Classifications

• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
  • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
  • A61B5/1118—Determining activity level
• • A—HUMAN NECESSITIES
  • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
  • A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
  • A01K11/00—Marking of animals
  • A01K11/006—Automatic identification systems for animals, e.g. electronic devices, transponders for animals
• • A—HUMAN NECESSITIES
  • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
  • A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
  • A01K29/00—Other apparatus for animal husbandry
  • A01K29/005—Monitoring or measuring activity, e.g. detecting heat or mating
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
  • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
  • A61B5/1116—Determining posture transitions
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/40—Detecting, measuring or recording for evaluating the nervous system
  • A61B5/4005—Detecting, measuring or recording for evaluating the nervous system for evaluating the sensory system
  • A61B5/4023—Evaluating sense of balance
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/48—Other medical applications
  • A61B5/4806—Sleep evaluation
  • A61B5/4809—Sleep detection, i.e. determining whether a subject is asleep or not
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B2503/00—Evaluating a particular growth phase or type of persons or animals
  • A61B2503/40—Animals
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
  • A61B2562/02—Details of sensors specially adapted for in-vivo measurements
  • A61B2562/0219—Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
  • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
  • A61B5/6813—Specially adapted to be attached to a specific body part
  • A61B5/6822—Neck
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
  • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
  • A61B5/683—Means for maintaining contact with the body
  • A61B5/6831—Straps, bands or harnesses
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
  • A61B5/7235—Details of waveform analysis
  • A61B5/7253—Details of waveform analysis characterised by using transforms
  • A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms

Definitions

• Monitoring the state of health of animals is of importance in any sector in which animals are kept for professional purposes.
• dairy farming it is important to know when cows are in calf, in order to be able, for instance, to dry off the cow timely or to adapt care of the cow.
• Health monitoring of animals is therefore not confined to dairy farming but is also important in other sectors of animal farming.
• condition monitoring systems for animals including monitoring systems that for detennining the current condition of the animal utilize movement sensors.
• a problem is that the accuracy for determining the current condition (for example: standing, lying, eating, ruminating, walking) often leaves to be desired. This is because, for one thing, the registered movements in many cases could match different such conditions.
• the present invention contemplates the provision of an animal condition determination methodology and associated system, with which on the basis of a movement sensor accurate condition determination is possible.
• the invention according a first aspect thereof provides a method for determining the condition of an animal, the method comprising the steps of:
• step b. converting the movements measured in step a. into a
• the method according to the present invention is based on recognition of the most probable current condition on the basis of the energies in the respective frequency subregions in the frequency spectrum of the measurement.
• specific behaviors of an animal can be recognized by the movements the animal makes. These specific behaviors, however, are much more accurately distinguishable from each other through their being characterized by specific often-occurring frequencies and intensities thereof in the movement signal.
• step f. comprises: comparing, for each of a plurality of frequency subregions, the amount of energy in the respective frequency subregion as determined in step e. with each of a plurality of expectation values of the amount of energy in the frequency subregion, wherein each expectation value belongs to one condition of a plurality of conditions of the animal, for determining the current condition of the animal.
• This comparison step can be implemented in various manners.
• step f. can be carried out by determining, for each amount of energy determined in step e. and for each condition of a plurality of conditions, a probability value indicating the probability that the determined amount of energy belongs to the respective condition.
• This probability value can be determined on the basis of probability distribution data for the expectation values for each condition of a plurality of conditions and for each frequency subregion.
• the probability distribution data then indicate the probability that a measured amount of energy in a frequency subregion matches the respective condition.
• the probability distribution data of the conditions with which the measured amount of energy is to be compared may for instance be stored in a data memory.
• the probability distribution data comprise, for all frequency subregions per frequency subregion, a probability distribution profile which indicates the course of the probability value depending on the amount of energy. Comparison of the determined amount of energy in step e. against this probability distribution profile for the respective frequency subregion hence provides the above-mentioned probability value for the respective condition.
• step f. is therefore preferably carried out for a plurality of frequency subregions, and in particular - according to some embodiments - preferably for all frequency subregions of the frequency spectrum.
• an overall probability value - or a parameter that is proportional to the overall probability value - can then be calculated by compiling the calculated probability values for different frequency subregions for the respective condition.
• the method according to the invention to that end comprises a step: g. calculating for each of the plurality of conditions a total probability value for the respective condition, whereby the total probability value for the respective condition is calculated by multiplying by each other the probability values of the frequency subregions for that condition as determined in step f.
• the associated probability values for the condition of 'slapen' ['sleeping'] are, for example:
• the total probability value can then be determined according to the present embodiments, as follows:
• the total probability values found can be normalized because the probability that the animal is in one of these conditions (leaving aside which condition that is, exactly) must always be equal to 1, provided that the plurality of possible conditions that are taken into account in the comparison is complete (i.e. if there are no conditions anymore that the animal could be in but which are not taken into account in the measurement).
• the plurality of possible conditions that are taken into account in the comparison is complete (i.e. if there are no conditions anymore that the animal could be in but which are not taken into account in the measurement).
• the conditions of the plurality of conditions relate to: stand ruminating, lie ruminating, stand resting, lie resting, eating, sleeping, walking, and ⁇ balance' which concerns all other possible conditions of the animal other than stand ruminating, lie ruminating, stand resting, lie resting, eating, sleeping and walking.
• the conditions included in the measurement can comprise one or more or all of the above conditions, with or without the balance mentioned.
• the invention is not limited to the use of all above-mentioned conditions, but can also be applied on the basis of some of them.
• additional conditions are used in the method which are not specifically identified here.
• the method furthermore comprises a step h. in which at least one group of conditions is formed, wherein the group comprises a subset of the plurality of
• stand ruminating and stand resting may be categorized under the group of conditions
• step h a plurality of different groups are formed.
• the conditions in step h. of each group can hence comprise a common activity of the animal such as standing or lying.
• a particular grouping to be used that may be formed in step h. concerns, according to a yet further embodiment, a group relating to stand ruminating, stand resting, eating and the balance or he resting, lie raminating and sleeping. By grouping these combinations this way, we can distinguish between the two conditions of standing or lying.
• the time period in which the movements are measured with the movement sensor can be suitably chosen for obtaining an accurate condition determination. Measuring the movements with the aid of the movement sensor may for instance be carried out during the time period to be measured by taking a series of sequential samples.
• the steps a. - f. and optionally the step g. and/or the step h. are carried out for mutually different time periods.
• the measurement may for instance be repeated periodically (for example, every 30 seconds).
• the time periods may be sequentially linked up, with measuring hence being done continuously but with the results per time period being processed according to frequency spectrum and further analyzed as described.
• Determining the frequency spectrum in step c. can, according to an embodiment, be implemented by carrying out a Fourier transformation (FT) of the movement signal.
• FT Fourier transformation
• the frequency subregions of some embodiments may in step d. be chosen so as to correspond to a plurality of bins of the frequency spectrum obtained via FT.
• the information obtained with the method about conditions of the animal for the different time periods can be collected for further processing.
• the total time span within which the animal is in a specific condition can be established by measurement, and be sent to a central server where these data are stored and/or further analyzed.
• the invention provides a system for detennining the condition of an animal, comprising a movement sensor which is configured to be attached to an animal for measuring movements of the animal, and a signal processing unit for processing the received information, wherein the system is configured to form a movement signal that represents the measured movements of the animal during a defined time period and wherein the signal processing unit is configured to carry out the following steps:
• step f. comprises: comparing, for one or more frequency subregions, the amount of energy determined in step e. with an expectation value belonging to at least one condition for determining the condition of the animal.
• the movement sensor can comprise, for example, an accelerometer or G-sensor, arranged on a tag worn by the animal.
• the tag to be worn by the animal is formed by a collar which can for instance be hung around the neck of a cow.
• the signal processing unit may also be on the tag. In effect, both the measurement and the condition determination can in their entirety take place on the tag. These data could then, later or simultaneously, be sent, or transferred, to a central processing system.
• data communication means may be present on the tag, such as, for example, a communication unit for wireless communication via WIFI or mobile data communication (GPRS, UMTS, LTE, etc.).
• WIFI wireless communication
• GPRS UMTS
• LTE Long Term Evolution
• Figure 1 is an illustration of a system according to the present invention
• Figure 2 shows a tag for use in a system according to the present invention
• Figure 3 is a schematic representation of sample-taking in a method according to the invention.
• Figure 4 shows a probability distribution graph of the expectation values for energies in a frequency subregion per condition
• Figure 5 shows a condition observation obtained with a method according to the present invention
• Figure 6 is a schematic representation of a method according to the present invention.
• FIG 1 schematically shows a system 1 according to the present invention.
• a cow 3 wears a collar 5 on which, among other things, an accelerometer or g-sensor is present.
• the collar 5 shown hangs over the neck of the cow 3, but one skilled in the art will understand that a collar 5 suspended under the neck can also be applied.
• Figure 2 shows a schematic representation of the collar 5 that is worn by the cow 3 in Figure 1.
• the collar 5 comprises an accelerometer 22 with which movements of the cow can be measured.
• the movement sensor 22 passes these measured values on to a signal processing unit 23. With these data, in the signal processing unit 23 (or other processing unit communicatively connected therewith) the current condition of the cow 3 can be established.
• This condition indicates the activity of the animal, and can hence comprise, for example, stand ruminating, lie ruminating, stand resting, lie resting, eating, sleeping, walking, and Ibalance' which concerns all other possible conditions of the animal other than stand ruminating, lie ruminating, stand resting, lie resting, eating, sleeping and walking.
• the method according to the invention in the embodiment shown is mainly carried out in the central signal processing unit 23, although the invention may also be implemented differently, whereby signal processing could for instance take place centrally.
• the collar 5 can further comprise a memory 25 or other data storage medium, in which are stored the
• the signal processing unit 23 can retrieve these data from another storage medium, if necessary obtained by wireless data
• the central processing unit 23 is furthermore connected with a data communication unit comprising an antenna 26 for forwarding measuring data, such as the established conditions.
• a data communication unit comprising an antenna 26 for forwarding measuring data, such as the established conditions.
• other data may be transmitted as well, such as the measured movement signal, the frequency spectrum, or the energies in the frequency subregions.
• FIG. 1 the forwarding of these data from the collar 5 to a central system 8 is schematically represented with wireless data signal 15.
• the central server 8 comprises a central processing unit 9 connected with a memory 10 on which the data can be stored and later be processed.
• central processing unit 9 is connected with data
• the central processing unit 8 is configured to receive wireless data signals from a plurality of collars such as collar 5, for condition monitoring of a plurality of animals at the same time.
• Data can be collected with the aid of the collar 5 during a particular time period. If possible, the data are collected periodically during a particular time period. Schematically, this is represented in Figure 3.
• Figure 3 it is shown that during a time period of, for example, five seconds, indicated by arrow 33, the movement sensor of the collar 5 takes multiple samples in order to record the movement. Every 30 seconds the collar 5 performs such a measurement as is represented by the successive
• measuring series 34 Between the measurements 33 and 34 is a particular time span in which no measuring is done. In this intervening period between the measurements 33 and 34, the collar 5 can be passive. However, in that period, other measurements may be performed with collar 5, as is indicated in Figure 3 by the periodic taking of samples such as sample 30. The taking of such intermediate samples is entirely optional and is not part of the present invention.
• the collar 5 can perform an ongoing measurement, whereby the movement sensor continuously takes samples of the movements made by the cow.
• the obtained samples can be divided up into time periods of, for example, five seconds, and be analyzed per time period according to the present invention.
• the obtained movement data are converted into a frequency spectrum. This can be done, for example, with the aid of Fast Fourier transformation (FFT). With Fast Fourier transformation the measured energy is divided up into frequency subregions (bins) and stored in the memory 25 of the collar 5. The frequency subregions, in an
• the alternative embodiment can also cover more than one bin.
• the current condition of the animal is obtained from this information in a predetermined manner.
• the condition determination takes place, according to a special embodiment of the invention, by comparing the measured energy value per frequency subregion, hence per bin in the present example, with a
• FIG 4 an illustrative representation is shown of the probability distribution for some eight different conditions for a specific frequency subregion.
• the probability distribution such as probability distribution curve 38, indicates what the probability (P) is that a particular measured amount of energy (E) matches a particular condition (in the case of curve 38 it is lie ruminating').
• the horizontal axis plots the measured energy E
• the vertical axis shows the probability P.
• the adjacent curve 39 indicates the probability distribution for the condition of 'stand raminating'.
• the probability that, based on the measurement in the respective frequency subregion, the cow is in the 'stand ruminating' condition is 0.09, and this condition is therefore, on the ground of the comparison of this one frequency subregion, more likely.
• the measured energy E is compared with the probability distributions for each of the conditions.
• the obtained probability values P for all frequency subregions are multiplied by each other for obtaining a quantity that indicates the total probability value for that condition.
• the condition with the highest total probability value is the current condition which the cow 3 is probably in at that moment.
• Figure 5 schematically indicates the measured probability values during a particular time span for a cow.
• the probability value for each of the eight conditions is represented. From the graph 40 it can be inferred that the cow at the beginning of the measurement, as indicated by probability curve 42, was sleeping. Because there is some similarity between movements in the condition of 'sleeping' and movements in the condition of lie resting * , it can be seen that in graph 40 the condition of lie resting', indicated by curve 46, still provides a relatively high probability value. From the measured measuring signal, it seems it can be convincingly established that the cow was in the condition of 'sleeping 1 (curve 42). The subsequent conditions of 'eating * 43, 'ruminating' 45, and again 'sleeping' 44 indicate the activities of the cow during the 24-hour period.
• FIG. 6 is a schematic representation of the method according to the present invention.
• the method starts with step 100 (step a) in which the movements of the animal are measured with the aid of the movement sensor during a particular time period (for example, time period 33).
• step 102 step b) the movements measured in step 100 are converted into a
• step 104 the frequency spectrum of the movement signal as determined in step 102 is established.
• step 106 this frequency spectrum is divided up into frequency subregions. Possibly, a frequency subregion may coincide with a single bin, but a frequency subregion can also contain several bins of the frequency spectrum, as the skilled person will
• step 108 for a plurality of the frequency subregions, per frequency subregion, the amount of energy in that respective subregion is determined. This is the amount of energy that will then, in step 110 (step i), be compared with the expectation value, in particular the probability distribution of the expectation value of the energy, for the different conditions.
• step 110 this comparison is done by comparing, for each of the conditions and for each frequency subregion, the measured amount of energy with the probability distribution curves (as schematically shown in Figure 4) to calculate therefrom a probability value for each condition.
• step 112 (step g) be multiplied by each other, for each condition.
• step 112 a a
• step 114 step h
• particular conditions may be put together to form a group.
• the probabilities for 'stand ruminating' and 'stand resting' may be grouped into a group
• the condition information thus eventually obtained is sent via the wireless data communication signal 15 to the central server 8 for further processing.
• This further processing can consist in summation of the probability values of conditions within the group, or selection of a highest probability value of a condition within the group.
• Other possible groups of conditions are, for example, a group comprising stand ruminating, stand resting, eating, and a balance.
• Yet another group can comprise the following conditions: lie resting, lie ruminating, and sleeping.
• the data may be processed by server 8, for example for compiling a graph as shown in Figure 5.
• the activities of several cows may be compared with each other, or with a data history for the respective cow, or with reference values for different state conditions (for example, great appetite or none, unexpectedly high or comparatively low sleeping and/or rest activity, cow is very active or restless).

