JP6635968B2 - Behavior identification device, behavior identification method, and program - Google Patents

Description

  The present invention relates to a behavior specifying device, a behavior specifying method, and a program.

  The milking period of a dairy cow is after the dairy cow has been mated (artificial insemination) to produce a calf (after calving), and this period is called the lactation period. It is known that the lactation period is about 305 days. In general, milking is stopped about 60 days before the scheduled delivery date in preparation for the next delivery. This 60-day period is called the dry period. Dairy cows repeat the calving, lactation and dry periods every year.

  Dairy farmers who raise dairy cows need to breed (artificial insemination) dairy cows every year during the dry period in order to continuously milk from dairy cows. In mating dairy cows (artificial insemination), it is necessary to discover the estrus of dairy cows. In order to detect the estrus of dairy cows, external signs of dairy cows are confirmed, and actions that are frequently observed during estrus are confirmed. In addition, management of the estrus time using a breeding record using a ledger is also performed.

Ryo Abe, `` Basic Seminar on Agriculture, Basics of Livestock Raising '', New Edition, Agricultural and Fishing Village Cultural Association, April 2008, p.109, p.122-124.

  Here, for example, on a large-scale dairy farm where the number of breeding animals is several thousand or more, it is a heavy burden for dairy farmers to confirm external signs and behavior of each dairy cow. . On the other hand, for example, if the behavior of the dairy cow being bred is specified, and the behavior that is often seen at the time of estrus can be easily confirmed, the burden on the dairy farmer can be reduced.

  Further, by specifying the behavior of the dairy cow, it is possible not only to detect estrus but also to detect an abnormal behavior due to illness or injury, which can contribute to health management of the dairy cow.

  One embodiment of the present invention has been made in view of the above points, and has as its object to specify the behavior of livestock.

  In order to solve the above problem, an action specifying device for specifying the action of livestock, a storage means for storing acceleration data measured by an acceleration sensor attached to the livestock, and acceleration data stored in the storage means Acquiring means for acquiring one or more acceleration data during a predetermined time; index value calculating means for calculating a predetermined index value from the one or more acceleration data acquired by the acquiring means; A specification unit for specifying the behavior of the livestock based on the index value calculated by the calculation unit and a specific model for specifying the behavior of the livestock created in advance.

  The behavior of livestock can be specified.

It is a figure showing an example of the whole composition of the action identification system concerning a first embodiment. It is a figure explaining an example of action specification of a cow. FIG. 4 is a diagram illustrating an example of measurement data stored in a measurement data storage unit according to the first embodiment. It is a figure showing an example of an action specific model. FIG. 3 is a diagram illustrating an example of a functional configuration of an action identification processing unit according to the first embodiment. 5 is a flowchart illustrating an example of an action specifying process according to the first embodiment. It is a figure showing an example of the whole action identification system composition concerning a 2nd embodiment. It is a figure which shows an example in the case of standing up or lying down by air pressure analysis. FIG. 11 is a diagram illustrating an example of measurement data stored in a measurement data storage unit according to the second embodiment. It is a figure showing an example of functional composition of an action specific processing part concerning a 2nd embodiment. It is a flow chart which shows an example of action (stand up or lying down) specific processing concerning a 2nd embodiment. It is a figure explaining an example of an acquisition range of measurement data and reference atmospheric pressure data concerning a third embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. Hereinafter, a case where the behavior of a cow is specified as an example of livestock will be described. However, livestock is not limited to cattle.

[First embodiment]
<Overall configuration>
First, the overall configuration of the behavior identification system 1 according to the present embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of an overall configuration of a behavior identification system 1 according to the first embodiment.

  As shown in FIG. 1, a behavior identification system 1 according to the present embodiment transmits a behavior identification device 10 for identifying the behavior of a cow, one or more tags 20 attached to the cow, and a predetermined radio wave to the surroundings. One or more leaky coaxial antennas 30 are included. In addition, it is preferable that the tag 20 is fixedly attached to the neck of the cow.

  The tag 20 is a device attached to a cow. One tag 20 is attached to one cow. The tag 20 includes an acceleration sensor that measures the acceleration (acceleration in three axes of the X axis, the Y axis, and the Z axis) of a cow wearing the tag 20, and the reception intensity (RSSI) of a radio wave received from the leaky coaxial antenna 30. : Received Signal Strength Indicator).

  The tag 20 transmits measurement data including the acceleration sensor value measured by the acceleration sensor and the RSSI value measured by the radio wave sensor to the behavior identification device 10 at every predetermined time (for example, every two seconds). The measurement data transmitted to the behavior identification device 10 is accumulated (stored) in a measurement data storage unit 200 described later.

The leaky coaxial antenna 30 is an antenna installed at a predetermined place such as a feed place or a water place in a barn. The leaky coaxial antenna 30 transmits a predetermined radio wave to the surroundings by the leaky coaxial cable. Hereinafter, when distinguishing between the leaky coaxial antenna 30 installed in the feeding ground and the leaky coaxial antenna 30 installed in the water place, the “leakage coaxial antenna 30 ₁ ” and the “leakage coaxial antenna 30” are respectively used. 30 ₂ ".

