NL2035126B1 - Method, system, apparatus and terminal for quality control of growth performance measurement data of breeding pigs - Google Patents
Method, system, apparatus and terminal for quality control of growth performance measurement data of breeding pigs Download PDFInfo
- Publication number
- NL2035126B1 NL2035126B1 NL2035126A NL2035126A NL2035126B1 NL 2035126 B1 NL2035126 B1 NL 2035126B1 NL 2035126 A NL2035126 A NL 2035126A NL 2035126 A NL2035126 A NL 2035126A NL 2035126 B1 NL2035126 B1 NL 2035126B1
- Authority
- NL
- Netherlands
- Prior art keywords
- feed intake
- pig
- weight
- quality control
- measurement
- Prior art date
Links
- 238000005259 measurement Methods 0.000 title claims abstract description 156
- 238000003908 quality control method Methods 0.000 title claims abstract description 116
- 238000000034 method Methods 0.000 title claims abstract description 75
- 230000012010 growth Effects 0.000 title claims abstract description 66
- 241000282887 Suidae Species 0.000 title claims abstract description 62
- 238000009395 breeding Methods 0.000 title claims abstract description 57
- 230000001488 breeding effect Effects 0.000 title claims abstract description 57
- 235000021050 feed intake Nutrition 0.000 claims abstract description 184
- 208000021017 Weight Gain Diseases 0.000 claims abstract description 30
- 235000019786 weight gain Nutrition 0.000 claims abstract description 30
- 230000004584 weight gain Effects 0.000 claims abstract description 30
- 238000007477 logistic regression Methods 0.000 claims abstract description 6
- 230000002159 abnormal effect Effects 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 9
- 206010000188 Abnormal weight gain Diseases 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 5
- 230000000717 retained effect Effects 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 238000012217 deletion Methods 0.000 claims 1
- 230000037430 deletion Effects 0.000 claims 1
- 241000282898 Sus scrofa Species 0.000 description 95
- 230000037396 body weight Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000007547 defect Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000013461 design Methods 0.000 description 5
- 241001465754 Metazoa Species 0.000 description 4
- 230000003542 behavioural effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000002068 genetic effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000007773 growth pattern Effects 0.000 description 2
- 230000008092 positive effect Effects 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 235000021052 average daily weight gain Nutrition 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009396 hybridization Methods 0.000 description 1
- 238000002789 length control Methods 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 230000005923 long-lasting effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K29/00—Other apparatus for animal husbandry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K29/00—Other apparatus for animal husbandry
- A01K29/005—Monitoring or measuring activity, e.g. detecting heat or mating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Environmental Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Animal Husbandry (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Biodiversity & Conservation Biology (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Pure & Applied Mathematics (AREA)
- Educational Administration (AREA)
- Mathematical Physics (AREA)
- Development Economics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Computational Mathematics (AREA)
- Evolutionary Biology (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Marine Sciences & Fisheries (AREA)
- Algebra (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Agronomy & Crop Science (AREA)
- Probability & Statistics with Applications (AREA)
Abstract
The invention belongs to the technical field of automatic growth performance measurement 5 of pigs, in particular to a method, system, apparatus and terminal for quality control of growth performance measurement data of breeding pigs; the method for quality control of the growth performance measurement data of the breeding pigs is characterized by comprising: acquiring measurement data and summarizing to obtain a measurement record sheet, and matching the measurement record sheet with pedigree information; performing quality control on the feed 10 intake rate of each pig by using a quartile method, and calculating the feed intake rate; and calculating weight gains of each pig at adjacent days during a measurement period, performing summary quality control, predicting the weight of each day of age with a Logistic regression model, and calculating to obtain a final weight record of each pig.
Description
METHOD, SYSTEM, APPARATUS AND TERMINAL FOR QUALITY CONTROL OF GROWTH
PERFORMANCE MEASUREMENT DATA OF BREEDING PIGS
The invention belongs to the technical field of automated growth performance measurement of pigs, and particularly relates to a method, a system, an apparatus and a terminal for quality control of growth performance measurement data of breeding pigs.
Currently, the growth performance measurement of breeding pigs is a whole process of raising breeding pigs to a target weight under the same standardized feeding conditions and management level, during which the growth performance indexes of breeding pigs are calculated by continuously recording the feed intake and weight change data of each pig. The growth performance indexes of breeding pigs include data such as age at the target weight (d), average daily weight gain (g/d) and feed conversion ratio (kg/kg feed intake/weight gain) during a measurement period. The growth performance measurement of breeding pigs provides data support for individual genetic assessment and population genetic parameter estimation of livestock. It can guide pig farm managers to improve their feeding management level, unleash the genetic potential of high-quality breeding pigs to improve hybridization plans, and also provide reference for consumers to purchase breeding pigs.
The growth performance measurement needs to be carried out continuously and is a long- lasting task, especially when the measurement population base is large, the workload is particularly huge. It is not only time-consuming and labour-intensive, but also difficult to ensure the accuracy of the measured data when the growth performance is measured manually. With an automated growth performance measurement system, testers can check the feed intake data and weight data of each pig under the condition of group feeding only by logging in the terminal of the measurement system. Upon the advent of the automated growth performance measurement system, the manpower, material resources, and time costs required for growth performance measurement has been greatly reduced.
Due to design defects, mechanical failures, or behavioural problems in live animals, the data recorded by an automated growth performance measurement apparatus are inaccurate in many cases, with a large number of missing values and abnormal values. If the data from automated growth performance measurement are applied directly without processing, the results thus obtained will not only directly affect the accurate assessment of the measured traits, thereby affecting the accuracy of the data collected from domestic pig improvement programs, but affect the effectiveness of breeding and reduce the improvement speed of breeding pigs. As such, more and more investigators have observed the problem of feed intake anomalies and set a threshold for abnormal feed intake greater than 1500 (g) but less than -20 (g), and a threshold for abnormal feed intake duration greater than 1 (h) of feed intake duration. However, both thresholds are set relatively broadly, with a considerable portion of abnormal data having not been controlled for quality, and the dimension of feed intake rate not been taken into account. On the other hand, there are few studies on quality control of weight data, and there are no proven standards.
From the above analysis, the problems and defects in the prior art are: for the quality control of the abnormal data of the automated growth performance measurement, only the threshold value of the abnormal values is provided, without introduction of the complete process from data download to quality control and the details that may be involved in the process. Moreover, the quality control conditions are relatively loose, and a significant part of the abnormal errors cannot be accused off.
In the existing methods for measuring the growth performance of breeding pigs, it is particularly a heavy workload to measure the growth performance manually, which is not only time-consuming and labour-intensive, but also difficult to ensure the accuracy of the measured data.
Due to design defects, mechanical failures, or behavioural problems in live animals, the data recorded by the existing automated growth performance measurement apparatus are inaccurate, thereby affecting the accuracy of breeding data.
For the problems in the prior art, the present invention provides a method, a system, an apparatus and a terminal for quality control of growth performance measurement data of breeding pigs, in particular relates to a method, a system, a medium, an apparatus and a terminal for quality control of growth performance measurement data of breeding pigs based on a quartile method and Logistic regression analysis, aiming at solving the problem that the accuracy of breeding data is influenced by inaccurate recorded data due to design defects, mechanical failures or behavioural problems in live animals.
The present invention is implemented by a method for quality control of growth performance measurement data of breeding pigs, the method for quality control of the growth performance measurement data of the breeding pigs comprising: acquiring measurement data and summarizing to obtain a measurement record sheet, and matching the measurement record sheet with pedigree information; performing quality control on the feed intake rate of each pig by using a quartile method, and calculating feed intake rate; and calculating weight gains of each pig at adjacent days of age in a measurement period, performing summary quality control, and calculating to obtain a final weight record of each pig; the method for quality control of the growth performance measurement data of the breeding pigs comprises the following steps: step 1: downloading all continuous measurement data in a measurement period from a growth performance measurement system for breeding pigs;
step 2: summarizing all measurement records of each pig at different measurement dates in a spreadsheet, and using an individual number of the pigs as a file name; directly deleting data without the individual number;
step 3: matching the measurement record sheet of each pig with pedigree information of the pig,
and adding columns of breed, gender, date of birth and days of age in the sheet;
step 4: performing feed intake quality control, calculating an average daily feed intake amount, an average daily feed intake time, an average daily feed intake duration, an average feed intake amount per time, an average feed intake duration per time and a feed intake rate index for each pig, and performing quality control on the feed intake rate by using a quartile method to obtain an upper edge and a lower edge of the feed intake rate;
step 5: calculating the feed intake rate of each feed intake record of each pig, deleting the record that the feed intake amount is less than the lower edge of the feed intake rate or greater than 1500 (g), and deleting the record that the feed intake duration is less than 1min or greater than 1h; calculating a single maximum feed intake amount by multiplying the feed intake duration by the upper edge of the feed intake rate, and obtaining a single minimum feed intake amount by multiplying the feed intake duration by the lower edge of the feed intake rate; and replacing the feed intake amount record that the feed intake rate is greater than the upper edge of the feed intake rate with the single maximum feed intake amount, and replacing the feed intake amount record that the feed intake rate is less than the lower edge of the feed intake rate with the single minimum feed intake amount;
step 6: respectively performing quality control by a quartile method on a plurality of weight records of each pig obtained by execution of the step 3 at different measured days of age, and deleting weight records beyond the upper edge and the lower edge;
step 7: averaging the plurality of weight records of each measured day of age remained after the execution of the step 6 as the weight for the measured day of age;
step 8: calculating weight gains of each pig at adjacent days of age in the measurement period, and summarizing all the weight gains of all the pigs in the measurement period; and performing quality control by the quartile method, and deleting weight records of abnormal weight gains;
step 9: using a Logistic regression model to respectively perform model fitting of the day-age- related weight on the weight records of each pig obtained by execution of the step 8, so as to predict the weight at each day of age;
step 10: calculating a plurality of difference values by subtracting the plurality of weight records at each measured day of age obtained by execution of the step 6 from predicted weight at the measured day of age of each pig obtained by the step 9;
step 11: summarizing the difference values of weights of all pigs at all measured days of age, and performing quality control by the quartile method to find upper and lower edges of the difference values; and retaining the weight records within the difference range, and replacing the weight records beyond the upper edge and the lower edge with predicted values; and step 12: taking the weight record resulting from execution of the step 11 as the final weight record for each pig.
Further, in step 1, entire CSV format data generated for measurement period is downloaded, format data including all records generated during measurement period, for quality control purposes from source.
In step 2, records of same pig distributed in different testing date tables are aggregated to obtain all testing records for each pig through its testing period.
In step 3, measurement record of each pig is matched with its pedigree information, there by observing growth regularity of each pig at different days of age, and performing inter-breed or intra-breed comparisons.
Further, in step 4, upper and lower edges of feeding rate are found by quartile method as standard of quality control, feeding rate relates to two categories of feeding amount and feeding length, and quality control is performed simultaneously on feeding amount and feeding length.
In step 5, quality control is performed on intake amount, intake length, and intake speed, and intake record of abnormal intake speed is replaced with maximum or minimum intake speed and pulled back into normal range.
In step 6, multiple body weight records of each pig at same measurement date were quality controlled by boxplot quality control based on performing step 3, and more outliers were filtered out.
Further, in step 7, a plurality of normal body weight records on the same measurement date remaining for ach pig after performing step 6 are averaged as the body weight of ach pig on the measurement date.
In step 8, abnormal weight gain is removed by calculating weight gain at adjacent measurement dates and summing up all weight gain records followed by boxplot quality control.
In step 9, day age and weight record of each pig after performing step 8 was modeled by logistic method to find normal weight interval for each pig at day age.
Further, in step 10, weight records of each pig on same measurement date are corrected against by difference between weight values of each pig at different days of age predicted by calculation model and weight records of each pig remaining on same measurement date after performing step 6.
In step 11, quality control is performed by aggregating all differences obtained by all pigs, and then using quartile method to find a reasonable interval of differences;
Body weight records within the range of differences where retained, and body weight records beyond the upper and lower margins where replaced with predicted values; Abnormal body weight records can be pulled back to normal range.
In step 12, final body weight records are subject to multiple quality control.
Another object of the present invention is to provide a system for quality control of growth performance measurement data of breeding pig applying the method for quality control of the growth performance measurement data of breeding pigs. The system for quality control of the growth performance measurement data of breeding pig comprises: 5 a measurement data acquisition module for downloading all continuous measurement data from a breeding pig growth performance measurement system; a data summarization module 2 for summarizing all measurement records of each pig into a spreadsheet; an information matching module for matching the measurement record sheet of each pig with pedigree information; a feed intake rate calculation module for performing quality control on the feed intake rate of each pig by using a quartile method and calculating the feed intake rate; and a weight calculation module for calculating weight gains of each pig at adjacent days of age in a measurement period, performing summary quality control, and calculating to obtain a final weight record of each pig.
Another object of the present invention is to provide a computer device, which comprises a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of: acquiring measurement data and summarizing to obtain a measurement record sheet, and matching the measurement record sheet with pedigree information; performing quality control on the feed intake rate of each pig by using a quartile method, and calculating the feed intake rate; calculating the weight gains of each pig at adjacent days of age during a measurement period, performing summary quality control, and calculating to obtain a final weight record of each pig.
Another object of the present invention is to provide a computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of: acquiring measurement data and summarizing to obtain a measurement record sheet, and matching the measurement record sheet with pedigree information; performing quality control on the feed intake rate of each pig by using a quartile method, and calculating the feed intake rate; calculating the weight gains of each pig at adjacent days of age during a measurement period, performing summary quality control, and calculating to obtain a final weight record of each pig.
Another object of the present invention is to provide an information data processing terminal for implementing the system for quality control of the growth performance measurement data of breeding pigs.
Combining the above technical solution and the technical problems solved, the advantages and positive effects of the technical solution as claimed by the present invention are analyzed from the following aspects as:
Firstly, in view of the above-mentioned technical problems in the prior art and the difficulty of solving the problems, a detailed and profound analysis of how the technical solution of the present invention solving the technical problems, and some creative technical effects brought about by solving the problems is conducted in close combination with the technical solution as claimed by the present invention, the results and data during the research and development process and etc.
The specific description is as follows:
The method of quality control of growth performance measurement data of breeding pig provided by the present invention can achieve the purpose of quality control from the source by downloading all the csv format data generated during the measurement period; the measurement records of each pig are matched with its pedigree information, so as to observe the growth pattern of each pig at different days of age and to make inter- or intra-breed comparisons. The feed intake rate of the present invention involves two categories of feed intake and feed intake duration, thereby achieving the purpose of simultaneously performing quality control on the feed intake and feed intake duration; the quality control was performed on a plurality of weight records for each pig on the same measured date, so that more abnormal values can be filtered out.
According to the present invention, a plurality of normal weight records remaining for each pig on the same measured date are averaged as the weight of each pig on that measured date, thus avoiding the interference from the abnormal values; abnormal weight gains are removed by calculating the weight gains on adjacent measured dates and summarizing all weight gain records and then performing box plot quality control, so that the situation that a plurality of weight records on the measured dates are abnormal can be avoided; the final weight obtained has been subject to many rounds of quality control, so that most abnormal data can be filtered out. The present invention can also effectively solve the problem that the accuracy of breeding data is influenced by inaccurate recorded data due to design defects, mechanical failures or behavioural problems in live animals.
Secondly, considering the technical solution as a whole or from the perspective of the product, the technical effects and advantages of the technical solution as claimed by the present invention are described as follows:
The method adopted by the present invention can carry out quality control on the abnormal growth performance measurement data, improve the accuracy and scientificity of the growth performance measurement data, thereby increasing the improvement speed of the growth speed and feed efficiency characteristics of Chinese breeding pigs.
Thirdly, as creative supporting evidences for the claims of the present invention, it is also embodied in the following important aspects:
The expected benefits and commercial value of the technical solution of the present invention after conversion are as follows:
The technical solution of the present invention, after conversion, can provide a reference for selecting high-quality breeding pigs in breeding pig farms, fully leveraging the value of growth performance measurement.
The technical solution of the present invention fills the technical gaps in the industry at home and abroad: the technical solution of the present invention overcomes the defect that the automated growth performance measurement system for breeding pigs does not have a systematic and complete quality control process.
A brief introduction is present below for the drawings to be used in the embodiments of the present invention so as to explain the technical solution of the embodiments of the present invention more clearly. It will be readily apparent to those of ordinary skill in the art that the accompanying drawings described below are only some embodiments of the present invention and other accompanying drawings can be obtained according to these drawings without any creative effort.
FIG. 1:is a flowchart of a method for quality control of performance measurement data of breeding pigs provided by an embodiment of the present invention;
FIG. 2:is a comparison chart of feed intake rate distribution before and after quality control provided by an embodiment of the present invention;
FIG. 3:is a comparison chart of feed intake distribution before and after quality control provided by an embodiment of the present invention;
FIG. 4:is a comparison chart of feed intake duration distribution before and after quality control provided by an embodiment of the present invention;
FIG. 5:is a comparison chart of the weight of some individuals before and after quality control using this method, as well as the predicted weight values of the model provided by an embodiment of the present invention;
FIG. 6:is a structural block diagram of a quality control system for growth performance measurement data of breeding pigs provided by an embodiment of the present invention; in which: 1, measurement data acquisition module;2, data summarization module;3, information matching module;4, feed intake rate calculation module; 5, weight calculation module.
The objects, the technical solution and the advantages of the present disclosure will become more apparent from the following detailed description of the present invention taken in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but are not used to limit the present invention.
Aiming at the problems in the prior art, the present invention provides a method, a system, an apparatus and a terminal for quality control of growth performance measurement data of breeding pigs, and the present invention will be described in detail taken in conjunction with the accompanying drawings.
Illustrative embodiments. In order to enable those skilled in the art to fully understand how the present invention is specifically implemented, this section provides the illustrative embodiments of the claimed technical solution.
As shown in FIG. 1, the method for quality control of growth performance measurement data of breeding pigs provided by the embodiments of the present invention comprises the steps of:
S 101: acquiring measurement data and summarizing to obtain a measurement record sheet, and matching the measurement record sheet with pedigree information;
S 102: performing quality control on the feed intake rate of each pig by using a quartile method, and calculating the feed intake rate;
S103: calculating the weight gains of each pig at adjacent days of age during a measurement period, performing summary quality control, and calculating to obtain a final weight record of each pig.
As a preferred embodiment, the method for quality control of growth performance measurement data of breeding pigs based on the quartile method and Logistic regression analysis provided by the embodiments of the present invention specifically comprises the steps of:
Step 1: downloading all the continuous measurement data during a measurement period from a growth performance measurement system for breeding pigs;
Step 2: for each pig, summarizing all the measurement records on different measured dates in a spreadsheet, with the individual number of the pig as the name of the spreadsheet; deleting the data without individual number directly;
Step 3: matching the measurement record sheet of each pig with its pedigree information, and adding the columns of breed, gender, date of birth and days of age in the sheet;
Step 4: performing feed intake quality control, calculating the indexes of average daily feed intake (kg), average daily feed intake times, average daily feed intake time (min), average feed intake per feeding (kg), average feed intake time per feeding (min) and feed intake rate (g/min) for each pig, and applying the quartile method to perform quality control on the feed intake rate so as to obtain an upper edge and a lower edge of the feed intake rate;
Step 5: calculating a feed intake rate for each feed intake record of each pig, deleting the records of the feed intake being less than the lower edge (g) or being greater than 1500 (g) of the feed intake rate, deleting the records of the feed intake time being less than 1 (min) or being greater than 1 (h}, calculating a single maximum feed intake by multiplying the feed intake duration by the upper edge of the feed intake rate, obtaining a single small feed intake by multiplying the feed intake duration by the lower edge of the feed intake rate, replacing the feed intake record of the feed intake rate being greater than the upper edge of the feed intake rate with the single maximum feed intake, and replacing the feed intake record of the feed intake rate being less than the lower edge of the feed intake rate with the single minimum feed intake;
Step 6: performing quality control on a plurality of weight records of each pig obtained at the step 3 at different measured days of age separately by the quartile method, and deleting the weight records beyond the upper edge and the lower edge;
Step 7: averaging the plurality of weight records at each measured day of age remaining from the execution of the step 6 as the weight at that measured day of age;
Step 8: calculating the weight gain of each pig at adjacent days of age during the measurement period, and summarizing all the weight gains of all the pigs during their measurement period, performing quality control by the quartile method, and deleting the weight records with abnormal weight gain;
Step 9: using a Logistic regression model to respectively perform model fitting of the day-age- related weight on the weight records of each pig resulting from the step 8, so as to predict the weight at each day of age;
Step 10: calculating a plurality of differences with the predicted weight of each pig at its measured day of age obtained at the step 9 minus the plurality of weight records at each measured day of age obtained at the step 6;
Step 11: summarizing the weight differences of all pigs at all measured days of age, and performing quality control by the quartile method to identify the upper and lower edges of the differences, and keeping the weight records within the range of the differences, and replacing the weight records beyond the upper and lower edges with predicted values;
Step 12: taking the weight records resulting from executing the step 11 as the final weight record for each pig.
At the step 1, it is preferably to download all csv format data generated during the measurement period, the format data including all records generated during the measurement period, thereby achieving the purpose of quality control from the source.
At the step 2, it is preferably to summarize the records of the same pig distributed in the sheets of different measured dates, so as to obtain all the measurement records of each pig during the whole measurement period.
At the step 3, it is preferably to match the measurement records of each pig with its pedigree information, so as to observe the growth pattern of each pig at different days of age and to make inter- or intra-breed comparisons.
At the step 4, it is preferably to identify the upper and lower edges of the feed intake rate as criteria for quality control by the quartile method, the feed intake rate involving two categories of feed intake and feed intake duration, thereby achieving the purpose of simultaneously performing quality control on the feed intake and feed intake duration.
At the step 5, it is preferably to perform quality control on the feed intake, feed intake duration and feed intake rate sequentially, and replace the feed intake records of abnormal feed intake rate with the maximum or minimum feed intake rate so as to pull back to the normal range.
At the step 6, it is preferably to perform, on the basis of the step 3, quality control on the plurality of weight records for each pig on the same measured date by the box plot quality control method, so that more abnormal values can be filtered out.
At the step 7, it is preferably to average the plurality of normal weight records remaining for each pig on the same measured date after the step 7 as the weight of each pig on that measured date, thus avoiding the interference from the abnormal values.
At the step 8, itis preferably to remove the abnormal weight gains by calculating the weight gains on the adjacent measured dates and summarizing all the weight gain records and then performing box plot quality control, so that the situation that the plurality of weight records on the measured dates are abnormal can be avoided.
At the step 9, it is preferably to perform the Logistic method for modelling the days of age and the weight records of each pig after the step 8 to identify a normal weight interval for each pig at that days of age.
At the step 10, it is preferably to correct the plurality of weight records for each pig on the same measured date again by calculating the differences with the weight values predicted by the model for each pig at different days of age minus the weight records retained for each pig on the same measured date after the step 6.
At the step 11, it is preferably to summarize all the differences obtained from all the pigs, and perform quality control using the quartile method to identify a reasonable interval of the differences.
At the step 12, it is preferably to perform many rounds of quality control on the final weight resulting from the step 12, so that most abnormal data can be filtered out.
In embodiments of the present invention, comparison of feed intake rate distribution before and after quality control is shown in FIG. 2, comparison of feed intake amount distribution before and after quality control is shown in FIG. 3, comparison of feed intake duration distribution before and after quality control is shown in FIG. 4, and comparison of weight of some individuals before and after quality control using this method, as well as the predicted weight values of a model is shown in FIG. 5.
As shown in FIG. 6, the system for quality control of growth performance measurement data of breeding pigs provided in the embodiment of the present invention comprises: a measurement data acquisition module 1 for downloading all continuous measurement data from a breeding pig growth performance measurement system; a data summarization module 2 for summarizing all measurement records of each pig into a spreadsheet; an information matching module 3 for matching the measurement record spreadsheet of each pig with pedigree information; a feed intake rate calculation module 4 for performing quality control on the feed intake rate of each pig by using a quartile method and calculating the feed intake rate;
and a weight calculation module 5 for calculating weight gains of each pig at adjacent days of age in a measurement period, performing summary quality control, and calculating to obtain a final weight record of each pig.
The technical solution of the present invention is further described below in conjunction with a specific embodiment.
The method for quality control of growth performance measurement data of the breeding pigs provided in the embodiment of the present invention specifically comprises the following steps: downloading all csv format data in a measurement period from a growth performance measurement system for breeding pigs; (1) downloading a total of 1, 223, 220 growth performance measurement records of 1608 pigs from June 27, 2021 to October 31, 2021 for a total of 127 days in a breeding pig farm; (2) for each pig, summarizing all the measurement records at different measurement dates in an excel sheet, with an individual number of the pig as a file name, and directly deleting data without the individual number, wherein 1806 sheets named by numbers of different pigs are obtained in total; (3) matching the measurement record sheet of each pig with pedigree information of the pig, and adding columns of breed, gender, date of birth and days of age in the sheet; (4) first performing feed intake quality control, calculating indexes of an average daily feed intake amount (kg), an average daily feed intake time, an average daily feed intake duration (min), an average feed intake amount per time {kg}, an average feed intake duration per time(min) and a feed intake rate (g/min) for each pig, and performing quality control on the feed intake rate by using a quartile method so as to obtain an upper edge of 66(g/min) and a lower edge of 18(g/min) of the feed intake rate; (5) calculating the feed intake rate of each feed intake record of each pig, deleting records of the feed intake amounts being less than the lower edge of 18 (g) of the feed intake rate or greater than 1500 (g), deleting records of the feed intake duration being less than 1min or greater than 1h, calculating a single maximum feed intake amount by multiplying the feed intake duration by the upper edge of 66 (g/min) of the feed intake rate, obtaining a single minimum feed intake amount by multiplying the feed intake duration by the lower edge of the feed intake rate, and replacing a feed intake amount record of the feed intake rate being greater than the upper edge of the feed intake rate with the single maximum feed intake amount, and replacing a feed intake amount record of the feed intake rate being less than the lower edge of the feed intake rate with the single minimum feed intake amount; (6) respectively performing quality control by the quartile method on a plurality of weight records of each pig obtained by execution of the step 3 at different measured days of age, and deleting weight records beyond the upper edge and the lower edge; (7) averaging the plurality of normal weight records of each pig at one same measurement date retained after the execution of the step 6 as the weight at the measurement date;
(8) calculating weight gains of each pig at adjacent measurement dates, summarizing all the weight gains of all the pigs, performing quality control by the quartile method, finding an upper edge of weight gain being 5(kg) and a lower edge being -3(kg), and deleting weight records at dates of abnormal weight gains with weight gain values greater than the upper edge of the weight gain or less than the lower edge of the weight gain; (9) using a Logistic method for modelling the days of age and the weight records of each pig after execution of the step 8, so as to find the normal weight interval of each pig at the day of age; a Logistic formula is shown as follows:
Yt=A/(1+Be-kt), wherein Yt. t-day age weight (kg); A: maximum weight (kg}; k: instantaneous growth rate;
B: biological constants; t: days of age; e: natural logarithm; (10) calculating difference values obtained by subtracting the weight records of each pig at the same measurement date retained after execution of the step 6 from the weight values predicted by a model of each pig at different days of age; (11)summarizing all difference values of all pigs, performing quality control by the quartile method to find an upper edge being 3(kg) and a lower edge being -4(kg) of the difference values, retaining the weight records within the upper edge and the lower edge, and replacing the weight records beyond the upper edge and the lower edge with predicted values;
I. Application Embodiments
In order to prove the creativity and technical value of the technical solution of the invention, this section provides embodiments of the claimed technical solution on specific products or related technologies.
The technical solution of the invention can be used for quality control of weight recording and feed intake recording for various brands of automated growth performance measurement systems.
II. Evidence of Relevant Effects of Embodiments
Embodiments of the present invention have achieved some positive effects in the process of research and development or use, and have great advantages compared with the prior art. The following contents are described in combination with data, charts and the like of the test process.
The minimum feed intake amount set by the present invention is greater than or equal to 18 (9); the minimum feed intake duration is greater than 1 (min); the feed intake rate is between 18 (g/min) and 66(g/min); compared with threshold values of maximum feed intake amount being greater than 1500(g), single minimum feed intake amount being less than -20(g), feed intake rate being 500(g/min) and feed intake duration being less than 1(h) set by others, the threshold values set in this study are more strict and reasonable, and the quality control effects on abnormal data can be better achieved.
It should be noted that embodiments of the present invention may be implemented in hardware, software, or a combination of hardware and software. The hardware may be implemented by using dedicated logic; The software may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or dedicated design hardware. Those ordinary skilled in the art may appreciate that devices and methods described above may be implemented using computer-executable instructions and/or contained in processor control codes, such codes are provided, for example, on a carrier medium such as a magnetic disk, a CD or a DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The device of the present invention and modules may be implemented by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc. or programmable hardware devices such as field programmable gate arrays, programmable logic devices, by software executed by various types of processors, or by a combination of the above hardware circuits and software, e.g. firmware.
The above is only the specific embodiment of the present invention, but the protection scope of the present invention is not limited to this. Any modification, equivalent substitution, improvement, etc. made by any person familiar with the technical field within the technical scope disclosed by the present invention within the spirit and principle of the present invention should be covered within the protection scope of the present invention.
Claims (9)
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210706793.3A CN115168342B (en) | 2022-06-21 | 2022-06-21 | Quality control method, system, equipment and terminal for boar growth performance measurement data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| NL2035126A NL2035126A (en) | 2024-01-05 |
| NL2035126B1 true NL2035126B1 (en) | 2024-01-26 |
Family
ID=83487897
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| NL2035126A NL2035126B1 (en) | 2022-06-21 | 2023-06-19 | Method, system, apparatus and terminal for quality control of growth performance measurement data of breeding pigs |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115168342B (en) |
| NL (1) | NL2035126B1 (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7399220B2 (en) * | 2002-08-02 | 2008-07-15 | Kriesel Marshall S | Apparatus and methods for the volumetric and dimensional measurement of livestock |
| CN104915535B (en) * | 2015-02-04 | 2019-04-30 | 湖南农业大学 | Biotic population dynamic prediction analyzes global general-use key factor preset group platform |
| CN104871999B (en) * | 2015-04-28 | 2018-03-16 | 范石军 | A kind of intelligence intensive domestic animal, poultry monitoring system and method |
| CN106172082A (en) * | 2016-07-12 | 2016-12-07 | 中国农业大学 | For the method analyzing poultry growth performance automatic measurement system noisy data |
-
2022
- 2022-06-21 CN CN202210706793.3A patent/CN115168342B/en active Active
-
2023
- 2023-06-19 NL NL2035126A patent/NL2035126B1/en active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115168342B (en) | 2023-05-05 |
| CN115168342A (en) | 2022-10-11 |
| NL2035126A (en) | 2024-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Steeneveld et al. | Economic consequences of investing in sensor systems on dairy farms | |
| Urioste et al. | Phenotypic and genetic characterization of novel somatic cell count traits from weekly or monthly observations | |
| Kocher et al. | The pattern of thoroughbred growth is affected by a foal's birthdate | |
| CN111985670A (en) | Aquaculture monitoring method and device and storage medium | |
| Waldner et al. | Identifying performance benchmarks and determinants for reproductive performance and calf survival using a longitudinal field study of cow-calf herds in western Canada | |
| Migose et al. | Accuracy of estimates of milk production per lactation from limited test-day and recall data collected at smallholder dairy farms | |
| Wolc et al. | Heritability of perching behavior and its genetic relationship with incidence of floor eggs in Rhode Island Red chickens | |
| NL2035126B1 (en) | Method, system, apparatus and terminal for quality control of growth performance measurement data of breeding pigs | |
| Lovarelli et al. | Relating lying behavior with climate, body condition score, and milk production in dairy cows | |
| Clegg et al. | A simulation approach to assessing bias in a fisheries self-sampling programme | |
| Steyn et al. | Optimal definition of contemporary groups for crossbred pigs in a joint purebred and crossbred genetic evaluation | |
| Plenio et al. | Application note: Validation of BovHEAT—An open-source analysis tool to process data from automated activity monitoring systems in dairy cattle for estrus detection | |
| Wethal et al. | A genetic study of new udder health indicator traits with data from automatic milking systems | |
| Seymour et al. | Associations between feed efficiency and aspects of lactation curves in primiparous Holstein dairy cattle | |
| Gao et al. | Genetic parameters and genomic prediction for feed intake recorded at the group and individual level in different production systems for growing pigs | |
| Gautam et al. | Risk factors for culling, sales and deaths in New Zealand dairy goat herds, 2000–2009 | |
| Johnston et al. | Using time‐series analysis techniques to enhance the understanding of musculoskeletal injury in Thoroughbred racehorses | |
| US11576354B2 (en) | Method for customized monitoring of sounds caused by respiratory distress | |
| Garrido-Izard et al. | Cleansing data from an electronic feeding station to improve estimation of feed efficiency | |
| Shrestha et al. | Financial vulnerability of dairy farms challenged by Johne's disease to changes in farm payment support | |
| Underwood et al. | Demographic variables are poor indicators of Wood Thrush productivity | |
| Hollifield et al. | Impact of including the cause of missing records on genetic evaluations for growth in commercial pigs | |
| Zumbach et al. | Use of serial pig body weights for genetic evaluation of daily gain | |
| Rees et al. | Measuring antimicrobial use on dairy farms: a longitudinal method comparison study | |
| Uskenov et al. | Automatic cattle weighing on pastures with behavioral analysis during drinking |