CN115136912A - Disease incidence prediction method for cultured shrimps by combining water quality parameters and behavior sounding - Google Patents
Disease incidence prediction method for cultured shrimps by combining water quality parameters and behavior sounding Download PDFInfo
- Publication number
- CN115136912A CN115136912A CN202110345830.8A CN202110345830A CN115136912A CN 115136912 A CN115136912 A CN 115136912A CN 202110345830 A CN202110345830 A CN 202110345830A CN 115136912 A CN115136912 A CN 115136912A
- Authority
- CN
- China
- Prior art keywords
- water quality
- shrimp
- shrimps
- channels
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 213
- 238000000034 method Methods 0.000 title claims abstract description 27
- 201000010099 disease Diseases 0.000 title claims abstract description 23
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 23
- 241000143060 Americamysis bahia Species 0.000 title claims abstract 36
- 241000238557 Decapoda Species 0.000 claims abstract description 310
- 238000012544 monitoring process Methods 0.000 claims abstract description 45
- 230000008859 change Effects 0.000 claims abstract description 38
- 230000002159 abnormal effect Effects 0.000 claims description 76
- 230000006399 behavior Effects 0.000 claims description 61
- 230000004634 feeding behavior Effects 0.000 claims description 50
- 230000007613 environmental effect Effects 0.000 claims description 46
- 230000003938 response to stress Effects 0.000 claims description 31
- 230000037406 food intake Effects 0.000 claims description 21
- 238000006243 chemical reaction Methods 0.000 claims description 16
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 9
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 4
- 229910052760 oxygen Inorganic materials 0.000 claims description 4
- 239000001301 oxygen Substances 0.000 claims description 4
- 230000020595 eating behavior Effects 0.000 claims description 3
- 230000003542 behavioural effect Effects 0.000 claims 2
- 230000008569 process Effects 0.000 abstract description 5
- 238000009360 aquaculture Methods 0.000 description 6
- 244000144974 aquaculture Species 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 241000894006 Bacteria Species 0.000 description 3
- 241000195493 Cryptophyta Species 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 3
- 230000019020 vocalization behavior Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012258 culturing Methods 0.000 description 2
- 230000006866 deterioration Effects 0.000 description 2
- 230000029142 excretion Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000004083 survival effect Effects 0.000 description 2
- 244000052616 bacterial pathogen Species 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006806 disease prevention Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 235000012631 food intake Nutrition 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 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
- 230000036285 pathological change Effects 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000001766 physiological effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; CARE OF BIRDS, FISHES, INSECTS; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K61/00—Culture of aquatic animals
- A01K61/50—Culture of aquatic animals of shellfish
- A01K61/59—Culture of aquatic animals of shellfish of crustaceans, e.g. lobsters or shrimps
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Abstract
The invention provides a method for predicting the morbidity of cultured shrimps by combining water quality parameters and behavior sounding, which comprises the steps of arranging nine independent signal acquisition units, and arranging a microprocessor, a water quality detector and a hydrophone in each independent unit to establish a water quality and acoustic parameter monitoring channel and analyze information; the signal acquisition unit records water quality parameters through a water quality detector, behavior sounding signals of shrimp aquatic organisms when the water quality is unchanged are acquired through a hydrophone, and the signal analysis unit judges the water quality change of the nine positions; the signal analysis unit comprises a double-channel water quality acoustic comprehensive algorithm model and a multi-channel water quality acoustic comprehensive algorithm model for analysis and judgment. The method for predicting the disease onset of the cultured shrimps by combining the water quality parameters and behavior sounding can effectively and reliably analyze and process the water quality parameters of the shrimp pond and realize the prediction of the disease onset of the shrimps in the shrimp pond.
Description
Technical Field
The invention relates to the technical field of aquaculture and information, in particular to a method for predicting the morbidity of cultured shrimps by combining water quality parameters and behavior sounding.
Background
The fact that the living state of the underwater cultured shrimps can be monitored in real time in the aquaculture process is the key of aquaculture informatization, and due to the fact that the optical visibility of the aquaculture environment is poor usually, the underwater shrimp aquaculture environment is limited at night, and effective observation and monitoring cannot be achieved only through a camera shooting method. In addition, with the development of intensive and economical cultivation, sudden water body deterioration, pathological changes of the cultivated shrimps, feed corruption pollution and the like can cause the death of the cultivated shrimps in the whole pond, so that the cultivation risk is increased. Therefore, the method is very important for obtaining the living conditions of the shrimps in real time in the culture environment and predicting the health condition.
The water quality maintenance in the culture process is the key for ensuring the growth of the cultured shrimps. In the process of culturing the young shrimps in the initial stage, water quality regulation, disease prevention and the like need to be considered, and the purposes of health care young shrimps culture and water quality pollution reduction can be achieved through methods of 'algae culture in the early stage, bacteria culture in the middle and later stages' experience, regular addition of beneficial bacteria and the like. However, there are many sudden influencing factors in the cultivation process, such as: in summer with higher water temperature or after heavy rains, algae are aged and died continuously, and harmful bacteria are propagated in large quantities; in addition, the prawns are easy to be infected by pathogenic bacteria and suffer from disease and the food intake is reduced due to the physical decline caused by stress; especially in the later stage of cultivation, as the feeding times and the feeding amount are unreasonably controlled, residual bait excrement, dead algae, protozoa and the like can settle, so that the bottom of the pond is decayed and fermented, and bottom mud is blackened and smelly. The sudden water quality deterioration causes the disease and death of the prawns, further causes the pollution of the water body of the whole pond and influences the ecological environment, and becomes a great risk hazard in the shrimp pond culture.
The culture environment is very important for culturing the shrimps, and on one hand, the water quality change needs to be mastered, and on the other hand, the behavior change of the underwater shrimps along with the water quality change needs to be determined by combining the behavior characteristics of the shrimps, so that the disease occurrence condition of the shrimps is determined.
The underwater shrimp activity condition in aquaculture is difficult to master, the underwater behavior characteristics of the shrimps can be determined by using the sound information, and the abnormal behavior condition of the shrimps in water can be determined according to the shrimp behaviors.
The prawn morbidity phenomenon can be timely and effectively early warned by utilizing the changes of the dissolved oxygen, the pH value, the temperature and the salinity parameters of different time and environment. The disease causes of the shrimps can be determined according to the change of the water quality environmental parameters and the behavior change of the shrimps, and the shrimps can be prevented and treated in time.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the method for predicting the disease onset of the cultured shrimps by combining the water quality parameters and behavior sounding, so that the water quality parameters of the shrimp pond can be effectively and reliably analyzed and processed, and the prediction of the disease onset of the shrimps in the shrimp pond is realized.
In order to achieve the purpose, the invention provides a method for predicting the onset of diseases of the cultured shrimps by combining water quality parameters and behavior sounding, which comprises the following steps:
s1: nine independent water quality and acoustic parameter monitoring channels are established by arranging a plurality of independent signal acquisition units in the shrimp pond, wherein each signal acquisition unit comprises a microprocessor, and a water quality detector and a hydrophone which are connected with the microprocessor; a signal analysis unit is connected with each signal acquisition unit;
s2: original signals are collected and recorded through the signal collecting unit, and the original signals comprise water quality parameters collected by the water quality detector and behavior sounding signals, collected by the hydrophone, of shrimp aquatic organisms generated when the water quality is unchanged;
s3: the microprocessor comprises a double-channel water quality acoustic comprehensive algorithm model, and the original signals are analyzed and judged by using the double-channel water quality acoustic comprehensive algorithm model to obtain the environment and shrimp state information of each acoustic parameter monitoring channel; the environment and shrimp state information comprises water quality environment parameter abnormal information, shrimp stress response information, shrimp non-ingestion behavior information and shrimp ingestion behavior abnormal information;
s4: the signal analysis unit comprises a multi-channel water quality acoustic comprehensive algorithm model; and judging whether the growth conditions of the shrimps in the shrimp pond are normal or not according to the multi-channel water quality acoustic comprehensive algorithm model and the environment and shrimp state information.
Preferably, in the step S3, the two-channel water quality acoustic comprehensive algorithm model receives the water quality parameters according to the length of a default input signal, and the water quality parameters include dissolved oxygen, pH value, temperature and salinity; comparing the original collected signals of the water quality and acoustic parameter monitoring channels with preset template signals, and opening shrimp acoustic parameter monitoring channels or outputting water quality environmental parameter abnormal information according to comparison results;
the two-channel water quality acoustic comprehensive algorithm model receives behavior sounding signals generated by the shrimp aquatic organisms when the water quality is unchanged according to the length of a default input signal, compares the behavior sounding signals generated by the shrimp aquatic organisms when the water quality is unchanged, which are originally collected by the water quality and acoustic parameter monitoring channels, with a preset stress template signal, and outputs stress response information of the shrimps, feeding-free behavior information of the shrimps, feeding behavior abnormal information of the shrimps or normal growth condition information of the shrimps.
Preferably, the S3 step further comprises the steps of:
s31: judging the water quality parameters of the water quality and acoustic parameter monitoring channels, calculating the standard deviation of the water quality parameters of the water quality and acoustic parameter monitoring channels, judging the water quality parameters to be normal and starting shrimp acoustic parameter monitoring channels when the standard deviation of the water quality parameters is less than or equal to a preset threshold value, and performing next judgment, otherwise, exiting the algorithm, and outputting and reporting abnormal information of the water quality environment parameters;
s32: if the shrimp acoustic parameter monitoring channel is opened, judging shrimp sounding signals in the water quality and acoustic parameter monitoring channels, wherein the shrimp sounding signals are acquired through the hydrophone, calculating the variation mean value of the shrimp sounding signals, and judging that the shrimps have no stress response and entering the next step of judgment when the variation mean value of the shrimp sounding signals is greater than or equal to a second threshold value or less than or equal to a first threshold value; when the variation mean value of the shrimp sounding signals is smaller than the second threshold value and larger than the first threshold value, judging that the shrimps have stress reactions, exiting the algorithm, and outputting and reporting the stress reaction information of the shrimps;
s33: judging the shrimp sounding signals in the water quality and acoustic parameter monitoring channels, calculating the mean value of the change of the shrimp sounding signals, judging the shrimp eating behavior when the mean value of the change of the shrimp sounding signals is greater than the second threshold value, and performing the next judgment; when the variation mean value of the shrimp sounding signals is smaller than the first threshold value and is kept smaller than the first threshold value within 24 hours, judging that the shrimps do not generate the feeding behavior, exiting the algorithm, and outputting and reporting the information of the shrimp non-feeding behavior;
s34: when the variation mean value of the shrimp sounding signals is larger than the second threshold value but the frequency appearing within 24 hours is smaller than a preset frequency threshold value, judging that the shrimp feeding behavior is abnormal, exiting the algorithm, and outputting and reporting the shrimp feeding behavior abnormal information; otherwise, outputting and reporting normal information of the shrimp growth condition.
Preferably, the S4 step further comprises the steps of:
s41: counting the number of channels reporting the abnormal information of the water quality environmental parameters, and entering the next judgment when the number of the abnormal information of the water quality environmental parameters is less than 5; when the number of the abnormal water quality environmental parameter information is more than or equal to 5, reporting that the number of the channels of the abnormal water quality environmental parameter information exceeds 50% of the total number of the channels, judging that the abnormal change of the water quality environmental parameter is detected, exiting the algorithm, and outputting that the water quality environmental parameter is abnormal;
s42: counting the number of channels reporting the stress response information of the shrimps, entering next judgment when the number of the channels reporting the stress response information of the shrimps is less than 5, judging that the shrimps are detected to have a disease occurrence phenomenon when the number of the channels reporting the stress response information of the shrimps is more than 50% of the total number of the channels when the number of the channels reporting the stress response information of the shrimps is more than or equal to 5, exiting the algorithm, and outputting that the shrimps have the disease occurrence;
s43: counting the number of channels reporting the information of the shrimp non-ingestion behavior, entering next judgment when the number of the channels reporting the information of the shrimp non-ingestion behavior is less than 5, and judging that the shrimp is possibly attacked when the number of the channels reporting the information of the shrimp non-ingestion behavior is more than or equal to 5 and the number of the channels reporting the information of the shrimp non-ingestion behavior exceeds 50 percent of the total number of the channels;
s44: counting the number of channels reporting the abnormal information of the shrimp feeding behavior, entering next judgment when the number of the abnormal information of the shrimp feeding behavior is less than 5, judging that the abnormal phenomenon of the shrimp growth condition is detected when the number of the channels reporting the abnormal information of the shrimp feeding behavior is more than or equal to 5 and the number of the channels reporting the abnormal information of the shrimp feeding behavior exceeds 50 percent of the total number of the channels, and exiting the algorithm at the moment to output the abnormal shrimp growth condition;
s45: counting the number of channels reporting the stress response information of the shrimps, comparing the number of the channels reporting the stress response information of the shrimps with the sum of the number of the channels reporting the non-feeding behavior information of the shrimps and the number of the channels reporting the abnormal feeding behavior information of the shrimps, and when the number of the channels reporting the stress response information of the shrimps is more than or equal to the sum of the number of the channels reporting the non-feeding behavior information of the shrimps and the number of the channels reporting the abnormal feeding behavior information of the shrimps, exiting the algorithm at this moment, outputting that the shrimps grow healthily, otherwise, outputting that the shrimp growth condition is normal.
Preferably, the signal acquisition unit records data for 30 minutes by default, and records data every 60 minutes.
Preferably, the method further comprises the steps of: and carrying out Fourier transform on the shrimp sounding signals of the water quality and acoustic parameter monitoring channels to obtain shrimp sounding pulse change signals, and taking the shrimp sounding pulse change signals as comparison signals.
Preferably, the multi-channel water quality acoustic comprehensive algorithm model outputs a report to a display unit and a terminal, and the display unit displays an analysis result in real time.
