WO2018020090A1

WO2018020090A1 - Method of detection and indication of the preparatory phase of birthing in an animal, corresponding device, recording medium and computer program product

Info

Publication number: WO2018020090A1
Application number: PCT/FR2017/051710
Authority: WO
Inventors: Johann Barbier; Julie DEWEZ
Original assignee: Union Evolution
Priority date: 2016-07-25
Filing date: 2017-06-27
Publication date: 2018-02-01
Also published as: FR3040871A1; PL3487447T3; EP3487447B8; EP3487447B1; WO2018020090A9; ES2928062T3; FR3040871B1; EP3487447A1

Abstract

The invention relates to a method of detection and indication of the preparatory phase of birthing in an animal of the bovine family or of the Equidae family. According to the invention, such a method comprises the steps of: -measuring the components of the acceleration of a portion of said animal's tail along three orthogonal axes; -processing said measurements, this processing being intended for detecting an occurrence of said preparatory phase comprising the determination of at least two data items from among: -datum Q representative of a raised or lowered position of the tail; -datum A representative of the activity; -datum C representative of the occurrence of an attack of colic; -datum T representative of the occurrence of contractions; -datum TR representative of the occurrence of stamping, and a binary automatic classification of the condition of said animal between a birthing preparation condition and a non-preparation condition, from said data items Q, A, C, T and/or TR; -generating an alert signal when the result of said binary automatic classification is a birthing preparation condition.

Description

Method for detecting and signaling the preparatory phase of an animal's farrowing, a device, a recording medium and a corresponding computer program product

1. Field of the invention

The field of the invention is that of agriculture, and in particular the monitoring of cattle and equines.

More specifically, the invention relates to a method and a device for detecting and reporting the preparatory phase of farrowing of an animal of the family of cattle or equines.

The invention also makes it possible to discriminate whether the farrowing is likely to proceed without difficulty or not.

2. State of the art

It is well known that, without human intervention, some of the cows or mares lose their newborns on the occasion of parturition.

It is therefore necessary for a breeder to exercise, day and night, a surveillance of the animals that have come to an end, in order to be able to intervene if necessary during the parturition to try to save the newborn or to reduce post-partum complications. partum.

It is also common to perform several projections simultaneously within the same herd, which complicates the task of monitoring the breeder insofar as calving or foaling will occur over the same period.

In order to prevent a farmer from having to remain permanently mobilized both during the day and at night, and to allow him to rest during calving or foaling, various techniques have been proposed.

Calving detection techniques are known to introduce sensors measuring temperature, pressure and / or acidity within the reproductive tract of a cow to identify the imminence of the farrowing . One of these techniques is for example to introduce a thermometer into the vaginal canal of the animal that will be expelled with the water bag. A disadvantage of these intrusive techniques is that the introduction and positioning of the sensors in the genital tract of the cow is delicate, and that it is a source of infection and / or irritation for the latter.

Another disadvantage of these intrusive techniques is that normal metabolic changes in the animal due to its activity can trigger false alarms.

Yet another disadvantage of these intrusive techniques is that they are expensive to implement.

It has also been proposed to fix a mercury or ball inclinometer on the tail of a cow or a mare, which will trigger an alarm when approaching the farrowing, when the tail of the animal remains raised. .

A disadvantage of this technique is that it raises reliability issues. Indeed, it is found that alerts can be triggered untimely, for example when the animal changes position or goes to bed.

It has also been proposed to strap the size of a cow with a belt that measures the uterine activity of the animal and sounds an alarm when the frequency of contractions increases.

This technique has several disadvantages: the belt presents a danger for the animal if it is too tight. However, it should not be too loose, as it may not work properly, requiring tightening every 3 to 4 hours. In addition this technique is expensive and does not allow in certain cases to distinguish the deformations due to the work of the animal other deformations resulting from a normal activity of the animal to eat or move.

Document WO-A1-2013 / 186235 also discloses a technique for detecting the imminence of a farrowing putting an accelerometer fixed on the tail of a cow, in order to estimate the overall activity of the animal. from the measurements of the acceleration.

A disadvantage of this known technique, which is to compare the sole global activity to a threshold to detect if the animal is about to put down, is that it is not accurate enough to detect the imminence of farrowing in more than 50 to 60% of animals.

3. Objectives of the invention

The invention particularly aims to overcome the disadvantages of the state of the art cited above.

More specifically, the invention aims to provide a technique for detecting and reporting the preparatory phase of farrowing of an animal that is reliable.

The invention particularly aims, in at least one particular embodiment of the invention, to propose such a detection and signaling technique which has a detection rate of the preparatory phase of farrowing at least equal to 80. % and advantageously greater than 85%.

Another object of the invention is to provide such a detection and reporting technique that is simple to implement and a reduced cost.

The object of the invention is also to provide a technique for detecting and signaling the preparatory phase of farrowing of an animal which makes it possible to detect whether the farrowing is going on without difficulty or not.

An object of the invention is also to propose such a detection and signaling technique that is reusable.

Another objective of the invention is to provide a technique for detecting and signaling the preparatory phase of farrowing of a bovine or equine which is reusable on several animals, which requires little maintenance and which is autonomous in energy over a period of several years.