  The behavior identification device 10 is one or more computers that identify the behavior of a cow. The behavior identification device 10 includes an behavior identification processing unit 100, a measurement data storage unit 200, and an behavior identification model 300.

  The behavior identification processing unit 100 identifies the behavior of the cow based on the measurement data stored in the measurement data storage unit 200 and the behavior identification model 300. The behavior identification processing unit 100 is realized by processing that causes one or more programs installed in the behavior identification device 10 to be executed by a CPU (Central Processing Unit) or the like.

  The measurement data storage unit 200 stores the measurement data received from the tag 20. The measurement data storage unit 200 can be realized by using an auxiliary storage device such as a hard disk drive (HDD) or a solid state drive (SSD).

  The action specifying model 300 is a model for specifying an action from an acceleration sensor value included in the measurement data. The action specifying model 300 is created in advance by a machine learning method such as an SVM (Support Vector Machine) according to the type of livestock and the type of action to be specified. The behavior identification model 300 is stored in, for example, an auxiliary storage device such as an HDD or an SSD.

  The configuration of the behavior identification system 1 shown in FIG. 1 is an example, and another configuration may be used. For example, the behavior identification device 10 may be configured by a plurality of computers. Further, for example, a device (such as a cloud server) connected to the behavior identification device 10 via a network may have a part of the functions of the behavior identification processing unit 100. Further, for example, instead of the tag 20, the cow may be equipped with an acceleration sensor and a radio wave sensor.

<Identification of cow behavior>
Here, the behavior of the cow identified by the behavior identification system 1 according to the present embodiment and an outline of the identification method will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of identifying the behavior of a cow.

  First, it is assumed that the behaviors of the cow identified by the behavior identification system 1 according to the present embodiment include, in the order of small motion, four items: "stand up", "lying down", "ruminate", and "activity". In addition, the “activity” is further categorized into three, “feeding”, “walking”, and “drinking”. Therefore, in the present embodiment, it is specified which of the six behaviors “coasting”, “lying down”, “rubbing”, “foraging”, “walking”, and “drinking” is performed by the cow. It shall be.

  "Standing" refers to a state where a cow is standing. "Lying down" refers to a state in which a cow is lying down. "Rumming" refers to a state in which a cow is performing rumination (returning food once swallowed to the mouth and chewing it again). “Activity” is a state in which a cow is performing any of “feeding”, “walking”, and “drinking”. "Eating" refers to the state in which a cow is eating food. “Walking” refers to a state where a cow is walking. "Drinking water" is a condition in which a cow is drinking water.

  Whether the cow is performing the “standing”, “lying”, “rubbing”, or “activity” behavior is specified by the motion intensity analysis. In the motion intensity analysis, based on the acceleration sensor value included in the measurement data and the behavior identification model 300, whether the behavior of the cow is “standing”, “lying”, “ruminating”, or “activity” To identify. More specifically, in the motion intensity analysis, the acceleration sensor value during a predetermined time (for example, 10 minutes) is converted from a predetermined index value (the maximum value of the swing width of the L2 norm of the acceleration sensor value during the predetermined time and The L2 norm of the acceleration sensor value is calculated. Note that the maximum value of the swing width of the L2 norm is the difference between the average value of the L2 norm of the acceleration sensor value during a predetermined time and the value of the L2 norm of each speed sensor value during the predetermined time. The absolute value is the maximum value.

  Then, in the behavior identification model 300 classified into four regions of “standing”, “lying”, “rubbing”, and “activity”, which of these four regions includes a point indicating the calculated index value? Identify the action by

In addition, when the activity is specified as “activity” by the motion intensity analysis, the position analysis determines which behavior of the cow is “feeding”, “walking”, or “drinking”. In the position analysis, based on the RSSI value included in the measurement data and a predetermined threshold, the behavior of the cow is specified as any one of “feeding”, “walking”, and “drinking”. More specifically, the position analysis, if the RSSI value of the radio wave received from the leaky coaxial antenna 30 ₁ which is disposed to feed field, has exceeded a predetermined threshold value (i.e., if the cow is in the feeding area) Specify "foraging". Similarly, RSSI value of the radio wave received from the installed leaky coaxial antenna 30 ₂ water field, if it exceeds a predetermined threshold value (i.e., if the cow is in the water field) identifies the "drinking". On the other hand, when neither of these is present (that is, when there is neither a feeding place nor a water place), it is specified as “walking”.

  When a tag (GPS) receiver or the like is included in the tag 20, for example, the position analysis may be performed using the position information acquired from the GPS receiver. In this case, from the position information acquired from the tag 20, it is sufficient to specify whether the cow is at the feeding place, at the water place, or at neither the feeding place nor the water place.

  As described above, the behavior identification system 1 according to the present embodiment uses the four values of “standing”, “lying”, “ruminating”, and “activity” based on the acceleration sensor value received from the tag 20 attached to the cow. Identify actions. When the behavior of the cow is specified as “activity”, the behavior identification system 1 according to the present embodiment further calculates “feeding”, based on the RSSI value received from the tag 20 attached to the cow. The three actions of “walking” and “drinking” are detailed. Thereby, it is possible to specify whether the behavior of the cow is “standing”, “lying”, “ruminating”, “foraging”, “walking”, or “drinking”.

