CN106993546A - A kind of cow oestrus monitoring method based on the time of ruminating and activity - Google Patents

A kind of cow oestrus monitoring method based on the time of ruminating and activity Download PDF

Info

Publication number
CN106993546A
CN106993546A CN201710277184.XA CN201710277184A CN106993546A CN 106993546 A CN106993546 A CN 106993546A CN 201710277184 A CN201710277184 A CN 201710277184A CN 106993546 A CN106993546 A CN 106993546A
Authority
CN
China
Prior art keywords
time
milk cow
cow
signal
ruminating
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
CN201710277184.XA
Other languages
Chinese (zh)
Inventor
张宇
尹艳玲
张心翮
沈维政
李想
戴百生
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.)
Northeast Agricultural University
Original Assignee
Northeast Agricultural University
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 Northeast Agricultural University filed Critical Northeast Agricultural University
Priority to CN201710277184.XA priority Critical patent/CN106993546A/en
Publication of CN106993546A publication Critical patent/CN106993546A/en
Pending legal-status Critical Current

Links

Classifications

    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01KANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
    • A01K29/00Other apparatus for animal husbandry
    • A01K29/005Monitoring or measuring activity, e.g. detecting heat or mating

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Environmental Sciences (AREA)
  • Biophysics (AREA)
  • Animal Husbandry (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Dairy Products (AREA)

Abstract

The invention discloses a kind of cow oestrus monitoring method based on the time of ruminating and activity, belong to animal individual sign monitoring field.Accurately judge the cow oestrus phase, be conducive to the becoming pregnant in time of milk cow, calving, improve lactation period and effectively improve production efficiency.The present invention ruminates time and activity information jointly and judges oestrus of milk cow by combined monitoring milk cow, the oestrus of milk cow is tentatively judged by the time of ruminating and activity information first, early warning is carried out to oestrus when the time of ruminating is less than setting thresholding and activity is higher than thresholding, then the specific time of cow oestrus is determined whether by activity information, estrus time hour can be specifically predicted.Judge the cow oestrus time by combining the time of ruminating and activity, detection probability can be effectively improved, and improve oestrous detection precision, so as to be become pregnant in time to milk cow, there is important directive significance to actual production.

