CN104077550A - Health index evaluating method and system for achieving animal behavior monitoring - Google Patents
Health index evaluating method and system for achieving animal behavior monitoring Download PDFInfo
- Publication number
- CN104077550A CN104077550A CN201410273554.9A CN201410273554A CN104077550A CN 104077550 A CN104077550 A CN 104077550A CN 201410273554 A CN201410273554 A CN 201410273554A CN 104077550 A CN104077550 A CN 104077550A
- Authority
- CN
- China
- Prior art keywords
- animal
- weighted value
- rfid
- translational speed
- residence time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a health index evaluating method and system for achieving animal behavior monitoring. The method comprises the steps that an RFID tag is put on each animal, and corresponding RFID tag collectors are arranged at animal activity points; the moving speed weighted value of each animal is obtained; the food scrambling capacity weighted value of each animal is obtained; the activity frequency weighted value of each animal is obtained; the sojourn time weighted value of each animal is obtained; the sum of the activity frequency weighted value and the sojourn time weighted value of each animal is obtained; the health index of each animal is judged based on the comprehensive weighted values of all the animals. According to the health index evaluating method and system, the animal behavior analyzing method adopted in the system is simple, practical and better suitable for collecting and analyzing mass data of large-scale breeding, the response of the system is accelerated, and the animal epidemic situation realizing time is shortened.
Description
Technical field
The present invention relates to information agriculture technical field, be specifically related to the method and system that a kind of health index of realizing animal behavior monitoring is evaluated.
Background technology
Along with agriculture development, the scale of the aquaculture of China is increasing, and cultivation density is more and more higher.But the observation method of the health of cultivated animal is still rested on to poultry feeders and regularly carry out the mode of colony's range estimation.This traditional approach cannot carry out careful observation to the situation of animal individual, can only to the health of animal population, assess by range estimation and staff's experience.This observed pattern can increase the test period of the improved test that carries out feed or breeding way.
Take poultry farming as example, and from early stage H1N1 to recent H7N9, bird flu is the nightmare of poultry farming always.These bird flus often can cause in same plant a large amount of poultry dead, its reason except avian influenza virus pathogenic strong, also because cannot carry out the early warning of epidemic disease at the initial stage of indivedual poultry morbidities.
Therefore need to a kind ofly can carry out to the health status of animal the method for comprehensive evaluation, for the different systems such as the animal condition monitoring in aquaculture, Disease Warning Mechanism, feed improvement are tested, breeding process information is reviewed provide evaluation foundation.
The feed of animal, the behavior such as perch, run are the important evidence of its Health and Disease of judgement.In recent years, some developed countries have obtained certain progress in to the research of animal behavior.Leroy T and Vranken E analyze the abnormal behaviour occurring under each state in hen growth course by image processing techniques, follow the tracks of hen growth course, and this method has been saved the time, has reduced labor cost.Australian Union's science and industrial research organizations sensor network are set up intelligent farm, and the necklace of wearing global position system GPS and wireless sensor node on stubbornness records the behavioural characteristic of relevant environment and ox.Kwong employing wireless sensor network technique is monitored cows to find disease and the situation such as crippled of ox.Nadimi etc. propose to adopt wireless sensor network node to measure the anglec of rotation and the movement velocity of ox neck, use the classify behavior of ox of classification tree.Yin makes the digital intelligent system that has proposed a kind of employing wireless sensor network monitoring milk cow behavioural characteristic, for predicting the situations such as oestrus of milk cow and disease.
Use image processing techniques to carry out to animal behavior the limitation that monitoring can be subject to image processing algorithm, its accuracy and resolution are not high, especially the identification of the id label code of animal and fast moving toy are restricted.
With the behavior of the careful monitoring of wireless sensor network energy animal, but due to breeding production process, there is the features such as strong destruction, high pollution, when system applies and breeding process, have several problems:
1) node is easily subject to animal unconscious destruction consciously;
2) node is easily subject to environmental pollution;
3) cost of node is higher;
4) be confined to node volume, node difficulty applies to toy.
Summary of the invention
The problem existing in view of the information acquisition end of above wireless sensor network, breeding production feature in the face of high pollution, strong destruction, small profits profit, the weakness of wireless sensor network information collection terminal can be avoided or reduce to native system, and develop the strong point of the mass data analysis of backstage cloud computing platform.At collection terminal with the strong sensor of reliability and only gather less essential information, and the center of gravity of system is placed on to background server, such as cloud computing server, from less Information Monitoring, excavate as far as possible many behavior characteristic information, rely on the powerful data mining capability analyzing animal behavior outcome of cloud computing server.
