Device and method for in-ovo determination of the sex of a fertilised bird egg

Abstract

The invention relates to a device (12) for the in-ovo determination of the sex of a fertilised bird egg (10), having – a light source (14) for emitting excitation radiation for exciting fluorescence in a region (16) inside the bird egg (10), - a spectroscopic apparatus (18) for analysing, in a temporally and / or spectrally-resolved manner, fluorescent radiation emitted from the region (16) inside the bird egg (10), - an evaluation unit (20) for determining the sex from the data determined by means of the spectroscopic apparatus (18) and – a measuring head (22) for jointly transmitting the excitation radiation into the bird egg (10) and receiving the fluorescence radiation from the bird egg (10). According to the invention, the measuring head (22) has an optical fibre system (28) with a head end (30) for transmitting the excitation radiation and receiving the fluorescence radiation. The invention also relates to a corresponding measuring head (22) and a corresponding method for the in-ovo determination of the sex of a fertilised bird egg (10).

Description

Device and method for in-ovo determination of the sex of a fertilised bird egg Description The invention relates to a device for in-ovo determination of the sex of a fertilised bird egg, comprising (i) a light source for emitting excitation radiation for exciting fluores- cence in a region inside the bird egg (ii) a spectroscopic apparatus for analysing, in a temporally and / or spectrally-resolved manner, fluorescence radiation emitted from the region inside the bird egg, (iii) an evaluation unit for determining the sex from the data determined by means of the spectroscopic apparatus, and (iv) a measuring head for jointly transmitting the excitation radiation into the bird egg and receiving the fluores- cence radiation from the bird egg, preferably through a single hole in the eggshell of the bird egg. The invention further relates to a corresponding measuring head for a device for in- ovo determination of the sex of a fertilised bird egg, which is adapted for jointly emitting excitation radiation into the bird egg and receiving fluorescence radiation from the bird egg, preferably through a single hole in the eggshell of the bird egg. The invention further relates to a method for in-ovo determination of the sex of a ferti- lised bird egg, comprising the steps of (a) emitting excitation radiation for exciting flu- orescence in a region inside the bird egg by means of a light source (b) fluorescence analysis, in a temporally and / or spectrally-resolved manner, of fluorescence radiation emitted from the region inside the bird egg by means of a spectroscopic apparatus, and (c) determining the sex from the data obtained by means of the spectroscopic apparatus, wherein by means of a measuring head, preferably through a single hole in the eggshell of the bird egg, the excitation radiation is transmitted into the bird egg and jointly therewith the fluorescence radiation is received from the bird egg. Currently, there is an effort to be able to determine the sex of a chick already in the fertilised chicken egg. In the bird egg, different fluorophores, in particular hormones, develop during growth in male and female chicks. Due to their complex structure, the corresponding mole- cules have an unpredictable fluorescence capacity. In fluorescence electron transitions from the excited to the ground state are observed. This process is time-dependent. Document DE 10 2016 004 051 B3 describes a device and a method for optical in-ovo determination of the sex of a fertilised bird egg. The method comprises the steps of: (a) emitting excitation radiation for exciting fluorescence in a region inside the bird egg by means of a light source, (b) fluorescence analysis, in a temporally and / or spectrally- resolved manner, of fluorescence radiation emitted from the region inside the bird egg by means of a spectroscopic apparatus, and (c) determinating the sex from the data obtained by means of the spectroscopic apparatus. By means of a measuring head comprising a beam splitter and optics, the excitation radiation is emitted into the bird egg and jointly therewith the fluorescence radiation is received from the bird egg through a single hole in the eggshell of the bird egg. However, for the method described therein, the hole must be relatively large, resulting in the risk of germ contamination. It is therefore an object of the invention to provide a device and a method in which in- ovo determination of the sex can be carried out precisely and safely with