing through electromagnetic interface filter, to filter out out-of-band frequency higher
Electromagnetic noise, filtered bioelectrical signals are input to analog-digital converter after preamplifier amplifies, and analog-digital converter is again
The bioelectrical signals of simulation are converted into the data signal for being easy to transmitting-receiving, and are sent to zigbee group-net communications module 4;
Zigbee group-net communication modules contain multiple ports, and the multichannel of the transmission of PCB circuit integrated modules 3 can be received parallel
Bioelectrical signals, relay to bioelectrical signals observation interface 6, realize the multiple network type communication of many receipts;
Signal process function storehouse 5, signal transacting interface handles function in function library by call signal, to bioelectrical signals
Handled, re-send to bioelectrical signals observation interface 6;In the present embodiment, signal process function storehouse includes filtering letter
The many kinds of function such as number, trap function, wavelet function and artificial neural network function;
As shown in figure 3, bioelectrical signals observation interface 6 is again including signal monitoring interface and signal transacting interface;Pass through life
Tab control 6.1 on thing electric signal observation interface, selection entering signal observation interface or signal transacting interface, wherein, Fig. 3
(a) it is signal monitoring interface, Fig. 3 (b) is signal transacting interface;
On signal monitoring interface, zigbee group-net communications module 4 and bioelectrical signals observation interface can be set at 6.2
COM1 between 6, selection needs signalling channel during entering signal processing interface, in communication, the signal of bioelectrical signals
Quality can directly be observed on instrument board 6.3, the relevant informations of bioelectrical signals by 2-D display boxes show respectively brain and
The bioelectrical signals on brain and limbs are shown at bioelectrical signals on limbs, i.e., 6.5 and 6.6 respectively;
In the present embodiment, as shown in Fig. 3 (a), 6.3 point 0 of instrument board --- 10 scales, the finger on instrument board 6.3
When pin refers to some scale, degree of the bioelectrical signals by external environmental interference is represented, wherein, " 0 " is preferable interference-free communication,
" 10 " table is that external environmental interference is violent;
On signal transacting interface, by pending signalling channels such as the displays of indicator lamp 6.10, user can be according to need
Will, the function in selective call signal processing function library, you can to call wherein some or multiple function pairs signal logical
Bioelectrical signals in road are handled, wherein, it is configured, has when specifically calling some function, then to corresponding function
Body setting procedure is as follows:
1) filter function during, signal process function storehouse can be called at 6.7, and set out and filter out frequency range
In the present embodiment, the wave filter in built-in function is butterworth filter (Butterworth), and user can root
According to needing to set filtering frequency range, extract and want the signal specific frequency range that deeply monitors, or for filter out low frequency spur and
High frequency supurious wave;For example, think to embody alpha frequency ranges (8Hz-12Hz) brain wave of Mental imagery in individually observation EEG signals,
The EEG signals of the frequency range on the basis of original EEG signals, can be then filtered out using filter function;
2) the trap function in signal process function storehouse, can be called at 6.8, the power frequency for setting out the removal of trap function is done
Scramble section
In the present embodiment, realize trap by the bandstop filter based on FIR, trap frequency be 50Hz or
60Hz;
3) wavelet function in, can calling signal process function storehouse at 6.9, the female ripple type of setting small echo, selects small echo
The number of plies of decomposition
In the present embodiment, wavelet function is built using mallat algorithms, its type is the female ripple of haar or db small echos, and
By setting the wavelet decomposition number of plies, different degrees of wavelet Smoothing is carried out to primary signal and handled, Decomposition order is more in principle,
Smoothing processing effect is better, it is likely that meeting lost part useful feature information, here, decomposition level selects 3 layers;