  Therefore, by displaying the specified behavior of the cow on, for example, the display device (display or the like) of the behavior identification device 10, it is possible to easily confirm the behavior that is often seen during estrus. In addition, it leads to early detection of abnormal behavior due to illness, injury, and the like, and health management of cattle can be easily performed.

<Measurement data stored in measurement data storage unit 200>
Here, the measurement data stored in the measurement data storage unit 200 according to the present embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating an example of the measurement data stored in the measurement data storage unit 200 according to the first embodiment. Note that when the measurement data is received from the tag 20, the behavior identification device 10 may cause the behavior identification processing unit 100 to store (accumulate) the received measurement data in the measurement data storage unit 200.

  As shown in FIG. 3, the measurement data storage unit 200 stores one or more measurement data for each tag ID for identifying a tag. Since one tag 20 is attached to one cow, the tag ID may be information for identifying a cow (individual cow identification information).

  The measurement data includes the date and time, the acceleration sensor value, and the RSSI value. The date and time is, for example, the date and time when the tag 20 transmitted the measurement data. Note that the date and time may be the date and time when the behavior identification device 10 receives the measurement data.

  The acceleration sensor value is a value of an acceleration measured by an acceleration sensor included in the tag 20. The acceleration sensor value includes an X component indicating an acceleration component in the X-axis direction, a Y component indicating an acceleration component in the Y-axis direction, and a Z component indicating an acceleration component in the Z-axis direction. For example, the measurement data at the date and time “t1” includes an X component “X1”, a Y component “Y1”, and a Z component “Z1” of the acceleration sensor value.

The RSSI value is an RSSI value measured by a radio wave sensor included in the tag 20. The RSSI value is, for example, include the RSSI value of the radio wave received from the leaky coaxial antenna 30 ₁ which is installed in the feeding stations, and radio waves RSSI values received from the leaky coaxial antenna 30 ₂ installed in the water field It is. For example, the measurement data of the date and time "t1", RSSI received RSSI values received from the leaky coaxial antenna 30 ₁ which is installed in the feeding grounds and "r11", the leaky coaxial antenna 30 ₂ installed in the water field The value “r12” is included.

  As described above, the measurement data stored in the measurement data storage unit 200 according to the present embodiment accumulates (stores) the measurement data including the date and time, the acceleration sensor value, and the RSSI value for each tag ID. Have been.

<Behavior identification model 300>
Here, an action specifying model 300 for specifying an action from the acceleration sensor value included in the measurement data will be described with reference to FIG. FIG. 4 is a diagram illustrating an example of the behavior identification model 300.

  As shown in FIG. 4, the behavior identification model 300 has a horizontal axis representing the maximum value of the amplitude of the L2 norm of the acceleration sensor value during a predetermined time (for example, 10 minutes), and a vertical axis representing the standard deviation of the L2 norm. In this case, the relationship is shown as a relationship graph showing the relationship between the maximum value and the standard deviation of the swing width and the action.

  For example, when the maximum value and the standard deviation of the swing width of the L2 norm of the acceleration sensor value for a certain 10 minutes are included in the area D1, the behavior of the cow for the 10 minutes is specified as “standing”. In addition, for example, when the maximum value and the standard deviation of the amplitude of the L2 norm of the acceleration sensor value for a certain 10 minutes are included in the area D2, the behavior of the cow during the 10 minutes is specified as “lying down”.

  Similarly, for example, when the maximum value and the standard deviation of the amplitude of the L2 norm of the acceleration sensor value for a certain 10-minute period are included in the area D3, the behavior of the cow for the 10-minute period is specified as "ruminating". In addition, the area D3 specified as “ruminating” may be further divided into “ruminating (raising)” that ruminates while standing, and “ruminating (raising)” that ruminates while lying down. .

  Similarly, for example, when the maximum value and the standard deviation of the amplitude of the L2 norm of the acceleration sensor value for a certain 10 minutes are included in the area D4, the behavior of the cow during the 10 minutes is specified as “activity”. .

  Although the example illustrated in FIG. 4 illustrates a case where the respective regions D1 to D4 of the behavior identification model 300 do not overlap each other, a portion where two or more of the respective regions D1 to D4 overlap each other. May be present.

  As described above, the behavior identification model 300 is a model in which a region representing the relationship between the maximum value and the standard deviation of the L2 norm of the acceleration sensor value during a predetermined time (for example, 10 minutes) and the behavior of the cow is defined. is there. Such an action specifying model 300 is created in advance by a machine learning method such as SVM. The SVM is an example, and may be created by various machine learning methods such as a neural network. Further, for example, even when the cow performs the same operation, the specific acceleration sensor value differs depending on the type of the acceleration sensor and the like. However, the positional relationship between the areas D1 to D4 indicating the respective actions is substantially fixed.

  Hereinafter, the maximum value of the swing width of the L2 norm is also simply referred to as “the maximum value of the L2 norm” or “the maximum value”.

