CN105796091B - A kind of intelligent terminal for removing electrocardiosignal vehicle movement noise - Google Patents

A kind of intelligent terminal for removing electrocardiosignal vehicle movement noise Download PDF

Info

Publication number
CN105796091B
CN105796091B CN201610113597.XA CN201610113597A CN105796091B CN 105796091 B CN105796091 B CN 105796091B CN 201610113597 A CN201610113597 A CN 201610113597A CN 105796091 B CN105796091 B CN 105796091B
Authority
CN
China
Prior art keywords
triple channel
signal segment
axis acceleration
vehicle movement
module
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
Application number
CN201610113597.XA
Other languages
Chinese (zh)
Other versions
CN105796091A (en
Inventor
姚剑
何挺挺
姚志邦
赵晓鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Mingzhong Technology Co ltd
Original Assignee
ZHEJIANG MEDZONE BIOMEDICAL MATERIALS AND EQUIPMENT RESEARCH INSTITUTE
Zhejiang Mingzhong Medical Technology Co Ltd
ZHEJIANG MINGZHONG TECHNOLOGY Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by ZHEJIANG MEDZONE BIOMEDICAL MATERIALS AND EQUIPMENT RESEARCH INSTITUTE, Zhejiang Mingzhong Medical Technology Co Ltd, ZHEJIANG MINGZHONG TECHNOLOGY Co Ltd filed Critical ZHEJIANG MEDZONE BIOMEDICAL MATERIALS AND EQUIPMENT RESEARCH INSTITUTE
Priority to CN201610113597.XA priority Critical patent/CN105796091B/en
Publication of CN105796091A publication Critical patent/CN105796091A/en
Application granted granted Critical
Publication of CN105796091B publication Critical patent/CN105796091B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/24Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316Modalities, i.e. specific diagnostic methods
    • A61B5/318Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/24Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316Modalities, i.e. specific diagnostic methods
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7203Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • A61B5/7207Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal of noise induced by motion artifacts
    • A61B5/721Signal 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
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235Details of waveform analysis

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Psychiatry (AREA)
  • Physiology (AREA)
  • Cardiology (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

The invention discloses a kind of intelligent terminals for removing electrocardiosignal vehicle movement noise, including processor and bluetooth communication unit;Processor is loaded with signal acquisition module, preprocessing module, neural metwork training module and denoising module.Intelligent terminal of the present invention acquires exercise data as neural network input sample using 3-axis acceleration sensor, it is pre-processed by the dynamic electrocardiogram (ECG) data of format conversion and method for normalizing before neural metwork training when and movement static to human body and the deviation that makes between the two is used as the supervision of neural network, and then noise model is established with the optimal way of ratio conjugate gradient using artificial neural network learning algorithm, the dynamic electrocardiogram (ECG) data obtained with monitoring subtracts corresponding motion artifacts and completes denoising.Whole equipment is easy and is easily achieved, and vehicle movement noise can be effectively automatically removed during cardioelectric monitor, obtains accurate electrocardiogram (ECG) data, guarantee is provided to the diagnosis and treatment of angiocardiopathy for doctor.

