Nothing Special   »   [go: up one dir, main page]

CN105962967A - Heart sound denoising method based on double-microphone stethoscope - Google Patents

Heart sound denoising method based on double-microphone stethoscope Download PDF

Info

Publication number
CN105962967A
CN105962967A CN201610343726.4A CN201610343726A CN105962967A CN 105962967 A CN105962967 A CN 105962967A CN 201610343726 A CN201610343726 A CN 201610343726A CN 105962967 A CN105962967 A CN 105962967A
Authority
CN
China
Prior art keywords
cardiechema signals
signal
heart sound
microphone
denoising method
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201610343726.4A
Other languages
Chinese (zh)
Inventor
梁庆真
黄凯
刘传银
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.)
Sichuan Changhong Electric Co Ltd
Original Assignee
Sichuan Changhong Electric 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 Sichuan Changhong Electric Co Ltd filed Critical Sichuan Changhong Electric Co Ltd
Priority to CN201610343726.4A priority Critical patent/CN105962967A/en
Publication of CN105962967A publication Critical patent/CN105962967A/en
Pending legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B7/00—Instruments for auscultation
    • A61B7/02—Stethoscopes
    • A61B7/04—Electric stethoscopes
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/46—Special adaptations for use as contact microphones, e.g. on musical instrument, on stethoscope
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R3/00—Circuits for transducers, loudspeakers or microphones
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R3/00—Circuits for transducers, loudspeakers or microphones
    • H04R3/005—Circuits for transducers, loudspeakers or microphones for combining the signals of two or more microphones
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R2410/00—Microphones
    • H04R2410/01—Noise reduction using microphones having different directional characteristics

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Acoustics & Sound (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Multimedia (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Otolaryngology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Instructional Devices (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

The invention discloses a heart sound denoising method based on a double-microphone stethoscope. The method comprises the following steps of signal connecting, signal processing, feature extracting and heart sound signal selecting. By means of the heart sound denoising method based on the double-microphone stethoscope, a doctor can hear clearer signals, and therefore the doctor can well diagnose heart conditions.

Description

Based on diamylose gram stethoscopic heart sound denoising method
Technical field
The present invention relates to signal processing technology field, be specifically related to based on diamylose gram stethoscopic heart sound denoising side Method.
Background technology
Heart sound is myocardial contraction diastole, valve opens and closes and blood flowing is clashed into ventricle wall and arterial wall etc. and caused Vibration, can directly reflect the information relevant with heart disease, therefore clinician is examined by heart sound detection Disconnected heart disease has the biggest assosting effect.
But, many extraneous factors can affect the collection of cardiechema signals.Heart sound is that weak electric signal is down to the most weak External noise lead to the false judgment of the pathology in signal and physiologic information, thus cause the mistake of disease Examine.Therefore it is extremely important to cardiechema signals denoising.
Summary of the invention
Instant invention overcomes extraneous factor in prior art and can affect the collection of cardiechema signals, thus cause disease The deficiency examined of mistake, it is provided that a kind of based on diamylose gram stethoscopic heart sound denoising method.
For achieving the above object, the present invention is by the following technical solutions:
A kind of based on diamylose gram stethoscopic heart sound denoising method, it comprises the following steps:
Step 1, gathers signal
By stethoscopic two mike synchronous acquisition cardiechema signals and noise signal, wherein, a Mike Wind, towards chest, is used for gathering cardiechema signals, and another is towards extraneous air, is used for gathering noise signal；
Step 2, signal processing
By blind source separation algorithm, the signal gathered is separated, cardiechema signals and noise signal are carried out point From；
Step 3, feature extraction
The cardiechema signals separated and noise signal are calculated its speech characteristic parameter respectively, forms characteristic vector；
Step 4, chooses cardiechema signals
Characteristic vector is inputted support vector machine, by support vector machine being supported, vector model selects heart sound Signal also exports, and supports that vector model is to be drawn by the normal of long-term acquisition and the training of pathology cardiechema signals.
Compared with prior art, the invention has the beneficial effects as follows:
This method can allow doctor hear relatively sharp signal, thus preferably Diagnosing Cardiac situation.
Accompanying drawing explanation
Fig. 1 is the stethoscopic structural representation of diamylose gram of an embodiment of the present invention.
As it is shown in figure 1, wherein corresponding reference is entitled:
1 first microphone module, 2 audio encoding and decoding modules, 3 digital signal processing modules, 4 bluetooth modules, 5 Second microphone module.
Detailed description of the invention
The present invention is further elaborated below in conjunction with the accompanying drawings.
A kind of based on diamylose gram stethoscopic heart sound denoising method, it comprises the following steps:
Step 1, gathers signal
By stethoscopic two mike synchronous acquisition cardiechema signals and noise signal, wherein, a Mike Wind, towards chest, is used for gathering cardiechema signals, and another is towards extraneous air, is used for gathering noise signal；
Step 2, signal processing
By blind source separation algorithm, the signal gathered is separated, cardiechema signals and noise signal are carried out point From；
Step 3, feature extraction
The cardiechema signals separated and noise signal are calculated its speech characteristic parameter respectively, forms characteristic vector；
Step 4, chooses cardiechema signals
Characteristic vector is inputted support vector machine, by support vector machine being supported, vector model selects heart sound Signal also exports, and supports that vector model is to be drawn by the normal of long-term acquisition and the training of pathology cardiechema signals.
The present invention provides a kind of diamylose gram stethoscope, a kind of diamylose gram bluetooth stethoscope as shown in Figure 1, it At the first microphone module 1, second microphone module 5, audio encoding and decoding module 2, digital signal Reason module 3 and bluetooth module 4；First microphone module 1 is arranged towards chest, is used for gathering cardiechema signals, Second microphone module 5 is arranged towards extraneous air, is used for gathering noise signal；Audio encoding and decoding module 2 Electrically connect with the first microphone module 1 and second microphone module 5 respectively, for the heart sound letter that will collect Number and noise signal carry out analog digital conversion and processing and amplifying；Digital signal processing module 3 and audio coding solution Code module 2 electrically connects, and the cardiechema signals after audio encoding and decoding module 2 being processed carries out enhancement process, And the cardiechema signals in signal selects after being processed audio encoding and decoding module 2 by speech characteristic parameter； Bluetooth module 4 electrically connects with digital signal processing module 3, for the cardiechema signals filtered out is transmitted, Bluetooth module 4 uses bluetooth 4.1 agreement to be transmitted.
The blind source separation method included in digital signal processing module 3 is a kind of Independent component analysis, i.e. FastICA algorithm, time complexity and the space complexity of this algorithm are the highest, existing Digital Signal Processing The level of module 3 is capable of, and effect is preferable.The core algorithm of speech characteristic parameter selects MFCC parameter As feature, pattern match uses support vector machine, is the identification model more commonly used.Support vector machine mould Type is that a large amount of normal and pathology heart sound the training by long-term acquisition obtains.
The essence of the present invention is described in detail by above detailed description of the invention, but can not be to the guarantor of the present invention The scope of protecting limits, it should be apparent that, under the enlightenment of the present invention, the art those of ordinary skill Many improvement and modification can also be carried out, it should be noted that these improve and modify all to fall the present invention's Within claims.