4), system may call upon the neural network classification function in signal process function storehouse, neural network classifier
Parameter need to train and obtain, because different human body bioelectrical signals reference energy difference is larger, therefore call nerve without setting
Before network class function, neural network classifier parameter need to be trained, training step is as follows:
S1:When kth trains study, a large amount of bioelectrical signals are extracted at monitored person and are used as training sample data, mark
It is designated as:X (k)=(x1(k),x2(k),...,xn(k)), wherein, k=1,2 ..., m, m ∈ M;
S2:During serial communication under 38400 baud rates, training sample data are sent to signal transacting interface;This
When signal transacting interface on be defaulted as Neural Networks Training Pattern;
S3:Complete the parameter training of neural network classifier
Training sample data are read at signal transacting interface, according to sample data, are issued in the serial communication of 38400 baud rates
Neural network classifier modeling parameters are sent, neural network model parameter, including input layer number n, hidden layer god are set
Through first number p, output layer neuron number q, it is allowed to error ε and maximum study number of times M;
Calculated and obtained by the software in step S2:
Hidden layer is inputted:
Hidden layer is exported:hoh(k)=f (hih(k)) h=1,2 ..., p;
Output layer is inputted:
Output layer is exported:yoo(k)=f (yio(k)) o=1,2 ... q;
Error function:
Wherein, bhAnd boFor constant vector, vector length is identical with hidden layer/output layer neuron number;whoIt is implicit
Layer connection weight;wihInput layer connection weight;F () is the S type functions that can be led,Net=x1w1+x2w2
+...+xnwn, wherein, xn、wnRespectively f () input and connection weight;
If desired output:do(k)=(d1(k),d2(k),...,dq(k)), according to output layer output and desired output, ask
Error function, then calculate error function to output layer neuron and the partial derivative of hidden layer neuron, i.e.,:
The local derviation that error function is inputted to output layer:
Wherein,For substitute symbol, i.e., with-δo(k) replacement-(do(k)-yoo(k))f′(yio(k));
Output layer inputs the local derviation to hidden layer connection weight:
Local derviation of the error function to hidden layer connection weight:
The local derviation that error function is inputted to hidden layer:
Local derviation of the error function to input layer connection weight:
Hidden layer inputs the local derviation to input layer connection weight:
According to above-mentioned local derviation equation, the connection weight of amendment hidden layer connection weight and input layer
Hidden layer connection weight:
Input layer connection weight:
μ, η are constant, are disposed as 0.01 in the present embodiment;The hidden layer connection obtained during for kth time training study
Weights,The input layer connection weight obtained during for kth time training study;Will to the number of times m for now, having completed training study
Increase is once;
Global error before calculating during k training study, global error:
Judge whether global error reaches that default precision or study number of times m reach upper limit M, if reached, neutral net
Classifier parameters training terminates;Otherwise return to step S1, carries out+1 training study of kth.
Wherein, neural network classifier can not be used different people, or even same person can not be made in different conditions
With so after being exited completely at signal transacting interface, this training result will be removed automatically, treating next time in use, needing again again
Collection training data is trained;
Bioelectrical signals pass through above-mentioned processing after the completion of, its relevant information by 2-D display boxes show respectively brain and
The bioelectrical signals on brain and limbs are shown at bioelectrical signals on limbs, i.e., 6.11 and 6.12 respectively.
Although illustrative embodiment of the invention is described above, in order to the technology of the art
Personnel understand the present invention, it should be apparent that the invention is not restricted to the scope of embodiment, to the common skill of the art
For art personnel, as long as various change is in the spirit and scope of the present invention that appended claim is limited and is determined, these
Change is it will be apparent that all utilize the innovation and creation of present inventive concept in the row of protection.
Claims (5)
1. a kind of bioelectrical signals monitoring system based on LabVIEW, it is characterised in that including:
One bioelectrical signals extraction equipment, including electroencephalogramsignal signal collection equipment and multiple limbs signal collecting devices, EEG signals
Collecting device and multiple limbs signal collecting devices include spring steel plate, stretchy nylon band and dry electrode slice, wherein, in brain electricity
At least include 3 dry electrode slices in signal collecting device;Dry electrode slice is attached by welding on corresponding spring steel plate, is passed through
It is stuck in when wearing bioelectrical signals extraction equipment on head and limbs, and welding position is relative with bioelectrical signals active regions
Should;Stretchy nylon band is located on spring steel plate, can further strengthen the closeness of contact of dry electrode slice and human body, increases biological electricity
The stability of signal acquisition;When extracting bioelectrical signals, bioelectrical signals extraction equipment is worn on head and each portion of limbs
On position, the bioelectrical signals on brain and each position of limbs are extracted respectively, then believe by the electromagnetic shielding connected on collecting device
Number line is sent to PCB circuit integrated modules;
Electromagnetic shield signal line, using the anti-tampering design of multilayer, wherein internal layer is signal transmssion line, and outer layer is rubber layer, in letter
The periphery of number transmission line is wire envelope;
PCB circuit integrated modules, including electromagnetic interface filter, preamplifier and analog-digital converter;Carried for receiving bioelectrical signals
The multichannel bioelectrical signals of taking equipment collection, and by the bioelectrical signals parallel processing of multichannel, be then forwarded to zigbee networkings and lead to
Believe module;
PCB circuit integrated modules are received after bioelectrical signals, are first passed through electromagnetic interface filter and are filtered out the higher electromagnetism of out-of-band frequency and make an uproar
Sound, filtered bioelectrical signals are input to analog-digital converter after preamplifier amplifies, and analog-digital converter again will simulation
Bioelectrical signals be converted into the data signal for being easy to transmitting-receiving, and be sent to zigbee group-net communication modules;
Zigbee group-net communication modules contain multiple COM1s, and the multichannel of PCB circuit integrated modules transmission can be received parallel
Bioelectrical signals, relay to bioelectrical signals observation interface, realize the multiple network type communication of many receipts;
Signal process function storehouse, signal transacting interface handles function in function library by call signal, and bioelectrical signals are carried out
Processing, re-sends to bioelectrical signals observation interface;
Bioelectrical signals observation interface, including signal monitoring interface and signal transacting interface;Pass through bioelectrical signals observation interface
On tab control, selection entering signal observation interface or signal transacting interface;
Wherein, signal monitoring interface includes COM1, instrument board, the first 2-D display boxes and the first bioelectrical signals passage again;
On signal monitoring interface, set logical between zigbee group-net communications module and bioelectrical signals observation interface by COM1
Letter, signalling channel during entering signal processing interface is needed by the first bioelectrical signals channel selecting, in communication, passes through instrument
The deflection scale of pointer directly observes the signal quality of bioelectrical signals on dial plate, will be raw finally by the first 2-D display boxes
The bioelectrical signals on brain and limbs in thing electric signal are shown respectively;
Signal transacting interface includes the second bioelectrical signals passage and the 2nd 2-D display boxes again;On signal transacting interface, pass through
Second bioelectrical signals channel selecting needs signalling channel during entering signal processing interface, and in communication, user is as needed
Selectivity calls the function in the signal process function storehouse, is configured further according to the function called, such as selection filter function,
Then set out and filter out frequency range;Trap function is such as selected, then sets out the Hz noise frequency range of trap function removal;Such as select small echo
Function, then set the female ripple type of small echo, select the number of plies of wavelet decomposition;Such as select neural network function, then when calling the function,
Train neural network classifier parameter;Bioelectrical signals pass through after the completion of the function processing in the signal process function storehouse,
The bioelectrical signals on the brain and limbs in the bioelectrical signals after processing are shown respectively by the 2nd 2-D display boxes
Show.
2. the bioelectrical signals monitoring system according to claim 1 based on LabVIEW, it is characterised in that described letter
Number processing function library at least include:Filter function, trap function, wavelet function and artificial neural network function.
3. the bioelectrical signals monitoring system according to claim 1 based on LabVIEW, it is characterised in that described instrument
Dial plate point 0 --- 10 scales, when the pointer on instrument board refers to some scale, represent that the bioelectrical signals are dry by external environment
The degree disturbed, wherein, " 0 " represents preferable interference-free communication, and " 10 " represent that external environmental interference is violent.