The invention provides a kind of method that health index of realizing animal behavior monitoring is evaluated, comprise the steps:
For every animal is worn RFID label, and at animal activity point, corresponding RFID label collector is set;
Based on RFID collector and speed behavioural characteristic function, obtain the translational speed of every animal, and to the translational speed of all animals based on normalized, obtain the translational speed weighted value of every animal;
Based on RFID collector and rob the food ability of robbing that food ability behavioural characteristic function obtains every animal, and to the food ability of robbing of all animals based on normalized, obtain the food ability of the robbing weighted value of every animal;
Based on RFID collector and motion frequency behavioural characteristic function, obtain the motion frequency of every animal, and to the motion frequency of all animals based on normalized, obtain the motion frequency weighted value of every animal;
The residence time of obtaining every animal based on RFID collector and residence time behavioural characteristic function, and to the residence time of all animals based on normalized, obtain weighted value residence time of every animal;
Calculate the aggregative weighted value of every animal, the translational speed weighted value that described aggregative weighted value is every animal, rob food ability weighted value, motion frequency weighted value and residence time weighted value sum;
Aggregative weighted value based on all animals is passed judgment on the health index of every animal.
The described translational speed step of obtaining every animal based on RFID collector and speed behavioural characteristic function is specially:
Utilize the distance of nearest two RFID collectors and the time of nearest two RFID collectors identification RFID label to obtain the translational speed of every animal.
Described normalized is specially:
Convert raw data to standardized normal distribution score value;
Normal distribution score value is obtained to the comprehensive evaluation value of every animal according to index comprehensive evaluation formula.
Accordingly, the system that the embodiment of the present invention also provides a kind of health index of realizing animal behavior monitoring to evaluate, comprising: the RFID label of wearing every animal, and the RFID label collector arranging at animal activity point;
And translational speed weighted value module, for obtain the translational speed of every animal based on RFID collector and speed behavioural characteristic function, and to the translational speed of all animals based on normalized, obtain the translational speed weighted value of every animal;
And rob food ability weighted value module, for based on RFID collector with rob the food ability of robbing that food ability behavioural characteristic function obtains every animal, and to the food ability of robbing of all animals based on normalized, obtain the food ability of the robbing weighted value of every animal;
And motion frequency weighted value module, for obtain the motion frequency of every animal based on RFID collector and motion frequency behavioural characteristic function, and to the motion frequency of all animals based on normalized, obtain the motion frequency weighted value of every animal;
And residence time weighted value module, for the residence time of obtaining every animal based on RFID collector and residence time behavioural characteristic function, and to the residence time of all animals based on normalized, obtain weighted value residence time of every animal;
Aggregative weighted value module, for calculating the aggregative weighted value of every animal, the translational speed weighted value that described aggregative weighted value is every animal, rob food ability weighted value, motion frequency weighted value and residence time weighted value sum;
Health index evaluation module, for the health index of every the animal of aggregative weighted value judge based on all animals.
Described translational speed weighted value module utilizes the distance of nearest two RFID collectors and the time of nearest two RFID collectors identification RFID label to obtain the translational speed of every animal.
Described normalized is specially:
Convert raw data to standardized normal distribution score value;
Normal distribution score value is obtained to the comprehensive evaluation value of every animal according to index comprehensive evaluation formula.
In the present invention, adopt RFID label collector as the behavior acquisition terminal of animal, only need wear ear tag pin ring etc. to animal, in the performances such as cost and antipollution, have absolute advantage; Compare conventional video monitoring method, relatively video method discrimination is low, cost is high, technical difficulty is large for the method that the present invention adopts.
The native system brief easily damaged Internet of Things collection terminal of trying one's best, and give full play to the powerful data mining capability of background server, gather the simplest two master datas, and produce a plurality of behavioural characteristics with data digging method, greatly strengthened system reliability, reduced the cost of system.The animal behavior analytical approach that system adopts is simple, practical, more can adapt to collection and the analysis of the mass data of large-scale farming, the response time of having accelerated system, has shortened the time that animal epidemics is realized.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skills, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is the method flow diagram that the health index of realizing animal behavior monitoring in the embodiment of the present invention is evaluated;
Fig. 2 is the system architecture schematic diagram that the health index of realizing animal behavior monitoring in the embodiment of the present invention is evaluated;
Fig. 3 is the concrete application scenarios schematic diagram that the health index of realizing broiler chicken behavior monitoring in the embodiment of the present invention is evaluated.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, rather than whole embodiment.Embodiment based in the present invention, those of ordinary skills, not making all other embodiment that obtain under creative work prerequisite, belong to the scope of protection of the invention.
Fig. 1 shows the method flow diagram that the health index of realizing animal behavior monitoring in the embodiment of the present invention is evaluated, and comprises the steps:
S101, for every animal, wear RFID label, and at animal activity point, corresponding RFID label collector is set;
S102, based on RFID collector and speed behavioural characteristic function, obtain the translational speed of every animal, and to the translational speed of all animals based on normalized, obtain the translational speed weighted value of every animal;
In the embodiment of the present invention, utilize the distance of nearest two RFID collectors and the time of nearest two RFID collectors identification RFID label to obtain the translational speed of every animal.
