CN106847262A - A kind of porcine respiratory disease automatic identification alarm method - Google Patents
A kind of porcine respiratory disease automatic identification alarm method Download PDFInfo
- Publication number
- CN106847262A CN106847262A CN201611237416.0A CN201611237416A CN106847262A CN 106847262 A CN106847262 A CN 106847262A CN 201611237416 A CN201611237416 A CN 201611237416A CN 106847262 A CN106847262 A CN 106847262A
- Authority
- CN
- China
- Prior art keywords
- pig
- signal
- cough
- respiratory disease
- sound
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/04—Training, enrolment or model building
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Abstract
The invention discloses a kind of porcine respiratory disease automatic identification alarm method, including set up the supporting vector machine model of pig cough sound and illnesses and gather the cough sound of pig and two steps are identified to signal.The present invention is by gathering the cough sound signal of pig and by supporting vector machine model it being analyzed, realize the automatic identification to porcine respiratory disease and alarm, energy is in good time, the health status of remote monitoring pig, a large amount of man power and materials of porcine respiratory disease detection are saved, swine rearing efficiency is improve.
Description
Technical field
It is especially a kind of by gathering, analyzing pig the present invention relates to the breathing problem automatic identification alarm method of pig
Cough sound is so as to the method that automatic identification alarm is carried out to porcine respiratory disease.
Background technology
Pork is common meat food materials in our daily lifes, accounts for 65 or so the percent of whole consumption of meat,
Live pig industry is the pillar industry of China's animal husbandry.China's pig-breeding is just progressively being raised scattered from traditional peasant household intensive to scale
Change transformation, the breathing problem to occurring in breeding process carries out fast monitored, can reduce the morbidity of the breathing problem of pig
Risk, reduces the waste of aquaculture cost.The throat comprising measurand or tracheae are received during porcine respiratory disease causes cough signal
Vibration information during stimulation, be can be used to distinguish the cough that other reasonses cause, and respiratory tract disease can be carried out by monitoring cough
The identification and early warning of disease.
Conventional detection means has two kinds, and a kind of is to take artificial working at a selected spot to record the health status of pig, but this method is not
Substantial amounts of time and energy are only consumed, and the degree of accuracy of data cannot also be guaranteed, and the environment on pig farm is typically poor,
Be not suitable for staff to stay inside for a long time.Another kind is exactly computer monitoring, and diagnosis can be improved by area of computer aided
Validity and promptness, mainly include Video Supervision Technique and audio analysis techniques.Audio signal is one-dimensional signal, amount of storage phase
To smaller, computational efficiency is higher, and relative to video monitoring system high cost, the shortcoming of complexity high, Audio Monitoring System is adopted
Collection equipment is simple and easy to apply, and cost is far below video monitoring, therefore the porcine respiratory disease automatic identification warning system based on sound
There are more preferable practicality and generalization, receive more and more attention.
The content of the invention
Breathing problem the present invention seeks to solve the problems, such as to occur in large scale of pig farm is difficult to real-time monitoring, carries
For the porcine respiratory disease automatic identification warning system that a kind of cough sound based on to pig is analyzed.
The present invention adopts the following technical scheme that realization:
1) foundation of supporting vector machine model:
Pig is gathered due to coughing that citric acid, various breathing problems induce by sound signal collecting device respectively on pig farm
Cough and other common acoustic signals, three kinds of effective voice signals that handmarking obtains, and it is converted into corresponding number respectively
Stored in word signal feeding voice signal management module;
Extract three kinds of audio digital signals of storage respectively with FPGA processing modules and it is pre-processed, including end points
Detection, denoising, exacerbation;
On the basis of pretreatment, FPGA processing modules extract three kinds of 12 Jan Vermeer cepstrum systems of audio digital signal respectively
Number, 12 dimension first-order difference characteristic parameters, constitute 24 dimensional feature vectors, using the characteristic parameter for extracting to supporting vector machine model
It is trained, cough and three kinds of supporting vectors of common acoustic of the pig that citric acid, various breathing problems induce is obtained respectively
Machine model, after training terminates, preservation model parameter;
2) gather the cough sound of pig and signal is identified:
The cough sound signal of pig is gathered by sound signal collecting device on pig farm and data signal is converted it into, sent
To enter stored in voice signal management module;
The audio digital signal of storage is extracted with FPGA processing modules and it is pre-processed, including end-point detection, gone
Make an uproar, aggravate;
On the basis of pretreatment, FPGA processing modules extract 12 Jan Vermeer cepstrum coefficients of audio digital signal, 12 dimensions
Number first-order difference characteristic parameter, constitutes 24 dimensional feature vectors;
By the supporting vector machine model after characteristic vector input training, Model Matching analysis is carried out, and to GPRS alarm moulds
Block exports recognition result, and the porcine respiratory disease that GPRS alarm modules will be detected sends warning message to remote monitoring terminal.
The end-point detection is using the double threshold based on short-time average zero-crossing rate and the dual judgement of short-time average energy
The terminal of method interception cough acoustical signal.
The denoising is to subtract the noise average energy for estimating to get from the energy value of cough acoustical signal using spectrum-subtraction
Value, reduces influence of the ambient noise to sound characteristic parameter extraction.
The beneficial effects of the invention are as follows:
The present invention can be breathed pig by the supporting vector machine model for setting up pig cough sound Yu suffer from breathing problem
Cough is accurately distinguished caused by tract disease and other reasons (such as environmental factor), so as to judge whether pig is ill and can accurately analyze
Go out the species of illnesses, by gathering the cough sound signal of pig and by supporting vector machine model it being analyzed, from
And realize carries out automatic identification and alarm to the breathing problem of pig.Energy of the invention is in good time, the health status of remote monitoring pig,
Substantial amounts of manpower and materials are saved, swine rearing efficiency is improve.
Brief description of the drawings
Fig. 1 is workflow schematic diagram of the invention.
Fig. 2 is apparatus structure schematic diagram used in the present invention.
Specific embodiment
The present invention is described in detail with embodiment below in conjunction with the accompanying drawings.
Realize the device that the method is used, including sound signal collecting device, voice signal management module, FPGA treatment
Module and GPRS alarm modules totally four modules.Sound signal collecting device is used to gather the voice signal of pig, and is converted into number
Word signal is stored in voice signal management module, and audio data transmitting then is sent into FPGA processing modules is processed.In FPGA
The identification mission to pig cough sound is completed in module and judges whether pig infects breathing problem and which kind of disease, and passed through
GPRS alarm modules send the warning message that pig infects breathing problem to remote monitoring terminal.
The method includes setting up the cough sound of the cough supporting vector machine model of pig and collection pig and signal is carried out
In two stages of identification, the foundation of wherein supporting vector machine model is comprised the following steps:
(1) pig is gathered because citric acid, various breathing problems induce by sound signal collecting device respectively on pig farm
Cough and other common acoustic signals, handmarking obtain three kinds of effective voice signals, and it is converted into respectively accordingly
Data signal feeding voice signal management module in stored;
(2) three kinds of audio digital signals of storage are extracted respectively with FPGA processing modules and it is pre-processed, including
End-point detection, denoising, exacerbation, wherein, the end-point detection is using based on short-time average zero-crossing rate and short-time average energy
The terminal of the double threshold method interception cough acoustical signal of dual judgement;The denoising is the energy from cough acoustical signal using spectrum-subtraction
The noise the average energy value for estimating to get is subtracted in value, reduces influence of the ambient noise to sound characteristic parameter extraction;
(3) on the basis of pretreatment, 12 Jan Vermeers that FPGA processing modules extract three kinds of audio digital signals respectively fall
Spectral coefficient, 12 dimension first-order difference characteristic parameters, constitute 24 dimensional feature vectors, using the characteristic parameter for extracting to SVMs
Model is trained, and the cough of the pig that citric acid, various breathing problems induce and three kinds of supports of common acoustic are obtained respectively
Vector machine model, after training terminates, preservation model parameter.