Description

A kind of cow oestrus monitoring method based on the time of ruminating and activity
Technical field
The invention belongs to animal individual sign monitoring field, and in particular to one kind passes through the time of ruminating and activity information phase With reference to come the method that monitors cow oestrus situation.
Background technology
In Cow product, the oestrous detection of milk cow has critical role, accurately heat situation is judged, favorably In the becoming pregnant in time of milk cow, calving, improve lactation period and effectively improve production efficiency.Traditional detection milk cow method is used mostly Professional judges the heat situation of milk cow by observing, but this method has three below shortcoming:1. it is scientific low, only It is subjective to judge by the experience of professional in itself, and just hold when the unfamiliar situation of professional occurs in milk cow It is easily caused the faulty operation to milk cow;2. poor real, according to statistics, start the ratio of heat with night at dusk apparently higher than white My god, the difficulty of the milk cow Artificial Diagnosis of night heat is very big, situation about can usually fail to report;3. workload is big, it is necessary to constantly Observation, the monitoring to the individual heat of milk cow could be realized.Meanwhile, also have by monitoring milk cow activity or when milk cow ruminates Between judge the heat situation of milk cow, but the activity of influence milk cow or ruminate the factor of time change and not only include hair Feelings, it is also relevant with a lot of other factors, therefore judged by single factor milk cow whether heat, detection probability is not high enough, together When can only probably estimate heat by ruminating and be in some day, and hour can not be accurate to.
A kind of patent of invention " method and device of continuous monitoring ruminant chewing activity " (publication number: CN102577995A), a kind of method of continuous monitoring ruminant chewing activity is disclosed, this method uses automatic logging software It is monitored with camera, it is necessary to which professional is analyzed its observed and recorded.This method efficiency is low, while needing multiple shootings Head is monitored to all milk cows, it is impossible to realize the accurate monitoring to individual milk cow." one kind is based on milk cow activity for utility model patent Measure the heat monitoring system of change " (publication number:CN204579481U), a kind of heat changed based on milk cow activity is disclosed Monitoring system, the system realizes three kinds of different data acquisitions and transmission means, and judges milk cow by institute's gathered data Heat situation.This method refers only to the difference of heat milk cow and non-heat milk cow activity, rather than tackles in single milk cow, due to The difference of milk cow individual, easily causes error;And heat is only discriminated whether by activity, it is not accurate enough.
The present invention is handled by chewing the voice signal produced to milk cow, is identified and is ruminated signal, is counted in one day Milk cow ruminates the time, and by defining activity threshold value to single milk cow, can be prevented effectively from cattle farm and unify activity threshold value The error caused.By milk cow activity and the combination of time is ruminated, heat early warning can be carried out to milk cow, can also be in early warning The time of cow oestrus is accurately found afterwards, to reach the purpose monitored to cow oestrus.
The content of the invention
In order to realize the accurate judgement to the cow oestrus time, and overcome the shortcoming of existing heat monitoring method, the present invention Propose a kind of cow oestrus monitoring method based on the time of ruminating and activity.
Its technical scheme is as follows:
Step 1:By the sound pick-up outfit in milk cow worn, the voice signal that collection milk cow produces by chewing activity, The activity information of milk cow is acquired by the pedometer bundled in milk cow leg simultaneously.
Step 2:The voice signal of collection is detected by energy measuring method and zero-crossing rate method, the letter that can be detected It is number main to include ruminating signal, feed signal, drinking-water signal and interference signal etc., by carrying out Fourier's change to voice signal Change, the frequency spectrum of observation signal, because three kinds of signals have different spectrum signatures, therefore can be identified from three kinds of signals anti- Hay signal, wherein the spectrum signature of three kinds of signals is respectively:Signal frequency is ruminated more than 1 hertz, frequency stabilization, drinking-water signal frequency Rate is less than 1 hertz, and frequency stabilization, feed signal and interference signal spectrum energy relatively disperse, and frequency is unstable.
Step 3:Obtain milk cow and ruminate time and milk cow activity information, according to the two information, judge whether milk cow sends out Feelings.The step number for ruminating time and milk cow walking of milk cow always first in statistics twenty four hours, is less than setting when the time of ruminating Thresholding and thresholding of the step number more than setting of walking, and the time was in milk cow should be in oestrus next time front and rear 4-5 days, Early warning is carried out to heat, represents that milk cow is in proestrum, the time counting method of wherein twenty four hours is:0:00 to 24: With the same day 12 between 00:00 to next day 12:Between 00, when meeting above-mentioned requirements using any time counting method, enter Row early warning, the step number walked after early warning using hour as interval stats milk cow, when step number exceedes setting thresholding, judges now milk cow Heat.
Can be more accurately to milk cow the beneficial effects of the invention are as follows the combination that time and activity are ruminated by milk cow Carry out early warning and the judgement of accurate estrus time., can be with simpler effective simultaneously by the analysis and processing to voice signal Differentiation ruminate, search for food, three behaviors of drinking water.Produced by by that to single milk cow given threshold, can avoid uniform threshold Error, compared to traditional heat monitoring method, with higher efficiency.
Brief description of the drawings
Fig. 1 is cow oestrus monitoring algorithm flow chart
Fig. 2 is that milk cow chews the voice signal schematic diagram produced.
Fig. 3 is short-time energy and the short-time zero-crossing rate of signal in Fig. 1.
Fig. 4 is that milk cow ruminates signal, drinking-water signal and the schematic diagram for feeding signal.
Fig. 5 is the amplitude spectrum for ruminating signal.
Fig. 6 is the amplitude spectrum of drinking-water signal.
Fig. 7 is the amplitude spectrum for the signal fed.
Fig. 8 is to ruminate time acquisition figure.
Fig. 9 is interior one day after before milk cow ruminates total to ruminate the time.
Figure 10 is the milk cow activity curve map being in heat.
Embodiment
The embodiment of the present invention is described in further detail with example below in conjunction with the accompanying drawings.Following instance is used for Illustrate the present invention, but be not limited to the scope of the present invention.
A kind of cow oestrus monitoring method based on the time of ruminating and activity that the present invention is provided, algorithm flow chart is as schemed Shown in 1, specific heat monitoring method mainly comprises the following steps:
(1) voice signal and activity information of collection milk cow.Can using SCR companies of Israel develop HR-Tag or Other sound pick-up outfits of person gather the voice signal that milk cow produces by chewing activity, after HR-Tag is linked by special rope, Gu The left side of milk cow neck is scheduled on close to left ear position, persistently listened to and remembered for the period with 2 hours by internal microphone system Record voice data.Pedometer can be mainly used in monitoring using the pedometer of commercial type or the pedometer of oneself exploitation The step number of milk cow walking, is bundled in milk cow back leg ankle portion, the activity information to milk cow is acquired by pedometer.
(2) analyzed and processed to gathering the voice signal come.Fig. 2 is that one section of milk cow of collection chews the voice signal produced Schematic diagram, it can be seen that have three useful signals and lasting interference signal in Fig. 2, three useful signals are to ruminate letter successively Number, drinking-water signal, feed signal.Fig. 3 is to ask for short-time energy and short-time zero-crossing rate to the voice signal of collection, works as alternative one Reach the thresholding of setting, you can be judged as useful signal rather than interference signal, by this method can by three useful signals from Extracted in voice signal.Fig. 4 is that milk cow ruminates signal, drinking-water signal and the schematic diagram for feeding signal, to these three signals Fourier's change is carried out, obtained frequency spectrum is respectively as shown in Fig. 5~7.From the figure, it can be seen that drinking-water signal frequency is less than 1 hertz Hereby, frequency peak is stable in 0.71Hz;Feed signal frequency unstable, have peak value in 0.11Hz and 1.07Hz;Ruminate signal Frequency is more than 1 hertz, and frequency peak is stable in 1.19Hz.Therefore the different spectrum signature of three kinds of signals is passed through, it is possible to will be anti- Hay signal distinguishing comes out, and statistics ruminates the duration.
(3) time ruminated by milk cow and milk cow activity information judge milk cow whether heat.The anti-of milk cow is obtained first Hay time and milk cow activity information, defining the time of ruminating afterwards judges that heat warning algorithm, an activity judge milk Ox heat algorithm, defines four Rule of judgment based on two algorithms, the heat feelings of milk cow is judged finally by this four conditions Condition and whole heat stage to milk cow is monitored.
Obtain milk cow ruminates the time:Short-time energy such as Fig. 8 is asked for the signal of ruminating identified in step 2, phase is set Thresholding is answered, only retains the time for reaching energy more than thresholding, it is t in figure to ruminate the time started1, the end time is ruminated in figure t2, therefore the time of ruminating acquirement can be made the difference by both:T=t2-t1.Milk cow activity information can be directly by reading pedometer number Value is obtained.
The time of ruminating judges heat warning algorithm:Intraday to ruminate the time general 380~530 in non-oestrus for milk cow Minute or so (specifically the time of ruminating is different to the different milk cow of different phase), it is intraday when cow oestrus to ruminate the time 10%~30% or so can then be declined.The time of ruminating significantly reduces during due to cow oestrus, therefore can be by the beginning of the time of ruminating Step judges the cow oestrus phase.Set a time threshold Tmin, represent heat early warning and ruminate the time, milk cow by the time of ruminating with The comparison of the threshold value can carry out early warning to cow oestrus, and the algorithm can primarily determine that the date of cow oestrus, anti-by milk cow The schematic diagram that the hay time carries out heat early warning is as shown in Figure 9.
Activity judges cow oestrus algorithm:Five thresholding variables, A are defined for every cow headaveIt is small for estrus 2 When activity average value;AminHeat incipient activity amount is represented, using AaveWith k product representation;AmaxRepresent heat peak period activity Amount, uses AaveWith c product representation;The activity maximum for obtaining the non-heat of milk cow by many experiments is less than estrus 2 hours Two times of activity average value, and activity during cow oestrus peak period is 3~5 times of estrus, thus k between 2~3 it Between, c is between 3~5, and T represents estrus duration.Obtained by many experiments Monitoring Data at the end of heat peak period just It is optimal breeding time when terminating preceding 1/3rd after 2/3rds times of whole oestrus T, i.e. heat.Pass through the work of one day Momentum number is compared with above-mentioned threshold value, you can carry out early warning to cow oestrus, and the cow oestrus time is accurately judged.
The time of ruminating judges that heat warning algorithm and activity judge the combination of cow oestrus algorithm, Ke Yizhun more than The estrus time of milk cow is really obtained, specific Rule of judgment is summarized as follows:
Milk cow early warning Rule of judgment:1.A > AminAnd T < Tmin, alarm sounds, and early warning may heat.
Cow oestrus Rule of judgment:2. Α > Αmax, it is determined that heat.
Optimal breeding time Rule of judgment:3. as A < Amax, and continuously less than up to one hour, when now for optimal breeding Between.
Terminate estrus time Rule of judgment:4.A < Aave, now heat terminated.
Be explained further the algorithm with reference to Fig. 9 and Figure 10, in statistics twenty four hours milk cow always ruminate time and milk cow The step number of walking, is less than D in the thresholding of setting such as Fig. 9 when the time of ruminating1And walking step number is more than in the thresholding of setting such as Figure 10 A1、A22 points, and the time was in milk cow should be in oestrus next time front and rear 4-5 days, carries out early warning to heat, represents Milk cow is in proestrum, and the time counting method of wherein twenty four hours is:0:00 to 24:With the same day 12 between 00:00 to Next day 12:Between 00, when meeting above-mentioned requirements using any time counting method, early warning is carried out.With hour after early warning The step number walked for interval stats milk cow, when step number exceedes A in setting thresholding such as Figure 103During point, now cow oestrus is judged;When Movable numerical quantity reaches A in Figure 104During point, then optimal breeding time has been reached;When movable numerical quantity reaches A in Figure 105During point, Terminate heat.