S103, based on RFID collector with rob the food ability of robbing that food ability behavioural characteristic function obtains every animal, and to the food ability of robbing of all animals based on normalized, obtain the food ability of the robbing weighted value of every animal;
S104, based on RFID collector and motion frequency behavioural characteristic function, obtain the motion frequency of every animal, and to the motion frequency of all animals based on normalized, obtain the motion frequency weighted value of every animal;
S105, the residence time of obtaining every animal based on RFID collector and residence time behavioural characteristic function, and to the residence time of all animals based on normalized, obtain weighted value residence time of every animal;
S106, calculate the aggregative weighted value of every animal, the translational speed weighted value that described aggregative weighted value is every animal, rob food ability weighted value, motion frequency weighted value and residence time weighted value sum;
S107, the aggregative weighted value based on all animals are passed judgment on the health index of every chicken.
It should be noted that, the normalized in the embodiment of the present invention is specially: convert raw data to standardized normal distribution score value; Normal distribution score value is obtained to the comprehensive evaluation value of every animal according to index comprehensive evaluation formula.
Accordingly, Fig. 2 also shows the system architecture schematic diagram that the health index of realizing animal behavior monitoring in the embodiment of the present invention is evaluated, and this system comprises: the RFID label of wearing every animal, and the RFID label collector arranging at animal activity point;
And translational speed weighted value module, for obtain the translational speed of every animal based on RFID collector and speed behavioural characteristic function, and to the translational speed of all animals based on normalized, obtain the translational speed weighted value of every animal;
It should be noted that, this translational speed weighted value module utilizes the distance of nearest two RFID collectors and the time of nearest two RFID collectors identification RFID label to obtain the translational speed of every animal.
And rob food ability weighted value module, for based on RFID collector with rob the food ability of robbing that food ability behavioural characteristic function obtains every animal, and to the food ability of robbing of all animals based on normalized, obtain the food ability of the robbing weighted value of every animal;
And motion frequency weighted value module, for obtain the motion frequency of every animal based on RFID collector and motion frequency behavioural characteristic function, and to the motion frequency of all animals based on normalized, obtain the motion frequency weighted value of every animal;
And residence time weighted value module, for the residence time of obtaining every animal based on RFID collector and residence time behavioural characteristic function, and to the residence time of all animals based on normalized, obtain weighted value residence time of every animal;
Aggregative weighted value module, for calculating the aggregative weighted value of every animal, the translational speed weighted value that described aggregative weighted value is every animal, rob food ability weighted value, motion frequency weighted value and residence time weighted value sum;
Health index evaluation module, for the health index of every the chicken of aggregative weighted value judge based on all animals.
It should be noted that, the RFID number of labels that animal is worn decides according to the quantity of letting animals feed, has all worn RFID label on every animal, and the RFID label collector arranging at animal activity point, generally in hen house outlet, frequent zone of action etc.Translational speed weighted value module, rob food ability weighted value module, motion frequency weighted value module and residence time weighted value module, aggregative weighted value module, health index evaluation module etc. run in server, it can provide for server the data of corresponding rfid system collection, by server, complete corresponding background process, thereby realize the accurate monitoring of animal etc.
It should be noted that, the normalized in the embodiment of the present invention is specially: convert raw data to standardized normal distribution score value; Normal distribution score value is obtained to the comprehensive evaluation value of every animal according to index comprehensive evaluation formula.
The present invention mainly using put formula cultivation in a suitable place to breed the animal behaviors such as domestic birds and animals as research object, by using the internet of things equipment monitoring animal behavior evaluatings such as RFID, wireless sensor network, for become more meticulous cultivation and disease warning system of animal provides data.In order to collect the practicality of enough evaluating and verification system, the present invention will be deployed in chicken farm, Jiang Gao town, and carry out the field test of a period of time.For the ease of comparing the result of manual observation and the result of system audit, the small-scale chicken group of this experimental selection is object of experiment.It is specific experiment object that system be take 33 animals of the formula of putting in a suitable place to breed cultivation of chicken farm fence.According to on-the-spot inspectional analysis, when having group, the daily routines of the animal in chicken farm also have certain individual difference.Daytime, most of animal all can be in a several fixing gathering activity of perching except feeding time.In more active animal Hui plant, run everywhere, sluggish animal can seldom be moved perching a little.
The movable habit that major part is put the animal of formula cultivation in a suitable place to breed is except feeding point feed, and several fix gregarious of being everlasting perch place activity.The present invention allows every animal wear RFID label band, and at several arrangement RFID label collector of fixedly perching, collector arrives with the frequency continuous acquisition of 3 times/second the id coding (also record gathers constantly simultaneously) that this perches animal a little, immediately uploads the data that collect with Radio Transmission Node.
It should be noted that, the animal in the embodiment of the present invention is the Culture style species such as poultry or domestic animal, such as Culture style species such as broiler chicken, meat duck, pork pig, mutton sheeps, is certainly also not limited to this type.The broiler chicken of take below describes whole implementation process in detail as introducing.