a significantly lower risk of germ contamination. In the device according to the invention for in-ovo determination of the sex of a fertilised bird egg, comprising (i) a light source for emitting excitation radiation for exciting fluo- rescence in a region inside the bird egg, (ii) a spectroscopic apparatus for analysing, in a temporally and / or spectrally-resolved manner, of fluorescence radiation emitted from the region inside the bird egg, (iii) an evaluation unit for determining the sex the data determined by means of the spectroscopic apparatus, and (iv) a measuring head for jointly emitting the excitation radiation into the bird egg and receiving the flu- orescence radiation from the bird egg, preferably through a single hole in the eggshell of the bird egg, it is provided that the measuring head comprises a light guide system with a head end for emitting the excitation radiation and receiving the fluorescence radiation. In this way, the emission and reception of corresponding radiation can be realized via a very small hole. In particular, the aforementioned device can be used to receive the fluorescence radiation on the eggshell. The hole then preferably has a hole size with a dimension or diameter D in the range of <semantics>0.5 mm≤D≤3 mm<annotation encoding="application / x-tex">0.5 \text{ mm} \leq D \leq 3 \text{ mm}< / annotation>< / semantics>. According to a preferred embodiment of the invention, it is provided that the light guide system is a Y-shaped light guide system with two light guide strands, which are brought together on the side of the head end. Here, in particular, it is provided that the light guide strands are formed as light guide bundles whose individual light guides are intertwined on the side of the head end. This means in the sense of the present invention that the light guides are intertwined, for example twisted. Such an intertwining could also be called interlacing with each other, wherein no mandatory regularity is provided in this braiding. According to a further preferred embodiment of the invention, it is provided that the region inside the bird egg is a germinal disc region and / or a bloodstream region and / or a region of embryonic structures. Which of these regions is selected depends in par- ticular on the stage of development in the fertilised bird egg According to still another preferred embodiment of the invention, the spectroscopic apparatus is an apparatus for analysing fluorescence radiation in a temporally-resolved manner or for analysing fluorescence radiation in a temporally and spectrally-resolved manner. If the frequencies from which sex information can be obtained are known, an analysis in a spectrally-resolved manner is often no longer necessary. According to still another preferred embodiment of the invention, the light source is a pulsed laser light source. Preferably, it may be provided that the light source comprises a laser for generating laser pulses. Further preferably, it may be provided that a fre- quency multiplying device is connected downstream of the laser for generating laser pulses, for example a frequency doubler, frequency tripler or a frequency quadrupler device. According to still another preferred embodiment of the invention, the excitation radia- tion is a radiation having a wavelength in a range from greater than or equal to 100 nm to less than or equal to 380 nm, preferably greater than or equal to 200 nm to less than or equal to 280 nm, for example a wavelength of 266 nm. According to still another preferred embodiment of the invention, the excitation radia- tion is pulsed and has a pulse length in a range from greater than or equal to 0.1 ns to less than or equal to 1 µs, preferably greater than or equal to 1 to less than or equal to 200 ns, particularly preferably greater than or equal to 2 ns to less than or equal to 20 ns. According to still another preferred embodiment of the invention, the excitation radia- tion is pulsed and has a pulse length in the femtosecond or picosecond range. According to still another preferred embodiment of the invention, the spectroscopic apparatus comprises a spectrometer (a spectrograph), wherein the spectrometer is preferably arranged to receive fluorescence radiation having a wavelength in a range of greater than or equal to 200 nm to less than or equal to 600 nm. Preferably, it can be provided that the spectroscopic apparatus comprises a multichan- nel detector and a shutter connected between the spectrometer and the multichannel detector. It may further be preferred that the laser on the one hand and the multichan- nel detector and the shutter on the other