CN105769173A - Electrocardiogram monitoring system with electrocardiosignal denoising function - Google Patents
Electrocardiogram monitoring system with electrocardiosignal denoising function Download PDFInfo
- Publication number
- CN105769173A CN105769173A CN201610111102.XA CN201610111102A CN105769173A CN 105769173 A CN105769173 A CN 105769173A CN 201610111102 A CN201610111102 A CN 201610111102A CN 105769173 A CN105769173 A CN 105769173A
- Authority
- CN
- China
- Prior art keywords
- triple channel
- axis acceleration
- module
- signal segment
- electrocardiogram
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/30—Input circuits therefor
-
- 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
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
- A61B5/7207—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal of noise induced by motion artifacts
- A61B5/721—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal of noise induced by motion artifacts using a separate sensor to detect motion or using motion information derived from signals other than the physiological signal to be measured
Abstract
The invention discloses an electrocardiogram monitoring system with an electrocardiosignal denoising function. The system comprises a three-axis acceleration sensor, an electrocardiogram monitor and an intelligent terminal. Movement data is collected by the three-axis acceleration sensor to be used as an input sample of a neural network; dynamic electrocardiogram data of a human body in the static and movement state is pretreated before neural network training through format conversion and normalization methods, and the deviation is used as supervision of the neural network, then, an artificial neural network learning algorithm is used for determining a noise model in a proportion conjugate gradient optimization mode, and the corresponding movement noise is subtracted from dynamic electrocardiogram data obtained through monitoring, so that denoising is finished. The whole system is simple, convenient and easy to achieve and capable of effectively removing vehicle movement noise in the electrocardiogram monitoring process to obtain accurate electrocardiogram data, and provides a guarantee for cardiovascular disease diagnosis and treatment.
Description
Technical field
The invention belongs to technical field of medical equipment, be specifically related to a kind of cardioelectric monitor system with electrocardiosignal noise removal function.
Background technology
Ambulatory electrocardiogram is for 24 hours dynamic electrocardiogram activity datas of record continuously, the electrocardio-activity data under different situations such as including rest, activity, work, dining, can help for finding the symptom such as arrhythmia and myocardial ischemia, provide important foundation for the clinical analysis state of an illness and diagnosis and treatment.Along with emerging in large numbers of portable wearable cardiac monitoring equipment so that user can carry out cardioelectric monitor very easily under various regimes.But ambulatory electrocardiogram signal is highly susceptible to the interference of various noise, main interference has the interference of AC influence, myoelectricity, baseline drift, conducting wire connection error, electrode slice and contact skin insufficient, development along with technology, major part ambulatory electrocardiogram equipment is all configured with various types of wave filter in order to eliminate these interference, but when portable dynamic ecg equipment uses on a moving vehicle, the interference of vehicle movement is likely to seriously limit the quality of ambulatory electrocardiogram signal.
The motion artifacts of vehicle can act on object onboard, including the cardioelectric monitor equipment that human body is dressed.And the state of vehicle movement can reflect the interference impact on cardioelectric monitor equipment well, the kinestate of vehicle can be obtained very easily by 3-axis acceleration sensor, thus analyzing influence mode and the degree of motion, provide data basis for eliminating vehicle movement interference.
3-axis acceleration sensor is the sensor of a kind of signal of telecommunication being converted to by physical signalling acceleration and being easy to measurement, the operation principle of current most of 3-axis acceleration sensor is pressure resistance type, piezoelectric type and condenser type, the acceleration produced is proportional to the change of resistance, voltage and electric capacity, by calculating the relation between these variable quantity and acceleration, the value of acceleration can be calculated.3-axis acceleration sensor can under the occasion not knowing object moving state in advance, by detecting x, y, the signal of z tri-axle, obtains its coordinate components, thus the kinestate of accurate judgment object, there is volume characteristic point little, lightweight, can measurement space acceleration, it is possible to accurately reflect the kinetic property of object comprehensively, obtain extensive use in fields such as Aero-Space, automobile, robot and medical science.
Most portable holter devices in the market, simple structure, do not eliminate vehicle movement noise function, being easily used under state of motion of vehicle is interfered causes ambulatory electrocardiogram jitter, the ecg wave form of record is not used to ecg analysis, not only limit the use scope of dynamic ecg monitoring equipment, it is also possible to make doctor that the diagnosis and treatment of cardiovascular patient are caused serious consequence.
Summary of the invention
Above-mentioned technical problem existing for prior art, the invention provides a kind of cardioelectric monitor system with electrocardiosignal noise removal function, effectively can automatically remove vehicle movement noise in cardioelectric monitor process, obtain accurate electrocardiogram (ECG) data, provide guarantee for doctor to the diagnosis and treatment of cardiovascular disease.
A kind of cardioelectric monitor system with electrocardiosignal noise removal function, is all connected by wireless telecommunications with intelligent terminal including 3-axis acceleration sensor, cardioelectric monitor device and intelligent terminal, described 3-axis acceleration sensor and cardioelectric monitor device；
Described cardioelectric monitor device includes monitor main body and several electrocardiogram acquisition electrodes, is provided with main control module, Signal-regulated kinase and bluetooth communication module in described monitor main body；Electrocardiogram acquisition electrode is connected with Signal-regulated kinase, and Signal-regulated kinase is connected with main control module, and main control module is connected with bluetooth communication module；Described electrocardiogram acquisition electrode, for picking up the faint electrocardiosignal of people's body surface, is sent into Signal-regulated kinase after amplifying Filtering Processing, main control module is carried out sampling and Digital Signal Processing, then pass through bluetooth communication module and electrocardiosignal is transferred to intelligent terminal；
Described intelligent terminal includes bluetooth communication module and processor, and described processor includes:
Signal acquisition module, for the exercise data that the training data under each Heart Rate States of correspondence that the electrocardiogram (ECG) data provided by the bluetooth communication module collection cardioelectric monitor device in intelligent terminal, electrocardiosignal simulative generator are provided and 3-axis acceleration sensor provide；Described electrocardiogram (ECG) data be user be everlasting day vehicle movement time detect, by cardioelectric monitor device, the triple channel ECG detecting signal segment that obtains；Described training data includes the m group triple channel static electrocardiosignal section being under arbitrary Heart Rate States that electrocardiosignal simulative generator produces when static and the m group triple channel exercise electrocardiogram signal section being under arbitrary Heart Rate States produced when vehicle movement, and m is the natural number more than 1；Described exercise data includes 3-axis acceleration sensor synchronous acquisition and the electrocardiosignal simulative generator 3-axis acceleration signal segment that produced triple channel exercise electrocardiogram signal section is corresponding when vehicle movement and is detected the 3-axis acceleration signal segment that the triple channel ECG detecting signal segment obtained is corresponding with cardioelectric monitor device when vehicle movement；
Pretreatment module, for carrying out pretreatment to the described static electrocardiosignal section of triple channel, triple channel exercise electrocardiogram signal section, triple channel ECG detecting signal segment and 3-axis acceleration signal segment；Simultaneously for any one Heart Rate States, make pretreated triple channel exercise electrocardiogram signal section under this Heart Rate States corresponding poor with triple channel static electrocardiosignal section, obtain m group triple channel electrocardio motion artifacts；
Neural metwork training module, for any one Heart Rate States, it is trained by artificial neural network learning algorithm according to the triple channel electrocardio motion artifacts under this Heart Rate States and pretreated 3-axis acceleration signal segment, the vehicle movement noise model of the electrocardiosignal that obtains leading about three for this Heart Rate States；
Denoising module, obtain one group of triple channel electrocardio motion artifacts for the Heart Rate States residing for user by vehicle movement noise model corresponding for corresponding with triple channel ECG detecting signal segment 3-axis acceleration signal segment input exports, and then make described triple channel ECG detecting signal segment deduct this triple channel electrocardio motion artifacts to be namely eliminated the triple channel electrocardiogram (ECG) data after vehicle movement noise.
The static electrocardiosignal section of triple channel, triple channel exercise electrocardiogram signal section, triple channel ECG detecting signal segment and 3-axis acceleration signal segment are carried out pretreatment and include form conversion and normalized by described pretreatment module, to obtain the data signal in appropriate format and scope.
Described pretreatment module is normalized based on following formula:
Wherein: x is the either signal value in signal segment, xminAnd xmaxThe respectively minima in signal segment and maximum, x' is corresponding x signal value after normalized.
The artificial neural network learning algorithm that described neural metwork training module adopts is using ratio conjugate gradient method as optimizing direction.
The detailed process that described neural metwork training module is trained by artificial neural network learning algorithm is as follows:
(1) it is divided into training set and test set and training set more than test set m group 3-axis acceleration signal segment corresponding with triple channel exercise electrocardiogram signal section after pretreatment；
(2) one neutral net being made up of input layer, hidden layer and output layer of structure is initialized；
(3) appoint from training set and take one group of 3-axis acceleration signal segment and substitute into above-mentioned neural computing and obtain the corresponding output result about electrocardio motion artifacts, calculate the cumulative error between this output result and this triple channel electrocardio motion artifacts corresponding to 3-axis acceleration signal segment；
(4) by gradient descent method, weight between input layer and hidden layer and between hidden layer and output layer in neutral net is modified according to this cumulative error, and then appoints from training set and take off one group of 3-axis acceleration signal segment and substitute into revised neutral net；
(5) travel through all 3-axis acceleration signal segments in training set according to step (3) and (4), take cumulative error minimum time corresponding neutral net be vehicle movement noise model.
