Biological testing equipment and trained models

Abstract

To improve inspection efficiency and versatility by enabling non-destructive inspection of a living body of an object to be inspected.SOLUTION: An inspection device of a living body includes: a calculation model storage unit and a determination unit. The calculation model storage unit stores a calculation model that is constructed based on a quadratic differential spectrum in absorbance about a wavelength of a near infrared region of diffuse reflected light or diffuse transmitted light obtained by irradiating a sample living body infected with a parasite and a sample living body not infected with a parasite with light of a near infrared region, and performs calculation related to presence or absence of infection with a parasite of a living body and / or a numerical damage level from no onset to maximum onset due to infection. The determination unit determines presence or absence of infection and / or a degree of damage by calculation results calculated from absorbance of light received by a light receiving unit and the calculation model stored in the calculation model storage unit.SELECTED DRAWING: Figure 9

Description

[Technical Field]

[0001] The present invention relates to a living body inspection device that inspects living bodies, such as plants and animals, for infection with parasites, and a trained model that can be used in this device. [Background technology]

[0002] Generally, living organisms such as edible plants, ornamental plants, or edible animals (fish and meat) can become infected with parasites and become unusable, so they are tested for parasitic infection. For example, in the case of nematodes as parasites, the following example of a living organism, garlic, can be used as a testing device.

[0003] In recent years, garlic has become infected with the parasitic nematode, C. difficile, and various countermeasures have been implemented. In this regard, it is essential to first test harvested garlic for C. difficile infection. Conventional methods for testing for C. difficile are described, for example, in Patent Document 1 (JP 2017-219423 A). This method involves crushing C. difficile nematodes, centrifuging the resulting body fluid, injecting the resulting fluid into a rabbit for immunization to obtain antiserum, and then removing reactants that exhibit nonspecific reactions from the antibody serum to obtain anti-nematode serum. Then, garlic samples are crushed and contacted with the anti-nematode serum to induce an antigen-antibody reaction. The antibodies in the anti-nematode serum are then labeled. If a reaction complex is formed, it is detected. Labeling methods using enzymes, fluorescent substances, or other conventional methods are used to detect the reaction complex.

[0004] In addition, as a method for extracting nematodes, for example, the Berman method is known, in which infected garlic clove whose surface has been sterilized is finely chopped and treated with chemicals on a funnel to obtain a nematode suspension (see Patent Document 1 (JP 2017-219423 A) and Patent Document 2 (JP 2010-100568 A) mentioned above). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 2017-219423 [Patent Document 2] Japanese Patent Application Laid-Open No. 2010-100568 Summary of the Invention [Problem to be solved by the invention]

[0006] However, in this conventional method of inspecting living organisms, the living organisms must be crushed one by one and treated with anti-nematode serum or the required chemicals, which is time-consuming and makes the inspection process extremely complicated. In addition, since the living organisms are destroyed, there is a problem that it cannot be used for products such as garlic, which are shipped in cloves, because it is not possible to inspect every product.

[0007] The present invention has been made in consideration of these problems, and aims to provide a living organism inspection device and a trained model that are capable of non-destructively inspecting living organisms, even those infected with parasites, thereby improving inspection efficiency and versatility. [Means for solving the problem]

[0008] In order to achieve the above object, the living body inspection device of the present invention is a living body inspection device for inspecting a living body as a test subject for infection with a parasite, the living body inspection device comprising: a light source unit that irradiates the test subject with light in the near-infrared region; a light receiving unit that receives diffuse reflected light or diffuse transmitted light from the test subject; and a control unit that determines whether the test subject is infected with a parasite based on the absorbance of the light received by the light receiving unit, The control unit is a calculation model storage unit that stores a calculation model that is constructed in advance based on the second derivative spectrum of absorbance at wavelengths in the near-infrared region of diffuse reflected light or diffuse transmitted light obtained from a sample organism infected with a parasite and a sample organism not infected with a parasite by irradiating the sample organism with light in the near-infrared region, and performs calculations related to the presence or absence of infection of the organism with a parasite and / or the degree of damage quantified as a predetermined maximum level of onset from no onset to onset due to infection; The device is configured to include a discrimination unit that determines the presence or absence of infection and / or the degree of damage based on the calculation results calculated from the absorbance of light received by the light receiving unit and the calculation model stored in the calculation model storage unit.

[0009] Here, the living organism may be a plant or animal infected with a parasite, whether living or dead. Examples include edible or ornamental plants such as vegetables and fruits, fish, and meat. Examples of parasites include protozoa, sarcoflagellates, sporozoa, ciliates, helminths, nematodes, cestodes, trematodes, and thorny heads.

[0010] In addition, infection refers to the state in which a parasite has infested the body, and onset refers to the appearance of some symptoms due to the parasite's infestation, such as changes in the body's tissues and the appearance of lesions in the body. The degree of damage can be determined not only on the surface but also when there is internal disease. Since it can distinguish not only on the surface but also internal disease, it can grasp even the very early stages of disease and is more suitable for diagnosing early stages of disease than visual examination.

[0011] As a result, this testing device irradiates a living organism to be tested with near-infrared light from the light source unit, receives diffusely reflected or transmitted light from the living organism to be tested with the light receiving unit, and determines the presence or absence of parasitic infection and / or the extent of parasitic damage in the living organism based on the calculation results calculated by the control unit using the absorbance of the received light and the calculation model. This allows for non-destructive testing of the living organism to improve testing efficiency and versatility. Furthermore, the use of the calculation model allows for reliable determination of the presence or absence of parasitic infection in the living organism and the extent of parasitic damage even when parasites have invaded the body or the infection is minimal, thereby improving testing accuracy. Furthermore, determining the extent of parasitic damage allows for easy quality assessment of the living organism. Furthermore, the degree of damage is a quantified value of the extent of the disease, allowing for reliable understanding of the extent of the disease. This allows for quality classification of living organisms, further improving versatility.

[0012] If necessary, the damage level can also be used to rank non-infected test subjects. This makes it possible to determine whether a subject is infected or not by determining the damage level, which is extremely efficient.

[0013] In this case, it is effective to determine the degree of damage based on the degree of discoloration that appears on the test subject. Although it depends on the parasite, the living body is suitable for those in which lesions appear on the surface of the living body when the disease develops due to infection with the parasite.

[0014] In this configuration, the damage level can be configured as an index in which 0 indicates no onset and 100 indicates the maximum onset. Furthermore, in this configuration, the damage level can be configured as a class in which no onset is 0 and the onset side increases in order for each predetermined index range when the degree of onset is expressed as an index with 0 being no onset and the maximum onset being 100. When configured as a class, it is easy to sort the quality of living organisms, and versatility can be further improved.

[0015] Furthermore, if necessary, the control unit may be configured to include a classification means for classifying test subjects according to the presence or absence of infection and / or according to the degree of damage based on the discrimination result of the discrimination unit. When classifying test subjects according to the presence or absence of infection, test subjects can be divided into two groups: those with and without infection, i.e., good and bad test subjects can be automatically sorted, which is extremely convenient. When classifying test subjects according to the degree of damage, test subjects can be automatically classified in stages, which is extremely convenient.

[0016] and, as necessary, the computational model is an analytical model constructed using statistical analysis or a trained model constructed using machine learning; The statistical analysis is selected from discriminant analysis, multiple regression analysis, PLS regression analysis, logistic regression analysis, and support vector machine (SVM), The above machine learning is configured to be selected from tree analysis such as decision trees (CART), regression trees, random forests, and gradient boosting trees; neural networks or deep learning (DNN) such as perceptrons, convolutional neural networks (CNN), recurrent neural networks (RNN), and residual networks (ResNet); and ensemble analysis consisting of a combination of these.

[0017] The computational model consists of an analytical model constructed using statistical analysis or a trained model constructed using machine learning, which can improve testing accuracy. In particular, when deep learning (DNN) is used, testing accuracy can be significantly improved. The wavelengths used in the computational model can be selected and combined from statistically significant wavelengths in the near-infrared region ranging from 700 nm to 2500 nm. This makes it possible to accurately determine whether a living organism is infected with a parasite and the degree of disease caused by this infection.

[0018] In addition, if necessary, The control unitThe above-mentioned calculation model is provided with a plurality of different types of calculation models, and a judgment unit is provided to judge whether or not to accept the judgment results of each calculation model. This makes it possible to obtain optimal results from the plurality of calculation models, thereby improving inspection accuracy.

[0019] In this case, when a plurality of different types of computational models for determining the presence or absence of infection are used as the computational model, the determination unit is effectively configured to prioritize any one of the discrimination results obtained using the computational models when the discrimination result indicates the presence of infection, thereby enabling accurate determination of whether a living organism is infected with a parasite.

[0020] Alternatively, when three or more different types of computational models for determining the presence or absence of infection are used as the computational model, it is effective that the judgment unit is configured to determine the infection presence or absence determination results of each computational model by majority vote, which also makes it possible to accurately determine whether a living body is infected with a parasite.

[0021] The parasites are nematodes (roundworms) that infect living plants. The living plants may be any plants that can be infected by nematodes, such as garlic, potato, sweet potato, or iris. Examples of nematodes include potato root-knot nematodes, root-knot nematodes (sweet potato root-knot nematode, Java root-knot nematode, arenaria root-knot nematode, northern root-knot nematode), root-knot nematodes (southern root-knot nematode, channel root-knot nematode, northern root-knot nematode, walnut root-knot nematode), peel nematodes (leaf nematode, peel nematode), stalk nematode, fire nematode, cyst nematode, spiral nematode, spine nematode, pin nematode, ring nematode, and soybean nematode.