hand are coupled via a Q-switch. According to a preferred embodiment of the invention, it is provided that the evaluation unit is an evaluation unit based on machine learning. Machine learning is (according to the current Wikipedia entry) a generic term for the "artificial" generation of knowledge from experience: an artificial system learns from examples and can generalize them after the learning phase is completed. To this end, algorithms of machine learning build a statistical model based on training data. According to another preferred embodiment of the invention, it is provided that the evaluation unit is an evaluation unit based on so-called feature engineering. Feature engineering is a form of data processing and describes the selection and preparation of features, which are used for creating a machine learning model. Preferably, it can be provided that the evaluation unit is configured to take into account the central moments of 2nd order (standard deviation) and 3rd order (skewness) during feature engineering. It may be provided that the evaluation unit is configured to form features from a data matrix. Here, the evaluation unit can be configured to form fea- tures both row-by-row and column-by-column. Preferably, it can be provided that the evaluation unit is configured for this purpose to eliminate features with weak separating properties, preferably with the aid of Fischer's linear discriminant analysis (LDA). Pref- erably, it can be provided that the evaluation unit is configured to determine the accu- racy of a classifier, wherein it can preferably be configured for the method of <semantics>5×2<annotation encoding="application / x-tex">5 \times 2< / annotation>< / semantics> Kross validation. In the measuring head according to the invention for a device for in-ovo determination of the sex of a fertilised bird egg, which is configured for jointly emitting excitation ra- diation into the bird egg and receiving fluorescence radiation from the bird egg, prefer- ably through a single hole in an eggshell of the bird egg, it is provided that the meas- uring head comprises a light guide system having a head end for emitting the excitation radiation and receiving the fluorescence radiation. The corresponding device for in-ovo determination of the sex of a fertilised bird egg is in particular a device mentioned above. In the method according to the invention for in-ovo sex determination of a fertilised bird egg, comprising the steps of (a) emitting excitation radiation for exciting fluorescence in a region inside the bird egg by means of a light source, (b) fluorescence analysis, in a temporally and / or spectrally-resolved manner, of fluo- rescence radiation emitted from the region inside the bird egg by means of a spectro- scopic apparatus, and (c) determining the sex from the data determined by means of the spectroscopic ap- paratus, wherein by means of a measuring head, preferably through a single hole in the eggshell of the bird egg, the excitation radiation emitted into the bird egg and jointly therewith the fluorescence radiation is received from the bird egg, it is provided that the measuring head comprises a light guide system and the emission of the excitation radiation into the bird egg and the reception of the fluorescence radiation from the bird egg are implemented via a head end of the light guide system which is moved close to the bird egg, preferably to the hole. Thus, according to a preferred embodiment of the method according to the invention, the excitation radiation is emitted into the bird egg and the fluorescence radiation is received from the bird egg through a single hole in the eggshell by means of the meas- uring head. The implementation of the method is usually preceded by a step of creating the hole in the eggshell. Here, in particular, it is intended that the hole is created without opening an egg skin underlying the eggshell. The fluorescence measurement can be carried out through this egg skin or egg skins. According to an alternative embodiment of the method according to the invention, it may be provided that by means of the measuring head the excitation radiation is emit- ted into the bird egg and the fluorescence radiation is received from the bird egg with- out the eggshell having a hole. The excitation radiation and the fluorescence radiation thus respectively penetrate the eggshell. Surprisingly, it has been found that the method described above nevertheless allows an in-ovo determination of the sex of a fertilised bird egg. According to a further alternative embodiment of the method according to the invention, it can be provided