<Functional configuration of action identification processing unit 100>
Next, a functional configuration of the behavior identification processing unit 100 according to the present embodiment will be described with reference to FIG. FIG. 5 is a diagram illustrating an example of a functional configuration of the behavior identification processing unit 100 according to the first embodiment.

  As illustrated in FIG. 5, the behavior identification processing unit 100 includes an acquisition unit 101, a preprocessing unit 102, an index value calculation unit 103, and an behavior identification unit 104.

  The acquisition unit 101 acquires measurement data from the measurement data storage unit 200. At this time, the acquisition unit 101 acquires measurement data for a predetermined time (for example, 10 minutes) from the measurement data storage unit 200 for each tag ID.

  The preprocessing unit 102 performs preprocessing on the measurement data acquired by the acquisition unit 101. The pre-processing includes, for example, a process of complementing loss (resampling) of measurement data, a process of removing noise, and the like. The preprocessing unit 102 calculates the L2 norm of the acceleration sensor value included in the measurement data after the loss complement, and performs a noise removal process using the calculated L2 norm.

  The index value calculation unit 103 calculates an index value from the L2 norm after the pre-processing by the pre-processing unit 102. For example, the index value calculation unit 103 calculates the maximum value and the standard deviation from the L2 norm after the preprocessing as the index value.

  The action specifying unit 104 determines four actions (“stand up”, “lying down”, “ruminate”, and “activity”) from the maximum value and the standard deviation calculated by the index value calculation unit 103 and the action specifying model 300. Identify. Further, when the “activity” is specified above, the action specifying unit 104 further specifies a detailed action (“feeding”, “walking”, or “drinking”) from the RSSI value included in the measurement data. I do. The action specifying unit 104 may specify the above four actions based on the maximum value and the standard deviation and a processing result of a program or the like that generates data equivalent to the action specifying model 300.

  The information indicating the action specified by the action specifying unit 104 may be stored in, for example, a DB (database) or a file realized by an auxiliary storage device such as an HDD or SSD, or may be displayed on a display or the like. It may be displayed on the device. Further, the information may be output to another device (for example, a PC, a smartphone, a tablet terminal, or the like) connected to the behavior identification device 10.

<Action identification processing>
Next, the action specifying process according to the present embodiment will be described with reference to FIG. FIG. 6 is a flowchart illustrating an example of the behavior specifying process according to the first embodiment. The action specifying process shown in FIG. 6 may be executed, for example, at a preset date and time, or may be repeatedly executed at predetermined time intervals (for example, every 24 hours).

  First, the acquisition unit 101 acquires measurement data for a predetermined time (for example, 10 minutes) for each tag ID from the measurement data storage unit 200 (step S11). As described above, the acquisition unit 101 acquires measurement data in a predetermined time unit (for example, 10 minutes) for each cow (tag ID) from the measurement data storage unit 200. In addition, such a predetermined time is not limited to 10 minutes, and for example, the user of the behavior identification device 10 can set an arbitrary time.

In the following, measurement data 1 for 10 minutes of the tag ID "Tag1", measured data 2, ..., when the measured data _{N 1} is obtained by the obtaining unit 101 continues the description.

  Next, the preprocessing unit 102 performs preprocessing on the measurement data acquired by the acquisition unit 101 (Step S12). That is, the pre-processing unit 102 performs a missing data complementing (resampling) process, a noise removal process, and the like of the measurement data. The loss complementing process is a process of complementing a loss when data cannot be acquired in order to increase the accuracy of collected data. Further, the noise removal processing is processing for removing data indicating instantaneous motion of the cow (for example, an operation of instantly shaking the body or an operation of instantly shaking the body).

Next, the index value calculation unit 103 calculates an index value (the maximum value and the standard deviation of the L2 norm) from the L2 norm after the preprocessing by the preprocessing unit 102 (Step S13). That is, to calculate the pretreated L2 norm a1, a2, a standard deviation σ and the maximum value m of · · · aN _3. The maximum value m is, L2 norm a1, a2, and the average value of · · · aN _3, the maximum value of the difference between the L2 norm ai (i = 1, ···, N 3).

  Next, the behavior specifying unit 104 uses the standard deviation σ and the maximum value m calculated by the index value calculating unit 103 and the behavior specifying model 300 to determine four behaviors (“stand up”, “lie down”, “ruminate”, and "Activity") is specified (step S14). That is, the action specifying unit 104 specifies which of the areas D1 to D4 on the action specifying model 300 contains the standard deviation σ and the maximum value m calculated by the index value calculating unit 103, Identify actions.

  Next, the action specifying unit 104 determines whether or not the action specified in step S14 is “activity” (step S15).

  In step S15, when it is determined that the specified action is not “activity” (that is, when the specified action is “standing”, “lying down”, or “rubbing”), the action specifying processing unit 100 performs the processing. Terminate.

On the other hand, when it is determined in step S15 that the specified action is “activity”, the action specifying unit 104 determines the measurement data 1, measurement data 2,. detailed behavior from the RSSI values contained in N ₂ ( "feeding", "walking", or "drinking") for specifying the (step S16).

That is, for example, measurement data 1, the measurement data 2, ..., measurement of the data _{N 2} RSSI values contained respectively, RSSI value of the radio wave is a predetermined received from the leaky coaxial antenna 30 ₁ and the leaky coaxial antenna 30 ₂ If the threshold is exceeded, the behavior specifying unit 104 specifies the detailed behavior as “eating” or “drinking”. On the other hand, if the RSSI value of the radio wave received from the leaky coaxial antenna 30 _1, both the RSSI value of the radio wave received from the leaky coaxial antenna 30 ₂ does not exceed the predetermined threshold, behavior identification unit 104, a detailed The action is specified as “walking”.

  As described above, the behavior identification system 1 according to the present embodiment can identify the behavior of the cow from the measurement data received from the tag 20 worn by the cow. At this time, the behavior identification system 1 according to the present embodiment uses the index value calculated from the acceleration sensor value included in the measurement data and the behavior identification model 300 created in advance by a machine learning method, thereby Identify actions. In particular, by using the standard deviation and the maximum value of the L2 norm as the index values, it is possible to specify “rumination”, which is a behavior specific to cattle, with high accuracy. In other words, it is possible to distinguish "ruminating", which is a behavior specific to cattle, from behaviors such as "standing" and "lying down" with high accuracy.

  The behavior of the cow identified in this way is displayed on, for example, a display device (display or the like) of the behavior identification device 10 and provided to a dairy farmer or the like, so that it is easy to confirm the behavior often seen when the cow is in estrus. Will be able to do it. In addition, it leads to early detection of abnormal behavior due to illness, injury, and the like, and health management of cattle can be easily performed.

[Second embodiment]
Next, a second embodiment will be described. In the first embodiment, four behaviors (“standing”, “lying”, “ruminating”, and “activity”) of the cow are specified using the acceleration sensor value. "May be difficult to distinguish from. That is, for example, even when the cow is "standing", the body may be moving little by little, while when the cow is "lying down", the body may be greatly moving. In such a case, in the above-described motion intensity analysis, it may be difficult to distinguish between “standing” and “lying” (in other words, “standing” and “lying” may be erroneously specified. ).

  Similarly, for example, even when a cow is "ruminating", it may be ruminating in a standing state, or may be ruminating in a lying state. In such a case, similarly, in the above-described motion intensity analysis, it may be difficult to distinguish between “standing” and “lying”.

  Therefore, in the second embodiment, a case will be described in which “standing” and “lying” are specified with higher accuracy by using an air pressure sensor.

  Note that, in the second embodiment, differences from the first embodiment will be mainly described, and portions having the same functions as those of the first embodiment and portions performing the same processing will be appropriately described. The description is omitted.

<Overall configuration>
First, the overall configuration of the behavior identification system 1 according to the present embodiment will be described with reference to FIG. FIG. 7 is a diagram illustrating an example of the entire configuration of the behavior identification system 1 according to the second embodiment.

  As shown in FIG. 7, the behavior identification system 1 according to the present embodiment includes a reference pressure sensor 40 that measures a reference pressure.

  The reference pressure sensor 40 is installed at a predetermined position in the barn (for example, on the ground in the barn), and measures the reference barometric pressure. The reference atmospheric pressure sensor 40 transmits the reference atmospheric pressure data including the reference atmospheric pressure sensor value indicating the measured atmospheric pressure to the behavior specifying device 10 at every predetermined time (for example, every 2 seconds). The reference atmospheric pressure data transmitted to the action specifying device 10 is stored (stored) in a reference atmospheric pressure data storage unit 400 described later.

  Further, the tag 20 according to the present embodiment further includes a barometric pressure sensor for measuring a barometric pressure. The tag 20 further transmits measurement data including a barometric pressure sensor value to the behavior identification device 10 at every predetermined time (for example, every two seconds). It should be noted that the tag 20 does not necessarily need to include a barometric pressure sensor. For example, a barometric pressure sensor may be attached to a cow separately from the tag 20.

  Furthermore, the behavior identification device 10 according to the present embodiment includes a reference atmospheric pressure data storage unit 400. The reference pressure data storage unit 400 stores the reference pressure data received from the reference pressure sensor 40. The reference atmospheric pressure data storage unit 400 can be realized using an auxiliary storage device such as an HDD or an SSD.

  The behavior identification processing unit 100 according to the present embodiment further includes the barometric pressure sensor value included in the measurement data stored in the measurement data storage unit 200 and the reference pressure data stored in the reference pressure data storage unit 400. Based on the reference barometric pressure sensor value, the behavior of the cow ("stand up" and "lying down") is specified.

<Specification of "Standing" and "Lying down" by barometric pressure sensor>
Here, among the behaviors of the cow specified by the behavior specifying system according to the present embodiment, an outline of a method of specifying “stand up” and “lying down” by the pressure sensor will be described with reference to FIG. FIG. 8 is a diagram illustrating an example of a case where standing or lying is specified by barometric pressure analysis.

  Whether the cow is performing the “standing” or “lying” behavior is specified by the barometric pressure analysis in addition to the motion intensity analysis described in the first embodiment. In the barometric pressure analysis, whether the behavior of the cow is “standing” or “lying down” is specified based on the barometric pressure sensor value included in the measurement data and the reference barometric pressure sensor value included in the reference barometric pressure data. More specifically, in the barometric pressure analysis, a difference between each barometric pressure sensor value and each reference sensor value during a predetermined time (for example, 24 hours) is calculated. Then, when the calculated difference (this difference is referred to as a “difference barometric pressure sensor value”) exceeds a predetermined threshold, it is identified as “lying down”. On the other hand, when the differential pressure sensor value does not exceed the predetermined threshold value, it is specified as “standing”. By using the differential pressure sensor value measured by the reference pressure sensor 40, for example, the measurement value of the pressure sensor included in the tag 20 attached to the cow is relatively independent of the weather (approach of low pressure, etc.). It can be determined whether the vehicle has gone up or down.

  By using the barometric pressure sensor value measured by the barometric pressure sensor as described above, if the differential barometric pressure sensor value exceeds the threshold value, it is specified as “lying down”, and if the differential barometric pressure sensor value does not exceed the threshold value, it is specified as “stand up”. Among them, “standing” and “lying” can be specified with high accuracy.

<Measurement data stored in measurement data storage unit 200>
Here, the measurement data stored in the measurement data storage unit 200 according to the present embodiment will be described with reference to FIG. FIG. 9 is a diagram illustrating an example of the measurement data stored in the measurement data storage unit 200 according to the second embodiment. Note that when the measurement data is received from the tag 20, the behavior identification device 10 may cause the behavior identification processing unit 100 to store (accumulate) the received measurement data in the measurement data storage unit 200.

  As shown in FIG. 9, one or more pieces of measurement data are stored in the measurement data storage unit 200 for each tag ID for identifying a tag. The measurement data according to the present embodiment further includes a barometric pressure sensor value. The barometric pressure sensor value is a barometric pressure value measured by a barometric pressure sensor included in the tag 20.

  As described above, the measurement data stored in the measurement data storage unit 200 according to the present embodiment includes the measurement date and time, the acceleration sensor value, the RSSI value, and the barometric pressure sensor value for each tag ID. Are stored (stored).

<Functional configuration of action identification processing unit 100>
Next, a functional configuration of the behavior identification processing unit 100 according to the present embodiment will be described with reference to FIG. FIG. 10 is a diagram illustrating an example of a functional configuration of the behavior identification processing unit 100 according to the second embodiment.

  As shown in FIG. 10, the behavior identification processing unit 100 according to the present embodiment further includes a difference value calculation unit 105. The functions of the acquisition unit 101 and the behavior identification unit 104 according to the present embodiment are different from those of the first embodiment.

  The acquisition unit 101 according to the present embodiment acquires measurement data for a predetermined period of time (for example, 24 hours) from the measurement data storage unit 200 for each tag ID when the behavior identification by the position analysis is performed. Is acquired from the reference atmospheric pressure data storage unit 400 during the period of time.

  The difference value calculation unit 105 calculates a difference pressure sensor value indicating a difference between the pressure sensor value included in the measurement data acquired by the acquisition unit 101 and the reference pressure sensor value included in the reference pressure data.

  Note that the preprocessing unit 102 may perform preprocessing on the measurement data acquired by the acquisition unit 101. In this case, the preprocessing unit 102 may perform a process of complementing the loss of the measured data, a process of removing noise (that is, a process of removing noise from the pressure sensor value), and the like. Then, in this case, the difference value calculation unit 105 calculates the difference pressure sensor value from the pressure sensor value included in the measurement data after the preprocessing performed by the preprocessing unit 102 and the reference pressure sensor value included in the reference pressure data. Good.

  The behavior identification unit 104 determines whether the cow's behavior is “standing” or “lying down” by determining whether or not the difference pressure sensor value calculated by the difference value calculation unit 105 exceeds a predetermined threshold. To identify. Note that the predetermined threshold may be, for example, an intermediate value between the maximum value and the minimum value of the differential pressure sensor values calculated from the pressure sensor values included in the measurement data acquired by the acquisition unit 101. This is because, for example, during 24 hours, a cow is considered to “stand” and “lie down” at least once.

  For example, when the tag 20 is worn on a cow collar or the like, the barometric pressure sensor value may increase due to the cow's “feeding” behavior or “drinking” behavior. This is because the cow is lowered from the standing state to feed and drink water. When the tag 20 is attached to a cow collar or the like, the height of the tag 20 from the ground when performing the “feeding” or “drinking” action is the ground of the tag 20 when the cow is “lying down”. Often the same as from. Therefore, the acquiring unit 101 acquires measurement data including the time period before and after the “feeding” or “water drinking” behavior is specified by the motion intensity analysis and the position analysis, and the barometric pressure sensor value included in the acquired measurement data. The intermediate value between the maximum value and the minimum value of the differential pressure sensor value calculated from the above can be used as the threshold value.

<Action (standing or lying down) specific processing>
Next, the action specifying process according to the present embodiment will be described with reference to FIG. FIG. 11 is a flowchart illustrating an example of an action (standing or lying down) specifying process according to the second embodiment. Note that the action specifying process illustrated in FIG. 11 may be executed, for example, at a preset date and time, or may be repeatedly executed at predetermined time intervals (for example, every 24 hours).