4. Presentation of the invention

These objectives, as well as others that will appear later, are achieved by a method of detecting and reporting the preparatory phase of farrowing of an animal of the family of cattle or family of equines. In the context of the invention, the term "preparatory phase of farrowing" in its general meaning. It is thus the phase preceding the engagement of the fetus in the pelvis, generally lasting between 2 and 24 hours, during which the first uterine contractions and cervical dilatation occur in particular. .

According to the invention, such a method for detecting and signaling the preparatory phase of birthing comprises the following steps in this order:

measuring the components of the acceleration of a portion of the tail of said animal along three orthogonal axes;

processing said measurements for detecting an occurrence of said preparatory phase comprising:

a step of projecting said measurements of the components in a direct orthonormal reference X, Y, Z where the Z axis is vertical and directed downwards and the X axis is horizontal and in the extension of the sacrum of said animal, in the case where the mark formed by said three orthogonal axes do not coincide with said orthonormal reference X, Y, Z;

at least two steps from the following steps a), b), c) d) and e): a) determination, for each measurement instant, of a data item Q representative of a raised or lowered position of said tail, comprising a step of calculating a value of the angle of the tail with respect to the vertical from the projections of the measurements of the components of the acceleration along the X and Z axes, or measurements of the components of the acceleration, when the mark formed by said three orthogonal axes coincides with said orthonormal coordinate system X, Y, Z, and a step of comparing said calculated angle with a predetermined threshold angle value; b) determination of a data item A representative of the activity of said animal, for each measurement instant, comprising a step of calculating the variations of each of the components of the acceleration with respect to its average value over a period predetermined from the projections of the measurements of the components of the acceleration along the X, Y and Z axes or measurements of the acceleration components, when the reference mark formed by the said three orthogonal axes coincides with the said orthonormal coordinate system X, Y, Z ;

c) determining a C-data representative of the occurrence of a colic attack in said animal comprising a step of applying a bandpass filter to said measurements of the components of the acceleration on at least two axes, and preference of the components of the acceleration on the X and Z axes d) determination of a data item T representative of the occurrence of contractions in said animal comprising a step of estimating the correlation coefficient, for each component of the acceleration, between a sequence of measurements of this component of the acceleration and a sequence of reference data;

e) determining a TR representative of the occurrence of trampling in said animal comprising a step of identifying a predominant frequency in the frequency spectrum for a sequence of measurements of the component of the acceleration following the Y axis to establish if said frequency is in a predetermined frequency range;

binary automatic classification of the state of said animal between a preparation state of the farrowing and a non-preparatory state, from said data Q, A, C, T and / or TR determined above, representative respectively of a raised or lowered position of tail, activity, occurrence of colic crisis, occurrence of contractions and occurrence of trampling;

generating a first warning signal when the result of said automatic binary classification is a preparation state of the farrowing. Thus, the invention proposes to exploit the measures of the acceleration of the tail of a cow, a mare or a donkey to classify the state of the animal between a state of readiness of the setting. low and a non-preparatory state from a reduced number of parameters Q, A, C, T and / or TR.

The inventors have indeed found that in animals the tail lifts, activity, colic attacks, contractions and trampling were the most characteristic manifestations that can be observed through the movements of the tail of the animal during the preparatory phase of farrowing and that each of these events triggered a specific and reproducible sequence of movements at least on part of a bovine or equine population. The inventors have also found that these specific sequences could vary between two breeds of cows or mares.

In nine particular embodiments of the invention, said step of processing said measurements comprises respectively steps a) and b), a) and c), a) and d), a) and e), b) and c) , b) and d), b) and e), c) and d), c) and e).

In a particular embodiment of the invention, said step of processing said measurements comprises at least three steps from steps a), b), c) d) and e).

In a particular embodiment of the invention, said step of processing said measurements comprises steps a), b) and c) or d).

In a particular embodiment of the invention, said step of processing said measurements comprises at least four steps from steps a), b), c), d) and e).

In a particular embodiment of the invention, said step of processing said measurements comprises the steps a), b), c) and d).

In a particular embodiment of the invention, said step of processing said measurements comprises the five steps a), b), c) d) and e).

This improves the detection rate of the preparatory phase of birth in a group of animals. In a particular embodiment of the invention, the classifier implemented in said automatic binary classification step is a linear classifier.

According to a particular aspect of the invention, during said automatic binary classification step, the output of the classifier implemented in said automatic classification step is compared with a predetermined classification threshold.

Advantageously, said step a) of determining a data representative of a raised or lowered position of the tail and / or said step b) of determining a datum representative of the activity and / or said step d) determining a data representative of the occurrence of contractions and / or said step e) of determining a datum representative of the occurrence of a trampling comprises a step of filtering said projections of the measurements or said measurements.

According to a particular aspect of the invention, said step a) of determining a datum representative of a raised or lowered position of the tail comprises a step of assigning to said datum Q a first value, preferably 1, when said angle value is greater than or equal to said threshold angle value and a second value, preferably 0 or -1, when said angle value is less than said threshold angle value.

According to a preferred aspect of the invention, said threshold angle value is between 32 ° and 37 °, preferably is substantially equal to 35 °.