In validation test on the spot of the present invention for being bound RFID label pin ring on the pin of 23 broiler chicken testing, and the feeding point in plant is settled RFID label collector, LOAD CELLS and Radio Transmission Node, with this, read id coding, id due in and the body weight corresponding to id of every broiler chicken, and then just can analyze broiler chicken whose body weight, rob the sequencing that arrives feeding point while eating; In plant, mainly perch and settled RFID tag recognizer for broiler chicken group's two, from the id of broiler chicken, be coded in that distance between collection point displacement time of two RFID label collectors and two RFID label collectors just can analyze the speed of running of every broiler chicken, motion frequency and in behavioural characteristics such as habitat residence times between collection point.Deployed with devices is shown in Fig. 3.
By the speed of running of broiler chicken, rob food ability, motion frequency, in habitat four behavioural characteristics residence time, can immediately realize injured or infect the chicken of epidemic disease, by these four behavioural characteristics, add that the body weight of broiler chicken can differentiate the performance number grade of broiler chicken online.Sick and weak broiler chicken run speed slow, rob that food ability is low, motion frequency is low, in habitat residence time long, by index comprehensive evaluation method, the behavioural characteristic data of four of chicken are carried out to data mining, can immediately realize the colony that ill chicken; The chicken that quality grade is high run speed fast, rob that food ability is strong, motion frequency is high, in habitat residence time short, and body weight is moderate, by above four behavioural characteristics, adds that the body weight of chicken carries out cluster analysis, just can excavate the grade of the broiler chicken of different qualities.
System is mainly comprised of the intermediate circuit of RFID tag recognizer, LOAD CELLS, wireless sensor network node and various piece.Wherein RFID tag recognizer model is JT900A, and the scan period of setting is 300 milliseconds; LOAD CELLS model is YZC-1B, composition error≤± 0.030%; Wireless sensor network node model is GAINS3, and communication frequency is 433MHz.In RFID label band, chip model is F43.
In field test of the present invention, two RFID tag recognizer are installed in two main habitats, at hen house-playground passage, a RFID tag recognizer and LOAD CELLS are installed, as shown in Figure 1.Every broiler chicken is all worn the RFID label band that is packaged with F43 chip.The frequency acquisition of perching RFID tag recognizer is a little 3 times/second, system can record the id coding of every broiler chicken and the moment occurring like this, and the fundamental function by software calculates and just can calculate every chicken and perch frequency and the running speed (habitat spacing is known) of a residence time, round different habitats at this; The sample frequency of the LOAD CELLS of feeding point and RFID tag recognizer is 3 times/second, and it can provide the body weight of broiler chicken, and broiler chicken is robbed the order that food successively arrives while recording feeding.
Animal behavior comprise rob food ability, run speed, perch time, motion frequency etc.The id collecting with RFID collector, the distance of collection constantly and between three RFID tag recognizer are set up the behavioural characteristic function of broiler chicken; By animal behavior characteristic, carry out data mining, can realize the generation of epidemic situation the very first time.
(1) run the structure of behavioural characteristic function of speed
The speed of running of animal can reflect health status and the active degree of animal.Be in a good state of health and more active animal, be often to skelp or at the double, quick march when daily routines; And the translational speed of sick or sluggish animal is slower.
When animal enters effective identified region of RFID tag recognizer, RFID tag recognizer will collect the id coding of this animal; When animal leaves effective identified region of RFID tag recognizer, the id of this animal coding will disappear.Therefore the id of an animal be coded in time that a RFID tag recognizer disappears therewith id be coded in mistiming of the time that another RFID tag recognizer occurs, just can think that this animal passes through the needed time of neighbor distance between these two RFID tag recognizer.Concrete formula is as follows:
Wherein V is the speed that animal is moved between two RFID tag recognizer, and Sr is two distances between RFID tag recognizer, and t1 is the time that animal leaves first RFID tag recognizer, and t2 is the time that animal enters second RFID tag recognizer.
Because animal is not autotelicly to move towards another RFID tag recognizer from a RFID tag recognizer, animal mobile mistiming between two RFID tag recognizer might not be the mistiming of traveling priority, so the data that traveling time is greater than certain threshold value are not used in the calculating of behavioural characteristic with regard to being considered to non-rectilinear Mobile data.Therefore select data that speed is larger to run velocity characteristic parameter as the animal of this id coding.
(2) structure of the behavioural characteristic function of animal activity frequency
The motion frequency of animal is one of important indicator of its activity and health status.Even if the animal that active degree is higher has fixing perching a little, also can in the playground of being everlasting, beat up and down; The animal that active degree is lower can rest on same perching a little for a long time, movement that can be not frequent.If animal is injured or be attacked by a disease, its active degree will greatly reduce, even always nest in certain position until die.If there is predator, strong noise source or other, can make the dysphoric factor of animal, the active degree of animal can significantly rise.As can be seen here, motion frequency is except judging the quality of animal individual, and the variation of active degree that can also be by individuality or colony is carried out early warning to affecting the factor of animal-breeding.
When animal enters effective identified region of RFID tag recognizer, RFID tag recognizer can record the id coding of this animal until this animal leaves effective identified region always, and one-in-and-one-out can assert that the movable number of times of this animal increases by 1 time like this.Due to RFID tag recognizer, can block because of the health of other animal or the marginal position of this animal in effective identified region cannot be realized the continuous identification of id coding, therefore threshold value need to be set eliminates the impact of discontinuous data on fundamental function.In same RFID tag recognizer, if disappearing, id coding is less than threshold value the interval time occurring again, can judge that animal under this id coding is disturbed but not has left effective identified region.Yi Tianwei unit analyzes the motion frequency of every animal every day, just can count the active degree of every animal.By the motion frequency to up-to-date a day and passing motion frequency, contrast, just can find that motion frequency raises suddenly, reduces the id numbering of the animal even disappearing, allows the staff of plant can tackle in time the sudden situations such as epidemic disease.
(3) animal is robbed the structure of the behavioural characteristic function of food ability
The feed desire of animal is the index of reflection activity and health status.In the relatively independent plant in feeding area and behaviour area, the time that every feed is thrown in, the animal healthy, activity is large can be very fast after feed is thrown in washes away food, and strong animal can be extruded into earlier position; Animal in poor condition of health or that catch can not rushed for feeding groove at once, even if there is the feed desire can be because of health compared with weak and after being pressed against yet.
Passage between feeding area-behaviour area is disposed RFID tag recognizer, just can identify and record id coding and elapsed time through the animal of passage.After the staff of plant completes feed and throws in, the present invention is encoded to timing zero point with the id of first admission passage, according in different time sections through the quantity of the id coding of passage, the time is divided into 10 equal portions that length does not wait.Apart from the id detecting in nearest time period at zero point, be encoded to the most actively, apart from the id monitoring in the time period farthest at zero point, be encoded to least active.
(4) structure of the behavioural characteristic function of the animal residence time
The time that animal stops in effective identified region of RFID tag recognizer is also the factor of judgement animal active degree and health status.The animal that active degree is higher, perching, the time of a little staying is shorter; And the animal that active degree is low or health status is poor is longer in the residence time of perching a little.
Part RFID tag recognizer is deployed in several main animal habitat points in playground, therefore by recording id numbering under each animal, enter and leave the time of effective identified region of these RFID tag recognizer, can calculate the time span that these animals stay in this region.By statistics every day, the id of every animal numbers the accumulative total residence time that is deployed in animal habitat point at each, can recognize the active degree of animal.If increase the residence time of certain animal these last few days suddenly, be likely that this animal is injured or catch and cause active degree to decline.
4, the data mining of animal behavior data---the online supervision of index comprehensive evaluation method to animal epidemics behavior
The mass data that animal behavior monitoring system is obtained is carried out data mining, not only can analyze individual health status and growth situation, can also the very first time find animal epidemics.The present invention by index comprehensive evaluation method to the speed of running of chicken, at habitat residence time, motion frequency, rob food ability and carry out data mining, can excavate weak in animal population or infect the individuality of epidemic disease.
Objective comprehensive evaluation method is by each evaluation index quantification, the nondimensional unified score that obtains all evaluation indexes of each evaluation object adopts index comprehensive evaluation method to carry out index comprehensive later, can obtain the comprehensive evaluation value of each animal, then draw according to the height of comprehensive evaluation value the quality that is evaluated animal.
Take validation test of the present invention as example.First with detecting by artificial means, known to have 6 broiler chicken be more obvious strong health, and 3 is sick and wounded small and weak broiler chicken, and wherein 1 body weight is gently small, has significantly injured sign on another two healths.The id coding of 6 strong broiler chicken is: 090A0033,090A0055,090A0059,04160001,090A0037,090A0051; The id coding of 3 sick and wounded chickens is: 070A0061,090A0047,090A0063.After the deployment the present invention of Ci plant, carried out the field test of 3 days.Altogether gathered 135700 data and be used as case analysis, partial data is as shown in table 3.The expression of the robbing food order numerical value maximum arrival feeding groove of running at first; More active the data representation chicken that habitat residence time is shorter; Motion frequency represents that the turnover of average one day of broiler chicken perches number of times a little, and this chicken of data representation that motion frequency is high is more active.
Table 1 poultry behavioural characteristic value
Above data are normalized by formula (2), convert raw data to standardized normal distribution score value.
Standard normal transformation for mula:
Wherein,
the average of table variable, the standard deviation of S table variable.。After conversion, obtain data as table 2:
Poultry behavioural characteristic value after table 2 normalization
Owing to robbing food order, speed and frequency, be all that numerical value is the bigger the better, be that numerical value is the smaller the better residence time.In order to allow them keep identical change direction by these four indexs for comprehensive evaluation computing, therefore need to be by the eigenwert revert all of residence time.After conversion, data are as shown in table 3.
Poultry behavioural characteristic value after table 3 normalization
According to the n of animal a behavioural characteristic, m animal carried out to index comprehensive evaluation, evaluate the quality of animal.The animal population of 24 hours Real-Time Monitoring large-scale farmings of system energy, therefrom finds that sick and weak colony is with the generation of early warning epidemic situation in time.The formula of index comprehensive evaluation is as follows:
ω wherein
jfor weight coefficient, meet following relational expression:
Wherein, behavioural characteristic variable φ
ithe comprehensive evaluation value that represents the animal that label code is i, a
ijj the variable that represents the animal that label code is i.
According to animal comprehensive evaluation above, all raw data that collect in validation test, through standardization, are carried out to comprehensive evaluation by many index comprehensive evaluations method to four behavioral trait values.Owing to being the overall target of evaluating animal, so ω
1=ω
2=ω
3=ω
4=1.As shown in table 4 by result after aggregative weighted evaluation.
Table 4 carries out the result of comprehensive evaluation to four behavioral trait values by index comprehensive evaluation method
After data processing, there are the data of 23 broiler chicken to can be used in the data processing of field test.System monitoring result, 6 strong chickens are: 090A0033,090A0055,090A0059,04160001,090A0037,090A0051,3 sick and wounded chickens are: 070A0061,090A0047,090A0063.Experiment is in full accord with legitimate reading.
To sum up, the native system brief easily damaged Internet of Things collection terminal of trying one's best, and give full play to the powerful data mining capability of background server, gather the simplest two master datas, and with data digging method, produce a plurality of behavioural characteristics, greatly strengthened system reliability, reduced the cost of system.The animal behavior analytical approach that system adopts is simple, practical, more can adapt to collection and the analysis of the mass data of large-scale farming, the response time of having accelerated system, has shortened the time that animal epidemics is realized.
One of ordinary skill in the art will appreciate that all or part of step in the whole bag of tricks of above-described embodiment is to come the hardware that instruction is relevant to complete by program, this program can be stored in a computer-readable recording medium, storage medium can comprise: ROM (read-only memory) (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), disk or CD etc.
The method and system of the health index evaluation that realizes animal behavior the monitoring above embodiment of the present invention being provided are described in detail, applied specific case herein principle of the present invention and embodiment are set forth, the explanation of above embodiment is just for helping to understand method of the present invention and core concept thereof; , for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention meanwhile.
Claims (6)
1. a method that realizes the health index evaluation of animal behavior monitoring, is characterized in that, comprises the steps:
For every animal is worn RFID label, and at animal activity point, corresponding RFID label collector is set;
Based on RFID collector and speed behavioural characteristic function, obtain the translational speed of every animal, and to the translational speed of all animals based on normalized, obtain the translational speed weighted value of every animal;
Based on RFID collector and rob the food ability of robbing that food ability behavioural characteristic function obtains every animal, and to the food ability of robbing of all animals based on normalized, obtain the food ability of the robbing weighted value of every animal;
Based on RFID collector and motion frequency behavioural characteristic function, obtain the motion frequency of every animal, and to the motion frequency of all animals based on normalized, obtain the motion frequency weighted value of every animal;
The residence time of obtaining every animal based on RFID collector and residence time behavioural characteristic function, and to the residence time of all animals based on normalized, obtain weighted value residence time of every animal;
Calculate the aggregative weighted value of every animal, the translational speed weighted value that described aggregative weighted value is every animal, rob food ability weighted value, motion frequency weighted value and residence time weighted value sum;
Aggregative weighted value based on all animals is passed judgment on the health index of every animal.
2. the method that the health index of realizing animal behavior monitoring as claimed in claim 1 is evaluated, is characterized in that, the described translational speed step of obtaining every animal based on RFID collector and speed behavioural characteristic function is specially:
Utilize the distance of nearest two RFID collectors and the time of nearest two RFID collectors identification RFID label to obtain the translational speed of every animal.
3. the method that the health index of realizing animal behavior monitoring as claimed in claim 1 is evaluated, is characterized in that, described normalized is specially:
Convert raw data to standardized normal distribution score value;
Normal distribution score value is obtained to the comprehensive evaluation value of every animal according to index comprehensive evaluation formula.
4. a system that realizes the health index evaluation of animal behavior monitoring, is characterized in that, comprising: the RFID label of wearing every animal, and the RFID label collector arranging at animal activity point;
And translational speed weighted value module, for obtain the translational speed of every animal based on RFID collector and speed behavioural characteristic function, and to the translational speed of all animals based on normalized, obtain the translational speed weighted value of every animal;
And rob food ability weighted value module, for based on RFID collector with rob the food ability of robbing that food ability behavioural characteristic function obtains every animal, and to the food ability of robbing of all animals based on normalized, obtain the food ability of the robbing weighted value of every animal;
And motion frequency weighted value module, for obtain the motion frequency of every animal based on RFID collector and motion frequency behavioural characteristic function, and to the motion frequency of all animals based on normalized, obtain the motion frequency weighted value of every animal;
And residence time weighted value module, for the residence time of obtaining every animal based on RFID collector and residence time behavioural characteristic function, and to the residence time of all animals based on normalized, obtain weighted value residence time of every animal;
Aggregative weighted value module, for calculating the aggregative weighted value of every animal, the translational speed weighted value that described aggregative weighted value is every animal, rob food ability weighted value, motion frequency weighted value and residence time weighted value sum;
Health index evaluation module, for the health index of every the animal of aggregative weighted value judge based on all animals.
5. the system that the health index of realizing animal behavior monitoring as claimed in claim 4 is evaluated, it is characterized in that, described translational speed weighted value module utilizes the distance of nearest two RFID collectors and the time of nearest two RFID collectors identification RFID label to obtain the translational speed of every animal.
6. the system that the health index of realizing animal behavior monitoring as claimed in claim 4 is evaluated, is characterized in that, described normalized is specially:
Convert raw data to standardized normal distribution score value;
Normal distribution score value is obtained to the comprehensive evaluation value of every animal according to index comprehensive evaluation formula.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410273554.9A CN104077550B (en) | 2014-06-18 | 2014-06-18 | The method and system that a kind of health index for realizing animal behavior monitoring is evaluated |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410273554.9A CN104077550B (en) | 2014-06-18 | 2014-06-18 | The method and system that a kind of health index for realizing animal behavior monitoring is evaluated |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104077550A true CN104077550A (en) | 2014-10-01 |
| CN104077550B CN104077550B (en) | 2017-06-06 |
Family
ID=51598800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410273554.9A Expired - Fee Related CN104077550B (en) | 2014-06-18 | 2014-06-18 | The method and system that a kind of health index for realizing animal behavior monitoring is evaluated |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104077550B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105766789A (en) * | 2016-03-12 | 2016-07-20 | 浙江大学 | Physical health detection method and system for chickens |
| CN106331622A (en) * | 2016-08-25 | 2017-01-11 | 广西小草信息产业有限责任公司 | Livestock monitoring system and method |
| CN106447117A (en) * | 2016-10-10 | 2017-02-22 | 重庆科技学院 | Pet feeding method and system based on pet daily data analysis |
| CN106817510A (en) * | 2016-12-20 | 2017-06-09 | 鲁东大学 | Alarm method and device of a kind of animal by external interference |
| CN107480892A (en) * | 2017-08-17 | 2017-12-15 | 广州市华南畜牧设备有限公司 | Comprehensive livestock-raising data rank method and device |
| CN109757403A (en) * | 2019-01-31 | 2019-05-17 | 福建省农业科学院科技干部培训中心 | Based on the method for inhabiting position and sleep quality assessment poultry quality |
| CN109757404A (en) * | 2019-01-31 | 2019-05-17 | 福建省农业科学院科技干部培训中心 | Based on the method for inhabiting position and run duration evaluation poultry quality |
| CN109767231A (en) * | 2017-11-01 | 2019-05-17 | 杭州沃朴物联科技有限公司 | A kind of system for verifying activity data in chicken developmental process |
| CN109892254A (en) * | 2019-01-31 | 2019-06-18 | 福建省农业科学院科技干部培训中心 | Based on the method for inhabiting position evaluation poultry quality |
| CN110288059A (en) * | 2019-06-24 | 2019-09-27 | 哈尔滨理工大学 | A kind of management method in wisdom pasture |
| CN110646568A (en) * | 2019-10-12 | 2020-01-03 | 中国农业科学院麻类研究所 | Feed palatability screening method based on animal group behaviors |
| CN111275911A (en) * | 2020-01-16 | 2020-06-12 | 珠海格力电器股份有限公司 | Danger prompting method, equipment and computer readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060196445A1 (en) * | 2004-07-15 | 2006-09-07 | Lawrence Kates | System and method for canine training |
| CN103488148A (en) * | 2013-09-24 | 2014-01-01 | 华北电力大学（保定） | Intelligent livestock behavior monitoring system based on internet of things and computer vision |
| CN103593802A (en) * | 2013-11-28 | 2014-02-19 | 南宁市深仕数码科技有限公司 | Animal disease detection early-warning system and method based on technology of internet of things |
-
2014
- 2014-06-18 CN CN201410273554.9A patent/CN104077550B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060196445A1 (en) * | 2004-07-15 | 2006-09-07 | Lawrence Kates | System and method for canine training |
| CN103488148A (en) * | 2013-09-24 | 2014-01-01 | 华北电力大学（保定） | Intelligent livestock behavior monitoring system based on internet of things and computer vision |
| CN103593802A (en) * | 2013-11-28 | 2014-02-19 | 南宁市深仕数码科技有限公司 | Animal disease detection early-warning system and method based on technology of internet of things |
Non-Patent Citations (2)
| Title |
|---|
| 姜晟等: "集约化家禽养殖无线传感器网络监测系统", 《农业网络信息》 * |
| 陆明洲等: "畜牧信息智能监测研究进展", 《中国农业科学》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105766789A (en) * | 2016-03-12 | 2016-07-20 | 浙江大学 | Physical health detection method and system for chickens |
| CN105766789B (en) * | 2016-03-12 | 2018-06-29 | 浙江大学 | The physical health detection method and system of chicken |
| CN106331622A (en) * | 2016-08-25 | 2017-01-11 | 广西小草信息产业有限责任公司 | Livestock monitoring system and method |
| CN106447117A (en) * | 2016-10-10 | 2017-02-22 | 重庆科技学院 | Pet feeding method and system based on pet daily data analysis |
| CN106447117B (en) * | 2016-10-10 | 2018-05-01 | 重庆科技学院 | Pet feeding method and system based on the daily data analysis of pet |
| CN106817510A (en) * | 2016-12-20 | 2017-06-09 | 鲁东大学 | Alarm method and device of a kind of animal by external interference |
| CN107480892A (en) * | 2017-08-17 | 2017-12-15 | 广州市华南畜牧设备有限公司 | Comprehensive livestock-raising data rank method and device |
| CN109767231A (en) * | 2017-11-01 | 2019-05-17 | 杭州沃朴物联科技有限公司 | A kind of system for verifying activity data in chicken developmental process |
| CN109757404A (en) * | 2019-01-31 | 2019-05-17 | 福建省农业科学院科技干部培训中心 | Based on the method for inhabiting position and run duration evaluation poultry quality |
| CN109757403A (en) * | 2019-01-31 | 2019-05-17 | 福建省农业科学院科技干部培训中心 | Based on the method for inhabiting position and sleep quality assessment poultry quality |
| CN109892254A (en) * | 2019-01-31 | 2019-06-18 | 福建省农业科学院科技干部培训中心 | Based on the method for inhabiting position evaluation poultry quality |
| CN109757404B (en) * | 2019-01-31 | 2021-10-15 | 福建省农业科学院科技干部培训中心 | Method for evaluating poultry quality based on perching position and movement time |
| CN109757403B (en) * | 2019-01-31 | 2021-10-15 | 福建省农业科学院科技干部培训中心 | Method for evaluating poultry quality based on perching position and sleep quality |
| CN109892254B (en) * | 2019-01-31 | 2021-12-14 | 福建省农业科学院科技干部培训中心 | Method for evaluating poultry quality based on perching position |
| CN110288059A (en) * | 2019-06-24 | 2019-09-27 | 哈尔滨理工大学 | A kind of management method in wisdom pasture |
| CN110646568A (en) * | 2019-10-12 | 2020-01-03 | 中国农业科学院麻类研究所 | Feed palatability screening method based on animal group behaviors |
| CN111275911A (en) * | 2020-01-16 | 2020-06-12 | 珠海格力电器股份有限公司 | Danger prompting method, equipment and computer readable storage medium |
| CN111275911B (en) * | 2020-01-16 | 2021-02-26 | 珠海格力电器股份有限公司 | Danger prompting method, equipment and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104077550B (en) | 2017-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104077550B (en) | The method and system that a kind of health index for realizing animal behavior monitoring is evaluated | |
| Gebhardt-Henrich et al. | Use of outdoor ranges by laying hens in different sized flocks | |
| Clark et al. | Site selection and nest success of ring-necked pheasants as a function of location in Iowa landscapes | |
| Campbell et al. | Free-range egg production: its implications for hen welfare | |
| Leif | Survival and reproduction of wild and pen-reared ring-necked pheasant hens | |
| Taylor et al. | Frequent range visits further from the shed relate positively to free-range broiler chicken welfare | |
| KR102165891B1 (en) | Livestock data analysis-based farm health state diagnosis system | |
| CN105091938A (en) | Poultry health monitoring method and system | |
| Feiyang et al. | Monitoring behavior of poultry based on RFID radio frequency network | |
| Islam et al. | Automated monitoring of cattle heat stress and its mitigation | |
| Boualit et al. | Environmentally mediated reproductive success predicts breeding dispersal decisions in an early successional amphibian | |
| CN110779575A (en) | Animal husbandry monitoring system based on big data platform | |
| CN109359624B (en) | Neural network-based prediction method and prediction device for feeding behavior of laying hens | |
| Mate et al. | Design and development of IoT-based intelligent solutions with blockchain for indian farmers on livestock management | |
| Lee et al. | Using spot pattern recognition to examine population biology, evolutionary ecology, sociality, and movements of giraffes: A 70-year retrospective | |
| McNew et al. | Human-mediated selection on life-history traits of Greater Prairie-Chickens | |
| Mavromati et al. | Assessing the economic efficiency in some broiler farms through the European production efficiency factor (EPEF) | |
| Riley et al. | Methods for estimating vital rates of greater sage‐grouse broods: A review | |
| CN111990282A (en) | Real-time measuring platform and method for livestock distribution density | |
| Campbell et al. | Poultry welfare monitoring: wearable technologies | |
| Miller et al. | Animal-mounted sensor technology to predict ‘time to calving’in beef and dairy cows | |
| McNew et al. | Effects of livestock grazing management on the ecology of Sharp-tailed Grouse, grassland birds, and their predators in norther mixed grass prairie habitats | |
| Machado-Gaye et al. | Using latent behavior analysis to identify key foraging areas for Adélie penguins in a declining colony in West Antarctic Peninsula | |
| Owoeye | On computational models of animal movement behaviour | |
| Mullican | Breeding Ecology of American Kestrels on the Llano Estacado of Texas |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170606 Termination date: 20180618 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |