CN107041732A - Animal heat monitoring system and the body temperature recognition methods based on machine learning - Google Patents
Animal heat monitoring system and the body temperature recognition methods based on machine learning Download PDFInfo
- Publication number
- CN107041732A CN107041732A CN201610084359.0A CN201610084359A CN107041732A CN 107041732 A CN107041732 A CN 107041732A CN 201610084359 A CN201610084359 A CN 201610084359A CN 107041732 A CN107041732 A CN 107041732A
- Authority
- CN
- China
- Prior art keywords
- body temperature
- animal
- information
- acceleration
- module
- 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.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
-
- 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
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Physiology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a kind of animal heat monitoring system and the body temperature recognition methods based on machine learning.The monitoring system includes：Harvester and intelligent terminal application, contact, body temperature and the acceleration information of the monitored animal of harvester collection, and judge whether to occur effectively contact according to contact size；Intelligent terminal application receives effective animal data of harvester, and is identified as animal heat state.The recognition methods, can learn to draw normal body temperature of the monitored animal under different motion state, and can identify the body temperature of animal based on the information that learns.The system of the present invention can realize the automatic detection and remote real time monitoring to animal heat, it is not necessary to which artificial detection is recorded, and can save substantial amounts of manpower；The method of the present invention can exclude the differences such as species, age, individual and the motion state of animal, really be made to measure for each monitored target, reach precisely effective temperature check target.
Description
Technical field
Field, more particularly to animal heat monitoring system and the body temperature recognition methods based on machine learning are monitored the present invention relates to animal health.
Background technology
Body temperature is the important health indicator of animal, and temperature monitoring is one of important way of evaluating animals ' health state, promptness, the standard of temperature monitoring
True property, reliability directly affect prevention, diagnosis, treatment and the post-operative recovery effect of disease.
Single body temperature sampling point is taken in conventional animal temperature check, is not easy to very much tracking animal heat change, and the measurement master to animal heat at present
To complete by hand, owner needs daily hand dipping animal heat, record body temperature, draw temperature curve, this is a very big workload.
Moreover, some animals, the Niu Wufa such as put in a suitable place to breed coordinates temperature check, generally requiring anesthesia could realize, for this kind of animal, traditional body temperature inspection
Survey mode can not implement high-frequency detection.
In addition, various animals, with species different age group, with species with age Different Individual, with individual animals different motion shape
State, often with different normal/healthy body temperature, such as：The body temperature that ox has under motion state is higher than its body temperature under sleep or inactive state；
And for example：Adult dogs normal body temperature is 37.5~38.5 DEG C, and it is 38~39 DEG C that the body temperature of pup is slightly higher, thus, the monitoring of animal heat is considered as animal
The difference such as species, age, individual, motion state, and traditional approach is difficult to accomplish comprehensively.
The content of the invention
It is an object of the invention to provide an animal heat monitoring system and the body temperature recognition methods based on machine learning, animal heat prison
Examining system can automatically pick up the body temperature information of animal, realize the real-time remote monitoring to animal heat, it is not necessary to which owner manually detects and records knot
Really, manpower is saved, testing result is more accurate, to solve the problem of traditional temperature check mode workload is big；Moreover, system uses the machine of being based on
The body temperature recognition methods of device study, can learn to draw normal body temperature of the monitored animal under different motion state, and can be based on learning just
Normal body temperature information identifies being in normal body temperature, cross high fever or crossing hypothermia for the body temperature of animal, i.e. animal.The animal heat of machine learning
State identification method can exclude the differences such as species, age, individual and the motion state of animal, really make to measure, reach for each monitored target
To accurate effective temperature check purpose.
To achieve the above object, the solution of the present invention is：One animal heat monitoring system, the system includes harvester and intelligent terminal application.
The harvester is worn on animal bodies, for information gatherings such as animal heat, acceleration, contacts；The intelligent terminal application connects
The information of harvester collection is received, and based on these information to animal heat state (such as health/normal body temperature, fever/hyperpyrexia, hypothermia)
It is identified；The harvester is connected with intelligent terminal application；
The harvester includes body temperature collector and binding strip, and the body temperature collector both sides are fixedly connected with length-adjustable binding strip, described
Binding strip is used to fix harvester with animal, and described tie up is embedded with pressure sensor, acceleration in abdominal belt internal battery group, described harvester
Sensor, temperature sensor, control module, data cache module and data transmission module are spent, described pressure sensor and temperature sensor is tight
Animal skin is pasted to set, the harvester can snapping connection by binding strip two ends, or be directly held together, realize and be worn on animal body
On；
The pressure sensor, temperature sensor and acceleration transducer are used for contact, temperature and the acceleration information for gathering animal；
The control module is connected with the pressure sensor, temperature sensor and acceleration transducer, for pressure sensor, TEMP
Device, the running parameter of acceleration transducer and their working condition is controlled, and contact, temperature and acceleration information can be received, and judge to connect
Whether breath of collecting mail is effective；
The data cache module is connected with the control module, is received from the control module and is cached effective contact, temperature and acceleration
Information；
The data transmission module is connected and intelligent terminal application connection with the data cache module, and data are obtained from the data cache module
Information, and it is sent to the intelligent terminal application；
The intelligent terminal caches mould using gathered data transport module, gathered data cache module, body temperature identification module, status data is included
Block；
The gathered data transport module is used for the animal data for receiving the harvester collection, and the gathered data caching mould is stored in after processing
Block；
The gathered data cache module is used to caching the animal data that receives, and it is data cached meet body temperature identification and require when, be transferred to
The body temperature identification module；
The animal data collected is identified as the body temperature of animal by the body temperature identification module, and by animal heat status data transfers to institute
State status data cache module；
The animal heat monitoring system is used for animal heat collection and comprised the following steps：
(1) frequency acquisition of the control module is set the pressure sensor, the acceleration transducer and the temperature sensor；
(2) the pressure sensor detection and the contact of animal skin, the acceleration transducer detect animal acceleration information, and the temperature is passed
Sensor detects animal heat information；
(3) contact information, acceleration information and the animal heat information detected in the control module receiving step (2), and pressed according to contact
Force information judges whether harvester contacts with animal skin：If be not in contact with, all information gathered in the same time are abandoned；If effectively connect
Touch, then data are stored in data cache module；
(4) intelligent terminal being arranged on owner's smart machine is applied receives the described of the harvester by the gathered data transport module
Contact information, acceleration information and body temperature information in data cache module, and the gathered data caching mould will be transferred to after information proper treatment
Block；
(5) acceleration information and body temperature information of the state recognition module based on animal of the intelligent terminal application identify the body temperature of animal
Information.
Optionally, the intelligent terminal, which is applied, includes human-computer interaction module.The human-computer interaction module is used to receive user mutual instruction, according to instruction
Required information is obtained from the gathered data cache module and status data cache module, and is looked into by modes such as screen or voices to user's displaying
Ask result.
Optionally, the intelligent terminal, which is applied, includes status data transfers module.The status data transfers module gives the status data transfers of body temperature
The intelligent monitor system at telecommunication network end, the system provides further intellectual analysis and service to status data.
Described harvester is worn on the neck of animal, or leg, or chest, or head etc., and battery pack is provided with the binding strip of harvester,
Battery capacity can be expanded, the data acquisition of longer time is realized；
Described pressure sensor is deposition tube resistance type or capacitance-type.
Described temperature sensor is the temperature sensor based on thermistor or thermocouple.
Described acceleration transducer is the acceleration transducer of piezoelectric type, or pressure resistance type, or condenser type etc..
The software and hardware that the intelligent terminal application can be developed or customized based on the main flow such as Android, IOS, Window 10 mobile platform
Platform.
To achieve the above object, the present invention provides a kind of body temperature recognition methods based on machine learning, can be for specifically monitored animal
Body carries out machine learning, learns and show that the animal is in the rule of all kinds of body temperatures, is then based on these rules and carries out body temperature identification, reaches
To the target of health monitoring.
The machine-learning process of the body temperature recognition methods based on machine learning comprises the following steps：
(1) for specific some or certain animal, under different body temperatures (such as health/normal body temperature, fever/hyperpyrexia, hypothermia),
For different motion state (such as sleep, static, light exercise, ordinary movement, strenuous exercise) collection acceleration a and body temperature t；
(2) sampled acceleration a and body temperature t information are gone with the time window of certain length, acceleration average value in time window is calculatedWith body temperature average value
Training examples are saved as, such as；
(3) training examples collection is read, acceleration average value is pressed to the sample of body temperature of the same raceSize is ranked up to sample；
(4) to the training examples collection after sequence, continuous sample body temperature average is pressed to body temperature of the same raceChanging value size is divided into several classes, finally obtains
The result of habit, saves as rule set, such as：
…
…
…
The machine recognition process of the body temperature recognition methods based on machine learning comprises the following steps：
(1) it is detected animal collection acceleration a and body temperature t for specific；
(2) sampled acceleration a and body temperature t information are gone with the time window of certain length, acceleration average value in time window is calculatedWith body temperature average value
(3) rule of acceleration and body temperature, i.e. acceleration average value are matched simultaneously from regular Integrated queryIn rule condition
In the range of, and body temperature average valueIn rule conditionIn the range of；
(4) if step (3) have found matched rule, the body temperature of animal is identified according to rule, and terminate identification process；
(5) if step (3) can not find matched rule, from rule of the body temperature for match query acceleration in the rule set of " normal body temperature "
Then, i.e. acceleration average valueIn rule conditionIn the range of, then, find out the body temperature in the rule condition of same rule
Scope
(6) ifThanSmall, then body temperature is " crossing hypothermia ", ifThanGreatly, then body temperature is " crossing high fever ".
What the present invention was reached has the beneficial effect that：
(1) Thermometer System of the invention can realize the automatic detection and remote real time monitoring to animal heat, it is not necessary to which manual record is detected
The body temperature situation of animal, saves substantial amounts of manpower, lighten one's labor power；
(2) Thermometer System of the invention is provided with acceleration transducer and pressure sensor, can detect whether harvester effectively connects with animal
Touch, and body temperature of the animal under different motion state, testing result is more accurate；
(3) Thermometer System of the invention is provided with intelligent terminal application, can the acceleration information based on animal, pressure information and body temperature information enter
Row learns and carries out Intelligent Recognition, and machine learning characteristic make it that the system goes for the body temperature identification of nearly all animal, and can take into account tested dynamic
The individual body temperature characteristic of thing, real to realize private customization, recognition result is also more accurate；
(4) present invention can also be uploaded to body temperature information in remote system, relevant people by being connected with the intelligent monitor system on telecommunication network
Member can understand the history body temperature situation of monitored animal at any time by network, and the different body temperature change of monitored target can be analyzed by expert system
Change, realize more accurately health monitoring；
(5) harvester of the invention provides the energy using battery pack, can realize the power demands of longer time, reduces the number of times of equipment charge,
Improve the efficiency that equipment is used.
Brief description of the drawings
Fig. 1 is the harvester structure chart of the present invention；
Fig. 2 is the animal heat monitoring system structure principle chart of the present invention；
Fig. 3 is the animal heat collecting flowchart figure of the present invention；
Fig. 4 is the learning process of the body temperature identification model of the present invention；
Fig. 5 is the implementation process of the body temperature identification model of the present invention.
Embodiment
The invention will now be described in further detail with reference to the accompanying drawings.
Embodiment one
Animal heat monitoring system in the present embodiment includes the harvester that wearing gathers in animals, for animal heat and for animal heat
The intelligent terminal application of monitoring.
As shown in figure 1, the harvester includes body temperature collector and binding strip, the body temperature collector both sides are fixedly connected with length-adjustable tie up
Ligature, described binding strip is used to fix harvester with animal, and described tie up in abdominal belt internal battery group, described harvester is embedded with pressure
Sensor, acceleration transducer, temperature sensor, described pressure sensor and temperature sensor are close to animal skin setting.The harvester
Can snapping connection by binding strip two ends, or be directly held together, realize wearing in animals.
As shown in Fig. 2 the harvester 1 include pressure sensor 11, temperature sensor 12, acceleration transducer 13, control module 14,
Data cache module 15 and data transmission module 16.The pressure sensor 11, temperature sensor 12 and acceleration transducer 13 and the control
Molding block 14 is connected, and the control module 14 is connected with the data cache module 15, the data cache module 15 and data transmission module 16
Connection.
As shown in Fig. 2 the intelligent terminal includes gathered data transport module 21, gathered data cache module 22, body temperature identification using 2
Module 23, status data cache module 24.The gathered data transport module 21 is connected with the gathered data cache module 22, the collection
Data cache module 22 is connected with the body temperature identification module 23, the body temperature identification module 23 and the status data cache module
24 connections.
As shown in figure 3, the body temperature collecting flowchart of the animal heat monitoring system comprises the following steps：
(1) step 101, the control module setting pressure sensor, acceleration transducer, temperature sensor that user passes through the harvester
Information gathering frequency, for the animal being in a good state of health, can set relatively low frequency acquisition, for the animal that health status is poor, then should set
Put higher frequency acquisition；
(2) step 102, the harvester detects the pressure information with animal contact by pressure sensor, and acceleration transducer detects animal simultaneously
Acceleration information, temperature sensor simultaneously detect animal body temperature information；
(3) step 103, the contact information of the control module detection collection, if contact value is more than threshold value, is determined as harvester
It there occurs and effectively contact with animal, all information effectively, go to step 104；If contact value be less than threshold value, be determined as harvester with
Effective contact does not occur for animal, and all information are invalid, go to step 107, that is, abandons invalid collection information, and terminate collecting flowchart；
(4) step 104, the data cache module of the harvester is by the contact information, acceleration information and the body temperature information that detect
Store；
(5) step 105, the intelligent terminal is applied from the harvester and receives contact information, acceleration information and animal heat information；
High and communication network is smooth for requirement of real-time, intelligent terminal application can obtain data by frequency acquisition；It is not high or logical for requirement of real-time
Communication network is poor or even disconnects, and intelligent terminal application can reduce data acquisition frequency or be transmitted again after communication network recovery is smooth；
(6) step 106, based on the body temperature recognition rule set after machine learning, the body temperature identification module of the intelligent terminal application
The acceleration and body temperature information of animal are identified as to the body temperature information of animal.
Embodiment two
The present embodiment two is on the basis of embodiment one, and intelligent terminal application is additionally provided with human-computer interaction module 26.The human-computer interaction module 26 with
Gathered data cache module 22 and status data cache module 24 are connected.
The human-computer interaction module 26 is used to receive the instruction that user is provided by interactive modes such as touch screen, keyboard and voices, and slow from gathered data
In storing module 22 and status data cache module 24 by instruction take out data, then with modes such as screen or voices by the data display of taking-up to user.
Embodiment three
The present embodiment three is on the basis of embodiment one or embodiment two, and intelligent terminal application is additionally provided with status data transfers module 25.The state
Data transmission module 25 is connected with local status data cache module 24 and long-range intelligent monitor system 3.
The status data transfers module 25 is remotely logical by Internet, TD-SCDMA or WCDMA etc. using 2 by described intelligent terminal
Letter net be connected with intelligent monitor system 3, for animal heat status information to be uploaded into intelligent monitor system 3, as historical data in case inquire about or
Carry out deeper into intellectual analysis.
Example IV
As shown in figure 3, the body temperature recognition methods based on machine learning includes a learning process and an identification process.
Learning process mainly by animal under the body temperature of " health/normal body temperature ", for different motion state acquisition acceleration and body temperature
Information, and different acceleration situations, and the animal normal body temperature range under different motion state are drawn by sorting algorithm.The machine-learning process
Comprise the following steps：
(1) for specific some or certain animal, under the body temperature of " health/normal body temperature ", for (such as the sleep, quiet of different motion state
Only, light exercise, ordinary movement, strenuous exercise) collection acceleration a and body temperature t；
(2) sampled acceleration a and body temperature t information are gone with the time window of certain length, acceleration average value in time window is calculatedWith body temperature average value
Training examples are saved as, such as；
(3) training examples collection is read, by acceleration average valueSize is ranked up to sample；
(4) to the training examples collection after sequence, by continuous sample body temperature averageChanging value size is divided into several classes, finally obtains the result of study, preserves
For rule set, such as：
…
The machine recognition process of the body temperature recognition methods based on machine learning comprises the following steps：
(1) it is detected animal collection acceleration a and body temperature t for specific；
(2) sampled acceleration a and body temperature t information are gone with the time window of certain length, acceleration average value in time window is calculatedWith body temperature average value
(3) from rule set match query acceleration rule, i.e. acceleration average valueIn rule conditionIn the range of, so
Afterwards, the body temperature in the rule condition of same rule is found out
(4) ifThanGreatly, and ratioSmall, then body temperature is " normal body temperature "；IfThanSmall, then body temperature is " mistake
Hypothermia "；IfThanGreatly, then body temperature is " crossing high fever ".
Embodiment five
The present embodiment five is on the basis of example IV, the base that the learning process is learnt in the body temperature information to " health/normal body temperature "
On plinth, increase the study to " fever/hyperpyrexia ", " hypothermia " body temperature information.The machine-learning process comprises the following steps：
(1) for specific some or certain animal, under different body temperatures (such as health/normal body temperature, fever/hyperpyrexia, hypothermia),
For different motion state (such as sleep, static, light exercise, ordinary movement, strenuous exercise) collection acceleration a and body temperature t；
(2) sampled acceleration a and body temperature t information are gone with the time window of certain length, acceleration average value in time window is calculatedWith body temperature average value
Training examples are saved as, such as；
(3) training examples collection is read, acceleration average value is pressed to the sample of body temperature of the same raceSize is ranked up to sample；
(4) to the training examples collection after sequence, continuous sample body temperature average is pressed to body temperature of the same raceChanging value size is divided into several classes, finally obtains
The result of habit, saves as rule set, such as：
…
…
…
The machine recognition process of the body temperature recognition methods based on machine learning comprises the following steps：
(1) it is detected animal collection acceleration a and body temperature t for specific；
(2) sampled acceleration a and body temperature t information are gone with the time window of certain length, acceleration average value in time window is calculatedWith body temperature average value
(3) rule of acceleration and body temperature, i.e. acceleration average value are matched simultaneously from regular Integrated queryIn rule condition
In the range of, and body temperature average valueIn rule conditionIn the range of；
(4) if step (3) have found matched rule, the body temperature of animal is identified according to rule, and terminate identification process；
(5) if step (3) can not find matched rule, from rule of the body temperature for match query acceleration in the rule set of " normal body temperature "
Then, i.e. acceleration average valueIn rule conditionIn the range of, then, find out the body temperature in the rule condition of same rule
Scope
(6) ifThanSmall, then body temperature is " crossing hypothermia ", ifThanGreatly, then body temperature is " crossing high fever ".
It is understood that the principle that embodiment of above is intended to be merely illustrative of the present and the illustrative embodiments that use, but the present invention is simultaneously
It is not limited to this.For those skilled in the art, without departing from the spirit and substance in the present invention, it can make various
Variations and modifications, these variations and modifications are also considered as protection scope of the present invention.
Claims (10)
1. a kind of animal heat monitoring system, it is characterised in that including：Harvester and intelligent terminal application, the harvester are connected with intelligent terminal application；
The harvester is worn on animal bodies, for information gatherings such as animal heat, acceleration, contacts；
The intelligent terminal application receives the information of harvester collection, and animal heat state (such as health/normal body temperature, fever/hyperpyrexia, hypothermia) is identified based on these information.
2. animal heat monitoring system according to claim 1, it is characterized in that, the harvester includes body temperature collector and binding strip, the body temperature collector both sides are fixedly connected with length-adjustable binding strip, described binding strip is used to fix harvester with animal, it is described to tie up abdominal belt internal battery group, pressure sensor is embedded with described harvester, acceleration transducer, temperature sensor, control module, data cache module and data transmission module, described pressure sensor and temperature sensor is close to animal skin setting, the harvester can snapping connection by binding strip two ends, or be directly held together, realize wearing in animals；
The pressure sensor, temperature sensor and acceleration transducer are used for contact, temperature and the acceleration information for gathering animal；
The control module is connected with the pressure sensor, temperature sensor and acceleration transducer, for pressure sensor, temperature sensor, the running parameter of acceleration transducer and control their working condition, and contact, temperature and acceleration information can be received, and judge whether receive information is effective；
The data cache module is connected with the control module, is received from the control module and is cached effective contact, temperature and acceleration information；
The data transmission module is connected and intelligent terminal application connection with the data cache module, obtains data message from the data cache module, and be sent to the intelligent terminal application.
3. animal heat monitoring system according to claim 1, it is characterised in that the intelligent terminal, which is applied, includes gathered data transport module, gathered data cache module, body temperature identification module, status data cache module；
The gathered data transport module is used for the animal data for receiving the harvester collection, and is stored in the gathered data cache module after processing；
The gathered data cache module is used to caching the animal data that receives, and it is data cached meet body temperature identification and require when, be transferred to the body temperature identification module；
The animal data collected is identified as the body temperature of animal by the body temperature identification module, and gives the status data cache module by animal heat status data transfers.
4. animal heat monitoring system according to claim 1, it is characterised in that the system is used for animal heat collection and comprised the following steps：
(1) frequency acquisition of the control module is set the pressure sensor, the acceleration transducer and the temperature sensor；
(2) the pressure sensor detection and the contact of animal skin, the acceleration transducer detect animal acceleration information, and the temperature sensor detects animal heat information；
(3) contact information, acceleration information and the animal heat information detected in the control module receiving step (2), and judge whether harvester contacts with animal skin according to contact information：If be not in contact with, all information gathered in the same time are abandoned；If effectively contact, data are stored in data cache module；
(4) it is arranged on the intelligent terminal on owner's smart machine and applies contact information, acceleration information and body temperature information in the data cache module that the harvester is received by the gathered data transport module, and the gathered data cache module will be transferred to after information proper treatment；
(5) acceleration information and body temperature information of the state recognition module based on animal of the intelligent terminal application identify the body temperature information of animal.
5. intelligent terminal application system according to claim 3, it is characterised in that the intelligent terminal application also includes：Human-computer interaction module；The human-computer interaction module is connected with the gathered data cache module and status data cache module；
The human-computer interaction module is used to receive user mutual instruction, obtains required information from the gathered data cache module and status data cache module according to instruction, and show Query Result to user by modes such as screen or voices.
6. intelligent terminal application system according to claim 3, it is characterised in that the intelligent terminal application also includes：Status data transfers module；The status data transfers module is connected with the status data cache module and the intelligent monitor system；
Intelligent monitor system of the status data transfers module by the status data transfers of body temperature to telecommunication network end, the system provides further intellectual analysis and service to status data.
7. animal heat monitoring system according to claim 1, it is characterised in that described harvester is worn on the neck of animal, or leg, or chest, or head etc., battery pack is provided with the binding strip of harvester, battery capacity can be expanded, the data acquisition of longer time is realized；
Described pressure sensor is deposition tube resistance type or capacitance-type；
Described temperature sensor is the temperature sensor based on thermistor or thermocouple；
Described acceleration transducer is the acceleration sensing of piezoelectric type, or pressure resistance type, or condenser type etc..
8. animal heat monitoring system according to claim 1, it is characterised in that the hardware and software platform that the intelligent terminal application can be developed or customized based on the main flow such as Android, IOS, Window 10 mobile platform.
9. to achieve the above object, the present invention provides a kind of body temperature recognition methods based on machine learning, this method includes：Learning process and identification process；
The machine-learning process comprises the following steps：
(1) for specific some or certain animal, under the body temperature of " health/normal body temperature ", acceleration and body temperature are gathered for different motion state (such as sleep, static, light exercise, ordinary movement, strenuous exercise)；
(2) sampled acceleration and body temperature information are removed with the time window of certain length, acceleration average value and body temperature average value in time window is calculated, saves as training examples；
(3) training examples collection is read, sample is ranked up by acceleration average value size；
(4) to the training examples collection after sequence, it is divided into several classes by continuous sample body temperature Change in Mean value size, finally obtains the result of study, save as rule set；
The machine recognition process comprises the following steps：
(1) animal collection acceleration and body temperature are detected for specific；
(2) sampled acceleration and body temperature information are removed with the time window of certain length, acceleration average value and body temperature average value in time window is calculated；
(3) from rule set match query acceleration rule, i.e., acceleration average value be in rule condition acceleration range in, then, find out the body temperature in the rule condition of same rule；
(4) if body temperature average ratio body temperature minimum value is big, and it is smaller than body temperature maximum, then body temperature is " normal body temperature "；If body temperature average ratio body temperature minimum value is small, body temperature is " crossing hypothermia "；If body temperature average ratio body temperature maximum is big, body temperature is " crossing high fever ".
10. the body temperature recognition methods according to claim 9 based on machine learning, its feature is in fourth, the learning process to the body temperature information of " health/normal body temperature " on the basis of learning, increase the study to " fever/hyperpyrexia ", " hypothermia " body temperature information, the rule set also increases corresponding rule；Correspondingly, the identification process is, it is necessary to increase the application to " fever/hyperpyrexia ", " hypothermia " body temperature rule；
Increase is to " fever/hyperpyrexia ", the study and identification of " hypothermia " body temperature, the rule set of recognizer can be made more comprehensively complete, the degree of accuracy of identification can be improved, but this mode needs more to recognize sample, adds the difficulty of learning process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610084359.0A CN107041732A (en) | 2016-02-05 | 2016-02-05 | Animal heat monitoring system and the body temperature recognition methods based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610084359.0A CN107041732A (en) | 2016-02-05 | 2016-02-05 | Animal heat monitoring system and the body temperature recognition methods based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107041732A true CN107041732A (en) | 2017-08-15 |
Family
ID=59543021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610084359.0A Pending CN107041732A (en) | 2016-02-05 | 2016-02-05 | Animal heat monitoring system and the body temperature recognition methods based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107041732A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108354594A (en) * | 2017-12-28 | 2018-08-03 | 杭州攻壳科技有限公司 | A kind of hog condition detection method and device based on wearable device |
| CN110333692A (en) * | 2019-07-04 | 2019-10-15 | 南京农业大学 | The automatic monitoring diagnosis system of pig fever based on thermal infrared |
| CN113091912A (en) * | 2021-03-31 | 2021-07-09 | 深圳市景新浩科技有限公司 | Infrared temperature measurement system and method based on Internet |
| WO2021196347A1 (en) * | 2020-03-31 | 2021-10-07 | 丰疆智能软件科技(南京)有限公司 | Cattle state monitoring system and monitoring method |
| JP7014280B1 (en) | 2020-10-29 | 2022-02-01 | 横浜ゴム株式会社 | Mirror system |
| CN115363601A (en) * | 2021-08-28 | 2022-11-22 | 淮阴工学院 | Intelligent eyebrow le assisting listening and speaking and use method thereof |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1803088A (en) * | 2006-01-20 | 2006-07-19 | 华南理工大学 | Alarming method of intelligent monitoring system |
| KR20090053326A (en) * | 2007-11-23 | 2009-05-27 | 재단법인서울대학교산학협력재단 | A method for recognizing states of a user using acceleration sensors |
| KR20090079434A (en) * | 2008-01-17 | 2009-07-22 | (주)모빌랩 | Bowling Game Motion recognition method of the handheld terminal uses the SIX-AXIS SENSOR |
| CN104083152A (en) * | 2014-07-17 | 2014-10-08 | 上海翰临电子科技有限公司 | Human body temperature monitoring method and body temperature monitoring system |
| CN104095615A (en) * | 2014-07-17 | 2014-10-15 | 上海翰临电子科技有限公司 | Human sleep monitoring method and system |
| CN105105737A (en) * | 2015-08-03 | 2015-12-02 | 南京盟联信息科技有限公司 | Motion state heart rate monitoring method based on photoplethysmography and spectrum analysis |
| CN204863123U (en) * | 2015-06-01 | 2015-12-16 | 广东顺德云迪爱智能科技有限公司 | Intelligence body temperature monitoring system |
| CN105224104A (en) * | 2015-09-01 | 2016-01-06 | 电子科技大学 | Pedestrian movement's state identification method of mode is held based on smart mobile phone |
-
2016
- 2016-02-05 CN CN201610084359.0A patent/CN107041732A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1803088A (en) * | 2006-01-20 | 2006-07-19 | 华南理工大学 | Alarming method of intelligent monitoring system |
| KR20090053326A (en) * | 2007-11-23 | 2009-05-27 | 재단법인서울대학교산학협력재단 | A method for recognizing states of a user using acceleration sensors |
| KR20090079434A (en) * | 2008-01-17 | 2009-07-22 | (주)모빌랩 | Bowling Game Motion recognition method of the handheld terminal uses the SIX-AXIS SENSOR |
| CN104083152A (en) * | 2014-07-17 | 2014-10-08 | 上海翰临电子科技有限公司 | Human body temperature monitoring method and body temperature monitoring system |
| CN104095615A (en) * | 2014-07-17 | 2014-10-15 | 上海翰临电子科技有限公司 | Human sleep monitoring method and system |
| CN204863123U (en) * | 2015-06-01 | 2015-12-16 | 广东顺德云迪爱智能科技有限公司 | Intelligence body temperature monitoring system |
| CN105105737A (en) * | 2015-08-03 | 2015-12-02 | 南京盟联信息科技有限公司 | Motion state heart rate monitoring method based on photoplethysmography and spectrum analysis |
| CN105224104A (en) * | 2015-09-01 | 2016-01-06 | 电子科技大学 | Pedestrian movement's state identification method of mode is held based on smart mobile phone |
Non-Patent Citations (1)
| Title |
|---|
| 向壔: "《家畜生理生化学》", 28 February 1989, 江西科学技术出版社 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108354594A (en) * | 2017-12-28 | 2018-08-03 | 杭州攻壳科技有限公司 | A kind of hog condition detection method and device based on wearable device |
| CN110333692A (en) * | 2019-07-04 | 2019-10-15 | 南京农业大学 | The automatic monitoring diagnosis system of pig fever based on thermal infrared |
| CN110333692B (en) * | 2019-07-04 | 2021-09-21 | 南京农业大学 | Pig heating automatic monitoring and diagnosis system based on thermal infrared |
| WO2021196347A1 (en) * | 2020-03-31 | 2021-10-07 | 丰疆智能软件科技(南京)有限公司 | Cattle state monitoring system and monitoring method |
| JP7014280B1 (en) | 2020-10-29 | 2022-02-01 | 横浜ゴム株式会社 | Mirror system |
| WO2022091461A1 (en) * | 2020-10-29 | 2022-05-05 | 横浜ゴム株式会社 | Mirror system and aircraft lavatory unit |
| JP2022072117A (en) * | 2020-10-29 | 2022-05-17 | 横浜ゴム株式会社 | Mirror system |
| CN113091912A (en) * | 2021-03-31 | 2021-07-09 | 深圳市景新浩科技有限公司 | Infrared temperature measurement system and method based on Internet |
| CN115363601A (en) * | 2021-08-28 | 2022-11-22 | 淮阴工学院 | Intelligent eyebrow le assisting listening and speaking and use method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107041732A (en) | Animal heat monitoring system and the body temperature recognition methods based on machine learning | |
| CN107041740A (en) | Animal heart rate monitoring system and the Heart Rate States recognition methods based on neutral net | |
| WO2019218602A1 (en) | Internet of things system for cow behavior and physiological characteristics, and operation method therefor | |
| CN108065938A (en) | Animal activity monitors system and the active state recognition methods based on neutral net | |
| CN108064745A (en) | Animal yelps monitoring system and the state identification method of yelping based on machine learning | |
| Alipio et al. | Intelligent wearable devices and biosensors for monitoring cattle health conditions: A review and classification | |
| CN109784200B (en) | Binocular vision-based cow behavior image acquisition and body condition intelligent monitoring system | |
| US11730424B2 (en) | Methods and systems to detect eating | |
| CN105766692B (en) | A kind of cow oestrus detection necklace | |
| KR102315991B1 (en) | Device and system for managing livestck remotly using artificial intelligence | |
| JP2009134590A (en) | Action identification system, action identification method, optimum sensor set determination method and optimum parameter determination method | |
| CN107803843A (en) | A kind of measuring of human health robot based on Raspberry Pi | |
| CN106559744A (en) | It is a kind of based on sparse identification and the body area network power-economizing method of compressed sensing | |
| CN106175779A (en) | A kind of animal health monitoring system | |
| CN105868519A (en) | Human body characteristic data processing method and apparatus | |
| CN108064746A (en) | Drinking water for animals monitors system and the drinking-water state identification method based on neutral net | |
| CN104115763A (en) | Dairy cow estrus monitoring device | |
| US20230225294A1 (en) | Apparatus and methodologies for improved detection of important biological states in animals | |
| CN113221776A (en) | Method for identifying general behaviors of ruminant based on artificial intelligence | |
| Eerdekens et al. | Dog's Behaviour Classification Based on Wearable Sensor Accelerometer Data | |
| CN108065939A (en) | Animal blood glucose monitors system and the blood sugar condition recognition methods based on machine learning | |
| CN108065935A (en) | Animal breath frequency monitoring system and the respiratory rate state identification method based on machine learning | |
| Chung et al. | Subcutaneous temperature monitoring through ear tag for heat stress detection in dairy cows | |
| CN205849445U (en) | A kind of human body physiological characteristics information collecting device merging multisensor | |
| CN108065937A (en) | Animal is run monitoring system and the state identification method of running based on neutral net |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170815 |
|
| WD01 | Invention patent application deemed withdrawn after publication |