The inventors have indeed found that a threshold angle value close to 35 ° allows an effective classification of the state of the animal.

In a particular embodiment of the invention, said step a) of determining a Q data representative of a raised or lowered position of said tail further comprises a step of reassigning to said value Q, for each moment of measurement tm _eS ure, of an average, over a predefined time interval Δΐ, of the values assigned to the data Q for the measurement instants preceding the measurement instant tm _eS ure included in the interval [tmesure-

Δΐ ^ tmesure]. In an advantageous embodiment of the invention, said step a) of determining a data item Q representative of a raised or lowered position of said tail comprises a step of weighting said value of the angle of the tail by the value of the measurement of the component of the acceleration, or of its projection, on the Y axis.

According to a particular embodiment of the invention, said step b) of determining the activity of said animal comprises a step of calculating the root mean square of the variations of the components of the acceleration along the X, Y and Z axes with respect to at their average value.

Preferably, during said step c) of a data representative of the occurrence of a colic attack, the cutoff frequencies of said bandpass filter are substantially equal to 6mHz and 12mHz.

The inventors have observed that colic attacks are manifested by jolts repeating over time, spaced from 2mn 45s to 5mn 30s.

Preferably, in said step d) of determining a data representative of the occurrence of contractions, said data reference sequence is a sequence of data representative of a peak of substantially triangular shape.

According to a particularly advantageous embodiment of the invention, in said step e) of determining the occurrence of a trampling, said frequency range is bounded by the frequencies 150mHz and 300mHz.

In a particular embodiment of the invention, a method for detecting and signaling the preparatory phase of farrowing of an animal as described above further comprises a step of determining a representative P data of the standing or lying state of said animal comprising a step of comparing the average over a predetermined period, preferably substantially equal to 1 minute, of the values of the measurements of the components of the acceleration, or of their projection, on the Y axis relative to a predetermined state threshold value and / or a step of comparing the number of sign changes of the acceleration on the Y axis over said predetermined period with respect to a threshold number.

Indeed, the inventors have found that, unlike in the case where the animal is lying down, the average acceleration of the component along the Y axis of the acceleration is substantially zero and there is a minimum number of sign changes of the acceleration following Y over a predetermined period, when the animal is standing.

Preferably, said state threshold value is substantially equal to 0.2 g.

In a particularly advantageous embodiment of the invention, a method for detecting and reporting the preparatory phase of an animal birth as described above further comprises a step of automatically classifying the state of the animal. said animal between a low-calving condition and an easy farrowing status from at least three data, preferably at least four data, more preferably at least five data, from the Q, A data, C, T, TR and P.

In a particularly advantageous embodiment of the invention, said step of automatic binary classification of the state of said animal between a difficult farrowing state and an easy farrowing state comprising the following steps:

obtaining at time t such that t = m .AT + T ₀ with m an integer, ΔΤ a predetermined time interval and T ₀ is the instant when said first warning signal is generated, a vector of five continuous real variables (Μ ^ ΐν, Μ ^ Μ ^ Μ ⁵ ) from a sequence of n successive values of said data Q, A, C, T and P over a predetermined period preceding the instant t, where

with i integer such that l≤i≤n, and M, ² is the duration since the last change from a supine position to standing or vice versa at the index i estimated from the sequence of successive values of P;

determination of a vector of characteristics F _t = (Ft ¹ , Ft ² , Ft ³ , Ft ⁴ , F _t ⁵ ) where F _t ^k , l≤k <5, is the maximum of the mean values of M ^k on subintervals of said predetermined period; assigning to each characteristic F ^k , l≤k <5, of said characteristic vector of a vote P _t ^k = log (P (F ^k = F _t ^k | H ₀ ) / P (F ^k = F _t ^k | Hi)) where P (F ^k = F _t ^k | H ₀ ) is the probability of observing the characteristic F ^k knowing that the farrowing is easy and P (F ^k = F _t ^k | Hi) is the probability of observe the characteristic F ^k knowing that farrowing is difficult, obtained by comparison with a statistical reference distribution constructed from observations on a sample of reference animals;

calculating a decision criterion f _t expressed as:

where αι <and Ok are predefined constants;

generating a second warning signal in the case where said decision criterion f _t is greater than or equal to a predetermined threshold value S.

Thus, in an unprecedented manner, the invention proposes to discriminate the birth condition of the animal between a difficult farrowing state and an easy farrowing state from the parameters Q, A, C, T and P.

According to an advantageous aspect of the invention, said time interval ΔΤ is between 30 seconds and 2 minutes, preferably is substantially equal to 1 minute.

According to a particular aspect of the invention, said predetermined period is of a duration substantially equal to 1 hour.

In a particular embodiment of the invention, a method for detecting and signaling the preparatory phase of farrowing an animal as described above further comprises a step of calculating a confidence index G expressing themselves in the form:

or ak, l≤k <5, is a predefined constant, and C is the confidence provided by the characteristic k, l≤k <5, which is expressed as: (Q ik

with _t the probability of observing the characteristic F ^k knowing that the farrowing is easy and / ¾ ^ - P ("™ f lHi) the probability of observing the characteristic F ^k knowing that the farrowing is difficult.

In an advantageous embodiment of the invention, a method for detecting and signaling the preparatory phase of farrowing an animal as described above comprises a step of determining the instant tf _in corresponding to the end of the farrowing, comprising a step of calculating at each instant t the sum S _t of the variations of the values of the data A representative of the activity over a predefined time interval preceding said instant t and a step of detecting the maximum values of St over a predetermined period, making it possible to determine the instant tf _in for which said value of St is maximum.

According to a particular aspect of the invention, said predefined time interval implemented during said step of determining the instant tf _in corresponding to the end of the farrowing is of a duration substantially equal to 20 minutes.

Preferably, said predetermined period implemented during said step of determining the _end time t corresponding to the end of the farrowing is of a duration at least equal to 30 minutes and preferably at least 50 minutes.

In an advantageous embodiment of the invention, a method for detecting and signaling the preparatory phase of farrowing an animal as described above comprises a step of generating an alert signal intended to signaling the occurrence of an abnormally long farrowing, when no second warning signal is generated 2 hours after the generation of said first warning signal.

In variants of this embodiment of the invention, the warning signal signaling the occurrence of an abnormally long farrowing can generate at any time chosen between lh and 2h after the generation of said first warning signal, without departing from the scope of the invention.

The invention also relates to a computer program product comprising program code instructions for implementing the step of processing the measurements of the method for detecting and signaling the preparatory phase of the farrowing of an animal. as described above and / or the step of automatic binary classification of the state of said animal between a difficult calving state and an easy calving state of the method of detecting and reporting the preparatory phase of farrowing an animal as described above, when executed by a processor.

The invention also relates to a processor-readable recording medium on which a computer program is recorded for the implementation of the step of processing the measurements of the method of detecting and signaling the preparatory phase of setting-up. the bottom of an animal as described above and / or the step of the binary automatic classification step of the state of said animal between a difficult farrowing state and an easy farrowing state of the method detection and reporting of the preparatory phase of farrowing of an animal as described above.

Finally, the invention also relates to a device for detecting and signaling the preparatory phase of farrowing of an animal of the family of cattle or the family of equidae comprising a sealed housing adapted to be fixed on a portion of the tail said animal containing:

a 3D accelerometer for measuring the components of the acceleration of said portion of the tail along 3 axes;

a recording medium as described above and a processor capable of executing the computer program as described above, recorded on said recording medium to process said measurements;

means for generating a first radiocommunication signal intended to alert imminence of the farrowing of said animal, configured so as to generate said first signal in the case where the result of said automatic binary classification is a state preparation of the farrowing; means for transmitting said first signal generated to a collector forming a relay or a terminal.

The device according to the invention thus cleverly integrates a software application recorded on a recording medium, ensuring a complete processing of the accelerometer measurements, which makes it possible to limit the energy consumption of the device because the quantity of signals it emits to the outside is very small and this gives it a particularly extended energy autonomy.

Advantageously, said first signal emitted by said transmitting means has a range of between 150 and 500 meters.

Thus, the signal can be transmitted to a relay located in or near the barn or stabule where the animal is parked, regardless of the location of the animal in the building. The signal can still be transmitted directly to a communication terminal of the farmer, such as a mobile phone or a personal assistant for example, if it is close to the building.

According to a particular embodiment of the invention, a device for detecting and signaling the preparatory phase of farrowing of an animal as described above comprises means for generating a second radiocommunication signal intended to alerting of the occurrence of a difficult birthing of said animal, configured to generate said second signal in the case where said processor calculates a decision criterion f _t greater than or equal to said predetermined threshold value S, said generating means said second signal being able to be said means for generating said first signal, and in that said transmitting means are capable of transmitting said second generated signal to a relay collector or a terminal.

5. List of figures

Other characteristics and advantages of the invention will emerge more clearly on reading the following description of an embodiment of the invention, given as a simple illustrative and nonlimiting example, and the appended drawings among which:

Figure 1 is a schematic view of a device according to the invention fixed on the tail of a cow;

Figure 2 is a schematic representation of the contents of the box shown with reference to Figure 1;

FIG. 3 is a diagrammatic representation of the steps of an exemplary method of detecting and signaling the preparatory phase of farrowing of an animal according to the invention; FIG. 4 details the substeps of the step of automatic binary classification of the state of an animal between a difficult farrowing state and an easy farrowing state, of the method presented with reference to FIG. ;

FIGS. 5A to 5E illustrate an example of the evolution over time of data Q, A, C, T and P at the approach of a farrowing for an animal.

6. Detailed description of an exemplary embodiment of the invention

A device 10 for detecting and signaling the preparatory farrowing phase according to the invention is shown with reference to FIG. 1, attached to the tail of a cow 11.

The device 10 is in the form of a sealed housing 12 whose face 13 in contact with the tail of the cow 11 is substantially frustoconical in shape so as to match the shape of the tail.