4. the bioelectrical signals monitoring system according to claim 1 based on LabVIEW, it is characterised in that described instruction
Practicing neural network classifier parametric technique is:
(4.1) when kth trains study, a large amount of bioelectrical signals is extracted at monitored person and are used as training sample data, mark
For:X (k)=(x1(k),x2(k),…,xn(k)), wherein, k=1,2 ..., m, m ∈ M;
(4.2) during serial communication under 38400 baud rates, training sample data are sent to signal transacting interface;
(4.3) parameter training of neural network classifier is completed
Training sample data are read at signal transacting interface, according to sample data, and god is sent under the serial communication of 38400 baud rates
Through network classifier modeling parameters, neural network model parameter, including input layer number n, hidden layer neuron are set
Number p, output layer neuron number q, it is allowed to error ε and maximum study number of times M;
Obtained by calculating:
Hidden layer is inputted:
Hidden layer is exported:hoh(k)=f (hih(k)) h=1,2 ..., p;
Output layer is inputted:
Output layer is exported:yoo(k)=f (yio(k)) o=1,2 ... q;
Error function:
Wherein, f () is the S type functions that can be led;
If desired output:do(k)=(d1(k),d2(k),…,dq(k)), according to output layer output and desired output, error is tried to achieve
Function, then error function is calculated to bhAnd boFor constant vector, vector length is identical with hidden layer/output layer neuron number;
whoIt is hidden layer connection weight;wihInput layer connection weight;The partial derivative of output layer neuron and hidden layer neuron, i.e.,:
The local derviation that error function is inputted to output layer:
Output layer inputs the local derviation to hidden layer connection weight:
Local derviation of the error function to hidden layer connection weight:
The local derviation that error function is inputted to hidden layer:
For substitute symbol;
Local derviation of the error function to input layer connection weight:
Hidden layer inputs the local derviation to input layer connection weight:
According to above-mentioned local derviation equation, the connection weight of amendment hidden layer connection weight and input layer
Hidden layer connection weight:
Input layer connection weight:
μ, η are constant,The hidden layer connection weight obtained during for kth time training study,Obtained during for kth time training study
The input layer connection weight arrived;
Global error before calculating during k training study, global error:
Judge whether global error reaches that default precision or study number of times m reach upper limit M, if reached, neural network classification
Device parameter training terminates;Otherwise return to step (4.1), carry out+1 training study of kth.
5. the bioelectrical signals monitoring system based on LabVIEW according to claim 1 or 4, it is characterised in that described
After neural network classifier is exited completely at signal transacting interface, this training result will be removed automatically, treat next time in use, again
Training data need to be resurveyed to be trained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510204734.6A CN104856666B (en) | 2015-04-27 | 2015-04-27 | A kind of bioelectrical signals monitoring system based on LabVIEW |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510204734.6A CN104856666B (en) | 2015-04-27 | 2015-04-27 | A kind of bioelectrical signals monitoring system based on LabVIEW |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104856666A CN104856666A (en) | 2015-08-26 |
CN104856666B true CN104856666B (en) | 2017-09-12 |
Family
ID=53903179
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510204734.6A Expired - Fee Related CN104856666B (en) | 2015-04-27 | 2015-04-27 | A kind of bioelectrical signals monitoring system based on LabVIEW |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104856666B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105549738B (en) * | 2015-12-10 | 2018-07-24 | 浙江大学 | A kind of brain signal real-time parallel processing method based on multi-core processor |
CN106073768B (en) * | 2016-05-31 | 2018-09-18 | 臧大维 | The highly sensitive non-invasive detection of human cortical brain's electroneurographic signal and analysis process system |
CN109157212A (en) * | 2018-08-30 | 2019-01-08 | 武汉吉星医疗科技有限公司 | The compound filter computing system and its method of electrocardiograph based on android system |
CN109445391A (en) * | 2018-11-08 | 2019-03-08 | 江苏大学 | A kind of aquaculture multi parameter intallingent monitoring system and its method based on Internet of Things |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5862803A (en) * | 1993-09-04 | 1999-01-26 | Besson; Marcus | Wireless medical diagnosis and monitoring equipment |
CN101032397A (en) * | 2007-04-05 | 2007-09-12 | 上海交通大学 | Portable wireless communication multichannel brain electric data collecting instrument |
CN102654793A (en) * | 2012-01-16 | 2012-09-05 | 中国人民解放军国防科学技术大学 | Electrocerebral-drive high-reliability control system based on dual-mode check mechanism |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020188216A1 (en) * | 2001-05-03 | 2002-12-12 | Kayyali Hani Akram | Head mounted medical device |
US20040073129A1 (en) * | 2002-10-15 | 2004-04-15 | Ssi Corporation | EEG system for time-scaling presentations |
-
2015
- 2015-04-27 CN CN201510204734.6A patent/CN104856666B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5862803A (en) * | 1993-09-04 | 1999-01-26 | Besson; Marcus | Wireless medical diagnosis and monitoring equipment |
CN101032397A (en) * | 2007-04-05 | 2007-09-12 | 上海交通大学 | Portable wireless communication multichannel brain electric data collecting instrument |
CN102654793A (en) * | 2012-01-16 | 2012-09-05 | 中国人民解放军国防科学技术大学 | Electrocerebral-drive high-reliability control system based on dual-mode check mechanism |
Also Published As
Publication number | Publication date |
---|---|
CN104856666A (en) | 2015-08-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104856666B (en) | A kind of bioelectrical signals monitoring system based on LabVIEW | |
CN105877766B (en) | A kind of state of mind detection system and method based on the fusion of more physiological signals | |
CN105078449B (en) | Senile dementia monitor system based on health service robot | |
CN106803081A (en) | A kind of brain electricity sorting technique based on Multi-classifers integrated | |
CN103110418B (en) | Electroencephalogram signal characteristic extracting method | |
CN104720797B (en) | One kind is based on myoelectricity noise cancellation method in single pass EEG signals | |
CN108670276A (en) | Study attention evaluation system based on EEG signals | |
CN102512153B (en) | Non-contact electrocardio monitoring mobile terminal and electrocardio monitoring method | |
CN103294199B (en) | A kind of unvoiced information identifying system based on face's muscle signals | |
CN101576772A (en) | Brain-computer interface system based on virtual instrument steady-state visual evoked potentials and control method thereof | |
CN105193431A (en) | Device for analyzing mental stress state of human body | |
CN104035563B (en) | W-PCA (wavelet transform-principal component analysis) and non-supervision GHSOM (growing hierarchical self-organizing map) based electrocardiographic signal identification method | |
CN103654799A (en) | Infant emotion detection method and device based on brain waves | |
CN105147281A (en) | Portable stimulating, awaking and evaluating system for disturbance of consciousness | |
CN102306303B (en) | Electroencephalography signal characteristic extraction method based on small training samples | |
CN108451527A (en) | One kind is to EEG signals categorizing system under different narcosises | |
CN113180670B (en) | Method for identifying mental state of depression patient based on finger pulse signals | |
CN106166065A (en) | A kind of wearable electrocardio health interacting platform based on social networks and its implementation | |
CN107292296A (en) | A kind of human emotion wake-up degree classifying identification method of use EEG signals | |
CN105286860A (en) | Motor imagery brain electrical signal recognition method based on dual-tree complex wavelet energy difference | |
CN106889981A (en) | A kind of intelligent terminal for extracting fetal heart frequency | |
CN106693145A (en) | Brain wave feedback training method and system | |
CN108364062B (en) | Deep learning model construction method based on MEMD and application of deep learning model in motor imagery | |
CN105205317B (en) | A kind of method and equipment for being used to reflect the cooperation degree of at least two participants | |
Wu et al. | A 16-channel nonparametric spike detection ASIC based on EC-PC decomposition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
EXSB | Decision made by sipo to initiate substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170912 Termination date: 20200427 |
|
CF01 | Termination of patent right due to non-payment of annual fee |