that the region inside the bird egg is removed from the egg and the method steps (a), (b) and (c) are carried out accordingly outside the egg. This alternative method according to the invention for in-ovo determination of the sex of a fertilised bird egg comprises the steps: Taking a sample from inside the bird egg, (a) emitting excitation radiation for exciting fluorescence in a region of the sample from the inside of the bird egg by means of a light source, (b) fluorescence analysis of fluorescence radiation emitted from the region of the sam- ple from inside the bird egg by means of a spectroscopic apparatus in a temporally and / or spectrally-resolved manner; and (c) determining the sex from the data obtained by means of the spectroscopic appa- ratus, wherein by means of a measuring head the excitation radiation is emitted into the sample from the inside the bird egg and jointly therewith the fluorescence radiation is received from the sample from the inside of the bird egg, wherein the measuring head comprises a light guide system and the emission of the excitation radiation into the sample from the inside of the bird egg and the reception of the fluorescence radia- tion from the sample from the inside of the bird egg are effected via a head end of the light guide system which is moved close to the sample. In the following, the invention is explained with reference to the accompanying draw- ings based on exemplary embodiments, wherein the features shown below may each individually or in combination represent an aspect of the invention. In the drawings: Fig. 1 is a structure with a bird egg and a device for in-ovo determination of the sex of said bird egg according to a preferred embodiment of the invention; Fig. 2 is a representation of the corresponding spectra representing values ajk of (aj1, ..., <semantics>ajn<annotation encoding="application / x-tex">a_{jn}< / annotation>< / semantics>) corresponding to the wavelength <semantics>λ=500.89<annotation encoding="application / x-tex">\lambda = 500.89< / annotation>< / semantics> nm for a male or female chicken egg; and Fig. 3 is the representation of a classifier (black line) for the first scenario and Experi- ment 2 (6-day, through the egg skin). Fig. 1 shows a schematic representation of a measurement setup with several bird eggs 10 and a device 12 for optical in-ovo determination of the sex of one of these bird eggs 10. The device 12 comprises a light source 14 for emitting excitation radiation in the form of light pulses for exciting fluorescence in a region 16 inside the bird egg 10, a spectroscopic apparatus 18 for analysing fluorescence radiation emitted from the region inside the bird egg 10 in a temporally and / or spectrally-resolved manner, a com- puter-based evaluation unit 20 for determining the sex from the data determined by the spectroscopic apparatus 18 and a measuring head 22 for jointly emitting the excitation radiation into the bird egg 10 and receiving the fluorescence radiation from the bird egg 10 through a single hole 24 in the eggshell 26 of the bird egg 10. The measuring head 22 comprises a light guide system 28 having a head end 30 for emitting the excitation radiation and receiving the fluorescence radiation. This head end 30 is also the head end of the measuring head 22 and is held against the hole 24 in the eggshell 26 for measuring. The light guide system 28 of the measuring head 22 is Y-shaped and comprises two light guide strands 32, 34, one light guide strand 32 for the excitation radiation and one light guide strand 34 for the fluorescence radiation. The two light guide strands 32, 34 are brought together on the side of the head end 30. The light guide strands 32, 34 are each formed as light guide bundles 36, 38 whose individual light guides (not shown in detail) are intertwined on the side of the head end 30. In the example shown, the light source 14 comprises a laser 40 for generating laser pulses and a frequency doubler device 42 connected downstream of the laser 40. Thus, the light source 14 is a pulsed laser light source. In the example shown, the spectroscopic apparatus 18 comprises a spectrometer (a spectrograph) 44, a multichannel detector 46 configured as an ICCD camera, and a shutter 48 interconnected between the spectrometer 44 and the multichannel detector 46. A coupling between the laser 40 on the one hand and the multichannel detector 46 and the shutter 48 on the other hand is implemented via a so-called Q-switch 50 and a pulse generator 52 on the detector side. A computer serves as the evaluation unit 20. In the example, the laser is an ND:YAG laser with a wavelength of 1064 nm. By means of frequency doubling, a wavelength of 266 nm is achieved for the excitation radiation. The laser-induced fluorescence signals are recorded by the multi-channel detector ICCD camera 46. The fiber bundle of the light guide system 28 not only guides the laser beam onto the sample, i.e. the inside of the bird egg 10, but also guides the generated fluorescence light to the detector 46. During the measurement, the complete spectrum is recorded at any time. This allows ZLIF measurements to be made directly on surfaces. The emission range is between 300 and 600 nm. The crucial region inside the bird egg 10 where fluorescence radiation is excited is a germinal disc region, a bloodstream region and / or an region of embryonic structures. An example of in-ovo determination of the sex of 3- to 6-day-old incubated chicken eggs by temporally-resolved fluorescence spectroscopy (ZLIF) by use of a device 12 is discussed below. In all examinations, the orientation of the region 16 of the embryonic structures (in short, of the embryo) to the measurement head 22 is crucial. The position of the em- bryo can be determined by candling. This example relates to the examinations of 3- or 6-day-old incubated eggs. By use of the measuring system, chicken eggs can be ex- amined in three ways: 1. measurement through the eggshell 26; 2. measurement without eggshell 26 through the intact egg skin; 3. measurement directly on the embryo. For the examinations of 3- or 6-day-old incubated eggs 10, the chicken eggs were aligned and then measured from above through the eggshell 26. In alternative two, the eggshell 26 was carefully removed so that a measurement could be made through the intact egg skin. In these two types of studies, the alignment of the embryo cannot be ensured without error. For this reason, in the third alternative, the egg skin was re- moved and a measurement was repeated directly on the embryo and on the blood veins. The ZLIF measurements can be taken as a function of equidistantly increasing times <semantics>τ1,…,τn<annotation encoding="application / x-tex">\tau_1, \ldots, \tau_n< / annotation>< / semantics> for a fixed n as series of values or equivalently as signal series or vectors a = <semantics>(a1,...,an)∈ℝn<annotation encoding="application / x-tex">(a_1, ..., a_n) \in \mathbb{R}^n< / annotation>< / semantics>. Since at each time <semantics>τj<annotation encoding="application / x-tex">\tau_j< / annotation>< / semantics>, <semantics>j=1,...,n<annotation encoding="application / x-tex">j = 1, ..., n< / annotation>< / semantics> the spectrum is recorded, it is possible to define the value series as (mathematical) matrices <semantics>A∈ℝm×n<annotation encoding="application / x-tex">A \in \mathbb{R}^{m \times n}< / annotation>< / semantics>: [Image disponible dans le document PDF, Image available in the PDF document] wherein the columns <semantics>(a1j,...,amj)T∈ℝmj<annotation encoding="application / x-tex">(a_{1j}, ..., a_{mj})^T \in \mathbb{R}^{mj}< / annotation>< / semantics> of A are the above spectra at time <semantics>τj<annotation encoding="application / x-tex">\tau_j< / annotation>< / semantics>. Thus, for each individual bird egg, the result of the ZLIF measurement corresponds to a ma- trix of associated measurement values. Depending on the type of the ZLIF measure- ment as well as the sex of 3- or 6-day-old incubated eggs, such matrices are assigned to one of the following classes: {Sex (m / f), Day (3 / 6), type (without eggshell., through int. egg skin, embryo)}. Here, for error-free assignment of the sexes, the samples were analysed from the em- bryo in the Gene Laboratory by quantitative real-time polymerase chain reaction (qPCR) and corresponding primer sets. Machine learning (ML) methods can be used to learn a system which allows a direct determination of sex from ZLIF measurements. These are the classical WIL methods as well as the own NIL relevant scientific publications of the inventors involved in this patent application. Classes of different sexes of yet same incubation periods and same types are of inter- est for learning the system. This is not a limitation, since usually both the incubation periods and the type of measurement are known. The reasoning leads to the binary classification problem for the two classes: <semantics>CX<annotation encoding="application / x-tex">C_X< / annotation>< / semantics> (for female) and <semantics>CY<annotation encoding="application / x-tex">C_Y< / annotation>< / semantics> (for male). For a set of chicken eggs of the same incubation periods, ZLIF measurements of the same type are carried out. Furthermore, the chicken eggs are assigned by qPCR to one of the classes <semantics>CX<annotation encoding="application / x-tex">C_X< / annotation>< / semantics> or <semantics>CY<annotation encoding="application / x-tex">C_Y< / annotation>< / semantics>. Thus we obtain objects with <semantics>AX∈CX<annotation encoding="application / x-tex">A_X \in C_X< / annotation>< / semantics> or <semantics>AY∈CY<annotation encoding="application / x-tex">A_Y \in C_Y< / annotation>< / semantics> with the structures corresponding to matrices A described above. For learning the system for direct sex determination, the following feature extraction from object A is carried out. Here, it is assumed that the values of individual rows of A, i.e., <semantics>(aj1,...,ajn)<annotation encoding="application / x-tex">(a_{j1}, ..., a_{jn})< / annotation>< / semantics>, <semantics>j=1,...,m<annotation encoding="application / x-tex">j = 1, ..., m< / annotation>< / semantics> are described by statistical distributions. Physically, the rows mean the temporally-resolved measurements for certain fixed wavelengths. Fig. 2 represents the example of a row <semantics>(aj1,...,ajn)<annotation encoding="application / x-tex">(a_{j1}, ..., a_{jn})< / annotation>< / semantics> for a fixed j corresponding to the wave- length = 500.89 nm for the measurement on a male (m) or female (w) chicken egg. It can be seen from the plot that by using different forms of the measurement series, the classification is possible in principle. Central moments of <semantics>aj:=(aj1,...,ajn),j=1,...,m<annotation encoding="application / x-tex">a_j := (a_{j1}, ..., a_{jn}), j = 1, ..., m< / annotation>< / semantics> describe statistical properties of <semantics>aj<annotation encoding="application / x-tex">a_j< / annotation>< / semantics>. The first three moments are mean value <semantics>μ<annotation encoding="application / x-tex">\mu< / annotation>< / semantics>, standard deviation <semantics>δ<annotation encoding="application / x-tex">\delta< / annotation>< / semantics> and skewness S: [Image disponible dans le document PDF, Image available in the PDF document] [Image disponible dans le document PDF, Image available in the PDF document] For each object, m features <semantics>(ai)<annotation encoding="application / x-tex">(a_i)< / annotation>< / semantics> and m features <semantics>S(ai)<annotation encoding="application / x-tex">S(a_i)< / annotation>< / semantics>, <semantics>j=1,...,m<annotation encoding="application / x-tex">j = 1, ..., m< / annotation>< / semantics> are extracted respec- tively. Thus, the feature vector <semantics>f∈ℝ2⋅m<annotation encoding="application / x-tex">f \in \mathbb{R}^{2 \cdot m}< / annotation>< / semantics> of each object is. [Image disponible dans le document PDF, Image available in the PDF document] To satisfy the accuracy of the classification of <semantics>CX<annotation encoding="application / x-tex">C_X< / annotation>< / semantics> and <semantics>CY<annotation encoding="application / x-tex">C_Y< / annotation>< / semantics> a feature selection is carried out. Here, by use of "Fisher's Linear Discriminant Analysis" (LDA), the features with weak separating properties are eliminated, since they contribute too little to the classi- fication and may worsen results. The features with strong separating properties are used to construct a classification hyperplane by use of LDA. Several datasets have been generated to train and validate the system for direct sex determination. For this purpose, a quantity <semantics>M1<annotation encoding="application / x-tex">M_1< / annotation>< / semantics> of <semantics>12+13<annotation encoding="application / x-tex">12 + 13< / annotation>< / semantics> chicken eggs were taken and measurements were carried out. In total there were about 30 chicken eggs, neverthe- less the sex by means of qPCR could not be determined for all of them. At a later time, the next ZLIF measurement took place on another quantity <semantics>M2<annotation encoding="application / x-tex">M_2< / annotation>< / semantics> of 15 + 10 chicken eggs. Here there were initially 40 chicken eggs, but as in the first test, the sex could not be determined for all. These two tests should show that the described method is suitable for direct sex determination. At least two measurements are necessary to validate the results. In the first test with the quantity <semantics>M1<annotation encoding="application / x-tex">M_1< / annotation>< / semantics>, 12 chicken eggs (6m + 6w, 3-day-old embryos) as well as 13 chicken eggs (6m + 7w, 6-day-old first without eggshell through the intact egg skin, then at embryos) were measured with ZLIF. In the