  First, the acquisition unit 101 acquires measurement data for a predetermined time (for example, 24 hours) from the measurement data storage unit 200 for each tag ID, and stores the reference pressure data for the predetermined time in the reference pressure data. It is obtained from the unit 400 (step S21).

In the following, measurement data 1 of a 24 hour period of the tag ID "Tag1", measured data 2, ..., and the measured data _{N 4,} reference atmospheric pressure data 1 for 24 hours, the reference atmospheric pressure data 2, ... , continuing with the case where the reference pressure data N ₄ is acquired by the acquisition unit 101. For the sake of simplicity, the description will be made on the assumption that the measurement data i and the reference atmospheric pressure data i (i = 1, 2,..., N ₄ ) are data at the same date and time.

  Next, the difference value calculation unit 105 calculates a difference pressure sensor value indicating a difference between the pressure sensor value included in the measurement data acquired by the acquisition unit 101 and the reference pressure sensor value included in the reference pressure data ( Step S22).

That is, the difference value calculation unit 105 calculates a difference pressure sensor value 1 between the pressure sensor value included in the measurement data 1 and the reference pressure sensor value included in the reference pressure data 1. Further, the difference value calculating unit 105 calculates a difference pressure sensor value 2 between the pressure sensor value included in the measurement data 2 and the reference pressure sensor value included in the reference pressure data 2. Similarly later, the difference value calculating unit 105 calculates the air pressure sensor value included in the measured data N _4, a differential pressure sensor value N ₄ with reference atmospheric pressure sensor value included in the reference pressure data N _4.

Next, the behavior identification unit 104 determines whether the difference barometric sensor value calculated by the difference value calculation unit 105 exceeds a predetermined threshold, and thereby determines whether the behavior of the cow is “standing” or “lying down”. It is determined which one is (step S23). That is, the behavior identification unit 104, differential pressure sensor value 1, the difference pressure sensor values 2, ..., by differential air pressure sensor value N ₄ to determine whether it exceeds a predetermined threshold, the behavior of the cow Specify whether the user is standing or lying down.

  For example, when a certain differential pressure sensor value exceeds a predetermined threshold, the behavior specifying unit 104 specifies the behavior of the cow at the date and time when the differential pressure sensor value was calculated as “lying down”. On the other hand, when a certain differential pressure sensor value does not exceed the predetermined threshold value, the behavior specifying unit 104 specifies the behavior of the cow at the date and time when the differential pressure sensor value is calculated as “standing”.

  The behavior specifying unit 104 may consider whether the behavior of the cow is “standing” or “lying down” in consideration of the result of the motion intensity analysis. More specifically, the barometric pressure analysis may not be performed on the date and time when the action is specified as “ruminating” or “activity” by the motion intensity analysis. On the other hand, when the behavior is identified as “standing” or “lying down” by the motion intensity analysis, the measurement data and the reference pressure data in a predetermined range including the specified date and time are acquired, and the pressure analysis is performed. Just do it.

  That is, if "rumination" or "activity" is specified by the motion intensity analysis, the barometric pressure analysis is not performed, while if "standing" or "lying" is specified by the motion intensity analysis, the barometric pressure analysis is performed. May be performed. Thus, when “standing” or “lying” is specified by the motion intensity analysis, pressure analysis for specifying “standing” or “lying” is performed with higher accuracy. As described above, the atmospheric pressure analysis may be performed according to the result of the operation intensity analysis.

  As described above, the behavior identification system 1 according to the present embodiment can identify the “stand-up” and “lying-down” behavior of the cow by the barometric pressure analysis using the barometric pressure sensor. Moreover, the behavior identification system 1 according to the present embodiment uses the barometric pressure analysis alone or in combination with the motion intensity analysis, so that the “standing” and “lying” behavior can be performed with higher accuracy than when the motion intensity analysis is used alone. Can be specified.

[Third embodiment]
Next, a third embodiment will be described. In the third embodiment, a case where the barn is of a free burn type will be described.

  As the barn, a free stall barn and a free barn barn are generally known. Unlike the free stall barn, the free barn barn often has a hill inside the barn. For this reason, in the free-burn barn, the behavior identification by the barometric pressure analysis may be erroneous.

  For example, it is assumed that the barometric pressure sensor value when the cow is “standing” on the plane below the hill is substantially the same as the barometric pressure sensor value when the cow is “lying” on the hill. In this case, “lying” on the hill may be erroneously identified as “standing”.

  Therefore, in the third embodiment, a description will be given of a case in which “standing” and “lying” are specified with high accuracy even in a free-burn barn by devising the acquisition range of the measurement data and the reference atmospheric pressure data.

  Note that, in the third embodiment, mainly the differences from the second embodiment will be described, and portions having the same functions as those of the second embodiment and portions performing the same processing will be appropriately described. The description is omitted.

<Acquisition of measurement data in freeburn barn>
If the barn is of the free burn type, the range between the measurement data and the reference pressure data acquired by the acquisition unit 101 is devised in step S21 in FIG. This will be described with reference to FIG. FIG. 12 is a diagram illustrating an example of an acquisition range of measurement data and reference atmospheric pressure data in a freeburn barn.

  As shown in FIG. 12, the cow is on the plane (below the hill) between time T1 and T2, climbs the hill between time T2 and T3, and is cow on the hill between time T3 and T4. Shall be In this case, in order to specify the behavior of the cow on the plane, the atmospheric pressure is analyzed using the measurement data and the reference atmospheric pressure data during the time T1 to T2 when the cow is on the plane. On the other hand, to specify the behavior of the cow on the hill, a barometric pressure analysis is performed using the measurement data and the reference atmospheric pressure data during the time T3 to T4 when the cow is on the hill.

  Whether the user is on a plane, climbing a hill, or on a hill can be specified using the acceleration sensor value and the barometric pressure sensor value. That is, for example, when the pressure sensor value changes little while the acceleration sensor value changes for a certain period of time, the cow can be identified as being on a plane. Also, for example, if both the barometric pressure sensor value and the acceleration sensor value change during a certain period of time, the cow can be identified as being climbing a hill. Further, for example, if it is specified that the cow is climbing a hill and then the cow is specified to be on a plane, the cow can be specified to be on the hill. It should be noted that during the downhill, it can be specified in the same way as during the uphill.

  It should be noted that there is a possibility that the cow "lys down" while climbing the hill (or while descending the hill). It is also possible that the cow "rises" while climbing the hill (or while climbing down the hill) and then "rises". In this case, for example, it may be specified from the change pattern of the acceleration sensor value or the change pattern of the atmospheric pressure sensor value while climbing the hill (or while descending the hill).

  As described above, the behavior identification system 1 according to the present embodiment can identify the “stand-up” and “lying-down” behavior of a cow by barometric pressure analysis using a barometric pressure sensor even in a free-burn barn.

  The present invention is not limited to the above-described embodiments specifically disclosed, and various modifications and changes can be made without departing from the scope of the claims.

REFERENCE SIGNS LIST 1 behavior identification system 10 behavior identification device 20 tag 30 leaky coaxial antenna 100 behavior identification processing unit 101 acquisition unit 102 preprocessing unit 103 index value calculation unit 104 behavior identification unit 200 measurement data storage unit 300 behavior identification model

Claims (7)

A behavior identification device that identifies the behavior of livestock,
Storage means for storing three-dimensional acceleration data measured by a three-axis acceleration sensor attached to the livestock;
Acquiring means for acquiring one or more three-dimensional acceleration data during a predetermined time from the three-dimensional acceleration data stored in the storage means;
An L2 norm of each of the one or more three-dimensional acceleration data acquired by the acquisition means is calculated, and a maximum value of the calculated one or more L2 norms and a standard deviation of the one or more L2 norms are used as index values. An index value calculating means for calculating as
Based on the index value calculated by the index value calculating means, and a specific model for specifying the behavior of the livestock created in advance, a specifying means for specifying the behavior of the livestock,
Have a,
The specific model is
An action specifying device , which is represented in a two-dimensional space in which the maximum value is a first axis and the standard deviation is a second axis, in an area where the index value and the action are associated with each other . The storage means,
Further, storing the radio wave intensity data measured by the radio wave sensor attached to the livestock,
The specifying means includes:
The behavior specifying device according to claim 1, wherein when the specified behavior of the livestock is a predetermined behavior, the detailed behavior of the livestock is specified based on the radio wave intensity data. The behavior includes a standing action indicating that the livestock is standing, and a lying behavior indicating that the livestock is lying down,
The storage means,
Furthermore, storing the atmospheric pressure data measured by the atmospheric pressure sensor attached to the livestock,
The specifying means includes:
The behavior specifying device according to claim 1 or 2 , wherein the standing action or the recumbent behavior of the livestock is specified based on the atmospheric pressure data. The specifying means includes:
The behavior specifying device according to claim 3 , wherein the standing action or the recumbent behavior of the livestock is specified based on the change pattern of the three-dimensional acceleration data or the change pattern of the atmospheric pressure data.   The behavior identification device according to claim 1, wherein the livestock is a cow. Behavior identification device that identifies the behavior of livestock,
A storage procedure for storing the three-dimensional acceleration data measured by the three-axis acceleration sensor attached to the livestock in a storage unit;
An acquisition procedure of acquiring one or more three-dimensional acceleration data during a predetermined time from among the three-dimensional acceleration data stored in the storage unit;
An L2 norm of each of the one or more three-dimensional acceleration data acquired by the acquisition procedure is calculated, and a maximum value of the calculated one or more L2 norms and a standard deviation of the one or more L2 norms are used as index values. Index value calculation procedure to calculate as
Based on the index value calculated by the index value calculation procedure and a specific model for specifying the behavior of the livestock created in advance, a specific procedure of specifying the behavior of the livestock,
The execution,
The specific model is
An action specifying method , wherein the index value and the action are represented in an area in a two-dimensional space in which the maximum value is a first axis and the standard deviation is a second axis . A program for causing a computer to function as each unit in the behavior specifying device according to any one of claims 1 to 5 .

Images