Claims (1)

1. one kind based on diamylose gram stethoscopic heart sound denoising method, it is characterised in that it comprises the following steps:
Step 1, gathers signal
By stethoscopic two mike synchronous acquisition cardiechema signals and noise signal, wherein, a Mike Wind, towards chest, is used for gathering cardiechema signals, and another is towards extraneous air, is used for gathering noise letter Number；
Step 2, signal processing
By blind source separation algorithm, the signal gathered is separated, cardiechema signals and noise signal are carried out point From；
Step 3, feature extraction
The cardiechema signals separated and noise signal are calculated its speech characteristic parameter respectively, forms characteristic vector；
Step 4, chooses cardiechema signals
Characteristic vector is inputted support vector machine, by support vector machine being supported, vector model selects heart sound Signal also exports, and supports that vector model is to be trained by the normal of long-term acquisition and pathology cardiechema signals Go out.
CN201610343726.4A 2016-05-23 2016-05-23 Heart sound denoising method based on double-microphone stethoscope Pending CN105962967A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610343726.4A CN105962967A (en) 2016-05-23 2016-05-23 Heart sound denoising method based on double-microphone stethoscope

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610343726.4A CN105962967A (en) 2016-05-23 2016-05-23 Heart sound denoising method based on double-microphone stethoscope

Publications (1)

Publication Number Publication Date
CN105962967A true CN105962967A (en) 2016-09-28

Family

ID=56955622

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610343726.4A Pending CN105962967A (en) 2016-05-23 2016-05-23 Heart sound denoising method based on double-microphone stethoscope

Country Status (1)

Country Link
CN (1) CN105962967A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106644037A (en) * 2016-12-28 2017-05-10 中国科学院长春光学精密机械与物理研究所 Voice signal acquisition device and method
CN110353725A (en) * 2019-07-10 2019-10-22 东南大学 A kind of heart sound acquisition and analysis system and method based on cloud framework
WO2020151169A1 (en) * 2019-01-23 2020-07-30 苏州美糯爱医疗科技有限公司 Method for automatic removal of frictional sound interference of electronic stethoscope
CN111739551A (en) * 2020-06-24 2020-10-02 广东工业大学 Multichannel cardiopulmonary sound denoising system based on low-rank and sparse tensor decomposition
CN111839582A (en) * 2020-06-17 2020-10-30 西北工业大学 Isolation type ear-covering electronic stethoscope

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102512138A (en) * 2011-11-24 2012-06-27 胡建斌 Cardiac sound monitoring and early warning method
CN202749088U (en) * 2012-08-08 2013-02-20 滨州学院 Voice reinforcing system using blind source separation algorithm
CN103315767A (en) * 2013-06-18 2013-09-25 西华大学 Determining method and system for heart sound signals
CN103479429A (en) * 2013-08-29 2014-01-01 无锡慧思顿科技有限公司 Heart comprehensive detection equipment based on heart sounds and electrocardiograms
WO2014163443A1 (en) * 2013-04-05 2014-10-09 Samsung Electronics Co., Ltd. Electronic stethoscope apparatus, automatic diagnostic apparatus and method
CN104581516A (en) * 2013-10-15 2015-04-29 清华大学 Dual-microphone noise reduction method and device for medical acoustic signals

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102512138A (en) * 2011-11-24 2012-06-27 胡建斌 Cardiac sound monitoring and early warning method
CN202749088U (en) * 2012-08-08 2013-02-20 滨州学院 Voice reinforcing system using blind source separation algorithm
WO2014163443A1 (en) * 2013-04-05 2014-10-09 Samsung Electronics Co., Ltd. Electronic stethoscope apparatus, automatic diagnostic apparatus and method
CN103315767A (en) * 2013-06-18 2013-09-25 西华大学 Determining method and system for heart sound signals
CN103479429A (en) * 2013-08-29 2014-01-01 无锡慧思顿科技有限公司 Heart comprehensive detection equipment based on heart sounds and electrocardiograms
CN104581516A (en) * 2013-10-15 2015-04-29 清华大学 Dual-microphone noise reduction method and device for medical acoustic signals

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106644037A (en) * 2016-12-28 2017-05-10 中国科学院长春光学精密机械与物理研究所 Voice signal acquisition device and method
WO2020151169A1 (en) * 2019-01-23 2020-07-30 苏州美糯爱医疗科技有限公司 Method for automatic removal of frictional sound interference of electronic stethoscope
CN110353725A (en) * 2019-07-10 2019-10-22 东南大学 A kind of heart sound acquisition and analysis system and method based on cloud framework
WO2021004345A1 (en) * 2019-07-10 2021-01-14 东南大学 Heart sound acquisition and analysis system and method employing cloud architecture
CN111839582A (en) * 2020-06-17 2020-10-30 西北工业大学 Isolation type ear-covering electronic stethoscope
CN111739551A (en) * 2020-06-24 2020-10-02 广东工业大学 Multichannel cardiopulmonary sound denoising system based on low-rank and sparse tensor decomposition

Similar Documents

Publication Publication Date Title
CN110353725A (en) A kind of heart sound acquisition and analysis system and method based on cloud framework
CN105962967A (en) Heart sound denoising method based on double-microphone stethoscope
CN108647565B (en) Data preprocessing method for classifying electrocardiosignals based on deep learning model
CN109907752B (en) Electrocardiogram diagnosis and monitoring system for removing motion artifact interference and electrocardio characteristic detection
CN109044396B (en) Intelligent heart sound identification method based on bidirectional long-time and short-time memory neural network
CN104473660B (en) A kind of abnormal recognition of heart sound method based on sub-belt energy envelope autocorrelation characteristic
CN109805954B (en) Method for automatically eliminating friction sound interference of electronic stethoscope
CN102715915A (en) Portable heart sound automatic sorting assistant diagnostic apparatus
CN108175436A (en) A kind of gurgling sound intelligence automatic identifying method
CN203828916U (en) Fetal heart sound signal detection and processing device
CN102934989A (en) Heart sound recognition device and method based on neural network
CN103680518A (en) Voice gender recognition method and system based on virtual instrument technology
CN112274174A (en) Intelligent electronic auscultation control system, method, storage medium and electronic stethoscope
CN105078435A (en) Fetal heart sound signal detection and processing device
CN105852903A (en) Double-microphone Bluetooth heart sound enhancing system of stethoscope
CN110811673A (en) Heart sound analysis system based on probabilistic neural network model
Zhong et al. Heart murmur recognition based on hidden Markov model
CN208586436U (en) A kind of intelligent sound washing machine
CN110507299B (en) Heart rate signal detection device and method
Kamarulafizam et al. Classification of heart sound based on multipoint auscultation system
CN112587104A (en) Method for filtering invalid pulse waveform
CN111275064B (en) Egg embryo classification method based on convolutional neural network and time sequence characteristics
CN203693631U (en) Intelligent online heart sound collection and analysis device
CN205814348U (en) Cardiac valve cardiechema signals mechanical vibration intelligent analysis system
CN215349053U (en) Congenital heart disease intelligent screening robot

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20160928

RJ01 Rejection of invention patent application after publication