second test with the quan- tity <semantics>M2<annotation encoding="application / x-tex">M_2< / annotation>< / semantics> 15 chicken eggs (3m + 12w, 3-day-old embryos) as well as 18 chicken eggs (14m + 4w, 6-day-old first without eggshell through the intact egg skin, then on em- bryos) were measured. On each chicken egg the ZLIF measurements have been re- peated 15 times. Thus, each chicken egg provides 15 objects for one of the classes. Table 1 summarizes the two tests with three experiments each. [Image disponible dans le document PDF, Image available in the PDF document] Table 1: Two tests with three experiments each for learning and validating the sys- tem. The term #obj. means number of objects. For the selected temporal resolution, n is 20, the spectrum is equidistantly recorded starting with <semantics>λ≈200,08<annotation encoding="application / x-tex">\lambda \approx 200,08< / annotation>< / semantics> nm to <semantics>λ=596,75<annotation encoding="application / x-tex">\lambda = 596,75< / annotation>< / semantics> nm and m = 1024. The feature vectors of each object thus correspond to: [Image disponible dans le document PDF, Image available in the PDF document] and have the lengths <semantics>2⋅m=2048<annotation encoding="application / x-tex">2 \cdot m = 2048< / annotation>< / semantics>. Two scenarios have been tested for learning and validating the system. In the first case, the classes Cx and Cy consist of the objects from both tests M1 and M2 and for teaching and testing the system, no distinction is made between tests. Thus, in CY in experiment 1 there are 135 objects, in experiment 2 there are 300 and in experiment 3 there are also 300 objects. In <semantics>CX<annotation encoding="application / x-tex">C_X< / annotation>< / semantics> in experiment 1 there are 270 objects, in experiment 2 there are 165 and in experiment 3 there are 165 objects. Then, the classes Cx and Cy have each been randomly subdivided into training objects and test objects. The classifier is designed for the training objects and the accuracy of the classifier is tested on the test objects. The <semantics>5×2<annotation encoding="application / x-tex">5 \times 2< / annotation>< / semantics> cross-validation method is used to determine the accuracy of the classifier. This is an established method for determining the accuracy of a classifier. The idea of the <semantics>5×2<annotation encoding="application / x-tex">5 \times 2< / annotation>< / semantics> cross-validation is to take an equal number of training objects and test objects, so that one can switch the training set to the test set and vice versa. The results of the 5 x 2 cross-validation provide a reliable mean value for the accuracy. Table 2 lists the results. [Image disponible dans le document PDF, Image available in the PDF document] Table 2: Results of <semantics>5×2<annotation encoding="application / x-tex">5 \times 2< / annotation>< / semantics> cross-validation for objects of both tests Fig. 3 shows the representation of a corresponding classifier (black line) for the first scenario and experiment 2 (6-day-old, through egg skin). In the second scenario, the tests distinguish between teaching and testing. In the sec- ond test, there are more objects than in the first. It is expected here that the more objects are used for training, the more stable the system is. For this reason, the clas- sifier is trained on the objects from experiment 2. and tested on the objects from ex- periment 1. The results can be found in Table 3 below. [Image disponible dans le document PDF, Image available in the PDF document] 1 1 ı Table 2: Results for accuracy during training on objects from M2 and testing on M1. Conclusion: The experiments carried out show that a direct sex determination is pos- sible in incubated chicken eggs using ZLIF. The incubation periods are between 3 and 6 days. A reliable accuracy between 76.67% and 92.27% can be achieved. This method has a great potential to improve the accuracy. The potentials are based on the optimization of the ZLIF experiment as well as on the optimization of the feature ex- traction, feature selection and the design of the classifier. Reference symbols 10 bird egg 12 device for in-ovo determination of sex 5 14 light source 16 region (inside bird egg) 18 spectroscopic apparatus 20 evaluation unit 22 measuring head 10 24 hole (in eggshell) 26 eggshell 28 light guide system 30 head end 32 light guide strand 15 34 light guide strand 36 light guide bundle 38 light guide bundle 40 laser 42 frequency doubler device 20 44 spectrometer 46 multichannel detector 48 shutter 50 Q-Switch 52 pulse generator 25

Claims