As can be seen in Figure 2, which is a schematic representation of the housing 12, it contains a 3D accelerometer 21 connected to an electronic card 22 incorporating a microcontroller 210, which performs the processing of the measurements provided by the accelerometer 21 , and an integrated circuit 24 ensuring an optimization of the energy consumed by the housing 12. The software application for processing the measurements is stored in the flash memory 211 of the microcontroller 210, which is read by the processor μΐ. Inside the housing 12, there is also an antenna 23 for transmitting a digital signal conforming to the GSM standard to a relay or a mobile phone and a battery L5, which supplies the accelerometer 21, the card 22 and the antenna 23 in energy.

The microcontroller 210 fitted to the card 22 processes the measurements delivered by the accelerometer 21 and makes it possible to generate a first warning signal, when the preparatory phase of farrowing is detected, and a second warning signal when a difficult calving is detected. detected. The first and the second warning signal are emitted by the antenna 23, in this particular embodiment of the invention.

In this particular embodiment of the invention, the measurements of the acceleration components are recorded at a sampling frequency of 4 Hz.

It should be noted that the acceleration measurements are not preserved after treatment. Indeed, the device 10 being provided to be able to operate without stopping several years, and more specifically from 5 to 10 years in this particular embodiment of the invention, providing a storage memory of sufficient capacity is not possible.

FIG. 3 is a diagrammatic representation of the steps E1-E10 of processing the measurements of the method for detecting and signaling the preparatory phase of farrowing of a cow according to the invention implemented in FIG. the software application stored in the flash memory 211.

The components of the acceleration along three orthogonal axes x, y and z linked to the housing 12 are measured every 25 ms by the accelerometer 21, in a step E0.

In a step E1, the measurements of the components are projected in a direct orthonormal coordinate system X, Y, Z, where the Z axis is a vertical axis and directed downwards, the X axis is horizontal and in the extension of the sacrum of said animal. For this purpose, the animal has previously calibrated the position of the x, y, z reference linked to the housing relative to the X, Y, Z mark. E2 is then determined for each measurement instant, a Q data representative of a raised or lowered position of said tail. During this step E1, the projected components of the acceleration are firstly filtered by applying a first-order filter (step E21) and a value of the angle of the tail with respect to the vertical 6 _that ue is calculated from the filtered ax and az projections of the measurements of the acceleration components along the X and Z axes, applying the formula 6 _that ue = atan (az / ax) (step E22). The calculated angle is then compared with a threshold angle value of 35 ° (step E23). A value 256 is assigned to Q for the time of measurement tm _eS ure if the calculated angle is greater than or equal to 35 °; otherwise a value of 0 is assigned to Q.

Subsequently (step E24) is reassigned to each data Q (tm _eS ure) an average over values of Q over the time interval [tm _eS ure-At; measurement] preceding the measurement instant tm _eS ure, with Δΐ = 1 hour in this particular embodiment of the invention, so as to smooth the variations of the data Q-

In E3, a data item A representative of the activity of the animal is determined by calculating (step E31) a root mean square of the variations of the projected and filtered components of the acceleration along the X, Y and Z axes with respect to their value. average over a minute.

In E4, a C-data representative of the occurrence of a colic crisis in the animal is determined by applying (Step 41) a 2nd order Chebyshev-type bandpass filter to the projections of the measurements of the components of the acceleration. on the X and Z axes whose cutoff frequencies are 6mHz and 12mHz and the sum of the squares of the projections of the measurements filtered by the bandpass filter on the C data is affected (step 42).

In E5, a T-value representative of the occurrence of contractions in the animal is determined by calculating an estimate (step 51) of the correlation coefficient, for each component of the projected acceleration on the X, Y or Z axis, between a sequence of 3.5s of the projection of the measurements of this component of the acceleration with a reference mask formed of a data sequence of a substantially triangular shaped peak 3.5s wide. The correlation coefficient obtained on each axis X, Y and Z is then integrated over a period of 15 minutes (step 52) and the sum of squares of the values of the correlation coefficient estimated on each axis X, Y is assigned to the value T. and Z (step 53).

In E6, a data item TR representative of the occurrence of trampling in the animal is determined by identifying (step E61) a predominant frequency in the frequency spectrum for a sequence of the projection of the component of the acceleration following Y-axis one minute and assigned (step E62) a value 1 if the frequency identified is in the frequency range [150mHz; 300mHz], -1 otherwise.

Examples of time course of data Q, A, C and T at the approach of a farrowing are illustrated respectively in Figures 5A to 5D.

The processing of the measurements is completed by applying to the data Q, A, C, T and TR, in a step E7, a linear classifier of a binary automatic classification algorithm known per se, and comparing the output of this classifier to a threshold Sdass equal to 5.10 ⁵ in this particular embodiment of the invention (step E71). This classifier makes it possible to discriminate the state of the animal between a state of preparation of the farrowing and a non-preparatory state as a function of the value of the output of the classifier with respect to the threshold Sdass.

It should be noted that this embodiment of the invention allows in 88% of cases a detection of the phase preparation farrowing, without false alarm.

A first warning signal is generated by the microcontroller 210, when the result of the automatic binary classification is a preparation state of the farrowing, in the step E8. This second alert signal is emitted by the antenna 23 in step E80.