Gather the cough sound of pig and signal is identified to comprise the following steps:
(1) the cough sound signal of pig is gathered by sound signal collecting device on pig farm and converts it into digital letter
Number, stored in feeding voice signal management module;
(2) audio digital signal of storage is extracted with FPGA processing modules and it is pre-processed, including end-point detection,
Denoising, exacerbation, wherein, the end-point detection is using the dual judgement based on short-time average zero-crossing rate and short-time average energy
The terminal of double threshold method interception cough acoustical signal;The denoising is subtracted from the energy value of cough acoustical signal using spectrum-subtraction
Noise the average energy value that estimation gets, reduces influence of the ambient noise to sound characteristic parameter extraction;
(3) on the basis of pretreatment, FPGA processing modules extract 12 Jan Vermeer cepstrum coefficients, 12 of audio digital signal
Dimension first-order difference characteristic parameter, constitutes 24 dimensional feature vectors;
(4) by the supporting vector machine model after characteristic vector input training, and recognition result is exported to GPRS alarm modules,
The porcine respiratory disease that GPRS alarm modules will be detected sends warning message to remote monitoring terminal.
Foregoing invention also include 24 dimension MFCC characteristic parameters extraction process include framing adding window, FFT,
Take absolute value or square value, triangle bandpass filter Mel filter, take the logarithm, discrete cosine transform, obtain 12 tie up MFCC parameters,
First-order difference MFCC parameters are sought, MFCC characteristic parameters are tieed up in combination 24.First-order difference calculation of characteristic parameters formula is as follows:
T is other.
Whether the identification module of FPGA distinguishes pig with breathing problem, with which kind of breathing problem, if distinguishing trouble
Sick then send kinds of Diseases warning information to long-distance monitorng device by GPRS module, now feeding and management person can be to target column
In swinery further look at and treat.
Fig. 2 is the schematic device that the method is used, including sound signal collecting device, voice signal management module,
FPGA processing modules and GPRS alarm modules.Sound signal collecting device is the wheat of a cough sound signal for gathering pig
Gram wind, the voice signal that it will can be collected is converted into data signal and is stored in voice signal management module, at the FPGA
Reason module is used to store supporting vector machine model, and the cough sound data signal input supporting vector machine model of pig is divided
Analysis, it includes an internal memory and chip, and in internal memory, the chip is used for the cough of pig for the supporting vector machine model storage
Audio digital signal is input into supporting vector machine model and is analyzed, and the knowledge to pig cough sound is completed in FPGA processing modules
Other task simultaneously judges whether pig infects breathing problem and which kind of disease, and sent out to remote monitoring terminal by GPRS alarm modules
Pig is sent to infect the warning message of breathing problem.
Claims (3)
1. a kind of porcine respiratory disease automatic identification alarm method, it is characterised in that comprise the following steps:
1) foundation of supporting vector machine model:
Pig farm by sound signal collecting device gather respectively pig due to citric acid, various breathing problems induce cough and
Other common acoustic signals, three kinds of effective voice signals that handmarking obtains, it is converted into corresponding data signal respectively
And send into and stored in voice signal management module;
Extract three kinds of audio digital signals of storage respectively with FPGA processing modules and it is pre-processed, including end points inspection
Survey, denoising, exacerbation;
On the basis of pretreatment, FPGA processing modules extract respectively three kinds of 12 Jan Vermeer cepstrum coefficients of audio digital signal,
12 dimension first-order difference characteristic parameters, constitute 24 dimensional feature vectors, and supporting vector machine model is entered using the characteristic parameter for extracting
Row training, obtains cough and three kinds of SVMs of common acoustic of the pig that citric acid, various breathing problems induce respectively
Model, after training terminates, preservation model parameter;
2) gather the cough sound of pig and signal is identified:
The cough sound signal of pig is gathered by sound signal collecting device on pig farm and data signal is converted it into, feeding sound
Stored in message management module;
The audio digital signal of storage is extracted with FPGA processing modules and it is pre-processed, including end-point detection, denoising, plus
Weight;
On the basis of pretreatment, FPGA processing modules extract 12 Jan Vermeer cepstrum coefficients, 12 dimensions one of audio digital signal
Order difference characteristic parameter, constitutes 24 dimensional feature vectors;
By the supporting vector machine model after characteristic vector input training, Model Matching analysis is carried out, and it is defeated to GPRS alarm modules
Go out recognition result, the porcine respiratory disease that GPRS alarm modules will be detected sends warning message to remote monitoring terminal.
2. porcine respiratory disease automatic identification alarm method as claimed in claim 1, it is characterised in that:The end-point detection is
Using the start-stop based on short-time average zero-crossing rate and the double threshold method of the dual judgement of short-time average energy interception cough acoustical signal
Point.
3. porcine respiratory disease automatic identification alarm method as claimed in claim 1, it is characterised in that:The denoising is to utilize
Spectrum-subtraction subtracts the noise the average energy value for estimating to get from the energy value of cough acoustical signal, reduces ambient noise special to sound
Levy the influence of parameter extraction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611237416.0A CN106847262A (en) | 2016-12-28 | 2016-12-28 | A kind of porcine respiratory disease automatic identification alarm method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611237416.0A CN106847262A (en) | 2016-12-28 | 2016-12-28 | A kind of porcine respiratory disease automatic identification alarm method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106847262A true CN106847262A (en) | 2017-06-13 |
Family
ID=59113536
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611237416.0A Pending CN106847262A (en) | 2016-12-28 | 2016-12-28 | A kind of porcine respiratory disease automatic identification alarm method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106847262A (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108369813A (en) * | 2017-07-31 | 2018-08-03 | 深圳和而泰智能家居科技有限公司 | Specific sound recognition methods, equipment and storage medium |
CN108550394A (en) * | 2018-03-12 | 2018-09-18 | 广州势必可赢网络科技有限公司 | A kind of method and device of diagnosing a disease based on Application on Voiceprint Recognition |
CN108701469A (en) * | 2017-07-31 | 2018-10-23 | 深圳和而泰智能家居科技有限公司 | Cough sound recognition methods, equipment and storage medium |
CN108935188A (en) * | 2018-07-05 | 2018-12-07 | 平安科技(深圳)有限公司 | Pig disease identification method, apparatus and electronic equipment |
CN109009129A (en) * | 2018-08-20 | 2018-12-18 | 南京农业大学 | Sow respiratory disease method for early warning based on acoustic analysis |
CN109243470A (en) * | 2018-08-16 | 2019-01-18 | 南京农业大学 | Broiler chicken cough monitoring method based on Audiotechnica |
CN109493874A (en) * | 2018-11-23 | 2019-03-19 | 东北农业大学 | A kind of live pig cough sound recognition methods based on convolutional neural networks |
CN109479750A (en) * | 2018-08-27 | 2019-03-19 | 华中农业大学 | A kind of plum mountain pig heat monitoring method based on acoustic information |
CN109498228A (en) * | 2018-11-06 | 2019-03-22 | 林枫 | Lung recovery therapeutic equipment based on cough sound feedback |
CN109567806A (en) * | 2018-11-08 | 2019-04-05 | 广州军区广州总医院 | A kind of traumatic Cervical cord injuries patient coughs sound evaluation system and evaluation method |
CN109602421A (en) * | 2019-01-04 | 2019-04-12 | 平安科技(深圳)有限公司 | Health monitor method, device and computer readable storage medium |
CN109637549A (en) * | 2018-12-13 | 2019-04-16 | 北京小龙潜行科技有限公司 | A kind of pair of pig carries out the method, apparatus and detection system of sound detection |
CN110265041A (en) * | 2019-07-01 | 2019-09-20 | 河南牧业经济学院 | A kind of method and system for the song behavior collected, analyze pig |
CN110689898A (en) * | 2019-11-18 | 2020-01-14 | 安徽农业大学 | Compression method and system for audio signal of live pig |
CN112472065A (en) * | 2020-11-18 | 2021-03-12 | 天机医用机器人技术(清远)有限公司 | Disease detection method based on cough sound recognition and related equipment thereof |
CN113056785A (en) * | 2018-12-18 | 2021-06-29 | 桑德托克斯公司 | Method for monitoring livestock facilities and/or livestock animals in livestock facilities using improved sound processing techniques |
WO2021189903A1 (en) * | 2020-10-09 | 2021-09-30 | 平安科技(深圳)有限公司 | Audio-based user state identification method and apparatus, and electronic device and storage medium |
CN113456055A (en) * | 2021-07-05 | 2021-10-01 | 自牧机器人(青岛)有限公司 | Poultry respiratory tract real-time monitoring system based on artificial intelligence |
CN115457966A (en) * | 2022-09-16 | 2022-12-09 | 东北农业大学 | Pig cough sound identification method based on improved DS evidence theory multi-classifier fusion |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110082574A1 (en) * | 2009-10-07 | 2011-04-07 | Sony Corporation | Animal-machine audio interaction system |
CN102088911A (en) * | 2008-06-17 | 2011-06-08 | 皇家飞利浦电子股份有限公司 | Acoustical patient monitoring using a sound classifier and a microphone |
CN105336331A (en) * | 2015-11-21 | 2016-02-17 | 太原理工大学 | Intelligent monitoring method and intelligent monitoring system for abnormal behaviors of pigs on basis of sound |
CN105513613A (en) * | 2015-11-30 | 2016-04-20 | 中国农业科学院农业信息研究所 | Livestock cough monitoring and early-warning method and device |
CN105997015A (en) * | 2016-06-12 | 2016-10-12 | 浙江大学 | Wearable device for animal vital sign multi-parameter monitoring |
-
2016
- 2016-12-28 CN CN201611237416.0A patent/CN106847262A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102088911A (en) * | 2008-06-17 | 2011-06-08 | 皇家飞利浦电子股份有限公司 | Acoustical patient monitoring using a sound classifier and a microphone |
US20110082574A1 (en) * | 2009-10-07 | 2011-04-07 | Sony Corporation | Animal-machine audio interaction system |
CN105336331A (en) * | 2015-11-21 | 2016-02-17 | 太原理工大学 | Intelligent monitoring method and intelligent monitoring system for abnormal behaviors of pigs on basis of sound |
CN105513613A (en) * | 2015-11-30 | 2016-04-20 | 中国农业科学院农业信息研究所 | Livestock cough monitoring and early-warning method and device |
CN105997015A (en) * | 2016-06-12 | 2016-10-12 | 浙江大学 | Wearable device for animal vital sign multi-parameter monitoring |
Non-Patent Citations (1)
Title |
---|
王浩安: "基于多层能量检测的动物声音检测与识别", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108369813A (en) * | 2017-07-31 | 2018-08-03 | 深圳和而泰智能家居科技有限公司 | Specific sound recognition methods, equipment and storage medium |
CN108701469A (en) * | 2017-07-31 | 2018-10-23 | 深圳和而泰智能家居科技有限公司 | Cough sound recognition methods, equipment and storage medium |
WO2019023877A1 (en) * | 2017-07-31 | 2019-02-07 | 深圳和而泰智能家居科技有限公司 | Specific sound recognition method and device, and storage medium |
WO2019023879A1 (en) * | 2017-07-31 | 2019-02-07 | 深圳和而泰智能家居科技有限公司 | Cough sound recognition method and device, and storage medium |
CN108701469B (en) * | 2017-07-31 | 2023-06-20 | 深圳和而泰智能控制股份有限公司 | Cough sound recognition method, device, and storage medium |
CN108550394A (en) * | 2018-03-12 | 2018-09-18 | 广州势必可赢网络科技有限公司 | A kind of method and device of diagnosing a disease based on Application on Voiceprint Recognition |
CN108935188A (en) * | 2018-07-05 | 2018-12-07 | 平安科技(深圳)有限公司 | Pig disease identification method, apparatus and electronic equipment |
CN109243470B (en) * | 2018-08-16 | 2020-05-05 | 南京农业大学 | Broiler cough monitoring method based on audio technology |
CN109243470A (en) * | 2018-08-16 | 2019-01-18 | 南京农业大学 | Broiler chicken cough monitoring method based on Audiotechnica |
CN109009129A (en) * | 2018-08-20 | 2018-12-18 | 南京农业大学 | Sow respiratory disease method for early warning based on acoustic analysis |
CN109009129B (en) * | 2018-08-20 | 2019-06-04 | 南京农业大学 | Sow respiratory disease early warning system based on acoustic analysis |
CN109479750A (en) * | 2018-08-27 | 2019-03-19 | 华中农业大学 | A kind of plum mountain pig heat monitoring method based on acoustic information |
CN109498228A (en) * | 2018-11-06 | 2019-03-22 | 林枫 | Lung recovery therapeutic equipment based on cough sound feedback |
CN109567806A (en) * | 2018-11-08 | 2019-04-05 | 广州军区广州总医院 | A kind of traumatic Cervical cord injuries patient coughs sound evaluation system and evaluation method |
CN109493874A (en) * | 2018-11-23 | 2019-03-19 | 东北农业大学 | A kind of live pig cough sound recognition methods based on convolutional neural networks |
CN109637549A (en) * | 2018-12-13 | 2019-04-16 | 北京小龙潜行科技有限公司 | A kind of pair of pig carries out the method, apparatus and detection system of sound detection |
CN113056785A (en) * | 2018-12-18 | 2021-06-29 | 桑德托克斯公司 | Method for monitoring livestock facilities and/or livestock animals in livestock facilities using improved sound processing techniques |
CN109602421A (en) * | 2019-01-04 | 2019-04-12 | 平安科技(深圳)有限公司 | Health monitor method, device and computer readable storage medium |
CN110265041A (en) * | 2019-07-01 | 2019-09-20 | 河南牧业经济学院 | A kind of method and system for the song behavior collected, analyze pig |
CN110689898A (en) * | 2019-11-18 | 2020-01-14 | 安徽农业大学 | Compression method and system for audio signal of live pig |
WO2021189903A1 (en) * | 2020-10-09 | 2021-09-30 | 平安科技(深圳)有限公司 | Audio-based user state identification method and apparatus, and electronic device and storage medium |
CN112472065A (en) * | 2020-11-18 | 2021-03-12 | 天机医用机器人技术(清远)有限公司 | Disease detection method based on cough sound recognition and related equipment thereof |
CN113456055A (en) * | 2021-07-05 | 2021-10-01 | 自牧机器人(青岛)有限公司 | Poultry respiratory tract real-time monitoring system based on artificial intelligence |
CN115457966A (en) * | 2022-09-16 | 2022-12-09 | 东北农业大学 | Pig cough sound identification method based on improved DS evidence theory multi-classifier fusion |
CN115457966B (en) * | 2022-09-16 | 2023-05-12 | 东北农业大学 | Pig cough sound identification method based on improved DS evidence theory multi-classifier fusion |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106847262A (en) | A kind of porcine respiratory disease automatic identification alarm method | |
EP2978305B1 (en) | Automated monitoring of animal nutriment ingestion | |
CN109243470B (en) | Broiler cough monitoring method based on audio technology | |
Bao et al. | Artificial intelligence in animal farming: A systematic literature review | |
Chelotti et al. | A real-time algorithm for acoustic monitoring of ingestive behavior of grazing cattle | |
Navon et al. | Automatic recognition of jaw movements in free-ranging cattle, goats and sheep, using acoustic monitoring | |
CN109009129B (en) | Sow respiratory disease early warning system based on acoustic analysis | |
CN111914685B (en) | Sow oestrus detection method and device, electronic equipment and storage medium | |
Chelotti et al. | An online method for estimating grazing and rumination bouts using acoustic signals in grazing cattle | |
CN103248703A (en) | Automatic monitoring system and method for live pig action | |
CN105336331A (en) | Intelligent monitoring method and intelligent monitoring system for abnormal behaviors of pigs on basis of sound | |
CN113785783B (en) | Livestock grouping system and method | |
CN103914732A (en) | Chewer rumination and swallowing frequency audio recognition algorithm | |
CN106781397A (en) | A kind of cattle and sheep supervisory systems | |
CN113947734A (en) | Pig physical sign information acquisition method and system | |
CN112820275A (en) | Automatic monitoring method for analyzing abnormality of suckling piglets based on sound signals | |
CN115048984A (en) | Sow oestrus recognition method based on deep learning | |
CN109479750A (en) | A kind of plum mountain pig heat monitoring method based on acoustic information | |
Wang et al. | A lightweight CNN-based model for early warning in sow oestrus sound monitoring | |
CN115810365A (en) | Pig health early warning method and system based on pig sound | |
CN103916462A (en) | Chewer rumination information collecting system | |
CN113516139A (en) | Data processing method, device, equipment and storage medium | |
CN111916096A (en) | Tibetan sheep grazing behavior monitoring method based on raspberry pie | |
CN207286066U (en) | A kind of porcine respiratory disease automatic identification warning device | |
CN206003119U (en) | A kind of Crazing in grassland sheep grazing behaviour detecting system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |