JP2023060548A - Crustacean molting sign identification program - Google Patents

Abstract

To enable accurate and automatic identification of molting timing of crustaceans while cultivating crustaceans at a culture farm.SOLUTION: A crustacean molting sign identification program for identifying signs of molting of crustaceans is provided, the program being configured to make a computer perform: an information acquisition step of acquiring captured image information of crustaceans; and an identification step of utilizing three or more levels of association between reference image information of the crustaceans acquired in the past and possibility of molting of the crustaceans to identify the possibility of molting based on the reference image information corresponding to the image information acquired in the information acquisition step.SELECTED DRAWING: Figure 4

Description

The present invention relates to a crustacean molting sign discrimination program.

In recent years, the weight of aquaculture has increased in the fisheries industry. In particular, crustaceans such as shrimp and crabs cannot be harvested in large quantities from the sea or rivers compared to the past, and the ratio of aquaculture is increasing more and more.

In the case of aquaculture, a farm is built, crustaceans are raised from juvenile fish in the fish tank, and after they grow large and have a lot of meat, they are landed. By the way, the taste of such crustaceans changes according to the elapsed time after molting. Therefore, the timing of landing is often determined based on the elapsed time after molting.

However, when it is desired to land crustaceans immediately after molting, there are many cases in which preparations for landing must be made immediately after signs of molting appear. Therefore, it is necessary to discriminate signs of molting of crustaceans with high accuracy, but the current situation is that such a technique has not yet been devised.

Therefore, the present invention has been devised in view of the above-mentioned problems, and the purpose thereof is to accurately and automatically determine the timing of molting of crustaceans in culturing crustaceans in aquaculture farms. To provide a crustacean molting sign discriminating program capable of discriminating both.

A crustacean molting sign discrimination program according to the present invention is a crustacean molting sign discrimination program for discriminating signs of molting of crustaceans, in which an information acquiring step of acquiring image information obtained by imaging the crustacean, and the possibility of molting of the crustacean based on the reference image information corresponding to the image information obtained in the information obtaining step, using three or more levels of association between the reference image information and the possibility of molting of the crustacean. It is characterized by causing a computer to execute a discrimination step of discriminating .

Even if there is no special skill or experience, it is possible to automatically determine the timing of molting of crustaceans with high accuracy when cultivating crustaceans at a farm without relying on human labor.

1 is a block diagram showing the overall configuration of a system to which the present invention is applied; FIG. It is a figure which shows the specific structural example of a search apparatus. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention.

A program for discriminating signs of molting of crustaceans to which the present invention is applied will be described in detail below with reference to the drawings.

First Embodiment FIG. 1 is a block diagram showing the overall configuration of a crustacean molting symptom determination system 1 in which a crustacean molting symptom determination program to which the present invention is applied is installed. A crustacean molting symptom discrimination system 1 includes an information acquisition unit 9 , a discrimination device 2 connected to the information acquisition unit 9 , and a database 3 connected to the discrimination device 2 .

The information acquisition unit 9 is a device for a person using this system to input various commands and information. The information acquisition unit 9 is not limited to a device for inputting text information, and may be configured by a device such as a microphone that can detect voice and convert it into text information. Further, the information acquisition unit 9 may be configured as an imaging device capable of capturing an image, such as a camera. The information acquisition unit 9 may be configured by a scanner having a function of recognizing a character string from a paper document. Further, the information acquisition unit 9 may be integrated with the discriminating device 2 to be described later. The information acquisition unit 9 outputs the detected information to the discrimination device 2 . Further, the information acquisition unit 9 may be configured by means for specifying position information by scanning map information. Further, the information acquisition unit 9 may be configured with an illuminance sensor for measuring a temperature sensor, a humidity sensor, and a wind direction sensor. The information acquisition unit 9 may also be configured with a communication interface that acquires weather data from the Meteorological Agency or a private weather forecast company. The information acquisition unit 9 may be composed of a body sensor worn on the body to detect body data, and the body sensor detects, for example, body temperature, heart rate, blood pressure, number of steps, walking speed, and acceleration. It may be configured with a sensor for Also, the body sensor may acquire biological data not only of humans but also of animals. The information acquisition unit 9 may be configured as a device that acquires information such as drawings by scanning or reading from a database. The information acquisition unit 9 may be configured by an odor sensor that detects odors and scents in addition to these.

In addition, the information acquisition unit 9 includes a water thermometer for measuring the water temperature of the farm, various sensors for measuring the amount of solar radiation, various sensors for measuring dissolved oxygen concentration, various sensors for measuring water quality, and the like. is also included.

The database 3 accumulates various kinds of information necessary for discriminating signs of molting of crustaceans.

The discrimination device 2 is composed of an electronic device such as a personal computer (PC), for example, but in addition to the PC, it is embodied in any other electronic device such as a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc. It may be one that is made into. A user can obtain a search solution by this discriminating device 2 .

FIG. 2 shows a specific configuration example of the discriminating device 2. As shown in FIG. This discriminating device 2 performs wired or wireless communication with a control unit 24 for controlling the entire discriminating device 2 and an operation unit 25 for inputting various control commands via operation buttons, a keyboard, or the like. A communication unit 26 for searching, a determination unit 27 for making various judgments, and a storage unit 28, represented by a hard disk or the like, for storing a program for performing a search to be executed are connected to the internal bus 21, respectively. . Further, the internal bus 21 is connected with a display unit 23 as a monitor for actually displaying information.

The control section 24 is a so-called central control unit for controlling each component mounted in the discriminating device 2 by transmitting control signals via the internal bus 21 . In addition, the control unit 24 transmits commands for various controls through the internal bus 21 according to operations through the operation unit 25 .

The operation unit 25 is embodied by a keyboard or a touch panel, and a user inputs an execution command for executing a program. The operation unit 25 notifies the control unit 24 when the execution command is input by the user. Upon receiving this notification, the control unit 24 cooperates with each component including the determination unit 27 to execute desired processing operations. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

The determination unit 27 determines the search solution. The determination unit 27 reads various information stored in the storage unit 28 and various information stored in the database 3 as necessary information in executing the determination operation. This determination unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any known artificial intelligence technology.

The display unit 23 is composed of a graphic controller that creates a display image based on control by the control unit 24 . The display unit 23 is implemented by, for example, a liquid crystal display (LCD).

When the storage unit 28 is configured with a hard disk, predetermined information is written to each address based on the control by the control unit 24, and this information is read as necessary. The storage unit 28 also stores a program for executing the present invention. This program is read and executed by the control unit 24 .

The operation of the crustacean molting sign discrimination system 1 configured as described above will be described.

In the crustacean molting sign discrimination system 1, it is assumed that, for example, as shown in FIG. 3, three or more degrees of association between the reference image information and the possibility of molting are set in advance. Reference image information is image data of crustaceans such as shrimp and crab captured by a camera. This reference image information is assumed to be a still image, but is not limited to this, and may be a moving image. The reference image information may be composed of data after image analysis. The reference image information may be composed not only of an RGB image, but also of a spectral image that is color-coded for each spectral band. In addition, information such as the pincers, legs, whiskers, beak, eyes, abdomen, and all other fins and colors of crustaceans that can be characteristic of crustaceans is extracted from the image information, and this is categorized. good too. In order to categorize them, a feature amount may be extracted from image information, and machine learning or deep learning technology may be used for discrimination. The reference image information may be sequentially captured in chronological order for each growth process of the crustacean to be photographed. This makes it possible to link reference image information to the growth process of crustaceans and the period after hatching and convert them into data.

The data of the reference image information may be, for example, the color, cracks, or the like of the crustacean crustacean. In such a case, the reference image information may be data indicating whether the crustacean is transparent or whitish.

Molting potential is information about the crustacean's ability to molt. The possibility of molting may be indicated literally as a percentage, but is not limited to this, and may be indicated by three levels such as high, normal, and low molting possibilities. However, it may be shown in two stages, whether to molt immediately or not to molt. Regarding how to score the possibility of molting, we asked experts who observed the crustaceans and zookeepers to judge the possibility of molting based on their past experiences, and also photographed the crustaceans at that time. You may make it learn as a data set with image information for reference.

In the example of FIG. 3, it is assumed that the input data are reference image information P01 to P03, for example. Such reference image information P01 to P03 as input data are linked to the possibility of shedding as output. In this output, molting possibilities A to D are displayed as output solutions. For example, the molting possibility A is 90%, the molting possibility B is 50%, and the molting possibility C is 25%.

The reference image information is associated with each other through three or more levels of association with the molting possibilities A to D as output solutions. The image information for reference is arranged on the left side through the degree of association, and the possibility of each molting is arranged on the right side through the degree of association. The degree of relevance indicates the degree of possibility of molting and the degree of relevance to the reference image information arranged on the left side. In other words, the degree of association is an index indicating whether each piece of reference image information is highly likely to be associated with the possibility of molting, and the most probable molting possibility is selected from the reference image information. It indicates the accuracy in doing so. In the example of FIG. 3, w13 to w19 are shown as association degrees. These w13 to w19 are shown in 10 stages as shown in Table 1 below, and the closer to 10 points, the higher the possibility of molting as an output and the higher the degree of correlation between each combination as an intermediate node. Conversely, the closer to one point, the lower the degree of correlation between each combination as an intermediate node and the price as an output.

The discrimination device 2 acquires in advance the degrees of association w13 to w19 of three or more stages shown in FIG. In other words, the discriminating device 2 accumulates past data sets that determine which of the reference image information and the possibility of molting in that case was adopted and evaluated in discriminating the actual search solution. is analyzed to create the degree of association shown in FIG.

For example, among the possibilities of molting for reference image information measured about a farm in the past, molting possibility A has the largest catch. By collecting and analyzing such data sets, the degree of association with the reference image information is strengthened.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference image information P01, analysis is performed from various data obtained as a result of evaluating the possibility of molting in the past. In the case of the reference image information P01, if there are many cases of the possibility of molting A, the degree of association leading to the evaluation of the possibility of molting is set higher, and if there are many cases of the possibility of molting B. , set a higher degree of association leading to an evaluation of this molting possibility. For example, in the example of the reference image information P01, the possibility of molting A and the possibility of molting C are linked. The degree of association of w14 leading to the possibility C of is set to 2 points.

Further, the degree of association shown in FIG. 3 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the outputs of the nodes of this neural network correspond to the degrees of association described above. Moreover, it is not limited to a neural network, and may be composed of all decision-making factors that constitute artificial intelligence.

In such a case, as shown in FIG. 4, reference image information is input as input data, the possibility of shedding is output as output data, and at least one hidden layer is provided between the input node and the output node. It may be machine-learned. Either or both of the input nodes and the hidden layer nodes are set with the above-mentioned degree of relevance, which serves as a weighting for each node, based on which the output is selected. Then, when the degree of association exceeds a certain threshold, the output may be selected.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data is used to search for the possibility of molting when actually newly determining the possibility of molting. In such a case, image information of crustaceans in the proposed farm is newly obtained. The farm to be proposed is not necessarily the same as the farm where the reference image information was measured, and image information of another farm may be used. The newly acquired image information is measured by the information acquisition unit 9 described above.

Based on the image information newly acquired in this way, the possibility of molting is determined. In such a case, reference is made to the degree of association shown in FIG. 3 (Table 1), which has been acquired in advance. For example, when the newly acquired image information is the same as or similar to P02, the possibility B of molting is associated with the degree of association w15, and the possibility C of molting is associated with the degree of association w16. there is In such a case, molting possibility B, which has the highest degree of association, is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the possibility of molting C, which has a low degree of association but the association itself is recognized, may be selected as the optimum solution. In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association.

In this way, it is possible to search for the most suitable molting possibility from the newly acquired image information and display it to the user. By looking at the results of this search, it becomes possible to determine the possibility of optimal molting for raising the fry in the farm more appropriately and increasing the catch. If the reference image information is categorized as described above, the acquired image information is also categorized according to the categorization, and then the possibility of molting is determined. FIG. 5 shows an example in which three or more degrees of association are set between a combination of the above-described reference image information and the above-described reference period information, and the possibility of molting for the combination.

Reference period information is information relating to the period from hatching of the crustacean for which the reference image information is acquired. The reference period information also indicates the period since the crustacean was born, and may be expressed in days, weeks, or hours since birth. Such reference period information may be acquired from a database managed by the vendor, or may be manually input each time.

In the example of FIG. 5, it is assumed that the input data are reference image information P01 to P03 and reference period information P18 to 21, for example. An intermediate node shown in FIG. 5 is a combination of reference image information as input data and reference period information. Each intermediate node is also connected to an output. In this output, the possibility of molting is displayed as the output solution.

Each combination (intermediate node) of reference image information and reference period information is associated with the possibility of molting as the output solution through three or more levels of association. The image information for reference and the period information for reference are arranged on the left side through the degree of association, and the possibility of molting is arranged on the right side through the degree of association. The degree of relevance indicates the degree of relevance to the possibility of molting with respect to the reference image information and the reference period information arranged on the left side. In other words, the degree of association is an index indicating whether each piece of reference image information and reference period information is highly likely to be associated with the possibility of shedding. This indicates the accuracy in selecting the most probable molting possibility from the

The discrimination device 2 acquires in advance the degrees of association w13 to w22 of three or more stages shown in FIG. In other words, in determining the actual search solution, the determination device 2 determines which of the reference image information, the reference period information obtained when the reference image information is acquired, and the possibility of shedding in that case. Whether it was suitable or not, accumulate past data, and build up the degree of association by analyzing these.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually searching for the possibility of molting fish. In such a case, the image information for which the possibility of molting is actually determined and the period information are obtained. Here, the period information relates to the period after hatching and the period after birth of the crustacean whose image information is to be acquired when newly determining the possibility of molting. This is the same as reference period information.

Based on the image information newly acquired in this way and the period information, the possibility of optimum molting is searched for. In such a case, reference is made to the degree of association shown in FIG. 5, which has been acquired in advance. For example, when the newly acquired image information is the same as or similar to P02 and the period information is the same or similar to P21, the node 61d is associated via the degree of association. This node 61d is associated with the molting possibility C with w19 and with the molting possibility D with the association degree w20. In such a case, the molting possibility C, which has the highest degree of association, is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the molting possibility D, which has a low degree of association but the association itself is recognized, may be selected as the optimum solution. In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association.

Further, the degree of association shown in FIG. 5 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the outputs of the nodes of this neural network correspond to the degrees of association described above. Moreover, it is not limited to a neural network, and may be composed of all decision-making factors that constitute artificial intelligence. In addition, the configuration related to artificial intelligence is the same as described in FIG.

Table 2 below shows examples of degrees of association w1 to w12 extending from the input.

Intermediate nodes 61 may be selected based on degrees of association w1 to w12 extending from this input. In other words, the greater the degree of association w1 to w12, the heavier the weight in selecting the intermediate node 61 may be. However, the degrees of association w1 to w12 may all have the same value, and the weighting in selecting the intermediate nodes 61 may all be the same.

According to the present invention, in addition to the reference image information described above, a combination of reference water quality information instead of the reference period information described above, and three or more levels of association with the possibility of molting for the combination. You may make it search for a solution based on.

This reference water quality information, which is added as an explanatory variable instead of the reference period information, indicates all water quality information in the area, and all data related to the water quality of crustacean farms, rivers, and seas. including. Examples of water quality data include pH (hydrogen ion concentration), dissolved oxygen content, chemical oxygen consumption, ammonia nitrogen content, nitrite nitrogen content, nitrate nitrogen content, and various other water quality data. Element content, number of coliform bacteria, water temperature, salinity, etc., but not limited to these. Water quality data also includes hardness, or consists of the content of the following chemicals: Examples of chemicals include antimony and its compounds, uranium and its compounds, nickel and its compounds, 1,2-dichloroethane, toluene, di(2-ethylhexyl) phthalate, chlorous acid, chlorine dioxide, dichloroacetonitrile, residual Chlorine, calcium, magnesium, etc. (hardness), but not limited to these. Such reference water quality information is managed in the database 3 for each region.

Such water quality information also influences the possibility of molting. During the solution search, the water quality information of the water in which the crustaceans to be identified actually live is acquired. Based on newly acquired image information and water quality information, the possibility of molting of crustaceans is determined. In such a case, the degree of association acquired in advance is referred to, and the possibility of molting is determined based on the above-described method. According to the present invention, in addition to the above-described reference image information, three or more levels of association between a combination of reference motion video information in place of the above-described reference period information and the possibility of shedding with respect to the combination. The solution search may be performed based on the degrees.

The motion image information for reference and the motion image information added as explanatory variables instead of the period information for reference are moving images of the movement of crustaceans in water. The movement of the crustacean may be patterned into a predetermined pattern and used as reference motion video information. In such a case, the movement trajectory and gestures of the crustacean may be analyzed through captured moving images, and the analyzed trajectory and pattern may be applied to a predetermined type. In such a case, in order to categorize the image, a feature amount may be extracted from the image information, and machine learning or deep learning technology may be used for determination. In this way, the movement of the crustacean that has been acquired in the past is imaged, and the reference motion image information acquired by applying the image to a pattern that has been typified in advance is learned. It is possible to perform a solution search through the reference motion video information corresponding to the motion video information obtained by capturing the motion of the subject and applying the motion video to a pattern categorized in advance.

Such motion image information also influences the possibility of molting. At the time of searching for a solution, the movement image information of the crustacean to be identified in the water in which the crustacean actually lives is acquired. Based on newly acquired image information and motion video information, the possibility of molting of crustaceans is determined. In such a case, the degree of association acquired in advance is referred to, and the possibility of molting is determined based on the above-described method.

According to the present invention, in addition to the reference image information described above, a combination of the reference acceleration information instead of the reference period information described above and the degree of association of three or more levels with the possibility of molting for the combination. You may make it search for a solution based on.

This reference acceleration information, which is added as an explanatory variable instead of the reference period information, is information relating to the acceleration when the crustacean moves in water. Acceleration information for reference may be obtained by acquiring an image of the movement of the crustacean and applying the moving acceleration of the crustacean from the image to a pattern categorized in advance. In such a case, in order to categorize the image, a feature amount may be extracted from the image information, and machine learning or deep learning technology may be used for determination.

During the solution search, the movement of the crustacean is actually imaged, and acceleration information is obtained by applying the movement acceleration of the crustacean from the image to a pattern that has been typified in advance. Based on newly acquired image information and acceleration information, the possibility of molting of crustaceans is determined. In such a case, the degree of association acquired in advance is referred to, and the possibility of molting is determined based on the above-described method.
According to the present invention, in addition to the above-described reference image information, there are three or more stages of combinations of reference food consumption information instead of the above-described reference period information, and the possibility of molting for the combination. A solution search may be performed based on the degree of association.

This reference food consumption information, which is added as an explanatory variable instead of the reference period information, is all information related to the amount of food consumed by crustaceans in water. The reference food consumption information and the food consumption information may be obtained by measuring the amount of food consumed by the crustaceans each time by a person in charge of breeding. The measurement method may be to measure the amount of food remaining when the amount of food is constant. The amount of remaining food indicates the amount of food remaining due to leftover food of crustaceans in the water of the farm. The amount of remaining food may be measured by analyzing an image captured by a camera installed in water or an image captured from the ground. Moreover, the measurement of the amount of remaining food may be estimated from the water quality data described above. Also, in such a case, artificial intelligence is used to create a trained model by weighting the degree of correlation of three or more stages between each of the above-mentioned chemical substances that make up the water quality data and the actually measured amount of remaining food. may be used to estimate the amount of remaining food via the water quality data. In addition, since the color of the water changes according to the turbidity of the water from the captured image, data on the color of the water and the amount of remaining food is collected, and machine learning is performed to determine the amount of remaining food. good too.
It should be noted that the reference food consumption information and food consumption information may be replaced with information on the type of food ingested.

During the search for a solution, information on the amount of food consumption is actually obtained from the crustacean to be identified. Based on newly acquired image information and food consumption information, the possibility of molting of crustaceans is determined. In such a case, the degree of association acquired in advance is referred to, and the possibility of molting is determined based on the above-described method.

According to the present invention, in addition to the reference image information described above, the combination of the reference solar radiation amount instead of the reference period information described above and the possibility of molting for the combination have three or more levels of association. You may make it search for a solution based on.

This reference solar radiation amount added as an explanatory variable instead of the reference period information is the solar radiation amount to the environment in which the crustaceans live. The amount of solar radiation affects the growth, appetite and movement of crustaceans, and also affects water temperature. Therefore, by combining this with the learning data and making a judgment, it is possible to make a judgment with higher accuracy.

At the time of searching for a solution, the amount of radiation in the environment in which the crustacean to be identified actually inhabits is acquired. Based on the newly acquired image information and the amount of solar radiation, the possibility of molting of the crustacean is determined. In such a case, the degree of association acquired in advance is referred to, and the possibility of molting is determined based on the above-described method.

In addition to reference image information, a combination of reference dissolved oxygen concentration instead of reference solar radiation and three or more degrees of association with the possibility of molting for the combination may be set.

This reference dissolved oxygen concentration added as an explanatory variable in place of the reference solar radiation is the dissolved oxygen concentration in the water of the environment in which the crustaceans live. Since the dissolved oxygen concentration is also a factor that greatly influences the relationship with the possibility of molting, it is added to the explanatory variables.

When searching for a solution, the dissolved oxygen concentration in the water in the environment where the crustacea to be identified actually inhabits is obtained. Based on newly acquired image information and dissolved oxygen concentration, the possibility of molting of crustaceans is determined. In such a case, the degree of association acquired in advance is referred to, and the possibility of molting is determined based on the above-described method.

It should be noted that the present invention is not limited to the above-described embodiments. The search solution corresponding to the output may also suggest the timing of molting instead of the possibility of molting. The timing of feeding indicates the hour and minute on which day the molting occurs. In such a case, at the stage of creating a trained model, data on the timing of molting is also read as a substitute for the possibility of molting and learned. As a result, as a search solution, not only the possibility of molting, but also the feeding timing is output.

In the above-mentioned degree of relevance, the degree of relevance is expressed by a 10-level evaluation, but it is not limited to this, and it may be expressed by a degree of relevance of 3 or more stages. For example, 100 steps or 1000 steps may be used. On the other hand, this degree of association does not include those expressed in two stages, that is, whether or not they are associated with each other, either 1 or 0.

According to the present invention configured as described above, anyone can easily determine and search for the possibility of molting without special skills or experience. Further, according to the present invention, it is possible to judge the search solution with a higher degree of accuracy than a human being does. Furthermore, by configuring the degree of association described above with artificial intelligence (neural network, etc.) and making it learn, it is possible to further improve the discrimination accuracy.

Since the above-described input data and output data may not be exactly the same in many cases during the learning process, information obtained by classifying these input data and output data according to type may be used. That is, the information P01, P02, . . . P15, 16, . A data set may be created between the data and the output data for learning.

In addition to reference image information, reference motion video information, reference period information, reference water quality information, reference acceleration information, reference food consumption information, reference food consumption information, A case has been described as an example in which a reference solar radiation amount, a reference dissolved oxygen concentration, and the like are combined, but the present invention is not limited to this. In other words, in addition to reference image information, the degree of association includes reference motion video information, reference period information, reference water quality information, reference acceleration information, reference food consumption information, reference food consumption information, and reference solar radiation. It may be composed of a combination of two or more of the amount, dissolved oxygen concentration for reference, and the like. In addition, the degree of association includes reference motion video information, reference period information, reference water quality information, reference acceleration information, reference food consumption information, reference food consumption information, reference solar radiation, and reference dissolved oxygen concentration. In addition to any one or more of the above, other factors may be added to this combination to form the degree of association.

In either case, data is input in accordance with the reference information of the degree of association, and the possibility of molting is obtained using the degree of association.

Further, according to the present invention, as shown in FIG. 6, the possibility of molting is determined based on the degree of relevance of a combination of two or more types of information, ie, information for reference U and information for reference V. FIG. This reference information U is reference image information, and reference information V is reference solar radiation amount, reference dissolved oxygen concentration, reference water quality data, reference movement image information, reference residual food amount, and reference residual ratio. shall be either

At this time, as shown in FIG. 6, the output obtained for the reference information U is used as it is as input data, and is associated with the output (possibility of shedding) through an intermediate node 61 in combination with the reference information V. may For example, after providing an output solution for reference information U (reference image information) as shown in FIG. An output (possibility of molting) may be searched.

Moreover, according to the present invention, it is characterized in that the optimum solution search is performed through the degree of association set to three or more stages. The degree of association can be described by a numerical value of, for example, 0 to 100% in addition to the 10 stages described above, but is not limited to this, and can be described by a numerical value of 3 or more stages. may be configured.

By discriminating the most probable molting possibility based on the degree of association represented by numerical values of three or more stages, the degree of association can be determined under a situation in which there are multiple candidates for the possibility of the search solution. It is also possible to search and display in descending order. If it is possible to display to the user in descending order of degree of association in this way, it is also possible to preferentially display more probable search solutions.

In addition to this, according to the present invention, it is possible to make a judgment without overlooking even a very low output discrimination result such as a correlation degree of 1%. Remind the user that even discrimination results with an extremely low degree of association are connected as slight signs, and that once in dozens or hundreds of times, the discrimination results may be useful. be able to.

Furthermore, according to the present invention, there is an advantage that a search policy can be determined by setting thresholds by performing a search based on three or more degrees of association. If the threshold value is lowered, even if the degree of association is 1%, it can be picked up without omission. be. On the other hand, if the threshold is set high, there is a high possibility that the optimal search solution can be detected with a high probability. Sometimes the solution is overlooked. It is possible to decide which one to place emphasis on based on the way of thinking of the user side and the system side, and it is possible to increase the degree of freedom in selecting such points to place emphasis on.

Furthermore, in the present invention, the degree of association described above may be updated. This update may reflect information provided via a public communication network such as the Internet, for example. In addition, when each reference information including reference image information is acquired, and knowledge, information, and data regarding the possibility of molting are acquired, the degree of association is increased or decreased accordingly.

In other words, this update corresponds to learning in terms of artificial intelligence. Since new data is acquired and reflected in the learned data, it can be said that it is a learning act.

In addition to updating the degree of association based on information that can be obtained from the public communication network, the system side or the user side based on the contents of research data, papers, conference presentations, newspaper articles, books, etc. by experts It may be updated manually or automatically. Artificial intelligence may be used in these update processes.

Second Embodiment In the second embodiment, reference motion video information and data sets of the possibility of shedding are learned.

In the example of FIG. 7, it is assumed that the input data are reference motion video information P01, P02, and P03 in each region. The reference moving image information P01, P02, and P03 as such input data are linked to the possibility of shedding as output.

The reference motion image information P01, P02, and P03 are associated with each other through three or more levels of association with the shedding possibilities A to B as output solutions. The motion image information for reference is arranged on the left side through the degree of association, and the possibility of each molting is arranged on the right side through the degree of association. The degree of relevance indicates the degree of possibility of shedding and the degree of relevance with respect to the reference motion video information arranged on the left side. In other words, the degree of association is an index indicating whether each piece of reference motion video information is highly likely to be associated with the possibility of shedding. It indicates accuracy in choosing sex.

Also, this degree of association may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the outputs of the nodes of this neural network correspond to the degrees of association described above. Moreover, it is not limited to a neural network, and may be composed of all decision-making factors that constitute artificial intelligence.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data through a data set of previous reference motion video information for each region and the possibility of shedding, in order to actually determine the possibility of shedding anew, the above-mentioned The possibility of molting will be explored using the learned data. These data sets may be created by reading from a database managed by a vendor. Since the solution search method is the same as that of the above-described first embodiment, the description thereof will be omitted.

The example of FIG. 8 is an example in which the degree of relevance is formed by combining reference motion video information and reference period information.

Assume that the input data are, for example, reference motion video information P01 to P03 and reference period information P14 to P17. An intermediate node shown in FIG. 8 is a combination of reference motion picture information as such input data and reference period information. Each intermediate node is also connected to an output. In this output, the possibility of molting is displayed as the output solution.

Each combination (intermediate node) of reference motion video information and reference period information is associated with the possibility of shedding as the output solution through three or more degrees of association. The motion image information for reference and the period information for reference are arranged on the left side through the degree of association, and the possibility of shedding is arranged on the right side through the degree of association. The degree of relevance indicates the degree of high relevance to the possibility of shedding with respect to the reference motion video information and the reference period information arranged on the left side. In other words, the degree of association is an index indicating whether each piece of reference motion video information and reference period information is highly likely to be associated with the possibility of shedding. This indicates the accuracy in selecting the most probable molting possibility from the period information. Therefore, the possibility of optimal shedding is searched for by combining the reference motion video information and the reference period information.

In the example of FIG. 8, w13 to w22 are shown as association degrees. These w13 to w22 are shown in 10 stages as shown in Table 1. The closer to 10 points, the higher the degree of correlation between each combination as an intermediate node and the output. The closer it is, the lower the degree of correlation between each combination as an intermediate node and the output.

The search device 2 acquires in advance three or more degrees of association w13 to w22 shown in FIG. In other words, the search device 2 accumulates past data as to whether the reference motion video information, the reference period information, and the possibility of molting in that case are suitable for determining the actual search solution. By analyzing these, the degree of association shown in FIG. 8 is created.

Further, the degree of association shown in FIG. 8 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the outputs of the nodes of this neural network correspond to the degrees of association described above. Moreover, it is not limited to a neural network, and may be composed of all decision-making factors that constitute artificial intelligence. Other configurations relating to artificial intelligence are the same as those described in FIGS.

In the example of the degree of association shown in FIG. 8, the node 61b is a node of the combination of the period information for reference P14 with respect to the motion video information for reference P01. The degree of association of gender E is w16. A node 61c is a node of a combination of reference period information P15 and P17 with respect to the reference motion video information P02, and the degree of association with the possibility B of shedding is w17, and the degree of association with the possibility D of shedding is w18. It's becoming

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually determining the possibility of molting. In such a case, the region for which the possibility of molting is to be determined is similarly entered. Then, the moving image information and the period information arranged for each region in the database 3 are obtained.

Based on the motion image information and period information newly acquired in this way, the possibility of optimum molting is searched for. In such a case, reference is made to the degree of association shown in FIG. 8 (Table 1), which has been acquired in advance. For example, when the newly acquired motion video information is the same as or similar to P02, and the period information is the same or similar to P17, the node 61d is associated via the degree of association. This node 61d is associated with the molting possibility C with w19 and with the molting possibility D with the association degree w20. In such a case, the molting possibility C, which has the highest degree of association, is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the molting possibility D, which has a low degree of association but the association itself is recognized, may be selected as the optimum solution. In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association.

The present invention is not limited to the above-described embodiment, and three or more degrees of association between the basic reference information and the possibility of molting may be used, as shown in FIG. 9, for example. In such a case, the solution search is performed based on three or more degrees of association between the reference information corresponding to the newly acquired information and the possibility of molting. The basic reference information includes all the above-mentioned reference information (reference image information, reference motion video information, reference period information, reference water quality information, reference acceleration information, reference food consumption information, etc.). , reference feed consumption information, reference solar radiation, reference dissolved oxygen concentration, etc.) can be applied.

In these cases, similarly, when information corresponding to reference information used as learning data is input, solution search is performed based on the above-described method.

The search solution obtained through the degree of association may be further modified or weighted based on other reference information.

The other reference information referred to here corresponds to any reference information other than the basic reference information when any of the reference information described above is used as the basic reference information.

For example, it is assumed that in certain reference period information F, which is one of other reference information, the possibility B of molting has been determined many times in the past. When period information corresponding to such reference period information F is newly acquired, the search solution B as the possibility of shedding is weighted. It is set in advance so as to perform processing to connect to B.

For example, the other reference information G is an analysis result that suggests the search solution C as a higher possibility of molting, and the reference information F is an analysis result that suggests the search solution D as a higher possibility of molting. It shall be a valid analysis result. After the setting with the reference information in this way, if the actually obtained information is the same as or similar to the reference information G, the process of increasing the weight of the molting possibility C is performed. On the other hand, when the actually acquired information is the same as or similar to the reference information F, processing is performed to increase the weight of the possibility D of molting. In other words, the degree of association itself leading to the possibility of molting may be controlled based on the reference information FH. Alternatively, after the possibility of molting is determined only by the degree of association described above, the obtained search solution may be modified based on the reference information FH. In the latter case, how the possibility of molting as a search solution is modified based on the reference information FH depends on what is designed on the system side each time.

The reference information is not limited to any one type, and the solution search may be performed based on two or more types of reference information. Similarly, in such a case, the discriminant pattern as a search solution obtained via the degree of association may be corrected to a higher value for a case that leads to the possibility of shedding suggested by the reference information.

Similarly, as shown in FIG. 10, even in the case of forming the degree of association with the possibility of molting for a combination of reference information serving as a keynote and other reference information, the reference information serving as a keynote any reference information (reference image information, reference motion video information, reference period information, reference water quality information, reference acceleration information, reference food consumption information, reference food consumption information, reference solar radiation amount, reference dissolved oxygen concentration, etc.) are also applicable. Other reference information includes any reference information other than the underlying reference information.

At this time, if the basic reference information is the reference motion video information, the other reference information includes any other reference information.

In such a case, the possibility of molting can be estimated by searching for solutions in the same way. At this time, as shown in FIG. 9 described above, the possibility of molting is corrected through other reference information (reference information F, G, H, etc.) for the search solution obtained through the degree of association. You may make it

At this time, the degree of association may be learned by combining not only one piece of other reference information but also two or more pieces of information.

Further, as shown in FIG. 11, the degree of association may be formed between only the basic reference information and the possibility of molting. This basic reference information is any reference information in the first and second embodiments (reference image information, reference motion video information, reference period information, reference water quality information, reference acceleration information, Reference food consumption information, reference food consumption information, reference solar radiation, reference dissolved oxygen concentration, etc.) are also applicable. Description of the solution search method in FIG. 11 will be omitted by citing the description of FIG.

In both the first embodiment and the second embodiment, the case of determining the possibility of molting of crustaceans living in aquaculture farms has been described as an example. Of course, it can also be applied to determine the molting potential of crustaceans that live naturally in rivers.

1 Crustacea Shedding Sign Discrimination System 2 Discrimination Device 21 Internal Bus 23 Display Unit 24 Control Unit 25 Operation Unit 26 Communication Unit 27 Discrimination Unit 28 Storage Unit 61 Node

Claims (9)

In a crustacean molting sign discrimination program for discriminating signs of molting of crustaceans,
an information acquisition step of acquiring image information obtained by imaging the crustacean;
Reference image information acquired in the past and reference image information according to the image information acquired in the information acquisition step using three or more levels of association with the possibility of molting of the crustacean. A crustacean molting sign discriminating program characterized by causing a computer to execute a discriminating step of discriminating the possibility of molting based on. The information acquisition step further acquires period information regarding a period from hatching of the crustacean,
In the estimating step, at least three stages of a combination having the reference image information and reference period information relating to the period after hatching of the crustacean from which the reference image information is acquired, and the possibility of molting. and further estimating the possibility of molting based on the reference image information corresponding to the image information obtained in the information obtaining step and the reference period information corresponding to the period information. The crustacean molting sign discrimination program according to claim 1. The information acquisition step further acquires water quality information about the quality of water in which the crustaceans grow,
In the estimation step, a combination of the reference image information and reference water quality information related to the quality of water in which crustaceans grow obtained in the past, and three or more degrees of association with the possibility of molting are used. and further estimating the possibility of molting based on reference image information corresponding to the image information obtained in the information obtaining step and reference water quality information corresponding to water quality information. The crustacean molting sign discrimination program described. The information acquisition step further acquires motion video information obtained by imaging the movement of the crustacean,
In the estimating step, a combination of the reference image information and the reference motion video information related to the movement of the crustacean acquired in the past and the degree of association with the possibility of molting are used in three or more stages, and 2. The possibility of molting is estimated based on the reference image information corresponding to the image information obtained in the information obtaining step and the reference moving image information corresponding to the moving image information. Crustacean Molting Sign Discrimination Program. The information acquisition step further acquires an image of the movement of the crustacean, and acquires motion image information by applying the image to a pattern categorized in advance,
In the estimating step, a combination having the reference image information and the reference motion image information obtained by acquiring an image of the movement of the crustacean in the past and applying the image to a pattern categorized in advance; Reference image information corresponding to the image information obtained in the information obtaining step and reference motion video information corresponding to the motion video information, using three or more levels of association with the possibility of molting. 2. The crustacean molting sign discriminating program according to claim 1, wherein the possibility of molting is estimated based on the information. The information acquisition step further acquires an image of the movement of the crustacean, and acquires acceleration information by applying the movement acceleration of the crustacean from the image to a pattern typified in advance,
In the estimating step, the reference image information and the reference acceleration information obtained by obtaining the image of the movement of the crustacean in the past and applying the movement acceleration of the crustacean from the image to a pattern typified in advance. and three or more degrees of association with the possibility of molting, and further reference image information according to the image information acquired in the information acquisition step and reference image information according to acceleration information 2. The crustacean molting sign discriminating program according to claim 1, wherein the possibility of molting is estimated based on acceleration information. The information acquisition step further acquires food consumption information related to the amount of food consumed by the crustaceans,
In the estimation step, a combination having the reference image information and the reference food consumption information related to the food consumption of the crustacean acquired in the past and the degree of association with the possibility of molting are evaluated at three levels or more. and further estimating the possibility of molting based on the reference image information corresponding to the image information obtained in the information obtaining step and the reference food consumption information corresponding to the food consumption information. The crustacean molting sign discrimination program according to claim 1. The information acquisition step further acquires motion video information obtained by imaging the movement of the crustacean,
2. The crustacean molting sign discriminating program according to claim 1, wherein said estimating step utilizes said degree of association and further estimates the possibility of molting based on said motion image information. The crustacean molting sign discriminating program according to any one of claims 1 to 8, wherein the degree of association is composed of nodes of a neural network in artificial intelligence.

Images