Landscapes

• Life Sciences & Earth Sciences (AREA)
• Health & Medical Sciences (AREA)
• Engineering & Computer Science (AREA)
• Biophysics (AREA)
• Animal Behavior & Ethology (AREA)
• General Health & Medical Sciences (AREA)
• Veterinary Medicine (AREA)
• Pathology (AREA)
• Public Health (AREA)
• Biomedical Technology (AREA)
• Heart & Thoracic Surgery (AREA)
• Medical Informatics (AREA)
• Molecular Biology (AREA)
• Surgery (AREA)
• Physics & Mathematics (AREA)
• Environmental Sciences (AREA)
• Physiology (AREA)
• Dentistry (AREA)
• Oral & Maxillofacial Surgery (AREA)
• Animal Husbandry (AREA)
• Biodiversity & Conservation Biology (AREA)
• Birds (AREA)
• Zoology (AREA)
• Computer Networks & Wireless Communication (AREA)
• Neurology (AREA)
• Neurosurgery (AREA)
• Anesthesiology (AREA)
• Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Applications Claiming Priority (2)

Publications (1)

Family

ID=55178284

Family Applications (1)

Country Status (3)

Families Citing this family (1)

Family Cites Families (3)

• 2015
  • 2015-10-06 NL NL2015576A patent/NL2015576B1/nl active
• 2016
  • 2016-10-05 EP EP16784991.8A patent/EP3358946A1/en active Pending
  • 2016-10-05 WO PCT/NL2016/050685 patent/WO2017061860A1/en active Application Filing

Also Published As

Similar Documents

Legal Events