Description

A kind of intelligent terminal for removing electrocardiosignal vehicle movement noise
Technical field
The invention belongs to technical field of medical equipment, and in particular to a kind of for removing electrocardiosignal vehicle movement noise Intelligent terminal.
Background technology
Holter is for continuously recording 24 hours dynamic electrocardiogram activity datas, including rest, activity, work, dining Etc. electrocardio-activity data under different situations, can help for finding the symptoms such as arrhythmia cordis and myocardial ischemia, be clinical point The analysis state of an illness and diagnosis and treatment provide important foundation.With emerging in large numbers for portable wearable cardiac monitoring equipment so that user can be each Very easily cardioelectric monitor is carried out under kind of state.But Holter signal is highly susceptible to the interference of various noises, it is main Interfere AC influence, myoelectricity interference, baseline drift, conducting wire connection error, electrode slice and skin contact insufficient etc., with The development of technology, most of Holter equipment is all configured with various types of filters to eliminate these interference, but Be portable dynamic ecg equipment on a moving vehicle in use, the interference of vehicle movement may seriously limit dynamic The quality of ECG signal.
The motion artifacts of vehicle can act on object onboard, including the cardioelectric monitor equipment that human body is dressed.And vehicle The state of movement can reflect influence of the interference to cardioelectric monitor equipment well, can be non-by 3-axis acceleration sensor The motion state for often easily obtaining vehicle carries to analyze the influence mode and degree of movement to eliminate vehicle movement interference For data basis.
3-axis acceleration sensor is a kind of sensor that physical signal acceleration is converted into the electric signal convenient for measuring, The operation principle of current most of 3-axis acceleration sensors is pressure resistance type, piezoelectric type and condenser type, the acceleration direct ratio of generation In the variation of resistance, voltage and capacitance, by calculating the relationship between these variable quantities and acceleration, you can calculate acceleration Value.3-axis acceleration sensor can under the occasion for not knowing object moving state in advance, by detect x, tri- axis of y, z Signal obtains its coordinate components, to the motion state of accurate judgement object, has small, light-weight characteristic point, can be with Steric acceleration is measured, the kinetic property of object can be accurately reflected comprehensively, in aerospace, automobile, robot and medicine etc. Field obtains extensive use.
Most portable holter devices currently on the market, simple structure do not eliminate vehicle movement noise work( Can, it is easily used to be interfered under state of motion of vehicle and causes Holter jitter, the ecg wave form of record It is not used to ecg analysis, not only limits the use scope of dynamic ecg monitoring equipment, it is also possible to make doctor to cardiovascular disease The diagnosis and treatment of patient cause serious consequence.
Invention content
For the above-mentioned technical problem present in the prior art, the present invention provides one kind for removing electrocardiosignal vehicle The intelligent terminal of motion artifacts can effectively automatically remove vehicle movement noise during cardioelectric monitor, obtain accurate Electrocardiogram (ECG) data provides guarantee for doctor to the diagnosis and treatment of angiocardiopathy.
A kind of intelligent terminal for removing electrocardiosignal vehicle movement noise, including processor and bluetooth communication unit, The processor is loaded with following functions module:
Signal acquisition module, for collecting the electrocardio that cardioelectric monitor device provides by the bluetooth communication module in intelligent terminal Training data and 3-axis acceleration sensor under each Heart Rate States of correspondence that data, electrocardiosignal simulative generator provide carry The exercise data of confession;The electrocardiogram (ECG) data is the daily threeway detected by cardioelectric monitor device in vehicle movement of user Road ECG detecting signal segment;The training data include electrocardiosignal simulative generator generated when static be in any heart The static electrocardiosignal section of m group triple channels under rate state and the m under any Heart Rate States generated in vehicle movement Group triple channel exercise electrocardiogram signal section, m are the natural number more than 1;The exercise data includes that 3-axis acceleration sensor is same Step acquisition corresponding three axis of the generated triple channel exercise electrocardiogram signal section in vehicle movement with electrocardiosignal simulative generator Acceleration signal section and corresponding with the triple channel ECG detecting signal segment that cardioelectric monitor device is detected in vehicle movement 3-axis acceleration signal segment;
Preprocessing module, for the static electrocardiosignal section of triple channel, triple channel exercise electrocardiogram signal section, threeway Road ECG detecting signal segment and 3-axis acceleration signal segment are pre-processed;Simultaneously for any Heart Rate States, make the heart rate Pretreated triple channel exercise electrocardiogram signal section work corresponding with the static electrocardiosignal section of triple channel is poor under state, obtains m groups three Channel electrocardio motion artifacts;
Neural metwork training module moves any Heart Rate States according to the triple channel electrocardio under the Heart Rate States Noise and pretreated 3-axis acceleration signal segment are trained by artificial neural network learning algorithm, are obtained being directed to and are somebody's turn to do Vehicle movement noise model of the Heart Rate States about three lead electrocardiosignals;
Denoising module, will three axis corresponding with triple channel ECG detecting signal segment for the Heart Rate States residing for user Acceleration signal section inputs output in corresponding vehicle movement noise model and obtains a set of three links road electrocardio motion artifacts, and then makes The triple channel ECG detecting signal segment subtracts the triple channel electrocardio motion artifacts and is eliminated after vehicle movement noise Triple channel electrocardiogram (ECG) data.
The preprocessing module is to the static electrocardiosignal section of triple channel, triple channel exercise electrocardiogram signal section, the triple channel heart It includes format conversion and normalized that power detection signal section and 3-axis acceleration signal segment, which carry out pretreatment, to obtain appropriate lattice Data-signal in formula and range.
The preprocessing module is normalized based on following formula:
Wherein:X is the either signal value in signal segment, xminAnd xmaxMinimum value and maximum value respectively in signal segment, X' is signal values of the corresponding x after normalized.
Artificial neural network learning algorithm used by the neural metwork training module is made with ratio conjugate gradient method To optimize direction.
The detailed process that the neural metwork training module is trained by artificial neural network learning algorithm is as follows:
(1) m groups 3-axis acceleration signal segment corresponding with triple channel exercise electrocardiogram signal section after pretreatment is divided into training Collection is with test set and training set is more than test set;
(2) one neural network being made of input layer, hidden layer and output layer of initialization structure;
(3) appoint from training set take one group of 3-axis acceleration signal segment substitute into above-mentioned neural computing obtain it is corresponding about The output of electrocardio motion artifacts is transported as a result, calculating the output result with the triple channel electrocardio corresponding to the 3-axis acceleration signal segment Accumulated error between moving noise;
(4) according to the accumulated error by gradient descent method in neural network between input layer and hidden layer and hide Weight between layer and output layer is modified, and then is appointed from training set and removed one group of 3-axis acceleration signal segment substitution amendment Neural network afterwards;
(5) according to all 3-axis acceleration signal segments in step (3) and (4) traversal training set, take accumulated error minimum When corresponding neural network be vehicle movement noise model.
Input layer is made of 3 neurons in the neural network of the neural metwork training module initialization structure, hidden It hides layer to be made of 10 neurons, output layer is made of 3 neurons.
The expression formula of neuron function g (z) is such as in the neural network of the described neural metwork training module initialization structure Under:
Wherein:Z is argument of function.
The vehicle movement noise model that the neural metwork training module obtains training, by three axis in test set Acceleration signal section substitutes into the vehicle movement noise model and obtains the corresponding output about electrocardio motion artifacts as a result, making survey one by one Examination concentrates the output result corresponding to each group of 3-axis acceleration signal segment to be compared with triple channel electrocardio motion artifacts, if surveying Examination be concentrated with a certain proportion of 3-axis acceleration signal segment comparison result be less than or equal to threshold value if, then the vehicle movement noise Model finally determines;Otherwise acquiring more threeways using electrocardiosignal simulative generator and 3-axis acceleration sensor The static electrocardiosignal section in road, triple channel exercise electrocardiogram signal section and 3-axis acceleration signal segment are through the signal acquisition in intelligent terminal The input of scale as neural metwork training module after module and preprocessing module to increase training set is trained.
The intelligent terminal can be smart mobile phone, tablet computer or PC machine.
Intelligent terminal of the present invention is led to using 3-axis acceleration sensor acquisition exercise data as neural network input sample Dynamic electrocardiogram (ECG) data when crossing static to human body before neural metwork training format conversion and method for normalizing and movement carries out pre- It handles and makes deviation between the two as the supervision of neural network, and then is total with ratio using artificial neural network learning algorithm The optimal way of yoke gradient establishes noise model, and the dynamic electrocardiogram (ECG) data obtained with monitoring subtracts corresponding motion artifacts and completes Denoising.Whole equipment is easy and is easily achieved, and vehicle movement noise can be effectively automatically removed during cardioelectric monitor, is obtained To accurate electrocardiogram (ECG) data, guarantee is provided to the diagnosis and treatment of angiocardiopathy for doctor.
Description of the drawings
Fig. 1 is the structural schematic diagram of intelligent terminal of the present invention.
Fig. 2 is the artificial nerve network model schematic diagram during electrocardiosignal denoising of the present invention.
Specific implementation mode
In order to more specifically describe the present invention, below in conjunction with the accompanying drawings and specific implementation mode is to technical scheme of the present invention It is described in detail.
As shown in Figure 1, for removing the intelligent terminal of electrocardiosignal vehicle movement noise using intelligent hand in the present embodiment Machine includes processor and bluetooth communication module in the smart mobile phone, and bluetooth communication module is connected with processor;Processor includes Signal acquisition module, preprocessing module, neural metwork training module and denoising module;Wherein:
Bluetooth communication module is communicated for intelligent terminal with electrocardiogram monitoring terminal, and intelligent terminal sends commands to prison Terminal is surveyed, monitoring terminal response command uploads electrocardiogram (ECG) data to intelligent terminal.
Signal acquisition module is used to receive the dynamic electrocardiogram (ECG) data from generator or monitor by bluetooth communication module And carry out the motion state data of acceleration sensor;Dynamic electrocardiogram (ECG) data includes that m groups are acquired in stationary state, is in Electrocardiosignal sequence E under a kind of Heart Rate States then has the static electrocardiogram (ECG) data E of n*m groups due to the Heart Rate States for having n kinds different;m What group was acquired in state of motion of vehicle, the electrocardiosignal sequence M under a kind of Heart Rate States, due to the heart rate for having n kinds different State then has n*m group exercise ECG data M.
Motion state data is what m groups were acquired in state of motion of vehicle, corresponds to three axis under wherein a kind of Heart Rate States Acceleration sensor outputs signals sequence Q [x, y, z] then has n*m group motion state sequences due to the Heart Rate States for having n kinds different Q [x, y, z] is arranged, m, n are the natural number more than 1.
Preprocessing module is used to carry out format conversion and normalized to dynamic electrocardiogram (ECG) data and motion state data, obtains To appropriate format and the initial data of range.In the present embodiment, data sampling rate 250, AD conversion digit is 24bit, is passed through Sample rate is reduced to 200 by down-sampled algorithm, and 24bit data are converted to 16bit by data compression algorithm, obtain capacity smaller Data, but need to meet the needs of neural metwork training module.Normalization algorithm uses linear transformation algorithm, and expression formula is:
Wherein:X is input vector, and max is the maximum value of x, and min is the minimum value of x, and f (x) is the later output of normalization Vector.
Neural metwork training module passes through artificial neuron to the pretreated motion state operational data sequence of above-mentioned n*m groups Network depth learning algorithm is trained and tests, and obtains noise model;Specific implementation is as follows:
(1) the pretreated motion state data sequence Q [x, y, z] being under a kind of Heart Rate States of m groups is divided into training Collection is with test set and training set is more than test set.
(2) initial neural network model is established according to artificial neural network learning algorithm:The neural network model is by inputting Layer, hidden layer, output are connected between input layer and hidden layer by formula (1) at up of three layers, and the input of input layer is three axis The activation primitive of acceleration transducer x, y, the operational data sequence of z-axis, hidden layer and output layer is formula (2), hidden layer by 10 neurons are constituted, and the output of output layer is 3-axis acceleration sensor x, y, the noise of z-axis, the neural network model of foundation As shown in Figure 2.
Wherein,WithFor the coefficient of hidden layer, g is tansig functions, i=1,2 ..., 10, j=1,2,3.
Wherein,WithFor the coefficient of output layer, i=1,2,3, j=1,2 ..., 10.
(3) one group of sample data of training set is input to the neural network under current weight coefficient, calculates input successively The output of each node of layer, hidden layer, output layer.
(4) it is calculated between the output layer output of all training samples and the expected result of training sample according to formula (3) Accumulated error E corrects the weight coefficient between input layer and each node of hidden layer according to conjugate gradient decent according to formula (4), The weight coefficient between hidden layer and each node of output layer is corrected according to formula (5):
Wherein:E is accumulated error,K-th of output of the output layer for single training sample Jing Guo neural network, okFor K-th of expected result of single training sample, m are training set total sample number, and p is output layer output sum.
Wherein:who(t) weight coefficient when being input to neural network for the t times sample between hidden layer and output layer, The output of output layer for single training sample Jing Guo neural network, o are the expected result of single training sample, xhFor hidden layer Output, α is learning rate.
Wherein:wih(t) weight coefficient when being input to neural network for the t times sample between input layer and hidden layer, xi For the output of input layer.
(5) it repeats step (3) and step (4) traverses all training sets, establish noise model, obtain weights when E minimums Then noise model corresponding to coefficient sets is tested the noise model using test set, if the accuracy of test is high In threshold value, then the noise model is best model;If the accuracy of test is less than threshold value, training sample repetition is continued growing Step (3) and step (4) train neural network, until training is completed.Trained obtained weight coefficient matrix is in the present embodiment:
Input layer and hidden layer:
Hidden layer and output layer:
Denoising module is used for the weights proportion according to each layer of neural network, restores the system function of noise model;By user The 3-axis acceleration output data for the embodiment human motion state that daily monitoring obtains substitutes into noise model, and output is made an uproar accordingly Sound as a result, then using the dynamic electrocardiogram (ECG) data that monitor obtains subtract noise model output noise figure, obtain removal noise Dynamic electrocardiogram (ECG) data afterwards.
This hair can be understood and applied the above description of the embodiments is intended to facilitate those skilled in the art It is bright.Person skilled in the art obviously easily can make various modifications to above-described embodiment, and described herein General Principle is applied in other embodiment without having to go through creative labor.Therefore, the present invention is not limited to the above embodiments, Those skilled in the art's announcement according to the present invention, the improvement made for the present invention and modification all should be in the protections of the present invention Within the scope of.

Claims (5)

1. a kind of intelligent terminal for removing electrocardiosignal vehicle movement noise, including processor and bluetooth communication unit;Its It is characterized in that, the processor is loaded with following functions module:
Signal acquisition module, for collecting the electrocardio number that cardioelectric monitor device provides by the bluetooth communication module in intelligent terminal Training data and 3-axis acceleration sensor under each Heart Rate States of correspondence provided according to, electrocardiosignal simulative generator provide Exercise data;The electrocardiogram (ECG) data is the daily triple channel detected by cardioelectric monitor device in vehicle movement of user ECG detecting signal segment;The training data include electrocardiosignal simulative generator generated when static be in any heart rate The static electrocardiosignal section of m group triple channels under state and the m groups under any Heart Rate States generated in vehicle movement Triple channel exercise electrocardiogram signal section, m are the natural number more than 1;The exercise data includes that 3-axis acceleration sensor synchronizes Corresponding three axis of the generated triple channel exercise electrocardiogram signal section in vehicle movement adds with electrocardiosignal simulative generator for acquisition Speed signal section and corresponding with the triple channel ECG detecting signal segment that cardioelectric monitor device is detected in vehicle movement 3-axis acceleration signal segment;
Preprocessing module, for the static electrocardiosignal section of triple channel, triple channel exercise electrocardiogram signal section, the triple channel heart Power detection signal section and 3-axis acceleration signal segment are pre-processed;Simultaneously for any Heart Rate States, make the Heart Rate States Under pretreated triple channel exercise electrocardiogram signal section it is corresponding with the static electrocardiosignal section of triple channel make it is poor, obtain m group triple channels Electrocardio motion artifacts;
Neural metwork training module, for any Heart Rate States, according to the triple channel electrocardio motion artifacts under the Heart Rate States And pretreated 3-axis acceleration signal segment is trained by artificial neural network learning algorithm, obtains being directed to the heart rate Vehicle movement noise model of the state about three lead electrocardiosignals;
Denoising module accelerates three axis corresponding with triple channel ECG detecting signal segment for the Heart Rate States residing for user Degree signal segment inputs output in corresponding vehicle movement noise model and obtains a set of three links road electrocardio motion artifacts, and then makes described Triple channel ECG detecting signal segment subtract the triple channel electrocardio motion artifacts and be eliminated the threeway after vehicle movement noise Road electrocardiogram (ECG) data;
The preprocessing module examines the static electrocardiosignal section of triple channel, triple channel exercise electrocardiogram signal section, triple channel electrocardio It includes format conversion and normalized to survey signal segment and 3-axis acceleration signal segment and carry out pretreatment, with obtain appropriate format and Data-signal in range;Wherein normalized is based on following formula:
Wherein:X is the either signal value in signal segment, xminAnd xmaxMinimum value and maximum value respectively in signal segment, x' are Signal values of the corresponding x after normalized;
The detailed process that the neural metwork training module is trained by artificial neural network learning algorithm is as follows:
(1) by m groups 3-axis acceleration signal segment corresponding with triple channel exercise electrocardiogram signal section after pretreatment be divided into training set and Test set and training set are more than test set;
(2) one neural network being made of input layer, hidden layer and output layer of initialization structure;
(3) appoint from training set and one group of above-mentioned neural computing of 3-axis acceleration signal segment substitution is taken to obtain corresponding to about electrocardio The output of motion artifacts is made an uproar as a result, calculating the output result with the triple channel electrocardio movement corresponding to the 3-axis acceleration signal segment Accumulated error between sound;
(4) according to the accumulated error by gradient descent method in neural network between input layer and hidden layer and hidden layer with Weight between output layer is modified, so appoint from training set remove one group of 3-axis acceleration signal segment substitute into it is revised Neural network;
(5) according to all 3-axis acceleration signal segments in step (3) and (4) traversal training set, accumulated error minimum when institute is taken Corresponding neural network is vehicle movement noise model;
The vehicle movement noise model that the neural metwork training module obtains training accelerates three axis in test set Degree signal segment substitutes into the vehicle movement noise model and obtains the corresponding output about electrocardio motion artifacts as a result, making test set one by one In output result corresponding to each group of 3-axis acceleration signal segment be compared with triple channel electrocardio motion artifacts, if test set In there is the comparison result of a certain proportion of 3-axis acceleration signal segment to be less than or equal to threshold value if, then the vehicle movement noise model It is final to determine;Otherwise it is quiet to acquire more triple channels using electrocardiosignal simulative generator and 3-axis acceleration sensor Only electrocardiosignal section, triple channel exercise electrocardiogram signal section and 3-axis acceleration signal segment are through the signal acquisition module in intelligent terminal Input with scale as neural metwork training module to increase training set after preprocessing module is trained.
2. intelligent terminal according to claim 1, it is characterised in that:People used by the neural metwork training module Artificial neural networks learning algorithm is with ratio conjugate gradient method direction as an optimization.
3. intelligent terminal according to claim 1, it is characterised in that:The neural metwork training module initialization structure Neural network in input layer be made of 3 neurons, hidden layer is made of 10 neurons, and output layer is by 3 neural tuples At.
4. intelligent terminal according to claim 1, it is characterised in that:The neural metwork training module initialization structure Neural network in neuron function g (z) expression formula it is as follows:
Wherein:Z is argument of function.
5. intelligent terminal according to claim 1, it is characterised in that:The intelligent terminal is smart mobile phone, tablet electricity Brain or PC machine.
CN201610113597.XA 2016-02-29 2016-02-29 A kind of intelligent terminal for removing electrocardiosignal vehicle movement noise Expired - Fee Related CN105796091B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610113597.XA CN105796091B (en) 2016-02-29 2016-02-29 A kind of intelligent terminal for removing electrocardiosignal vehicle movement noise

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610113597.XA CN105796091B (en) 2016-02-29 2016-02-29 A kind of intelligent terminal for removing electrocardiosignal vehicle movement noise

Publications (2)

Publication Number Publication Date
CN105796091A CN105796091A (en) 2016-07-27
CN105796091B true CN105796091B (en) 2018-09-28

Family

ID=56465929

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610113597.XA Expired - Fee Related CN105796091B (en) 2016-02-29 2016-02-29 A kind of intelligent terminal for removing electrocardiosignal vehicle movement noise

Country Status (1)

Country Link
CN (1) CN105796091B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108470158B (en) * 2018-03-08 2020-05-12 华南理工大学 Method for searching error minimum network computing structure for dynamic ECG data
LU100925B1 (en) * 2018-09-10 2020-03-10 Iee Sa Removing noise caused by vehicular movement from sensor signals using Deep Neural Networks
CN113491513B (en) * 2020-04-08 2023-06-30 华为技术有限公司 Heart rhythm detection control method and terminal
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

Citations (3)

* Cited by examiner, † Cited by third party
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

Patent Citations (3)

* Cited by examiner, † Cited by third party
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

Also Published As

Publication number Publication date
CN105796091A (en) 2016-07-27

Similar Documents

Publication Publication Date Title
CN105769173B (en) A kind of cardioelectric monitor system with electrocardiosignal noise removal function
CN110420019B (en) Deep regression heart rate estimation method for ballistocardiogram signals
EP3692900A1 (en) Artificial intelligence self-learning-based static electrocardiography analysis method and apparatus
CN107536599A (en) The System and method for of live signal segmentation and datum mark alignment framework is provided
CN109907752A (en) A kind of cardiac diagnosis and monitoring method and system of the interference of removal motion artifacts and ecg characteristics detection
CN105796091B (en) A kind of intelligent terminal for removing electrocardiosignal vehicle movement noise
CN111317600B (en) Artificial limb control method, device, system, equipment and storage medium
CN109431492B (en) Electrocardiogram lead data simulation reconstruction method based on neural network algorithm
CN110148466B (en) Computer-aided diagnosis method for atrial fibrillation with cardiac shock signal based on transfer learning
CN105534517A (en) Method for removing vehicle motion noise in three-lead electrocardiosignal
Song et al. Nas-ppg: Ppg-based heart rate estimation using neural architecture search
CN106446762A (en) Motion imagination EEG classification processing method based on sparse representation classification algorithm
CN108509823A (en) The detection method and device of QRS complex
CN108523868A (en) Self-calibration system and method for blood pressure measurement
Turgunov et al. A new dataset for the detection of hand movements based on the SEMG signal
Fu et al. Finger gesture recognition using sensing and classification of surface electromyography signals with high-precision wireless surface electromyography sensors
CN111543983B (en) Electroencephalogram signal channel selection method based on neural network
CN113143270A (en) Bimodal fusion emotion recognition method based on biological radar and voice information
Li et al. Human-computer interaction system design based on surface EMG signals
Yang et al. Wrist movement detection for prosthesis control using surface EMG and triaxial accelerometer
Rashkovska et al. Clustering of heartbeats from ECG recordings obtained with wireless body sensors
CN113520413B (en) Lower limb multi-joint angle estimation method based on surface electromyogram signals
CN113057646B (en) Electrocardiogram mapping method and system
CN113768516B (en) Electrocardiogram abnormality degree detection method and system based on artificial intelligence
Benatti et al. Biomedical Signal Analysis 1

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: 20190729

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: 20200918

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: 20180928