In this particular embodiment of the invention, in a step E9, a data item P representative of the standing or lying state of said animal is also determined. In this step E9, comparing (step E91) the average over a period of 1 minute preceding the measurement instant tm _eS u re, values of the projection on the Y axis of the measurements of the acceleration with respect to a state threshold value equal to 0.2 g and the value 1, corresponding to a standing position, is assigned (step E92) when the average is less than the state threshold value and the value 0 otherwise, corresponding to a supine position.

In a variant of this particular embodiment of the invention, it may be envisaged to determine the data P from the number of sign changes of the acceleration on the Y axis over a predetermined period, for example from 1 minute. If this number of sign changes is greater than or equal to a threshold, for example equal to 10 over a period of 1 minute, then we can assign the value 1, corresponding to a standing position, to the data P, and 0 otherwise .

An example of evolution over time of the data P at the approach of a farrowing is illustrated in Figure 5E.

A step E10 of automatic binary classification of the state of the animal is then carried out between a difficult farrowing state and an easy farrowing state from the Q, A, C, T and P data.

A second alert signal is generated by the microprocessor 210 in a step E20, in the case where the output of the classifier implemented during step E10 is less than or equal to a predetermined threshold value S, equal to -0, 8741 in this particular embodiment of the invention. This second alert signal is emitted by the antenna 23 in step E30.

In relation with FIG. 4, step E10 is detailed.

This step E10 begins with the formation (substep E101) from the instant T ₀ the moment when said first alert signal is generated at step E8, at and each instant t such t = m .AT + T ₀ with m an integer and ΔΤ = lmn, of a vector of five continuous real variables (Μ ^ ΐν, Μ ^ Μ ^ Μ ⁵ ) from the sequence of the 240 successive values of the data Q, A, C, T and P over a period of one minute preceding the instant t. This vector of five continuous real variables

with i integer such that l≤i <240, and M, ² is the duration since the last changing from a supine position to standing or vice versa at the index i estimated from the sequence of successive values of P.

Then, in a substep 102, a vector of characteristics F _t = (Ft ¹ , Ft ² , Ft ³ , Ft ⁴ , F _t ⁵ ) is determined, where F _t ^k , l≤k <5, is the maximum of mean values of M ^k during the hour before time t.

It should be noted that for the instants preceding the instant T ₀ , the value 0 is assigned to the discrete variables M ^k , l≤k <5.

In E103, we attribute to each characteristic F ^k , l≤k <5, of the characteristic vector a vote Pt ^k constructed from the ratio, in logarithmic scale, of the probability P (F ^k = F _t ^k | Ho) d observe the characteristic F ^k knowing that the farrowing is easy and the probability P (F ^k = F _t ^k | Hi) to observe the characteristic F ^k knowing that the farrowing is difficult, ie P _t ^k = log (P (F ^k = F _t ^k | H ₀ ) / P (F ^k = F _t ^k | H i)).

P (F ^k = F _t ^k | H ₀ ) and P (F ^k = F _t ^k IH i) are, in the sub-step E103, determined by comparison with a statistical reference distribution constructed from observations on a sample of reference animals.

Then, in a sub-step E104, a decision criterion f _t , or classifier, is calculated, expressing the form:

5

A ^ O _k )

!

WHERE i = 0.19, i = 0.59, ₃ = 0.27; at ₄ = 0.49 and at ₅ = 0.27 and

0.107; 0 ₃ = - 0.206; 0 ₄ = - 0.003; 0 ₅ = - 0.138 in this particular embodiment of the invention.

The value of this decision criterion f _t constitutes the output of the classifier implemented in state E10.

In step E10, a subscript E105 is further calculated with a confidence index G expressed as:

where αι <, l≤k <5, are constants, and. ^ is the confidence provided by the characteristic k, l≤k <5, which is expressed as: e

the probability of observing the characteristic F ^k knowing that the farrowing is easy and p ^:::::

the probability of observing the characteristic F ^k knowing that the farrowing is difficult.

This confidence coefficient is transmitted to the farmer when the second warning signal is issued.

The exemplary embodiment detailed above makes it possible to detect a difficult calving in 82% of the cases, with a confidence index greater than 0.78.

Moreover, in step E40, the instant tf _in corresponding to the end of the farrowing is determined. This step E40 is intended to prevent a second warning signal is issued, inadvertently and inappropriate, after the end of calving.

This step E40 comprises the computation (step 401) at each instant t, such that t = m .AT + T ₀ with m an integer and ΔΤ = 1 mn, of the sum S _t of the variations of the values of the data A representative of the activity over a time interval of 20 minutes preceding the instant t and a detection of the maximum of the values of St over a period of 50 minutes, from which the instant tf _in is deduced (step 402).

In this particular embodiment of the invention, as soon as the instant tone is exceeded, the microcontroller is advantageously configured to no longer generate any second warning signal.

Note further that an alert signal for signaling the occurrence of an abnormally long farrowing is generated by the microcontroller 210 when no second warning signal is generated 2 hours after the generation of the first warning signal without the end of farrowing time tf _in is exceeded.