Claims (3)

1. a kind of cow oestrus monitoring method based on the time of ruminating and activity, it is characterised in that:
Step 1:By the sound pick-up outfit in milk cow worn, the voice signal that collection milk cow produces by chewing activity, simultaneously The activity information of milk cow is acquired by the pedometer bundled in milk cow leg;
Step 2:The voice signal of collection is detected by energy measuring method and zero-crossing rate method, the signal master that can be detected To include ruminating signal, feed signal, drinking-water signal and interference signal etc., then be identified from several signals and ruminate letter Number, and statistics ruminates the time;
Step 3:Obtain milk cow ruminate time and milk cow activity information, according to the two information, judge milk cow whether heat.
2. a kind of cow oestrus monitoring method based on the time of ruminating and activity according to claim 1, its feature exists In:The method that signal is ruminated in described identification is:By carrying out Fourier transformation, the frequency spectrum of observation signal, root to voice signal It is believed that number different spectrum signature, signal is ruminated so as to distinguish, wherein ruminating, drinking water and drinking the spectrum signature difference of feed number For:Signal frequency is ruminated more than 1 hertz, frequency stabilization, drinking-water signal frequency is less than 1 hertz, and frequency stabilization feeds signal and dry Disturb signal spectrum energy relatively to disperse, frequency is unstable.
3. a kind of cow oestrus monitoring method based on the time of ruminating and activity according to claim 1 step 3, it is special Levy and be:It is described the time to be ruminated according to milk cow and milk cow activity information judges whether the method for heat is milk cow:Unite first The step number for ruminating time and milk cow walking of milk cow always, is less than the thresholding of setting and walking when the time of ruminating in meter twenty four hours Step number is more than the thresholding of setting, and the time is in milk cow should be in oestrus next time front and rear 4-5 days, and heat is carried out Early warning, represents that milk cow is in proestrum, the time counting method of wherein twenty four hours is:0:00 to 24:Between 00 and work as Day 12:00 to next day 12:Between 00, when meeting above-mentioned requirements using any time counting method, early warning, early warning are carried out The step number walked afterwards using hour as interval stats milk cow, when step number exceedes setting thresholding, judges now cow oestrus.
CN201710277184.XA 2017-04-25 2017-04-25 A kind of cow oestrus monitoring method based on the time of ruminating and activity Pending CN106993546A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710277184.XA CN106993546A (en) 2017-04-25 2017-04-25 A kind of cow oestrus monitoring method based on the time of ruminating and activity

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710277184.XA CN106993546A (en) 2017-04-25 2017-04-25 A kind of cow oestrus monitoring method based on the time of ruminating and activity

Publications (1)

Publication Number Publication Date
CN106993546A true CN106993546A (en) 2017-08-01

Family

ID=59434209

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710277184.XA Pending CN106993546A (en) 2017-04-25 2017-04-25 A kind of cow oestrus monitoring method based on the time of ruminating and activity

Country Status (1)

Country Link
CN (1) CN106993546A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109566453A (en) * 2019-01-25 2019-04-05 深圳市云辉牧联科技有限公司 A kind of cows heat exposure method and apparatus
WO2019114203A1 (en) * 2017-12-15 2019-06-20 中国农业科学院北京畜牧兽医研究所 Estrus early warning method for cows
CN110728268A (en) * 2019-11-29 2020-01-24 东北农业大学 Milk cow rumination identification method based on decision tree classifier and bridle pressure envelope signal
CN111685060A (en) * 2020-06-10 2020-09-22 彭东乔 Method for recognizing oestrus behavior of ruminant based on artificial intelligence
CN114208714A (en) * 2021-12-01 2022-03-22 中国科学院亚热带农业生态研究所 Neck-ring type wearable milk cow rumination behavior monitoring device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030205208A1 (en) * 2000-07-19 2003-11-06 Avshalom Bar-Shalom Method and system for monitoring physiological conditions of, and/or suitability of animal feed for ruminant animals
CN101123874A (en) * 2005-01-19 2008-02-13 Scr工程有限公司 A method and device for detecting estrus
CN103914732A (en) * 2014-03-17 2014-07-09 东华大学 Chewer rumination and swallowing frequency audio recognition algorithm
CN104663499A (en) * 2015-02-13 2015-06-03 中国农业科学院北京畜牧兽医研究所 Cow oestrus monitoring system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030205208A1 (en) * 2000-07-19 2003-11-06 Avshalom Bar-Shalom Method and system for monitoring physiological conditions of, and/or suitability of animal feed for ruminant animals
CN101123874A (en) * 2005-01-19 2008-02-13 Scr工程有限公司 A method and device for detecting estrus
CN103914732A (en) * 2014-03-17 2014-07-09 东华大学 Chewer rumination and swallowing frequency audio recognition algorithm
CN104663499A (en) * 2015-02-13 2015-06-03 中国农业科学院北京畜牧兽医研究所 Cow oestrus monitoring system

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
S. REITH ET AL.: "Simultaneous analysis of activity and rumination time, based on collar-mounted sensor technology, of dairy cows over the peri-estrus period", 《LIVESTOCK SCIENCE》 *
SHUANG ZHANG ET AL.: "Research on the Real-time Monitoring System of Cow’s Rumination", 《INTERNATIONAL JOURNAL OF SMART HOME》 *
张谊: "《畜牧生产学实习指导》", 30 September 2013, 北京理工大学出版社 *
李建国 等: "《规模化生态奶牛养殖技术》", 31 January 2013, 中国农业大学出版社 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019114203A1 (en) * 2017-12-15 2019-06-20 中国农业科学院北京畜牧兽医研究所 Estrus early warning method for cows
CN109566453A (en) * 2019-01-25 2019-04-05 深圳市云辉牧联科技有限公司 A kind of cows heat exposure method and apparatus
CN109566453B (en) * 2019-01-25 2021-11-16 深圳市云辉牧联科技有限公司 Cattle group estrus uncovering method and device
CN110728268A (en) * 2019-11-29 2020-01-24 东北农业大学 Milk cow rumination identification method based on decision tree classifier and bridle pressure envelope signal
CN111685060A (en) * 2020-06-10 2020-09-22 彭东乔 Method for recognizing oestrus behavior of ruminant based on artificial intelligence
CN114208714A (en) * 2021-12-01 2022-03-22 中国科学院亚热带农业生态研究所 Neck-ring type wearable milk cow rumination behavior monitoring device

Similar Documents

Publication Publication Date Title
CN106993546A (en) A kind of cow oestrus monitoring method based on the time of ruminating and activity
US10761107B2 (en) Apparatus and method for detecting disease in dairy animals
Benaissa et al. Classification of ingestive-related cow behaviours using RumiWatch halter and neck-mounted accelerometers
Schirmann et al. Validation of a system for monitoring rumination in dairy cows
Ungar et al. Classifying cattle jaw movements: comparing IGER behaviour recorder and acoustic techniques
Ambriz-Vilchis et al. Comparison of rumination activity measured using rumination collars against direct visual observations and analysis of video recordings of dairy cows in commercial farm environments
Huzzey et al. Changes in feeding, drinking, and standing behavior of dairy cows during the transition period
DE60133106T2 (en) METHOD AND SYSTEM FOR MONITORING PHYSIOLOGICAL CONDITIONS OF, AND / OR FITNESS OF ANIMAL FEEDINGSTUFFS FOR REPURCHASES
Ueda et al. The use of a physical activity monitor to estimate the eating time of cows in pasture
Galli et al. Acoustic monitoring of short-term ingestive behavior and intake in grazing sheep
Tani et al. Automatic recognition and classification of cattle chewing activity by an acoustic monitoring method with a single-axis acceleration sensor
CN103914732B (en) Chewer rumination and swallowing frequency audio recognition algorithm
Nielsen et al. Validation and comparison of 2 commercially available activity loggers
Yoshitoshi et al. Distinguishing cattle foraging activities using an accelerometry-based activity monitor
CN110741962A (en) Oestrus and health monitoring method based on cow behavior recognition algorithm
EP3764780A2 (en) System and method for determining animal behavioral phenotypes
Shen et al. Rumination recognition method of dairy cows based on the change of noseband pressure
CN107410082A (en) Recognition methods is ruminated based on ruminant noseband pressure change
CN103340599B (en) Method of monitoring ruminant animals in real time
Norbu et al. Assessment of RumiWatch noseband sensors for the quantification of ingestive behaviors of dairy cows at grazing or fed in stalls
CN111916096B (en) Tibetan sheep grazing behavior monitoring method based on raspberry pie
CN114184755B (en) Automatic monitoring and water eutrophication prevention system and method for aquaculture water
CN106952175A (en) Individual feeding amount estimation method based on milk cow noseband pressure change
CN111109123B (en) Beef cattle natural hybridization process monitoring method based on 4G network
CN106993545A (en) Drinking-water quantity monitoring method based on ruminant noseband pressure change

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: 20170801