In the neutral net that described neural metwork training module initialization builds, input layer is made up of 3 neurons, and hidden layer is made up of 10 neurons, and output layer is made up of 3 neurons.
In the neutral net that described neural metwork training module initialization builds, the expression formula of neuron function g (z) is as follows:
Wherein: z is argument of function.
The vehicle movement noise model that described neural metwork training module obtains for training, 3-axis acceleration signal segment in test set is substituted into one by one this vehicle movement noise model and obtains the corresponding output result about electrocardio motion artifacts, the output result corresponding to each group of 3-axis acceleration signal segment is made in test set to compare with triple channel electrocardio motion artifacts, if test is concentrated with the comparative result of a certain proportion of 3-axis acceleration signal segment less than or equal to threshold value, then this vehicle movement noise model is finally determined；Otherwise, electrocardiosignal simulative generator and the static electrocardiosignal section of the more triple channel of 3-axis acceleration sensor collection, triple channel exercise electrocardiogram signal section and 3-axis acceleration signal segment is utilized to be trained as the input of neural metwork training module through the signal acquisition module in intelligent terminal with after pretreatment module increasing the scale of training set.
Described intelligent terminal can be smart mobile phone, panel computer or PC.
Cardioelectric monitor system of the present invention utilizes 3-axis acceleration sensor to gather exercise data and inputs sample as neutral net, by form conversion and method for normalizing before neural metwork training human body is static and motion time dynamic electrocardiogram (ECG) data carry out pretreatment and make deviation between the two as the supervision of neutral net, and then using artificial neural network learning algorithm to establish noise model with the optimal way of ratio conjugate gradient, the dynamic electrocardiogram (ECG) data obtained with monitoring deducts the motion artifacts of correspondence and namely completes denoising.Whole system is easy and is easily achieved, it is possible to effectively automatically removes vehicle movement noise in cardioelectric monitor process, obtains accurate electrocardiogram (ECG) data, provides guarantee for doctor to the diagnosis and treatment of cardiovascular disease.
Accompanying drawing explanation
Fig. 1 is the structural representation of cardioelectric monitor system of the present invention.
Fig. 2 is the structural representation of intelligent terminal in cardioelectric monitor system of the present invention.
Fig. 3 is the artificial nerve network model schematic diagram in electrocardiosignal denoising process of the present invention.
Detailed description of the invention
In order to more specifically describe the present invention, below in conjunction with the drawings and the specific embodiments, technical scheme is described in detail.
As it is shown in figure 1, the present invention has the cardioelectric monitor system of electrocardiosignal noise removal function, including 3-axis acceleration sensor, cardioelectric monitor device and smart mobile phone；Wherein:
Cardioelectric monitor device includes monitor main body and multiple electrocardiogram acquisition electrode, is provided with main control module, voltage detection module, bluetooth communication module, Signal-regulated kinase, automatic shutdown module, power management module and driving module in monitor main body；Monitor body surfaces is provided with shift knob and low pressure display lamp 1；Wherein:
Power management module is for providing running voltage for other functional modules in electrocardiogram acquisition electrode and monitor main body.
Electrocardiogram acquisition electrode is connected with Signal-regulated kinase, and it is for picking up the faint electrocardiosignal of people's body surface.
Signal-regulated kinase is connected with main control module, and it is amplified sending main control module to after filtering etc. processes for the faint electrocardiosignal that electrocardiogram acquisition electrode is picked up；In present embodiment, Signal-regulated kinase is sequentially connected with forms by inputting buffer stage, preposition instrument amplifier stage, high pass filter, interstage amplifier section, low pass filter and power frequency notch filter.
Driving module to be connected with main control module and shift knob, it is for driving power management module to electrocardiogram acquisition electrode discharge by main control module, and user can pass through shift knob and start cardioelectric monitor device.
Voltage detection module is connected with power management module and low pressure display lamp 1, and it is for detecting the information of voltage of power management module；The running voltage provided for cardioelectric monitor device when power management module is less than in a preset value situation, and low pressure display lamp 1 is lighted, to point out user cardioelectric monitor device is charged or changes battery.
Automatic shutdown module is connected with power management module and main control module, and it can make cardioelectric monitor device in long-time idle situation, is cut off by the power supply of cardioelectric monitor device, enters resting state, reduces power consumption；In present embodiment, a timer it is provided with in automatic shutdown module, timer is connected with main control module, timer is set with certain time interval (10s), this interval is exceeded when main control module does not have electrocardiosignal, automatic shutdown module automatically by dump, will enter resting state, reduce power consumption.
Bluetooth communication module is connected with main control module, and electrocardiosignal is radioed to smart mobile phone by bluetooth communication module by main control module.In present embodiment, bluetooth communication module follows bluetooth standard protocol；Module supports the interface such as UART, USB, SPI, PCM, SPDIF, and supports SPP bluetooth serial ports agreement, has that cost is low, volume is little, low in energy consumption, transmitting-receiving susceptiveness advantages of higher, and only need to be equipped with fraction of peripheral cell can be achieved with its power.
3-axis acceleration sensor is used for synchronous acquisition and electrocardiosignal simulative generator and the cardioelectric monitor device exercise data that produced electrocardiosignal is corresponding when vehicle movement；This exercise data includes 3-axis acceleration sensor synchronous acquisition and the electrocardiosignal simulative generator 3-axis acceleration signal segment that produced triple channel exercise electrocardiogram signal section is corresponding when vehicle movement and is detected the 3-axis acceleration signal segment that the triple channel ECG detecting signal segment obtained is corresponding with cardioelectric monitor device when vehicle movement.
As in figure 2 it is shown, include processor and bluetooth communication module in present embodiment in smart mobile phone, bluetooth communication module is connected with processor；Processor includes signal acquisition module, pretreatment module, neural metwork training module and denoising module；Wherein:
Bluetooth communication module communicates for intelligent terminal and electrocardiogram monitoring terminal, and intelligent terminal sends commands to monitoring terminal, and monitoring terminal response command uploads electrocardiogram (ECG) data to intelligent terminal.
Signal acquisition module is used for being received the kinestate data of the dynamic electrocardiogram (ECG) data from generator or monitor and acceleration transducer by bluetooth communication module；Dynamic electrocardiogram (ECG) data includes what m group gathered when resting state, is in the electrocardiosignal sequence E under a kind of Heart Rate States, with the Heart Rate States that n kind is different, then has the static electrocardiogram (ECG) data E of n*m group；M group gathers when state of motion of vehicle, is in the electrocardiosignal sequence M under a kind of Heart Rate States, with the Heart Rate States that n kind is different, then has n*m group exercise ECG data M.
Kinestate data are that m group gathers when state of motion of vehicle, corresponding to the 3-axis acceleration sensor output signal sequence Q [x under wherein a kind of Heart Rate States, y, z], with the Heart Rate States that n kind is different, then there are n*m group kinestate sequence Q [x, y, z], m, n are the natural number more than 1.
Pretreatment module, for dynamic electrocardiogram (ECG) data and kinestate data are carried out form conversion and normalized, obtains the initial data of appropriate format and scope.In the present embodiment, data sampling rate is 250, and AD conversion figure place is 24bit, by down-sampled algorithm, sample rate is reduced to 200, by data compression algorithm, 24bit data are converted to 16bit, obtain the data that capacity is less, but the demand of neural metwork training module need to be met.Normalization algorithm adopts linear transformation algorithm, and its expression formula is:
Wherein: x is input vector, max is the maximum of x, and min is the minima of x, and f (x) is the later output vector of normalization.
The pretreated kinestate operational data sequence of above-mentioned n*m group is trained by artificial neural network degree of depth learning algorithm and is tested by neural metwork training module, obtains noise model；Specific implementation is as follows:
(1) it is divided into training set and test set and training set more than test set pretreated for m group kinestate data sequence Q [x, y, z] being under a kind of Heart Rate States.
(2) set up initial neural network model according to artificial neural network learning algorithm: this neural network model by input layer, hidden layer, export into up of three layers, it is connected by formula (1) between input layer with hidden layer, the input of input layer is 3-axis acceleration sensor x, y, the operational data sequence of z-axis, the activation primitive of hidden layer and output layer is formula (2), hidden layer is made up of 10 neurons, output layer is output as 3-axis acceleration sensor x, y, the noise of z-axis, the neural network model of foundation is as shown in Figure 3.
Wherein,WithFor the coefficient of hidden layer, g is tansig function, i=1,2 ..., 10, j=1,2,3.
Wherein,WithFor the coefficient of output layer, i=1,2,3, j=1,2 ..., 10.
(3) the one of training set group of sample data is input to the neutral net under current weight coefficient, calculates the output of input layer, hidden layer, each node of output layer successively.
(4) the cumulative error E between output layer output and the expected result of training sample of all training samples is calculated according to formula (3), according to conjugate gradient decent, revise input layer and each internodal weights coefficient of hidden layer according to formula (4), revise hidden layer and each internodal weights coefficient of output layer according to formula (5):
Wherein: E is cumulative error,Export through the kth of the output layer of neutral net for single training sample, okFor the kth expected result of single training sample, m is training set total sample number, and p is output layer output sum.
Wherein: whoT () is the weights coefficient that the t time sample is input to during neutral net between hidden layer and output layer,For the output through the output layer of neutral net of the single training sample, o is the expected result of single training sample, xhFor the output of hidden layer, α is learning rate.
Wherein: wihT () is the weights coefficient that the t time sample is input to during neutral net between input layer and hidden layer, xiOutput for input layer.
(5) repeat step (3) and step (4) travels through all training sets, set up noise model, the noise model corresponding to weights coefficient sets when acquirement E is minimum, then using test set that this noise model is tested, if the accuracy of test is higher than threshold value, this noise model is best model；If the accuracy of test is lower than threshold value, then continues to increase training sample and repeat step (3) and step (4) training neutral net, until having trained.The present embodiment is trained the weights coefficient matrix obtained be:
Input layer and hidden layer:
Hidden layer and output layer:
Denoising module is for the weights proportion according to each layer of neutral net, the system function of reduction noise model；The 3-axis acceleration output data embodying human motion state daily for user monitoring obtained substitute in noise model, export corresponding noise result, then use the dynamic electrocardiogram (ECG) data that monitor obtains to deduct the noise figure of noise model output, obtain the dynamic electrocardiogram (ECG) data after removing noise.
The above-mentioned description to embodiment is to be understood that for ease of those skilled in the art and apply the present invention.Above-described embodiment obviously easily can be made various amendment by person skilled in the art, and General Principle described herein is applied in other embodiments without through performing creative labour.Therefore, the invention is not restricted to above-described embodiment, those skilled in the art's announcement according to the present invention, the improvement made for the present invention and amendment all should within protection scope of the present invention.
Claims (9)
1. there is a cardioelectric monitor system for electrocardiosignal noise removal function, be all connected by wireless telecommunications with intelligent terminal including 3-axis acceleration sensor, cardioelectric monitor device and intelligent terminal, described 3-axis acceleration sensor and cardioelectric monitor device；It is characterized in that:
Described cardioelectric monitor device includes monitor main body and several electrocardiogram acquisition electrodes, is provided with main control module, Signal-regulated kinase and bluetooth communication module in described monitor main body；Electrocardiogram acquisition electrode is connected with Signal-regulated kinase, and Signal-regulated kinase is connected with main control module, and main control module is connected with bluetooth communication module；Described electrocardiogram acquisition electrode, for picking up the faint electrocardiosignal of people's body surface, is sent into Signal-regulated kinase after amplifying Filtering Processing, main control module is carried out sampling and Digital Signal Processing, then pass through bluetooth communication module and electrocardiosignal is transferred to intelligent terminal；
Described intelligent terminal includes bluetooth communication module and processor, and described processor includes:
Signal acquisition module, for the exercise data that the training data under each Heart Rate States of correspondence that the electrocardiogram (ECG) data provided by the bluetooth communication module collection cardioelectric monitor device in intelligent terminal, electrocardiosignal simulative generator are provided and 3-axis acceleration sensor provide；Described electrocardiogram (ECG) data be user be everlasting day vehicle movement time detect, by cardioelectric monitor device, the triple channel ECG detecting signal segment that obtains；Described training data includes the m group triple channel static electrocardiosignal section being under arbitrary Heart Rate States that electrocardiosignal simulative generator produces when static and the m group triple channel exercise electrocardiogram signal section being under arbitrary Heart Rate States produced when vehicle movement, and m is the natural number more than 1；Described exercise data includes 3-axis acceleration sensor synchronous acquisition and the electrocardiosignal simulative generator 3-axis acceleration signal segment that produced triple channel exercise electrocardiogram signal section is corresponding when vehicle movement and is detected the 3-axis acceleration signal segment that the triple channel ECG detecting signal segment obtained is corresponding with cardioelectric monitor device when vehicle movement；
Pretreatment module, for carrying out pretreatment to the described static electrocardiosignal section of triple channel, triple channel exercise electrocardiogram signal section, triple channel ECG detecting signal segment and 3-axis acceleration signal segment；Simultaneously for any one Heart Rate States, make pretreated triple channel exercise electrocardiogram signal section under this Heart Rate States corresponding poor with triple channel static electrocardiosignal section, obtain m group triple channel electrocardio motion artifacts；
Neural metwork training module, for any one Heart Rate States, it is trained by artificial neural network learning algorithm according to the triple channel electrocardio motion artifacts under this Heart Rate States and pretreated 3-axis acceleration signal segment, the vehicle movement noise model of the electrocardiosignal that obtains leading about three for this Heart Rate States；
Denoising module, obtain one group of triple channel electrocardio motion artifacts for the Heart Rate States residing for user by vehicle movement noise model corresponding for corresponding with triple channel ECG detecting signal segment 3-axis acceleration signal segment input exports, and then make described triple channel ECG detecting signal segment deduct this triple channel electrocardio motion artifacts to be namely eliminated the triple channel electrocardiogram (ECG) data after vehicle movement noise.
2. cardioelectric monitor system according to claim 1, it is characterized in that: the static electrocardiosignal section of triple channel, triple channel exercise electrocardiogram signal section, triple channel ECG detecting signal segment and 3-axis acceleration signal segment are carried out pretreatment and include form conversion and normalized by described pretreatment module, to obtain the data signal in appropriate format and scope.
3. cardioelectric monitor system according to claim 2, it is characterised in that: described pretreatment module is normalized based on following formula:
Wherein: x is the either signal value in signal segment, xminAnd xmaxThe respectively minima in signal segment and maximum, x' is corresponding x signal value after normalized.
4. cardioelectric monitor system according to claim 1, it is characterised in that: the artificial neural network learning algorithm that described neural metwork training module adopts is using ratio conjugate gradient method as optimizing direction.
5. cardioelectric monitor system according to claim 1, it is characterised in that: the detailed process that described neural metwork training module is trained by artificial neural network learning algorithm is as follows:
(1) it is divided into training set and test set and training set more than test set m group 3-axis acceleration signal segment corresponding with triple channel exercise electrocardiogram signal section after pretreatment；
(2) one neutral net being made up of input layer, hidden layer and output layer of structure is initialized；
(3) appoint from training set and take one group of 3-axis acceleration signal segment and substitute into above-mentioned neural computing and obtain the corresponding output result about electrocardio motion artifacts, calculate the cumulative error between this output result and this triple channel electrocardio motion artifacts corresponding to 3-axis acceleration signal segment；
(4) by gradient descent method, weight between input layer and hidden layer and between hidden layer and output layer in neutral net is modified according to this cumulative error, and then appoints from training set and take off one group of 3-axis acceleration signal segment and substitute into revised neutral net；
(5) travel through all 3-axis acceleration signal segments in training set according to step (3) and (4), take cumulative error minimum time corresponding neutral net be vehicle movement noise model.
6. cardioelectric monitor system according to claim 5, it is characterised in that: in the neutral net that described neural metwork training module initialization builds, input layer is made up of 3 neurons, and hidden layer is made up of 10 neurons, and output layer is made up of 3 neurons.
7. cardioelectric monitor system according to claim 5, it is characterised in that: in the neutral net that described neural metwork training module initialization builds, the expression formula of neuron function g (z) is as follows:
Wherein: z is argument of function.
8. cardioelectric monitor system according to claim 5, it is characterized in that: the vehicle movement noise model that described neural metwork training module obtains for training, 3-axis acceleration signal segment in test set is substituted into one by one this vehicle movement noise model and obtains the corresponding output result about electrocardio motion artifacts, the output result corresponding to each group of 3-axis acceleration signal segment is made in test set to compare with triple channel electrocardio motion artifacts, if test is concentrated with the comparative result words less than or equal to threshold value of a certain proportion of 3-axis acceleration signal segment, then this vehicle movement noise model is finally determined；Otherwise, electrocardiosignal simulative generator and the static electrocardiosignal section of the more triple channel of 3-axis acceleration sensor collection, triple channel exercise electrocardiogram signal section and 3-axis acceleration signal segment is utilized to be trained as the input of neural metwork training module through the signal acquisition module in intelligent terminal with after pretreatment module increasing the scale of training set.
9. cardioelectric monitor system according to claim 1, it is characterised in that: described intelligent terminal is smart mobile phone, panel computer or PC.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610111102.XA CN105769173B (en) | 2016-02-29 | 2016-02-29 | A kind of cardioelectric monitor system with electrocardiosignal noise removal function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610111102.XA CN105769173B (en) | 2016-02-29 | 2016-02-29 | A kind of cardioelectric monitor system with electrocardiosignal noise removal function |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105769173A true CN105769173A (en) | 2016-07-20 |
| CN105769173B CN105769173B (en) | 2018-08-28 |
Family
ID=56403825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610111102.XA Expired - Fee Related CN105769173B (en) | 2016-02-29 | 2016-02-29 | A kind of cardioelectric monitor system with electrocardiosignal noise removal function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105769173B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108158578A (en) * | 2017-12-14 | 2018-06-15 | 北京顺源开华科技有限公司 | Noise segments recognition methods, ECG signal processing method and processing device |
| CN108594937A (en) * | 2018-04-18 | 2018-09-28 | 余海波 | Portable terminal |
| CN108742538A (en) * | 2018-06-20 | 2018-11-06 | 大国创新智能科技(东莞)有限公司 | Sign measurement method and medical robotic system based on big data and artificial intelligence |
| CN108968941A (en) * | 2018-05-25 | 2018-12-11 | 深圳市太空科技南方研究院 | A kind of arrhythmia detection method, apparatus and terminal |
| CN109788906A (en) * | 2016-09-28 | 2019-05-21 | 皇家飞利浦有限公司 | Patient monitoring devices |
| CN110141216A (en) * | 2019-05-29 | 2019-08-20 | 清华大学深圳研究生院 | A kind of recognition methods, training method and the system of electrocardiosignal QRS characteristic wave |
| LU100925B1 (en) * | 2018-09-10 | 2020-03-10 | Iee Sa | Removing noise caused by vehicular movement from sensor signals using Deep Neural Networks |
| CN111184508A (en) * | 2020-01-19 | 2020-05-22 | 武汉大学 | Electrocardiosignal detection device and analysis method based on joint neural network |
| CN112067015A (en) * | 2020-09-03 | 2020-12-11 | 青岛歌尔智能传感器有限公司 | Step counting method and device based on convolutional neural network and readable storage medium |
| CN112089412A (en) * | 2020-04-17 | 2020-12-18 | 中国人民解放军第二军医大学 | Method for performing algorithm denoising by using motion sensor in cooperation with electrocardiogram monitoring |
| CN115836867A (en) * | 2023-02-14 | 2023-03-24 | 中国科学技术大学 | Dual-branch fusion deep learning electroencephalogram noise reduction method, device and medium |
| CN116304777A (en) * | 2023-04-12 | 2023-06-23 | 中国科学院大学 | Self-adaptive electrocardiosignal denoising method and system based on reference signal during rest |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20240006527A (en) * | 2021-05-11 | 2024-01-15 | 하만 베커 오토모티브 시스템즈 게엠베하 | Fused context sensors to improve biosignal extraction |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104665849A (en) * | 2014-12-11 | 2015-06-03 | 西南交通大学 | Multi-physiological signal multi-model interaction-based high-speed railway dispatcher stress detecting method |
| CN105246400A (en) * | 2013-03-15 | 2016-01-13 | 佐尔医药公司 | Ecg noise reduction system for removal of vehicle motion artifact |
| WO2016024081A1 (en) * | 2014-08-13 | 2016-02-18 | Saumarez Richard C | Improvement to analysing physiological electrograms |
-
2016
- 2016-02-29 CN CN201610111102.XA patent/CN105769173B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105246400A (en) * | 2013-03-15 | 2016-01-13 | 佐尔医药公司 | Ecg noise reduction system for removal of vehicle motion artifact |
| WO2016024081A1 (en) * | 2014-08-13 | 2016-02-18 | Saumarez Richard C | Improvement to analysing physiological electrograms |
| CN104665849A (en) * | 2014-12-11 | 2015-06-03 | 西南交通大学 | Multi-physiological signal multi-model interaction-based high-speed railway dispatcher stress detecting method |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109788906A (en) * | 2016-09-28 | 2019-05-21 | 皇家飞利浦有限公司 | Patient monitoring devices |
| CN108158578A (en) * | 2017-12-14 | 2018-06-15 | 北京顺源开华科技有限公司 | Noise segments recognition methods, ECG signal processing method and processing device |
| CN108594937A (en) * | 2018-04-18 | 2018-09-28 | 余海波 | Portable terminal |
| CN108968941A (en) * | 2018-05-25 | 2018-12-11 | 深圳市太空科技南方研究院 | A kind of arrhythmia detection method, apparatus and terminal |
| CN108742538B (en) * | 2018-06-20 | 2022-04-01 | 大国创新智能科技(东莞)有限公司 | Physical sign measuring method based on big data and artificial intelligence and medical robot system |
| CN108742538A (en) * | 2018-06-20 | 2018-11-06 | 大国创新智能科技(东莞)有限公司 | Sign measurement method and medical robotic system based on big data and artificial intelligence |
| LU100925B1 (en) * | 2018-09-10 | 2020-03-10 | Iee Sa | Removing noise caused by vehicular movement from sensor signals using Deep Neural Networks |
| WO2020053148A1 (en) | 2018-09-10 | 2020-03-19 | Iee International Electronics & Engineering S.A. | Removing noise caused by vehicular movement from sensor signals using deep neural networks |
| CN110141216A (en) * | 2019-05-29 | 2019-08-20 | 清华大学深圳研究生院 | A kind of recognition methods, training method and the system of electrocardiosignal QRS characteristic wave |
| CN111184508A (en) * | 2020-01-19 | 2020-05-22 | 武汉大学 | Electrocardiosignal detection device and analysis method based on joint neural network |
| CN112089412A (en) * | 2020-04-17 | 2020-12-18 | 中国人民解放军第二军医大学 | Method for performing algorithm denoising by using motion sensor in cooperation with electrocardiogram monitoring |
| CN112067015A (en) * | 2020-09-03 | 2020-12-11 | 青岛歌尔智能传感器有限公司 | Step counting method and device based on convolutional neural network and readable storage medium |
| CN115836867A (en) * | 2023-02-14 | 2023-03-24 | 中国科学技术大学 | Dual-branch fusion deep learning electroencephalogram noise reduction method, device and medium |
| CN115836867B (en) * | 2023-02-14 | 2023-06-16 | 中国科学技术大学 | Deep learning electroencephalogram noise reduction method, equipment and medium with double-branch fusion |
| CN116304777A (en) * | 2023-04-12 | 2023-06-23 | 中国科学院大学 | Self-adaptive electrocardiosignal denoising method and system based on reference signal during rest |
| CN116304777B (en) * | 2023-04-12 | 2023-11-03 | 中国科学院大学 | Self-adaptive electrocardiosignal denoising method and system based on reference signal during rest |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105769173B (en) | 2018-08-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105769173A (en) | Electrocardiogram monitoring system with electrocardiosignal denoising function | |
| CN107714023B (en) | Static electrocardiogram analysis method and device based on artificial intelligence self-learning | |
| CN107788976A (en) | Sleep monitor system based on Amplitude integrated electroencephalogram | |
| CN103190905B (en) | Multi-channel surface electromyography signal collection system based on wireless fidelity (Wi-Fi) and processing method thereof | |
| CN110123314B (en) | Method for judging brain concentration and relaxation state based on electroencephalogram signals | |
| CN104490387B (en) | Wireless portable and the Wearable ECG detector of motion artifacts can be suppressed | |
| CN111317600B (en) | Artificial limb control method, device, system, equipment and storage medium | |
| CN103110416A (en) | Remote electrocardio intelligent monitoring system | |
| CN202288542U (en) | Artificial limb control device | |
| CN105534517A (en) | Method for removing vehicle motion noise in three-lead electrocardiosignal | |
| CN107822629A (en) | The detection method of extremity surface myoelectricity axle | |
| CN105796091A (en) | Intelligent terminal for removing electrocardiosignal vehicle motion noise | |
| CN104267807A (en) | Hand action mechanomyography based man-machine interaction method and interaction system | |
| CN101449971A (en) | Portable cardiac diagnosis monitoring device based on rhythm mode | |
| CN106667436A (en) | Sleep diagnosis method and system | |
| CN105943022B (en) | A kind of cardioelectric monitor system that there are three leads to reconstruct 12 lead function | |
| CN111297340A (en) | Movement state monitoring method based on combination of GPS and heart rate | |
| CN106974644A (en) | A kind of electrocardiogram R wave detection method and system | |
| CN110751060B (en) | Portable motion mode real-time identification system based on multi-source signals | |
| CN116687409B (en) | Emotion recognition method and system based on digital twin and deep learning | |
| CN111543983B (en) | Electroencephalogram signal channel selection method based on neural network | |
| CN204581273U (en) | A kind of hand held ECG Signal Sampling System for identity validation | |
| CN105686827A (en) | Microcontroller based electromyogram signal processing and feature extraction method | |
| CN115607167A (en) | Lightweight model training method, atrial fibrillation detection method, device and system | |
| CN109770851A (en) | A kind of health of heart condition monitoring system and method based on Bluetooth wireless communication |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20190724 Address after: 312000, Zhejiang, Shaoxing City, Pingjiang Road, No. 328, ninth, one floor Patentee after: ZHEJIANG MEDZONE MEDICAL EQUIPMENT CO.,LTD. Address before: 312000, Shaoxing, Pingjiang Road, No. 328, ninth, two, Zhejiang Co-patentee before: ZHEJIANG MEDZONE MEDICAL EQUIPMENT CO.,LTD. Patentee before: ZHEJIANG MINGZHONG TECHNOLOGY Co.,Ltd. Co-patentee before: ZHEJIANG MEDZONE BIOMEDICAL MATERIAL AND DEVICE Research Institute |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200922 Address after: Room 703, 7 / F, No. 3766, Nanhuan Road, Binjiang District, Hangzhou City, Zhejiang Province Patentee after: ZHEJIANG MINGZHONG TECHNOLOGY Co.,Ltd. Address before: 312000, Zhejiang, Shaoxing City, Pingjiang Road, No. 328, ninth, one floor Patentee before: ZHEJIANG MEDZONE MEDICAL EQUIPMENT Co.,Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180828 |