<pat:ClaimStatement>Claims< / pat:ClaimStatement> <pat:Claims com:id="claims"> <pat:Claim com:id="CLM-00001"> <pat:ClaimNumber>1< / pat:ClaimNumber> <pat:ClaimText>1. A device for in-ovo determination of the sex of a fertilised bird egg, the device comprising: a light source for emitting excitation radiation for exciting fluorescence in a region inside the bird egg; a spectroscopic apparatus for analysing fluorescence radiation emitted from the region inside of the bird egg in a temporally or spectral-resolved or temporally and spectrally-resolved manner to generate data; an evaluation unit for determining the sex from the data determined by means of the spectroscopic apparatus; and a measuring head for jointly emitting the excitation radiation into the bird egg and receiving the fluorescence radiation from the bird egg; characterized in that the spectroscopic apparatus is a device for analysing fluorescence radi- ation in a temporally-resolved or temporally and spectrally-resolved manner; the measuring head comprises a light guide system with a head end for emitting the excitation radiation and receiving the fluorescence radiation; and the light guide system is a Y-shaped light guide system having two light guide strands which are brought together on the side of the head end. < / pat:ClaimText> < / pat:Claim> <pat:Claim com:id="CLM-00002"> <pat:ClaimNumber>2< / pat:ClaimNumber> <pat:ClaimText>2. The device according to claim 1, characterized in that the light guide strands are formed as light guide bundles, the individual light guides of which are intertwined at the side of the head end. < / pat:ClaimText> < / pat:Claim> <pat:Claim com:id="CLM-00003"> <pat:ClaimNumber>3< / pat:ClaimNumber> <pat:ClaimText>3. The device according to any one of claims 1 or 2, characterized in that the eval- uation unit is an evaluation unit based on machine learning. < / pat:ClaimText> < / pat:Claim> <pat:Claim com:id="CLM-00004"> <pat:ClaimNumber>4< / pat:ClaimNumber> <pat:ClaimText>4. The device according to any one of claims 1 to 3, characterized in that the eval- uation unit is an evaluation unit based on feature engineering. < / pat:ClaimText> < / pat:Claim> <pat:Claim com:id="CLM-00005"> <pat:ClaimNumber>5< / pat:ClaimNumber> <pat:ClaimText>5. A method for in-ovo determination of the sex of a fertilised bird egg, the method comprising the steps of: emitting excitation radiation for exciting fluorescence in a region inside the bird egg by means of a light source; analysing fluorescence radiation emitted from the region inside the bird egg by means of a spectroscopic apparatus in a temporally or spectrally-re- solved or temporally and spectrally-resolved manner to generate data; and determining the sex from the data obtained by the spectroscopic appa- ratus, wherein by means of a measuring head the excitation radiation is emitted into the bird egg and jointly therewith the fluorescence radiation is received from the bird egg, characterized in that the spectroscopic apparatus is a device for analysing fluorescence radi- ation in a temporally-resolved or temporally and spectrally-resolved manner; the measuring head comprises a light guide system and the emission of the excitation radiation into the bird egg and the reception of the fluorescence radiation from the bird egg is effected via a head end of the light guide system which is brought close to the bird egg; and the light guide system is a Y-shaped light guide system having two light guide strands which are brought together on the side of the head end. < / pat:ClaimText> < / pat:Claim> <pat:Claim com:id="CLM-00006"> <pat:ClaimNumber>6< / pat:ClaimNumber> <pat:ClaimText>6. The method according to claim 5, characterized in that by means of the meas- uring head the excitation radiation is emitted into the bird egg and jointly there- with the fluorescence radiation is received from the bird egg through a single hole in the eggshell of the bird egg. < / pat:ClaimText> < / pat:Claim> <pat:Claim com:id="CLM-00007"> <pat:ClaimNumber>7< / pat:ClaimNumber> <pat:ClaimText>7. The method according to claim 6, further comprising, prior to emitting the exci- tation radiation into the bird egg: forming the hole in the eggshell without opening an egg skin underlying the eggshell. < / pat:ClaimText> < / pat:Claim> <pat:Claim com:id="CLM-00008"> <pat:ClaimNumber>8< / pat:ClaimNumber> <pat:ClaimText>8. The method according to any one of claims 5 to 7, characterized in that the region inside the bird egg is at least one of a germinal disc region, a bloodstream region, and a region of embryonic structures. < / pat:ClaimText> < / pat:Claim> < / pat:Claims>