[0022] In this case, the living organism is selected from garlic, potato, sweet potato, and iris, and the parasite is a potato-lesion nematode.

[0023] In this case, the test object is composed of garlic bulbs, which are collections of garlic cloves. Since each garlic bulb is inspected, the inspection efficiency is high. Furthermore, since garlic is mainly shipped in the form of garlic bulbs, the inspection efficiency is also high in this respect.

[0024] If the test subject is a garlic bulb with clusters of scales, the damage level is determined based on the degree of discoloration that appears on the test subject, as necessary, and is calculated using the following damage level index, with 0 representing no onset and 100 representing the maximum onset of onset.

[0025] Damage index = ((number of scales at t=1) + (number of scales at t=2 x 2) + (number of scales at t=3 x 3) + (number of scales at t=4 x 4)) / (total number of scales surveyed x 4) x 100 where: t is a number corresponding to the size of the discolored area caused by parasitic infection per garlic bulb, and is set so that the larger the value, the larger the size of the discolored area, and is set to four categories: t=1, t=2, t=3, and t=4.

[0026] Furthermore, if the test subject is a garlic bulb with clusters of scales, the degree of damage is determined, if necessary, based on the degree of discoloration that appears on the test subject, and the degree of onset is expressed as an index with no onset being 0 and the maximum with onset being 100, and is expressed as the following degree of onset, with no onset being 0 and the side with onset being composed of classes that increase in order for each specified index range.

[0027] Severity of onset (index) = ((number of scales at t=1) + (number of scales at t=2 x 2) + (number of scales at t=3 x 3) + (number of scales at t=4 x 4)) / (total number of scales surveyed x 4) x 100 where: t is a number corresponding to the size of the discolored area caused by parasitic infection per garlic bulb, and is set so that the larger the value, the larger the size of the discolored area, and is set to four categories: t=1, t=2, t=3, and t=4.

[0028] and a receiving unit that is moved by the robot after the inspection by the inspection unit and receives the object to be inspected and that receives the object to be inspected and that receives the object to be inspected and that receives the object to be inspected and that receives the object to be inspected and that receives the object to be inspected and that receives the object to be inspected and that receives the object to be inspected and that receives the object to be inspected and that receives the object to be inspected and that receives the object to be inspected and that receives the object to be inspected and that receives the object to be inspected and that receives the object to be inspected and that is

[0029] Furthermore, if necessary, an inspection section having the light source section and light receiving section and for inspecting the test object is provided, and the inspection section is configured to include an inspection unit having a detection section with the light source section and light receiving section exposed on one end surface, and the inspection unit is configured to be provided with a dustproof mechanism that sprays air along the detection section to form an air curtain that covers the detection section. Since the light source section and light receiving section of the detection section can be kept clean at all times, inspection can be performed reliably and maintenance can be made easier.

[0030] In order to achieve the object of the present invention, the trained model of the present invention is a trained model for causing a computer to function to output a calculation result relating to the presence or absence of infection of a living organism with a parasite, The absorbance of the sample organism is measured in advance, and the presence or absence of parasites in the organism is confirmed. Gobetsu The presence or absence of the parasites was used as an indicator to identify the parasite-free sample organisms. Using the second derivative spectrum of absorbance Absorbance data and parasite-infected sample organisms Using the second derivative spectrum of absorbanceThe absorbance data is correlated with the presence or absence of parasites, and this correlated data is used as training data. The system is trained using this training data. Near-infrared light is irradiated onto a living subject, and diffuse reflected light or diffuse transmitted light from the living subject is received. The absorbance of the received light is measured. Using the second derivative spectrum of absorbance The computer is configured to function so as to output a quantified value indicating whether or not a living body is infected with a parasite from the absorbance data.

[0031] Another trained model of the present invention is a trained model for causing a computer to function to output a calculation result relating to the degree of damage, which is a numerical value representing the degree of onset, from a predetermined level of no onset to a maximum level of onset, due to infection of a living organism with a parasite, The absorbance of the sample organism is measured in advance, and the degree of damage caused by the infection of the organism's parasites is determined. Gobetsu The damage level of the certified organism is used as an index to measure the damage level of the sample organism that has not developed the disease. Using the second derivative spectrum of absorbance Absorbance data and the affected sample organisms Using the second derivative spectrum of absorbance The absorbance data is associated with the degree of damage to the living body, and this associated data is used as training data. The training data is used for learning. Near-infrared light is irradiated onto the living body to be examined, and diffuse reflected light or diffuse transmitted light from the living body to be examined is received. The absorbance of the received light is measured. Using the second derivative spectrum of absorbance The computer is configured to function so as to output a value that quantifies the degree of damage caused by the onset of disease due to parasitic infection in a living organism from the absorbance data, which also achieves the same functions and effects as those described above. [Effects of the Invention]

[0032] According to the present invention, near-infrared light is irradiated onto a living organism to be examined, diffusely reflected or transmitted light from the living organism is received, the absorbance of the received light is measured, and the results of calculations based on the absorbance and a computational model are used to determine the presence or absence of parasitic infection and / or the extent of parasitic damage in the living organism. This allows for non-destructive testing of the living organism, improving testing efficiency and versatility. Furthermore, the use of a computational model allows for reliable determination of the presence or absence of parasitic infection in a living organism and determination of the extent of parasitic damage, even when parasites have invaded the organism or the infection is minimal, thereby improving testing accuracy. Furthermore, determining the extent of parasitic damage allows for easy quality assessment of the living organism. Furthermore, the degree of damage is a quantified value of the extent of the onset, allowing for reliable understanding of the extent of the onset. This allows for the quality of living organisms to be classified, further improving versatility. [Brief explanation of the drawings]

[0033] [Figure 1] 1 is a perspective view showing a living body testing device according to an embodiment of the present invention; [Figure 2] 1 is a diagram showing garlic as a living organism to be examined by a living organism examination device according to an embodiment of the present invention, together with a holder. [Figure 3] 1 is a front view showing a living body testing device according to an embodiment of the present invention; [Figure 4] 1 is a plan view showing a living body testing device according to an embodiment of the present invention; [Figure 5] 1 is a side view showing a living body testing device according to an embodiment of the present invention; [Figure 6] 1A and 1B are diagrams showing the relationship between a gripping hand of a robot and an inspection unit, together with the operation process of the gripping hand, in a living body inspection device according to an embodiment of the present invention. [Figure 7] 1A and 1B show an examination unit in a living body examination device according to an embodiment of the present invention, in which FIG. 1A is a perspective view of the examination unit, and FIG. 1B is a view showing an examination section of the examination unit. [Figure 8]1 is a cross-sectional view showing a state in which a testing unit is testing garlic as a living organism in a living organism testing device according to an embodiment of the present invention. [Figure 9] 2 is a block diagram showing the configuration of a control unit in the biological testing device according to the embodiment of the present invention. FIG. [Figure 10] FIG. 10 is a diagram schematically illustrating a trained model according to an embodiment of the present invention used by a control unit in a biological testing device according to an embodiment of the present invention. [Figure 11] 4 is a flowchart showing a control flow in a control unit of a living body testing device according to an embodiment of the present invention. [Figure 12] 4 is a flowchart showing a control flow in a control unit of a living body testing device according to an embodiment of the present invention, illustrating a control flow of a sample measurement and discrimination routine. [Figure 13] 4 is a flowchart showing a control flow of a parasite discrimination routine, which is a control flow of a control unit of a living body inspection device according to an embodiment of the present invention. [Figure 14] FIG. 1( a ) is a graph showing the correlation between actual measured values ​​and estimated values, and FIG. 1( b ) is a table showing the underlying numerical values, relating to the calculation model (multiple regression analysis (determining the presence or absence of infection)) of Example 1 of the present invention. [Figure 15] FIG. 1 shows a verification example of the calculation model (multiple regression analysis (determining whether or not there is infection)) of Example 1 of the present invention, where (a) is a graph showing the correlation between actual measured values ​​and estimated values, and (b) is a table showing the underlying numerical values. [Figure 16] FIG. 10( a ) is a graph showing the correlation between actual measured values ​​and estimated values, and FIG. 10( b ) is a graph showing the verification results, relating to the calculation model (multiple regression analysis (damage level (index) determination)) of Example 2 of the present invention. [Figure 17] FIG. 10(a) is a table showing the correlation between actual measured values ​​and estimated values, and FIG. 10(b) is a table showing the verification results of the calculation model (logistic regression model (infection determination)) of Example 3 of the present invention. [Figure 18]FIG. 10(a) is a table showing the correlation between actual measured values ​​and estimated values, and FIG. 10(b) is a table showing the verification results of the calculation model (logistic regression model (damage level (6 levels) discrimination)) of Example 4 of the present invention. [Figure 19] FIG. 10A is a table showing the correlation between actual measured values ​​and estimated values, and FIG. 10B is a graph showing the distribution of estimated probabilities for the computational model (AI-trained model A (infection determination)) of Example 5 of the present invention. [Figure 20] This is a table showing the verification results of the computational model (AI trained model A (determining whether or not there is infection)) of Example 5 of the present invention. [Figure 21] 10A is a table showing the correlation between actual measured values ​​and estimated values, and FIG. 10B is a table showing the verification results of the calculation model (AI-trained model B (damage level (6 levels) discrimination)) of Example 6 of the present invention. [Figure 22] FIG. 10(a) is a graph showing the correlation between actual measured values ​​and estimated values, and FIG. 10(b) is a graph showing the verification results of the calculation model (AI-trained model C (damage level (index) determination)) of Example 7 of the present invention. [Figure 23] 10A is a table showing the correlation between actual measured values ​​and estimated values, and FIG. 10B is a table showing the verification results of the computational model (AI-trained model D (infection determination)) of Example 8 of the present invention. [Figure 24] 9A is a table showing the correlation between actual measured values ​​and estimated values, and FIG. 9B is a table showing the verification results of the calculation model (AI-trained model E (damage level (6 levels) discrimination)) of Example 9 of the present invention. [Figure 25] FIG. 10 is a graph showing the correlation between actual measured values ​​and estimated values ​​for the calculation model (AI-trained model F (damage level (index) discrimination)) of Example 10 of the present invention, and FIG. 11 is a graph showing the verification results. [Figure 26] This is a table showing the correlation between actual measured values ​​and estimated values ​​for the computational model (AI-trained model G (infection determination)) of Example 11 of the present invention, and (a) is a table showing the verification results. [Figure 27](a) is a table showing the correlation between actual measured values ​​and estimated values, and (b) is a table showing the verification results of the calculation model (AI-trained model H (damage level (6 levels) discrimination)) of Example 12 of the present invention. [Figure 28] FIG. 13 is a graph showing the correlation between actual measured values ​​and estimated values ​​for the calculation model (AI-trained model I (damage level (index) determination)) of Example 13 of the present invention, and FIG. 14 is a graph showing the verification results. DETAILED DESCRIPTION OF THE INVENTION

[0034] A living organism inspection device according to an embodiment of the present invention will be described below with reference to the accompanying drawings. As shown in FIGS. 1 to 9, the living organism inspection device S according to an embodiment of the present invention inspects a living organism, which is a test subject W, for parasite infection. As shown in FIG. 2, the living organism is a harvested garlic plant, and the parasite is a potato lesion nematode. The test subject W is composed of a garlic bulb with a collection of scales Wa. The garlic bulb (test subject W) has a flower diameter Wb protruding several centimeters above, a disk stalk Wc below, is covered with an exoskeleton, and is washed and dried. Infection by the parasite begins on the disk stalk Wc side. F indicates a parasitic lesion (shown by a dotted line). Generally, the lesion F is hidden by the exoskeleton and is difficult to see. In severe cases, the lesion extends to the exoskeleton and becomes prominent on the surface.

[0035] The biological testing device S according to the embodiment includes a base 1, a transport unit 2 mounted on the base 1 and transporting test subjects W one by one at a predetermined interval, a robot 10 mounted near the base 1, a gripping hand 12 mounted at the tip of the robot arm 11 of the robot 10 for gripping the test subject W during transport by the transport unit 2 and positioning the test subject W at the testing position Y, an testing unit 30 mounted at the tip of the robot arm 11 of the robot 10 near the gripping hand 12 for testing the test subject W positioned at the testing position Y by the gripping hand 12, a receiving unit 50 moved by the robot 10 after the testing by the testing unit 30 and receiving the test subject W gripped by the gripping hand 12, and a control unit 60 for implementing testing functions and controlling the transport unit 2, the robot 10, and the testing unit 30. Reference numeral 70 in the figure denotes a display unit such as a CRT.

[0036] In the robot 10, as shown in FIG. 6, the gripping hand 12 is attached to the tip of the robot arm 11 via an opening / closing actuator 13 that opens and closes the gripping hand 12, which is capable of swinging. By swinging the opening / closing actuator 13, the gripping hand 12 can move to two positions: a gripping position X where the object W to be inspected on the transport section 2 can be grasped, and an inspection position Y where inspection is performed in the inspection section 30.

[0037] The conveying unit 2 includes an endless belt conveyor 3 driven by a motor (not shown) and a plurality of holders 20 arranged at predetermined intervals along the direction of movement of the belt conveyor 3 to hold the test subject W. As shown in FIG. 2, the holders 20 support and hold the garlic bulbs of the test subject W with their stalks Wc facing up. The holders 20 include a cup-shaped holder body 23 having a cylindrical side wall 21 and an upper wall 22, the lower surface of which is fixed to the surface of the belt conveyor 3; an insertion hole 24 formed in the upper wall 22 of the holder body 23 and centered on the axis of the holder body 23, through which the garlic bulb with a flower diameter Wb is inserted; and a conical support recess 25 formed over the entire or upper side of the insertion hole 24 (the entire insertion hole 24 in this embodiment) that supports the periphery of the flower diameter Wb side of the garlic bulb. This allows the stalk Wc side of the garlic bulb of the test subject W held by the gripping hand 12 to face the inspection unit 30.

[0038] The base 1 is provided with a position detection sensor (not shown) that detects when the test object W, transported by the belt conveyor 3 of the transport unit 2, is positioned at a predetermined position where it can be grasped by the gripping hand 12 of the robot 10, and based on the detection of this position detection sensor, the test object W is grasped and removed by the gripping hand 12 of the robot 10. A camera 26 is provided above the belt conveyor 3 of the transport unit 2 to capture an image of the test object W being transported. The image captured by the camera 26 makes it possible to determine the size of the test object W.

[0039] 6 to 8, the inspection section 30 is configured to include a cylindrical inspection unit 31, a support rod 32 that supports the inspection unit 31 at the tip of the robot arm 11 near the gripping hand 12, and a cover 33 that is provided on the tip side of the inspection unit 31 and covers the inspection object W positioned at the inspection position Y. Because the inspection section 30 and the gripping hand 12 are provided on the robot arm 11, the inspection object W can be inspected while being transported, and subsequent sorting work can be performed extremely efficiently.

[0040] As shown in FIGS. 7 and 8 , the inspection unit 31 includes a cylindrical unit main body 34, a light source unit 35 formed from the tips of multiple optical fibers and irradiating light in the near-infrared region onto the test object W, and a detection unit 37 including a light receiving unit 36 ​​formed from the tips of optical fibers and receiving diffusely reflected light or diffusely transmitted light from the test object W. The optical fibers are collected and held in a cylindrical solid holder 38, and an end face of each optical fiber is exposed at one end face of the holder 38 facing the test object W, and this end face serves as the detection unit 37. The holder 38 is held in the solid cylindrical unit main body 34 coaxially with the axis of the holder 38. The detection unit 37, which is one end face of the holder 38, is positioned rearward of the end face of the unit main body 34 facing the test object W, and a recess 39 is formed in front of the detection unit 37.

[0041] The inspection unit 31 also includes a dustproof mechanism 40 that protects the detection unit 37 from dust. The dustproof mechanism 40 includes a protruding portion 41 that protrudes from a portion of the outer periphery of the end face of the unit body 34, and this protruding portion 41 is formed with an air injection port 42 that injects air along one end face of the unit body 34 to form an air curtain that covers the recess 39. An air passage 43 that is parallel to the axis of the unit body 34 and guides air to the air injection port 42 is formed in the unit body 34. Reference numeral 44 denotes an air supply pipe connected to the air passage 43 at the other end of the unit body 34. Since the light source unit 35 and the light receiving unit 36 ​​of the detection unit 37 can be kept clean at all times, inspections can be performed reliably and maintenance can be made easier.

[0042] The receiving unit 50 is equipped with six chutes 51 that receive the test objects W. The chutes 51 are provided corresponding to the determined damage level (0 to 5) described below, and the robot 10, upon receiving a command from the control unit 60, throws the test objects W held by the gripping hands 12 after inspection into the corresponding chutes 51. That is, this device is equipped with a sorting means 52 that sorts the test objects W according to the presence or absence of parasitic infection, in this embodiment, according to the damage level, and the sorting means 52 is composed of the robot 10 and the receiving unit 50, which are controlled as required by the control unit 60, and sorting is performed by these functions.

[0043] The control unit 60 includes a calculation processing unit 61 that performs overall control, as shown in Fig. 9. The calculation processing unit 61 includes a calculation model storage unit 62 that stores a calculation model that is constructed based on the second derivative spectrum of absorbance at wavelengths in the near-infrared region of diffuse reflected light or diffuse transmitted light obtained from a sample living organism infected with a parasite and a sample living organism not infected with a parasite by irradiating the sample living organism with light in the near-infrared region in advance, and that performs calculations related to the presence or absence of parasite infection in the living organism and / or the degree of damage that is quantified as a predetermined maximum level of onset from no onset to onset due to infection.

[0044] The calculation processing unit 61 also includes a discrimination unit 63 that discriminates the presence or absence of infection and / or the degree of damage based on the calculation results calculated from the absorbance of light received by the light receiving unit 36 ​​and the calculation model stored in the calculation model storage unit 62. That is, the discrimination unit 63 has an infection discrimination function that discriminates whether or not a living organism is infected with a parasite based on the calculation results calculated from the absorbance of light received by the light receiving unit 36 ​​and the calculation model. The discrimination unit 63 also has a damage degree discrimination function that discriminates the degree of damage, which is a numerical value representing the degree of onset, ranging from a predetermined maximum of no onset to onset, due to infection of a living organism with a parasite, based on the calculation results calculated from the absorbance of light received by the light receiving unit 36 ​​and the calculation model.

[0045] In the embodiment, the damage level is determined based on the degree of discoloration that appears on the subject W, as shown in Figure 2. Subjects W that are not infected can also be ranked in terms of damage level. In the embodiment, no onset includes no infection. If it is desired to closely examine the damage level and the presence or absence of infection, it is possible to deal with this using the respective trained models. Two types of damage level are used. One type of damage level is an index in which no onset is set to 0 and the maximum of onset is 100. In more detail, this is done using the damage level below.

[0046] Damage index = ((number of scales at t=1) + (number of scales at t=2 x 2) + (number of scales at t=3 x 3) + (number of scales at t=4 x 4)) / (total number of scales surveyed x 4) x 100 where: t is a number corresponding to the size of the discolored area caused by parasitic infection per garlic bulb, and is set so that the larger the value, the larger the size of the discolored area, and is set to four categories: t=1, t=2, t=3, and t=4.

[0047] The other damage level is configured as a rank that increases in order for each predetermined index range on the side of onset, where the degree of onset is expressed as an index with no onset being 0 and the maximum onset being 100. In this embodiment, the damage level is set to the following six ranks.

[0048] Damage level 0 = severity of onset 0 Severity of onset 0<Damage level 1≦Severity of onset 20 Onset level 20<Damage level 2≦Onset level 40 Severity of onset 40<Damage level 3≦Severity of onset 60 Severity of onset 60<Damage level 4≦Severity of onset 80 Severity of onset 80<Damage level 5≦Severity of onset 100

[0049] The severity of the disease is determined as follows: Severity of onset (index) = ((number of scales at t=1) + (number of scales at t=2 x 2) + (number of scales at t=3 x 3) + (number of scales at t=4 x 4)) / (total number of scales surveyed x 4) x 100 where: t is a number corresponding to the size of the discolored area caused by parasitic infection per garlic bulb, and is set so that the larger the value, the larger the size of the discolored area, and is set to four categories: t=1, t=2, t=3, and t=4.

[0050] The computational model is an analytical model constructed using statistical analysis or a trained model constructed using machine learning, Statistical analysis was selected from discriminant analysis, multiple regression analysis, PLS regression analysis, logistic regression analysis, and support vector machine (SVM). Machine learning is selected from tree analysis such as decision trees (CART), regression trees, random forests, and gradient boosted trees; neural networks or deep learning (DNN) such as perceptrons, convolutional neural networks (CNN), recurrent neural networks (RNN), and residual networks (ResNet); and ensemble analysis consisting of a combination of these.

[0051] In more detail, in multiple regression analysis, PLS regression analysis, and logistic regression analysis, near-infrared rays are irradiated onto a sample organism infected with a parasite and a sample organism not infected with a parasite in advance, the diffuse reflected light or diffuse transmitted light from the sample organism is received, the absorbance of the received light is measured, and an analytical model (computational model) relating to the wavelengths attributed to the parasite is identified by statistical analysis of the second-order derivative spectrum of the absorbance, near-infrared rays are irradiated onto the object W to be tested, the diffuse reflected light or diffuse transmitted light from the organism of the subject W is received, the absorbance of the received light is measured, and the results calculated from these absorbances and the analytical model determine whether the organism is infected with a parasite and / or the degree of damage, which is a numerical value representing the degree of onset due to infection, from a predetermined maximum of no onset to onset.

[0052] <Multiple regression analysis> The analytical model is determined by multiple regression analysis, where the absorbance spectrum of the light received from the sample is subjected to MSC processing and then second-order differentiation. MSC (Multiplicative Scatter Correction) is a preprocessing method for removing multiplicative factors (such as light scattering) and additive factors that occur in the measured spectrum (hereinafter the same).

[0053] The analytical model was specified by an equation (discriminant) that satisfies the relationship of the following general formula (B) using the absorbances of wavelengths 1 to n that have high correlation coefficients as variables.

[0054]

Number

[0055] In the general formula (B), when selecting the first wavelength (λ1) to the nth wavelength (λn), first, measure the absorbance of the sample biological body in advance. Whether the biological body is infected with parasites is determined by other means such as a culturing method using the Baermann method later. Using whether the sample is infected with parasites or not as an indicator, the correlation coefficient attributed to the above parasites obtained by multiple regression analysis of the absorbance of the sample biological body infected with the above parasites and the absorbance of the sample biological body not infected with the above parasites is selected for the wavelength range of near-infrared light of the first wavelength (λ1) with the highest correlation coefficient. Next, the wavelength range of the second wavelength (λ2) that belongs to the above parasites and has a correlation coefficient higher than the correlation coefficient of the wavelength range of the near-infrared light of the first wavelength (λ1) is selected by multiple regression analysis of the wavelength range of the near-infrared light of the first wavelength (λ1) and the wavelength range of 700 nm to 2500 nm. Then, the wavelength range of the third wavelength (λ3) that belongs to the above parasites and has a correlation coefficient higher than the correlation coefficient of the wavelength ranges of the near-infrared lights of the first wavelength (λ1) and the second wavelength (λ2) is selected by multiple regression analysis of the wavelength ranges of the near-infrared lights of the first wavelength (λ1) and the second wavelength (λ2) and the wavelength range of 700 nm to 2500 nm. In this way, the wavelength range of the nth wavelength (λn) that belongs to the above parasites and has a correlation coefficient not less than the correlation coefficient of the wavelength range of the near-infrared light of the first wavelength (λ1) is selected by multiple regression analysis of the wavelength ranges of the near-infrared lights of the first wavelength (λ1) to the (n - 1)th wavelength (λn - 1) and the wavelength range of 700 nm to 2500 nm.

[0056] <PLS regression analysis> The above analysis model was calculated and identified by the PLS (Partial least square projection to Latent Structure) analysis method after secondarily differentiating the absorbance spectrum of the light received from the above sample object after MSC processing.

[0057] <Logistic regression analysis method> The trained model was determined by calculating and identifying the absorbance spectrum of the light received from the sample object using logistic regression analysis after MSC processing and second-order differentiation.

[0058] <Support Vector Machine (SVM)> The trained model was identified using the SVM (Support Vector Machine) method by second-order differentiation of the absorbance spectrum of the light received from the sample object after MSC processing.

[0059] Next, we will give an example of deep learning methods. <Deep Learning Method (1)> For example, the trained model is a trained model obtained by MSC processing of the absorbance spectrum of light received from the sample living body, followed by second-order differentiation using a so-called ensemble method that combines a deep learning decision tree and a random forest method. The ensemble method results in a statistically superior trained model. The combination is not limited to this, and may be selected and combined as appropriate. These are types A to C of AI trained models described below.

[0060] <Deep Learning Method (2)> The trained model is a model trained using the deep learning DNN (Deep Neural Network) method, which is obtained by second-order differentiation of the absorbance spectrum of the light received from the sample organism after MSC processing. These are types D to F of the AI ​​trained models described below.

[0061] <Deep Learning Method (3)> The trained model is the one described below, which is the AI ​​trained model G to I type, in which the absorbance spectrum of the light received from the sample organism is subjected to MSC processing and then quadratically differentiated, and the waveform is visualized using the deep learning CNN (Convolutional Neural Network) method.

[0062] In an embodiment, the trained model for the presence or absence of infection is a trained model for causing a computer to function to output a calculation result relating to the presence or absence of infection of a parasite (potato lesion nematode) of a living organism (garlic), The absorbance of a sample organism is measured in advance, and the presence or absence of parasites in the organism is then confirmed by another means such as a culture method. Using the confirmed presence or absence of parasites as an indicator, the absorbance data of the sample organism not infected with parasites and the absorbance data of the sample organism infected with parasites are matched to the presence or absence of parasites, respectively, and this matched data is used as training data.The computer is trained using this training data, and near-infrared light is irradiated onto the organism to be tested, diffuse reflected light or diffuse transmitted light from the organism to be tested is received, the absorbance of the received light is measured, and a value quantifying whether the organism is infected with a parasite is output from the absorbance data.

[0063] In addition, the trained model for the degree of damage related to onset is a trained model for causing a computer to function so as to output a calculation result relating to the degree of damage quantified as the degree of onset from a predetermined maximum of no onset to onset due to infection with a parasite (potato lesion nematode) of a living organism (garlic), The absorbance of a sample organism is measured in advance, and the degree of damage caused by parasitic infection in the organism is then determined by another means, such as visual inspection. Using the determined degree of damage as an index, the absorbance data of the non-infected sample organism and the absorbance data of the infected sample organism are each associated with the degree of damage to the organism. This associated data is used as training data, and the computer is trained using this training data. The computer is then caused to irradiate the subject organism with near-infrared light, receive diffusely reflected or transmitted light from the subject organism, measure the absorbance of the received light, and output a value quantifying the degree of damage caused by parasitic infection in the organism from the absorbance data. Figure 10 shows an example of the configuration of the trained model. In this embodiment, for example, 550 absorbance data sets at wavelength intervals of 2 nm are input to the input layer.

[0064] In the embodiment, a plurality of different types of computation models are provided as the computation model, and these can be selectively used. Figures 9 and 13 show cases where types A to F are used as multiple regression analysis models, logistic regression analysis models, support vector machines (SVMs), and AI-trained models, and types G to I are used as other AI-trained models. Specific details of these will be described in the examples below.

[0065] The calculation processing unit 61 includes a plurality of different calculation models and a judgment unit 64 that judges whether to accept the judgment results of each calculation model. When selecting a plurality of different calculation models for determining the presence or absence of infection, the judgment unit 64 can be configured to prioritize and adopt any one of the judgment results of the calculation models that determines the presence or absence of infection. The judgment unit 64 can also be configured to use three or more different calculation models for determining the presence or absence of infection, and to adopt the judgment results of each calculation model by majority vote. When determining the degree of damage, any one of the calculation models related to the degree of damage can be selected and used. In this case, calculations can be performed using all calculation models, and the results can be selectively used. The judgment unit 64 adopts the calculation results of the selected calculation model. The display unit 70 can display the calculation results of all calculation models. In this embodiment, six levels of damage level are output as the final result.

[0066] 9, in the control unit 60, the arithmetic processing unit 61 has an operation control unit 65, which has a processing history storage function, a result display function on the display unit 70, a robot 10 operation function, an internet communication function, and a light intensity control function. The control unit 60 also has a communication unit 66 controlled by the internet communication function, an inspection control unit 67 which has a spectrometer and controls the inspection unit 30, such as controlling the spectrometer control circuit, a drive control unit 68 which has a transport unit control circuit which controls the transport unit 2 and a robot control circuit which controls the robot 10, and the like, and an operation command unit 69 which has a keyboard (not shown) and a setting panel (not shown) and the like.

[0067] The processing history storage function in the operation control unit 65 accumulates and stores the cumulative number of measurements of the test object W, the discrimination results, and the cumulative results in chronological order. The Internet communication function is a function for understanding the discrimination situation and system status when using the device in a remote location, and for remotely performing maintenance such as updating the application (discrimination method). By using this Internet communication function, the test object W can be inspected regardless of location, thereby improving the versatility of the device. The light intensity control function adjusts the light intensity of the light source and the sensitivity of the sensor in the spectroscopic unit so that the light detection sensor in the spectroscopic unit can perform measurements at an appropriate level.

[0068] Various data are displayed on the display unit 70. The display on the display unit 70 is operated by the screen operation unit (operation command unit 69), and can be switched appropriately to display an input setting screen, a discrimination result display screen, an error display screen, etc. The discrimination results may be displayed on an LCD panel. The discrimination results may also be output as voice. Furthermore, an interface for outputting data to the outside may be provided.

[0069] In this embodiment, when the discrimination unit 63 determines the degree of damage, the calculation processing unit 61 causes the classification means 52 to classify the test objects W according to the degree of damage. That is, when the discrimination unit 63 determines the degree of damage, the calculation processing unit 61 operates the robot 10 via the robot operation function of the operation control unit 65 and the robot control circuit of the drive control unit 68 so as to classify the test objects W according to the determined degree of damage, and causes the test objects W grasped by the grasping hand 12 to be thrown into the corresponding chute 51. In addition, the control unit 60 performs various other controls.

[0070] Therefore, when the living body testing device S according to this embodiment is used to test the subject W, the procedure is as follows: This will be explained using the flow charts shown in FIGS. As shown in Figure 11, when the main power supply switch (not shown) is turned on, the control unit 60 starts up and checks each mechanism, such as the spectrometer, sensor, and lamp (1-1). At this time, a screen indicating that the system is being initialized appears on the display unit 70, and the indicator light turns yellow (1-2). After the check operation for each mechanism is completed, a reference waveform that serves as the basis for calculating absorbance is measured (1-3), and this is stored in the memory unit inside the control unit 60 (1-4). The main screen is then displayed, and the indicator light turns green (1-8). If a setting value is called up from the setting panel (not shown) during this time (1-5), a confirmation screen for the accumulated lamp lighting time, date and time, etc. is displayed (1-6). To perform an inspection, operate the setting panel to return to the main screen (1-7).

[0071] A garlic bulb as the test object W is placed on the holder 20 with its stem Wc facing up. When the indicator light on the main screen is green, pressing the start switch (1-9) of the control button executes a measurement and discrimination routine for the test object W (1-10). In this measurement and discrimination routine for the test object W, as shown in FIG. 12, the control unit 60 first issues an instruction to operate the belt conveyor 3 of the transport unit 2 (2-1), and the test object W is transported. During this transport process, the position detection sensor detects that the test object W has reached a predetermined position where it will be grasped by the gripping hand 12 of the robot 10 (2-2). An image is then captured by the camera (2-3). The test object W is then grasped by the gripping hand 12 of the robot 10 at the predetermined position and removed. The test object W is then positioned at the inspection position Y, and the inspection unit 30 measures the test object W. In the inspection unit 30, light is irradiated onto the subject W from the light source unit 35, and the diffusely reflected or diffusely transmitted light is received by the light receiving unit 36 ​​and transmitted via optical fiber to a spectroscopic unit in the inspection control unit 67, where the intensity of the near-infrared wavelength is converted into voltage for each wavelength range and extracted and transmitted to the calculation processing unit 61 (2-4).The intensity spectrum of the diffusely reflected or diffusely transmitted light is then obtained and discrimination is performed using a separate parasite discrimination routine (2-5).

[0072] In the discrimination routine, as shown in FIG. 13, noise reduction processing is performed on the diffused light intensity (diffuse light spectrum) transmitted from the spectrometer (3-1, 3-2), the reference waveform stored during initialization is read (3-3), and the near-infrared absorbance of the measurement object W is calculated (3-4). The absorbance is standardized (3-5), and then second-order derivative processing is performed (3-6). The second-order derivative spectrum is then centered and scaled (3-7). This spectrum is used to discriminate using a computation model pre-stored in the computation model storage unit 61. Discrimination is performed using multiple regression analysis (3-8), logistic regression analysis (3-9), AI-trained model (1) (2) type A to F calculation (3-10), AI-trained model (3) type G to I calculation (3-11), and support vector machine (SVM) calculation (3-12).

[0073] When multiple computation models with different types for discriminating the presence or absence of infection are selected as computation models, if any one of the discrimination results from the computation models discriminates the presence of infection, the judgment unit 64 preferentially adopts that discrimination result (3-13) and calculates the final discrimination result (3-14). Alternatively, when three or more computation models with different types for discriminating the presence or absence of infection are used as computation models, the judgment unit 64 decides and adopts the discrimination results of the infection presence or absence of each computation model by majority vote (3-13) and calculates the final discrimination result (3-14). In this embodiment, a computation model for discriminating the degree of damage is used as the computation model, and the judgment unit 64 adopts the calculation result of the selected computation model (3-13) and calculates the final discrimination result (3-14). In this embodiment, six levels of damage degree are output as the final result. All judgment results can be viewed on the display unit 70.

[0074] Once the measurement of the test object W is complete, the process returns to FIG. 12, and based on the damage level results, the robot 10 is operated to place the test object W into the corresponding chute 51 of the receiving unit 50 for sorting (2-6). The process also returns to FIG. 11, and the discrimination results and the cumulative total of discrimination results up to that point are displayed (1-13). If an error occurs in any of the mechanisms or the emergency stop button is pressed during this process (1-11), an error occurrence screen is displayed and the indicator light turns red (1-12). To recover, check the lamp, spectrometer, sensor, and other mechanisms. The discrimination results and the diffused light spectrum during measurement of the test object W are stored in the memory function within the control unit 60. This process is repeated until the stop button is pressed (1-15). [Example]

[0075] Next, an example of a calculation model will be shown, along with the results of verification performed by actually inspecting and verifying the calculation model. <Example 1: Multiple regression analysis (determining whether or not an infection is present)> The garlic bulbs used as test subject W were produced in an experimental field in Rokunohe Town, Aomori Prefecture, and 12,480 garlic bulbs prepared for shipping were used. As shown in Figure 14, the data for creating the multiple regression analysis model was obtained by subjecting all test subjects W to near-infrared spectroscopy, culturing the test subjects W with potato-lesion nematodes using the Bellman method, and then examining the test subjects W to confirm whether they were infected. The presence or absence of infection was then correlated with the absorbance data of the near-infrared spectral wavelengths of the samples. Using this creation data, the wavelengths necessary to determine the presence or absence of infection were searched for in order of highest correlation, and a multiple regression analysis model for the presence or absence of infection was created.

[0076] Specifically, 191 wavelengths with a logarithmic value of 0.069 or greater were used for the multiple regression analysis model to determine the presence or absence of infection. As shown in Figure 14, the correlation coefficient for the multiple regression model for the presence or absence of infection was 0.6898. Although a correlation was observed, it could not be said to be highly correlated. However, when the discriminant value for the multiple regression analysis model was set to 0.5 or greater as "infected," the discriminant value for "not infected" was 99.6%, and the discriminant value for "infected" was 99.6%. This multiple regression analysis model can determine the presence or absence of potato-lesion nematode infection in garlic, depending on the discriminant value set.

[0077] The discrimination rate and accuracy were verified using the calculation model according to Example 1 (multiple regression model for the presence or absence of infection). 200 garlic bulbs produced in an experimental field in Rokunohe, Aomori Prefecture, and prepared for shipping were used as test subjects W. The results are shown in Figure 15. From these results, the multiple regression model for the presence or absence of infection had a multiple correlation coefficient of 0.6836 (Figure 15(a)). When the discrimination value of the estimated value was set to 0.5 or more, the accuracy of this multiple regression model for discriminating the presence or absence of infection was 0.9422, and it was possible to discriminate 97.1% of cases as "not infected" and 90.7% of cases as "infected" (Figure 15(b)).

[0078] <Example 2: Multiple regression analysis (damage level (index) discrimination)> The garlic bulbs used for the test (W) were 12,480 garlic bulbs prepared for shipping from the same production area as above. After near-infrared spectroscopy testing of the garlic bulbs for test (W), the test garlic bulbs were cultured for potato leaf nematodes using the Bellman method, and the damage level was calculated by calculating the extent of lesions on the garlic using the damage level (index) described above. A multiple regression model for the damage level (index) was created using 196 wavelengths (not shown) selected with a logarithmic value of 0.018 or higher. A multiple regression equation using these wavelengths was used as a damage level (index) prediction multiple regression model. As shown in Figure 16(a), the multiple regression model yielded a correlation coefficient of 0.7815, indicating that the damage level (index) could be predicted.

[0079] The discrimination rate and accuracy were verified using the calculation model (multiple regression model of damage level (index)) according to Example 2. 200 garlic bulbs prepared for shipping from the same production area as above were used. The results are shown in Figure 16(b). From these results, the correlation coefficient of the multiple regression model was 0.7965. The results showed that it was possible to estimate the damage level (index).

[0080] <Example 3: Logistic regression model (infection status determination)> For the garlic bulbs of the test subject W, 12,480 garlic bulbs prepared for shipping from the same production area as above were used. After near-infrared spectroscopy of the garlic bulbs of the test subject W, they were cultured for C. elegans using the Bellman method to confirm the presence or absence of infection. Using the test data, the wavelengths required to determine the presence or absence of infection were searched in order of highest correlation to create a logistic regression model for infection. Specifically, 164 wavelengths (not shown) with a logarithmic value of 0.039 or higher were used for the determination using the logistic regression model for infection. As shown in Figure 17(a), the discrimination accuracy of the logistic regression model for C. elegans infection was 95.4% for "no infection" and 96.0% for "infection." In other words, it is an extremely accurate model.

[0081] The discrimination rate and accuracy were verified using the computational model according to Example 3 (a logistic regression model for discriminating between the presence and absence of infection). 200 garlic bulbs prepared for shipping from the same production area as above were used. The results are shown in Figure 17(b). From these results, the accuracy of discriminating between the presence and absence of infection using the logistic regression model was 0.9674 on average, and it was possible to discriminate between "no infection" and "infection" with an accuracy of 97.7% and 92.9%.

[0082] <Example 4: Logistic regression model (damage level (6 levels) discrimination)> For the garlic bulbs of test subject W, 3,120 garlic bulbs prepared for shipping from the same production area as above were used as the data for creation. Near-infrared spectroscopy testing was performed on all test subjects W, and then the test garlic bulbs were cultured for potato leaf nematodes using the Bellman method, and the level of damage was calculated based on the extent of the garlic lesions using the above-mentioned damage level (6 levels). The logistic regression analysis model for the damage level (6 levels) was created by analyzing near-infrared spectroscopic absorbance data corresponding to the measured value data of the above-mentioned damage level (6 levels) using the logistic regression analysis method as training data and creating a regression equation.

[0083] As shown in Figure 18(a), the logistic regression analysis model performed a statistical analysis of the actual measured values ​​and estimated values ​​of the damage level (6 levels), and showed an accuracy of 0.7583, an average precision of 0.7149, an average recall of 0.4044, and an average F-score of 0.4295.Although the recall tends to be low, the logistic regression analysis model is a model that can classify the damage level (6 levels) of garlic caused by potato-lesion nematodes.

[0084] The discrimination rate and accuracy were verified using the computational model according to Example 4 (a logistic regression model for discriminating the degree of damage (6 levels)). Using 870 garlic bulbs prepared for shipping from the same production area as above, the discrimination rate and accuracy of the logistic regression model for discriminating the presence or absence of infection for the degree of damage (6 levels) were verified. The results are shown in Figure 18(b). From these results, it can be seen that the classification accuracy of the ordered logistic regression model for the degree of damage (6 levels) varied from 0.000 to 0.8709 depending on the degree of damage, but that this was possible by changing the classification class.

[0085] <Example 5: AI trained model A (infection determination)> For the garlic bulbs of the test subjects W, 15,075 garlic bulbs prepared for shipping from the same production area as above were used as supervised training data. This training data was prepared by culturing the test garlic bulbs for potato leaf nematodes using the Berman method after near-infrared spectroscopy testing for all test subjects W, and then checking for infection. The presence or absence of infection was correlated with the absorbance data of the sample at near-infrared spectroscopic wavelengths. The basic structure of the trained model in this example consists of an input layer (550 absorbance data sets at 2 nm wavelength intervals are input), an intermediate layer, and an output layer (the same applies in the following examples).

[0086] This trained model A uses near-infrared spectroscopic absorbance data corresponding to the aforementioned actual measured data of infection presence or absence as training data, and creates 3 to 5 types of models using the cross-5-fold validation method of deep learning (DNN method), and 3 to 10 types of models using the cross-5-fold method of gradient boosting trees, and is constructed using an ensemble method to select the optimal model based on the accuracy rate, error rate, recall rate, and F-value of each model.

[0087] As shown in Figure 19(a), statistical analysis has shown that the trained model A has extremely high discrimination accuracy, with an AUC of 0.9999, an Accuracy of 0.9992, a Precision of 0.9992, a Recall of 0.9992, and an F-score of 0.9992. Also, as shown in Figure 19(b), the training data used to establish the trained model A is distributed in a manner that allows for extremely clear separation.

[0088] The discrimination rate and accuracy were verified using the computational model according to Example 5 (AI-trained model A for determining the presence or absence of infection). 3,873 garlic bulbs prepared for shipping from the same production area as above were used. As shown in Figure 20, this trained model A had a multiple correlation coefficient of 0.9979, and the discrimination accuracy for the presence or absence of infection was 100.0% for no infection and 99.9% for infection. This shows that this model can discriminate the presence or absence of potato-lesion nematode infection in garlic with high accuracy.

[0089] <Example 6: AI trained model B (damage level (6 levels) discrimination)> For the test subject W, 12,480 garlic bulbs prepared for shipping from the same production area as above were used as supervised training data. Near-infrared spectroscopy was performed on all test subjects W. The test garlic bulbs were then cultured for potato lesion nematodes using the Bellman method, and the damage level was calculated based on the severity of the lesions on the garlic bulbs using the six levels of damage described above. Trained model B for the six levels of damage was constructed using near-infrared spectroscopic absorbance data corresponding to the measured damage levels (six levels) as training data. Three to five models were created using a cross-five-fold validation method with deep learning (DNN) and three to ten models were created using a cross-five-fold gradient boosting tree method. The optimal model was then selected using an ensemble method based on the accuracy rate, error rate, recall, and F-score of each model.

[0090] As shown in Figure 21(a), in a statistical analysis of the measured and estimated damage levels (six levels), the trained model B showed an accuracy of 0.9965, an average precision of 0.9986, an average recall of 0.9902, and an average F-score of 0.9943, demonstrating extremely high discrimination accuracy, goodness of fit, and recall. In other words, this model can classify the damage level (six levels) of garlic caused by potato-lesion nematodes with high accuracy.

[0091] The discrimination rate and accuracy were verified using the computational model (AI-trained model B for damage level (6 levels) discrimination) according to Example 6. 3,120 garlic bulbs prepared for shipping from the same production area as above were used. The results are shown in Figure 21(b). From these results, the trained model B for damage level (6 levels) had an accuracy of 0.9999 between the actual measured value and the estimated value, and an average precision of 0.9979, demonstrating extremely high discrimination accuracy and goodness of fit. In other words, it can be seen that this model is capable of classifying the damage level (6 levels) of garlic caused by potato-lesion nematodes with high accuracy.

[0092] <Example 7: AI trained model C (damage level (index) determination)> For the test subject W, 12,480 garlic bulbs prepared for shipping from the same production area as above were used as supervised training data. The actual damage index was calculated by near-infrared spectroscopy testing of all test subjects W, culturing the test garlic bulbs for potato lesion nematodes using the Bellman method, and calculating the extent of garlic lesions using the above damage index. To create the trained model C for the damage index, the measured damage data described above was used as supervised data. Three to five models were created using deep learning (DNN) cross-validation (5-fold) and three to ten models were created using gradient boosting tree cross-validation (5-fold). The optimal model was determined based on the statistical results of the coefficient of determination, median error, mean error, and PMSE.

[0093] As shown in Figure 22(a), the coefficient of determination for the damage index of trained model C between the measured and predicted values ​​was 0.9809. With a median error of 0.303, a mean error of 2.36, an RMSE of 5.98, and a coefficient of determination of 0.9809, extremely high prediction accuracy was achieved. Therefore, trained model C is a model that can quickly, accurately, and non-destructively predict the damage index of garlic caused by potato-lesion nematode infection.

[0094] The method and accuracy were verified using the calculation model (damage level (index) discrimination AI trained model C) according to Example 7. 3,120 garlic bulbs prepared for shipping from the same production area as above were used. The results are shown in Figure 22(b). From these results, trained model C showed extremely high prediction accuracy, with a coefficient of determination of 0.9936, a median error of 0.1646, a mean error of 0.9788, and an RMSE of 3.5269. In other words, it can be seen that this model is capable of predicting the damage level (index) of garlic caused by potato-lesion nematodes with high accuracy.

[0095] <Example 8: AI trained model D (infection determination)> 18,960 garlic cloves prepared for shipping from the same production area as above were used as training data for the garlic bulbs of test subject W. The training data for this trained model D was created by testing all test subjects W with near-infrared spectroscopy, then cultivating the test garlic for potato-lesion nematodes using the Berman method to check for infection, and correlating the presence or absence of infection with the absorbance data of the sample at the near-infrared spectroscopic wavelength.

[0096] The trained model D uses the deep learning DNN (deep neural network) method as its basic structure, and is composed of an input layer, five intermediate layers (composed of activation functions such as drop and Relu functions), and an output layer, and uses Adam (adaptive moment estimation) as the optimization algorithm, with LearningRate 0.1, Momentum 0.9, Weight Decay 0.0001, Learning Rate Scheduler Exponential, Multipier 0.1, Interval 600540 iterations, etc. This trained model was created with attention to overfitting.

[0097] As shown in Figure 23(a), this trained model D has an AUC (Area Under the Curve) of 0.9998, Accuracy of 0.9994, Precision of 0.9996, Recall of 0.9972, and an F-score of 9.994, demonstrating extremely high discrimination accuracy and making it an extremely effective model for determining whether or not a patient is infected with potato-lesion nematodes.

[0098] The trained model D for determining the presence or absence of infection according to Example 8 was used to verify its discrimination rate and accuracy. 3,914 garlic bulbs prepared for shipping from the same production area as above were used. As shown in Figure 23(b), the trained model D had an infection discrimination accuracy of 100.0% at Precision 1.0. This means that the model can accurately determine whether garlic is infected with potato-lesion nematodes.

[0099] <Example 9: AI trained model E (damage level (6 levels) discrimination)> For the test subject W, 15,600 garlic bulbs prepared for shipping from the same production area as above were used as supervised training data. All test subjects W were subjected to near-infrared spectroscopy testing, and then the test garlic bulbs were cultured for potato leaf nematodes using the Bellman method. The damage level was calculated based on the severity of the lesions on the garlic using the six levels described above. The trained model E was created using deep learning (DNN: deep neural network) with near-infrared spectroscopic absorbance data corresponding to the measured damage level (six levels) as training data. The trained model E consists of an input layer, six hidden layers (activation functions such as drop and Relu functions), and an output layer. The optimization algorithm used was Adams, with a weight decay of 0.0001, and consideration was given to overfitting.

[0100] As shown in Figure 24(a), trained model E had an accuracy of 0.9976 between the actual measured value and the estimated value, an average precision of 0.9991, an average recall of 0.9945, and an average F-measure of 0.9968. This means that it has extremely high discrimination accuracy, goodness of fit, and recall, and is a trained model that can be used as an extremely effective method for discriminating and classifying the degree of damage (6 levels).

[0101] The discrimination rate and accuracy were verified using the computational model (AI-trained model E for discriminating damage level (6 levels)) according to Example 9. 3,873 garlic bulbs prepared for shipping from the same production area as above were used. The results are shown in Figure 24(b). From these results, the trained model E for damage level (6 levels) had an average precision of 0.9994, indicating extremely high fitness and can be used to classify the degree of damage. In other words, it can be seen that the trained model E is a model that can quickly, accurately, and non-destructively predict the degree of damage (6 levels) caused by garlic potato-lesion nematode infection.

[0102] <Example 10: AI trained model F (damage level (index) determination)> For the garlic bulbs of test subject W, 12,480 garlic bulbs prepared for shipping from the same production area as above were used as supervised learning data. The actual damage index was calculated by culturing the tested garlic bulbs for potato leaf nematodes using the Bellman method after near-infrared spectroscopy testing for all test subjects W, and calculating the extent of the garlic lesions using the above-mentioned damage index. The trained model F was created using deep learning (DNN: deep neural network) with the near-infrared spectroscopy absorbance data corresponding to the actual damage index data described above as training data.

[0103] The trained model F is based on the DNN method, and after repeated basic consideration and ingenuity to obtain optimal conditions for the input layer, intermediate layer, and output layer, it is composed of an input layer, five intermediate layers (composed of activation functions such as drop and Relu functions), and an output layer, and is trained using Adam (Adaptive moment estimation) as the optimization algorithm, with LearningRate 0.1, Momentum 0.9, Weight Decay 0.0001, Learning Rate Scheduler Exponential, Multipier 0.1, Interval 600540 iterations, etc. This model is characterized by being created with attention to overfitting.

[0104] As shown in Figure 25(a), the trained model F for the damage index was a highly accurate model based on statistical data analysis of the estimated values ​​and the actual measured values, with a coefficient of determination of 0.9987, a median error of 0.2737, a mean error of 0.2593, and an RMSE of 1.6037. This model can quickly, accurately, and non-destructively estimate the damage level caused by garlic lesion nematode infection.

[0105] The discrimination rate and accuracy were verified using the computational model (damage level (index) discrimination AI trained model F) according to Example 10. 2,851 garlic bulbs prepared for shipping from the same production area as above were used. The results are shown in Figure 25(b). From these results, trained model F obtained test results in a statistical data analysis of the predicted values ​​and the actual measured values, with a multiple correlation coefficient of 0.999, a mean error of 0.5260, a median error of 0.2743, and an RMSE of 1.3025. In other words, it can be seen that trained model F is a model that can quickly, accurately, and non-destructively predict the damage level (index) of garlic caused by potato-lesion nematode infection.

[0106] <Example 11: AI trained model G (infection determination)> The training data for the test subject W consisted of 12,480 garlic bulbs prepared for shipping from the same production area as above. The training data for this trained model G was prepared by testing all test subjects W using near-infrared spectroscopy, cultivating the test garlic for potato-lesion nematodes using the Berman method, and then checking for infection, and correlating the presence or absence of infection with the absorbance data of the sample at the near-infrared spectroscopic wavelength.

[0107] The trained model G was created using deep learning (CNN: convolutional neural network) using near-infrared spectroscopic absorbance data corresponding to the actual measured data on the presence or absence of infection as training data. The trained model G visualizes the waveform (1 row, 550 columns) of the near-infrared spectroscopic absorbance data, and is composed of an input layer, six intermediate layers (activation functions such as drop and Relu functions), and an output layer. The optimization algorithm used was Adams, with Weight Decay set to 0.0001, and care was taken to prevent overfitting.

[0108] As shown in Figure 26(a), this trained model G had an Accuracy of 1.0000 between the actual measured and estimated values, an average Precision of 1.0000, an average Recall of 1.0000, and an average F-score of 1.0000. This means that it has extremely high discrimination accuracy, goodness of fit, and recall, and can be used as an extremely effective method for determining whether or not a patient is infected with potato-lesion nematodes.

[0109] The trained model G for determining the presence or absence of infection according to Example 11 was used to verify its discrimination rate and accuracy. 3,121 garlic bulbs prepared for shipping from the same production area as above were used. As shown in Figure 26(b), the trained model G had an infection discrimination accuracy of 100.0%. This means that the trained model G can accurately determine whether garlic is infected with potato-lesion nematodes.

[0110] <Example 12: AI trained model H (damage level (6 levels) discrimination)> For the test subject W, 12,480 garlic bulbs prepared for shipping from the same production area as above were used as supervised training data. All test subjects W were subjected to near-infrared spectroscopy testing. Subsequently, the test garlic bulbs were cultured for potato leaf nematodes using the Bellman method, and the damage level on the garlic was calculated using the six levels described above. The trained model H was created using deep learning (CNN: convolutional neural network) with near-infrared spectroscopic absorbance data corresponding to the measured damage level (six levels) as training data. The trained model H was created by imaging the waveform (1 row, 550 columns) of near-infrared spectroscopic absorbance measurement data. It is composed of an input layer, six hidden layers (activation functions such as drop and Relu functions), and an output layer. The optimization algorithm was Adams, with a weight decay of 0.0001 and consideration given to overfitting.

[0111] As shown in Figure 27(a), the trained model H had an Accuracy of 1.0000 for the actual measured and estimated values, an average Precision of 1.0000, an average Recall of 1.0000, and an average F-measure of 1.0000. This means that the model has extremely high discrimination accuracy, goodness of fit, and recall, and can be used as an extremely effective method for discriminating and classifying the degree of damage (6 levels).

[0112] The discrimination rate and accuracy were verified using the computational model (AI-trained model H for discriminating damage level (6 levels)) according to Example 12. 3,120 garlic bulbs prepared for shipping from the same production area as above were used. The results are shown in Figure 27(b). From these results, it was revealed that trained model H has a fitness of 1.000 and can be used to classify the damage level (6 levels). In other words, it can be seen that trained model H is a model that can quickly, accurately, and non-destructively predict the damage level (6 levels) caused by garlic potato-lesion nematode infection.

[0113] <Example 13: AI trained model I (damage level (index) determination)> For the garlic bulbs of test subject W, 12,480 garlic bulbs prepared for shipping from the same production area as above were used as supervised training data. The actual measured values ​​of the damage index were determined by near-infrared spectroscopy testing of all test subjects W, followed by culturing the tested garlic bulbs for potato leaf nematodes using the Bellman method, and calculating the extent of lesions on the garlic using the above-mentioned damage index. The trained model I was created using deep learning (CNN: convolutional neural network) using near-infrared spectroscopic absorbance data corresponding to the actual measured value data of the damage index described above as training data. Trained Model I is constructed by imaging the waveform (1 row, 550 columns) of near-infrared spectroscopic absorbance data using the CNN method, and is composed of an input layer, six intermediate layers (activation functions such as drop and Relu functions), and an output layer.The optimization algorithm used is Adams, with Weight Decay set to 0.0001, and attention paid to overfitting.

[0114] As shown in Figure 28(a), the trained model I is a highly accurate model, with a coefficient of determination of 0.9831, a median error of 1.2806, a mean error of 4.2906, and an RMSE of 5.8131 in statistical data analysis of the estimated values ​​and the measured values. This model can quickly, accurately, and non-destructively estimate the damage index caused by garlic lesion nematode infection.

[0115] The discrimination rate and accuracy were verified using the calculation model (damage level (index) discrimination AI trained model I) according to Example 13. 2,851 garlic bulbs prepared for shipping from the same production area as above were used. The results are shown in Figure 28(b). From these results, the statistical multiple correlation coefficient between the estimated values ​​and the measured values ​​was 0.999, with a mean error of 4.2590, a median error of 1.2513, and RMSE of 5.72955. In other words, it can be seen that the trained model I is a model that can quickly, accurately, and non-destructively predict the damage level (index) of garlic caused by potato-lesion nematode infection.

[0116] In the above embodiment, discrimination was performed by combining five discrimination methods: discriminant analysis, multiple regression analysis, PLS analysis, backpropagation of neural networks, and SVM. However, this is not necessarily limited to these methods; any one of these methods may be used, or several methods may be combined, and modifications may be made as appropriate. Furthermore, in the above embodiment, discrimination was performed in six levels, but this is not necessarily limited to this; the number of levels may be determined as appropriate. Furthermore, in the embodiment, the test subject was a garlic stalk, but this is not necessarily limited to this; individual clove tests may also be performed, and modifications may be made as appropriate.

[0117] Furthermore, although the embodiments have been described using examples of garlic as the living organism and potato-lesion nematode as the parasite, the present invention is not limited to these and can be applied to various plants and the nematodes that parasitize them. Furthermore, the present invention can, of course, be applied to various living organisms and various parasites, not limited to plants and nematodes. In short, those skilled in the art can easily make many modifications to these exemplary embodiments without substantially departing from the novel teachings and effects of the present invention, and these many modifications are within the scope of the present invention. [Explanation of symbols]

[0118] S Biological testing equipment W Test subject (garlic bulb) Wa scale Wb flower diameter Wc stem 1 base 2. Conveyor section 3. Conveyor belt 10. Robot 11 Robotic Arm 12 Grasping Hand 13 Opening and closing actuator X gripping position Y inspection position 20 Holding part 21 Side wall 22 Upper Wall 23 Holding body 24 Insertion hole 25 Bearing recess 26 Camera 30 Inspection Department 31 Inspection Unit 32 Support rod 33 Cover 34 Unit body 35 Light source section 36 Light receiving part 37 Detection unit 38 Holding body 39 Recess 40 Dustproof mechanism 41 Protruding part 42 Air nozzle 43 Air passage 50 Receiving Department 51 Shooter 52 Separation means 60 Control Unit 61 Processing unit 62 Calculation model storage unit 63 Discrimination part 64 Judgment Department 65 Operation control section 66 Communications Department 67 Inspection Control Unit 68 Drive control unit 69 Operation command section 70 Display section

Claims

1. A living body testing device for testing a living body as a test subject for infection with a parasite, a light source unit that irradiates the test subject with light in the near-infrared region; a light receiving unit that receives diffuse reflected light or diffuse transmitted light from the test subject; and a control unit that determines whether the test subject is infected with a parasite based on the absorbance of the light received by the light receiving unit, The control unit is a calculation model storage unit that stores a calculation model that is constructed in advance based on the second derivative spectrum of absorbance at wavelengths in the near-infrared region of diffuse reflected light or diffuse transmitted light obtained from a sample organism infected with a parasite and a sample organism not infected with a parasite by irradiating the sample organism with light in the near-infrared region, and performs calculations related to the presence or absence of infection of the organism with a parasite and / or the degree of damage quantified as a predetermined maximum level of onset from no onset to onset due to infection; a determination unit that determines the presence or absence of infection and / or the degree of damage based on a calculation result calculated from the absorbance of light received by the light receiving unit and the calculation model stored in the calculation model storage unit, The computational model is an analytical model constructed using statistical analysis or a trained model constructed using machine learning, The statistical analysis is selected from discriminant analysis, multiple regression analysis, PLS regression analysis, logistic regression analysis, and support vector machine (SVM); The machine learning is selected from tree analysis such as decision trees (CART), regression trees, random forests, and gradient boosting trees, neural networks such as perceptrons, convolutional neural networks (CNN), recurrent neural networks (RNN), and residual networks (ResNet), deep learning (DNN), and ensemble analysis consisting of a combination of these, A biological testing device characterized by having a classification means for classifying test subjects according to whether or not they are infected, and / or according to the degree of damage, based on the discrimination results of the discrimination section of the control section.

2. 2. The living body testing device according to claim 1, wherein the damage level is also ranked for non-infected test subjects.

3. 3. The living body inspection device according to claim 1, wherein the degree of damage is determined based on the degree of discoloration appearing on the subject.

4. 4. The living body inspection device according to claim 3, wherein the damage level is an index in which 0 indicates no onset and 100 indicates the maximum onset.

5. The biological testing device of claim 3, characterized in that the degree of damage is expressed as an index where the degree of onset is 0 for no onset and 100 for the maximum of onset, and the degree of onset is represented by a rank that increases in order for each specified index range.

6. A biological testing device as described in any one of claims 1 to 5, characterized in that the control unit has multiple different types of calculation models as the calculation models, and has a judgment unit that judges whether or not to accept the judgment results of each calculation model.

7. The biological testing device of claim 6, wherein when a plurality of different types of calculation models for determining whether or not an infection is present are used as the calculation model, the judgment unit is configured to prioritize any one of the determination results using each calculation model that determines whether or not an infection is present.

8. The biological testing device according to claim 6, characterized in that when three or more different types of computational models for determining the presence or absence of infection are used as the computational models, the judgment unit is configured to determine the infection presence or absence determination results of each computational model by majority vote.

9. 9. The living organism inspection device according to claim 1, wherein the parasite is a nematode that infects a living plant.

10. 10. The living organism inspection device according to claim 9, wherein the living organism is garlic, potato, sweet potato, or iris, and the parasite is a potato-lesion nematode.

11. 11. The living body testing device according to claim 10, wherein the test object is a garlic bulb with a collection of garlic clove pieces.

12. The biological testing device described in claim 11, characterized in that the damage level is determined based on the degree of discoloration appearing in the subject, and is composed of the following damage level index, with 0 representing no onset and 100 representing the maximum onset: Damage index = ((number of scales in t = 1) + (number of scales in t = 2 x 2) + (number of scales in t = 3 x 3) + (number of scales in t = 4 x 4)) / (total number of scales surveyed x 4) x 100 where: t is a number corresponding to the size of the discolored area caused by parasitic infection per garlic bulb, and is set so that the larger the value, the larger the size of the discolored area, and is set to four categories: t=1, t=2, t=3, and t=4.

13. The biological testing device described in claim 11, characterized in that the degree of damage is determined based on the degree of discoloration appearing on the subject, and the degree of onset is expressed as an index where 0 represents no onset and 100 represents the maximum of onset, and the degree of onset is expressed as the following degrees of onset, where 0 represents no onset and the onset side is composed of classes that increase in order for each specified index range. Severity of onset (index) = ((number of scales at t = 1) + (number of scales at t = 2 x 2) + (number of scales at t = 3 x 3) + (number of scales at t = 4 x 4)) / (total number of scales surveyed x 4) x 100 where: t is a number corresponding to the size of the discolored area caused by parasitic infection per garlic bulb, and is set so that the larger the value, the larger the size of the discolored area, and is set to four categories: t=1, t=2, t=3, and t=4.

14. 14. A living body examination device as described in any one of claims 1 to 13, comprising: a base; a transport unit provided on the base for transporting the test objects one by one at a predetermined interval; a robot provided near the base; a gripping hand at the tip of the robot arm of the robot for gripping the test object during the transport process by the transport unit and positioning the test object at an examination position; an examination unit having the light source unit and the light receiving unit, provided at the tip of the robot arm of the robot near the gripping hand, and performing an examination on the test object positioned at the examination position by the gripping hand; and a receiving unit that is moved by the robot after the examination by the examination unit and receives the test object gripped by the gripping hand.

15. A living body inspection device as described in any one of claims 1 to 14, characterized in that it comprises an inspection section having the light source section and light receiving section and inspecting the subject, the inspection section being configured with an inspection unit having a detection section with the light source section and light receiving section exposed on one end surface, and the inspection unit is provided with a dustproof mechanism that sprays air along the detection section to form an air curtain covering the detection section.

16. A trained model for causing a computer to function to output a calculation result relating to whether or not a living organism is infected with a parasite, The absorbance of a sample living organism is measured in advance, and the presence or absence of parasites in the organism is then determined by a separate means. Using the determined presence or absence of parasites as an indicator, absorbance data using the second derivative spectrum of the absorbance of a sample living organism that is not infected with parasites and absorbance data using the second derivative spectrum of the absorbance of a sample living organism that is infected with parasites are respectively associated with the presence or absence of parasites, and this associated data is used as training data.The trained model is characterized in that it is trained using this training data, and the computer is caused to function in such a way that near-infrared light is irradiated onto the living organism to be tested, diffuse reflected light or diffuse transmitted light from the living organism to be tested is received, the absorbance of the received light is measured, and a value that quantifies whether the organism is infected with a parasite is output from the absorbance data using the second derivative spectrum of the absorbance.

17. A trained model for causing a computer to function to output a calculation result relating to the degree of damage quantified as a predetermined level of onset from no onset to a maximum of onset due to infection of a living organism with a parasite, The absorbance of a sample organism is measured in advance, and the degree of damage caused by infection of the organism with a parasite is then determined by a separate means. Using the determined degree of damage to the organism as an index, absorbance data using the second derivative spectrum of the absorbance of a sample organism without the disease and absorbance data using the second derivative spectrum of the absorbance of a sample organism with the disease are each matched to the degree of damage to the organism, and this matched data is used as training data, and the model is trained using this training data.The trained model is characterized in that it functions to irradiate a test organism with near-infrared light, receive diffuse reflected light or diffuse transmitted light from the test organism, measure the absorbance of the received light, and output a value that quantifies the degree of damage caused by infection of the organism with a parasite from the absorbance data using the second derivative spectrum of the absorbance.

Images