Claims

1. A method for detecting and reporting the preparatory phase of farrowing of an animal of the family of cattle or of the equidae family, characterized in that it comprises the following steps in this order:

at least two of the following steps a), b), c), d) and e): a) determination, for each measurement instant, of a given data item;

Q representative of a raised or lowered position of said tail, comprising a step of calculating a value of the angle of the tail with respect to the vertical from the projections of the measurements of the components of the acceleration along the X axes and Z, or measurements of the components of the acceleration, when the mark formed by said three orthogonal axes coincides with said orthonormal coordinate system X, Y, Z, and a step of comparing said calculated angle with a predetermined threshold angle value; b) determining a data item A representative of the activity of said animal, for each measurement instant, comprising a step of calculating the variations of each of the components of the acceleration relative to its average value over a predetermined period from the projections of the measurements of the acceleration components along the X, Y and Z axes or measurements of the acceleration components, formed by said three orthogonal axes coincides with said orthonormal coordinate system X, Y, Z;

generating a first warning signal when the result of said automatic binary classification is a preparation state of the farrowing.

2. A method for detecting and signaling the preparatory phase of an animal's farrowing according to claim 1, characterized in that the classifier implemented in said automatic binary classification step is a linear classifier.

3. A method for detecting and signaling the preparatory phase of farrowing of an animal according to claim 1, characterized in that, during said step of automatic binary classification, the output of the classifier put implemented in said automatic classification step is compared to a predetermined classification threshold.

4. A method for detecting and signaling the preparatory phase of farrowing an animal according to any one of claims 1 to 3, characterized in that said step a) of determining a data representative of a position raising or lowering of the tail and / or said step b) of determining a datum representative of the activity and / or said step d) of determining a datum representative of the occurrence of contractions and / or said step e ) determining a data representative of the occurrence of a trampling comprises a step of filtering said projections of the measurements or said measurements.

5. A method for detecting and signaling the preparatory phase of farrowing of an animal according to any one of claims 1 to 4, characterized in that said step a) of determining a data representative of a position raising or lowering the tail comprises a step of assigning to said data Q a first value, preferably 1, when said value of the angle is greater than or equal to said threshold angle value and a second value. , preferably 0 or -1, when said value of the angle is smaller than said threshold angle value.

6. A method for detecting and signaling the preparatory phase of farrowing of an animal according to any one of claims 1 to 5, characterized in that said threshold angle value is between 32 ° and 37 °, preferably is substantially equal to 35 °.

7. A method for detecting and signaling the preparatory phase of farrowing of an animal according to any one of claims 1 to 6, characterized in that said step a) of determining a data Q representative of a raised or lowered position of said tail further comprises a step of reassigning to said value Q, for each measurement instant tmesu re, an average, over a predefined time interval Δΐ, of the values assigned to the data Q for the moments of measurement preceding the time of measurement tmesu re included in the interval [su re-At; tmesu re].

8. A method for detecting and signaling the preparatory phase of farrowing an animal according to any one of claims 1 to 7, characterized in that said step a) of determining a representative Q data of a raised or lowered position of said tail comprises a step of weighting said value of the angle of the tail by the value of the measurement of the component of the acceleration, or of its projection, on the Y axis.

9. A method for detecting and signaling the preparatory phase of farrowing of an animal according to any one of claims 1 to 8, characterized in that said step b) of determining the activity of said animal comprises a step of calculating the root mean square of the variations of the components of the acceleration along the X, Y and Z axes with respect to their mean value.

10. A method for detecting and signaling the preparatory phase of farrowing of an animal according to any one of claims 1 to 9, characterized in that, in said step c) a data representative of the occurrence of a colic attack, the cutoff frequencies of said bandpass filter are substantially equal to 6mHz and 12mHz.

1. A method for detecting and signaling the preparatory phase of farrowing of an animal according to any one of claims 1 to 10, characterized in that, in said step d) of determining a data representative of the occurrence of contractions, said data reference sequence is a sequence of data representative of a substantially triangular shaped peak.

12. A method for detecting and signaling the preparatory phase of farrowing of an animal according to any one of claims 1 to 10, characterized in that, in said step e) of determining the occurrence of a trampling, said frequency range is bounded by the frequencies 150mHz and 300mHz.

13. A method for detecting and signaling the preparatory phase of farrowing an animal according to any one of claims 1 to 12, characterized in that it further comprises a step of determining a representative P data. of the standing or lying state of said animal comprising a step of comparing the average over a predetermined period, preferably substantially equal to 1 minute, of the values of the measurements of the components of the acceleration, or of their projection, on the axis Y with respect to a predetermined state threshold value and / or a step of comparing the number of sign changes of the acceleration on the Y axis over said predetermined period with respect to a threshold number.

14. A method for detecting and signaling the preparatory phase of farrowing of an animal according to claim 13, characterized in that said threshold state value is substantially equal to 0.2 g.

15. A method for detecting and signaling the preparatory phase of farrowing of an animal according to any one of claims 1 to 14, characterized in that it further comprises a step of automatic classification of the binary state said animal between a difficult farrowing state and an easy farrowing state from at least three data, preferably at least four data, even more preferably at least five data, among the data Q, A, C , T, TR and P.

16. A method for detecting and signaling the preparatory phase of an animal's farrowing according to claim 15, characterized in that said step of automatic binary classification of the state of said animal between a difficult farrowing state and an easy birthing state includes the following steps:

obtaining at time t such that t = m.AT + T ₀ with m an integer, ΔΤ a predetermined time interval and T ₀ is the instant when said first warning signal is generated, of a vector of five continuous real variables (Μ ^ ΐν, Μ ^ Μ ^ Μ ⁵ ) from a sequence of n successive values of said data Q, A, CT and P over a predetermined period preceding the instant t, where

- determination of a feature vector

where F _t ^k , l≤k <5, is the maximum of the average values of M ^k over subintervals of said predetermined period;

assigning to each characteristic F ^k , l≤k <5, of said characteristic vector of a vote P _t ^k = log (P (F ^k = F _t ^k | H ₀ ) / P (F ^k = F _t ^k | Hi)) where P (F ^k = F _t ^k | H ₀ ) is the probability of observing the characteristic F ^k knowing that the farrowing is easy and P (F ^k = F _t ^k | Hi) is the probability of observe the characteristic F ^k knowing that farrowing is difficult, obtained by comparison with a statistical reference distribution constructed from observations on a sample of reference animals;

calculating a decision criterion f _t expressed in the form: fi ^{■■■■■■■■■} Χ Η- 'β ^~ Ok) where αι _< and Ok are predefined constants;

and in that it further comprises a step of generating a second warning signal in the case where said decision criterion f _t is greater than or equal to a predetermined threshold value S.

17. A method for detecting and signaling the preparatory phase of birthing an animal according to claim 16, characterized in that said time interval ΔΤ is between 30 seconds and 2 minutes, preferably is substantially equal to 1 minute.

18. A method for detecting and signaling the preparatory phase of birthing of an animal according to any one of claims 16 and 17, characterized in that said predetermined period is of a duration substantially equal to 1 hour.

19. A method for detecting and signaling the preparatory phase of birthing of an animal according to any one of claims 16 to 18, characterized in that it further comprises a step of calculating a confidence index. _t C being expressed in the form:

where αι <, l≤k <5, is a predefined constant, and e is the confidence brought by the elm:

the probability of observing the characteristic F ^k knowing that the farrowing is easy and F _? ^' ----- P { ^K -

20. A method for detecting and signaling the preparatory phase of birthing of an animal according to any one of claims 16 to 19, characterized in that it comprises a step of determining the instant tf _in corresponding to the end of the farrowing, comprising a step of calculating, at each instant t, the sum S _t of the variations of the values of the data A representative of the activity over a predefined time interval preceding said instant t and a step of detecting the maximum values of St over a predetermined period, for determining the time tf _in for which said value of S _t is maximum.

21. A method for detecting and signaling the preparatory phase of birthing of an animal according to claim 20, characterized in that said predefined time interval implemented during said step of determining the corresponding instant tf _in at the end of the farrowing is of a duration substantially equal to 20 minutes.

22. A method of detecting and signaling the preparatory phase of an animal birth according to any one of claims 20 and 21, characterized in that said predetermined period implemented during said step of determining the instant tf _in corresponding to the end of the farrowing is of a duration at least equal to 30 minutes and preferably at least equal to 50 minutes .

23. A method for detecting and signaling the preparatory phase of birthing of an animal according to any one of claims 16 to 22, characterized in that it comprises a step of generating an alert signal for to signal the occurrence of an abnormally long farrowing, when no second warning signal is generated 2 hours after the generation of said first warning signal.

24. A computer program product comprising program code instructions for implementing the process step of the method for detecting and reporting the preparatory phase of the farrowing of an animal according to one of the following: Claims 1 to 22 and / or the step of automatic binary classification of the condition of said animal between a difficult birthing state and an easy farrowing state of the method for detecting and reporting the preparatory phase of birthing of an animal according to claims 16 to 22, when executed by a processor.

25. A processor-readable recording medium on which a computer program is recorded for implementing the process step of the method of detecting and reporting the preparatory phase of farrowing a animal according to one of claims 1 to 22 and / or the step of the step of automatic binary classification of the state of said animal between a difficult farrowing state and an easy farrowing state of the method of detecting and signaling the preparatory phase of farrowing an animal according to claims 16 to 22.

26. A device for detecting and signaling the preparatory phase of calving of an animal of the family of cattle or of the family of equidae comprising a sealed casing able to be fixed on a portion of the tail of said animal containing: a 3D accelerometer for measuring the components of the acceleration of said portion of the tail along 3 axes;

a recording medium according to claim 25 and a processor adapted to execute the computer program according to claim 24 recorded on said recording medium for processing said measurements;

means for generating a first radiocommunication signal intended to alert imminence of the farrowing of said animal, configured so as to generate said first signal in the case where the result of the automatic binary classification is a state of preparation for the farrowing;

means for transmitting said first signal generated to a collector forming a relay or a terminal.

27. A device for detecting and signaling the preparatory phase of birthing of an animal according to claim 26, characterized in that it comprises means for generating a second radiocommunication signal intended to alert the occurrence a difficult birth of said animal, configured so as to generate said second signal in the case where said processor calculates a decision criterion f _t greater than or equal to said predetermined threshold value S, said means for generating said second signal being able to be said means for generating said first signal, and in that said transmitting means are adapted to transmit said second generated signal to a relay collector or a terminal.