Due to the adoption of the technical scheme, the invention has the following beneficial effects:
according to the method for predicting the growth conditions of the shrimps in the shrimp pond based on water quality and shrimp feeding and sounding information comprehensive analysis, water quality parameter signals and shrimp behavior sounding information of corresponding water areas are acquired by a plurality of signal acquisition units which are combined with a microprocessor, a water quality parameter recorder and a hydrophone, the water quality condition of water environment and the shrimp growth condition are obtained through judgment of a double-channel water quality acoustic comprehensive algorithm model, and the water quality monitoring algorithm model and the shrimp behavior sounding judgment algorithm model output judgment results through the multi-channel water quality acoustic comprehensive algorithm model are analyzed and comprehensively judged, so that a relatively accurate result of the shrimp growth condition of the shrimp pond can be obtained. According to the method, the water quality environmental parameter and the shrimp sounding signal are effectively and reliably analyzed and processed by researching the corresponding relation between the change of the water quality environmental parameter and the behavior sounding of the shrimps and the growth condition of the shrimps, the prediction of the shrimp disease occurrence condition of the shrimp pond is improved, a good effect is achieved in the aspect of predicting the shrimp disease occurrence of the shrimp pond, and the full-automatic shrimp pond shrimp growth analysis prediction based on signal processing can be realized by applying a shrimp pond multi-channel water quality-acoustics online monitoring model.
Drawings
FIG. 1 is a schematic diagram of a method for predicting the onset of diseases of cultured shrimps by combining water quality parameters and behavior sounding according to an embodiment of the invention;
FIG. 2 is a flow chart of dual-channel water quality acoustic comprehensive algorithm model judgment according to the embodiment of the invention;
FIG. 3 is a flow chart of multi-channel water quality acoustic comprehensive algorithm model judgment according to the embodiment of the invention.
Detailed Description
The following description of the preferred embodiments of the present invention will be provided in conjunction with the accompanying drawings, which are set forth in detail below to provide a better understanding of the function and features of the invention.
Referring to fig. 1 to 3, a method for predicting the onset of disease of cultured shrimps by combining water quality parameters and behavior sounding according to an embodiment of the present invention includes the steps of:
s1: nine independent water quality and acoustic parameter monitoring channels are established by arranging a plurality of independent signal acquisition units in the shrimp pond, and each signal acquisition unit comprises a microprocessor, and a water quality detector and a hydrophone which are connected with the microprocessor; and a signal analysis unit is connected with each signal acquisition unit.
The invention establishes nine independent channel units, each channel unit comprises a water quality parameter monitoring channel and a shrimp sounding monitoring channel, and each independent unit is internally provided with a water quality detector and a hydrophone so as to establish respective monitoring channels for water quality and shrimp sounding. The invention predicts the onset of the shrimps by nine channel units, can effectively avoid the random excretion physiological activity of aquatic organisms of the shrimps and the influence of the analysis result of the whole water composition of the artificially fed shrimp pool, judges whether the behavior of the shrimps is abnormal or not by sounding in water, and improves the accuracy of predicting the onset of the shrimps in the water.
S2: the signal acquisition unit is used for collecting and recording original signals, wherein the original signals comprise water quality parameters collected by the water quality detector and behavior sounding signals generated by shrimp aquatic organisms collected by the hydrophone when the water quality is unchanged.
And collecting original signals, and recording related parameters of water quality and sounding signals of daily activities of shrimps by a signal acquisition unit. The signal unit comprises a water quality sensor for recording water quality parameters and a hydrophone for recording the sounding behaviors of the shrimps. The water quality sensor is the existing sensor, and changes of the sensed chemical component content of water quality are converted into electric signals, so that the changes of the water quality are recorded. The hydrophone is an existing hydrophone, and converts sensed shrimp sounding signals into electric signals, so that the sounding behaviors of shrimps are recorded.
S3: the microprocessor comprises a double-channel water quality acoustic comprehensive algorithm model, and the original signals are analyzed and judged by using the double-channel water quality acoustic comprehensive algorithm model to obtain the environment and shrimp state information of each acoustic parameter monitoring channel; the environment and shrimp state information comprises water quality environment parameter abnormal information, shrimp stress response information, shrimp non-ingestion behavior information and shrimp ingestion behavior abnormal information;
s4: the signal analysis unit comprises a multi-channel water quality acoustic comprehensive algorithm model; and judging whether the growth conditions of the shrimps in the shrimp pond are normal or not through a multi-channel water quality acoustic comprehensive algorithm model and the environment and shrimp state information.
The signal analysis unit judges the growth condition of the shrimps.
S3, receiving water quality parameters by the dual-channel water quality acoustic comprehensive algorithm model according to the length of a default input signal, wherein the water quality parameters comprise dissolved oxygen, a pH value, a temperature and salinity; comparing the original collected signals of the water quality and acoustic parameter monitoring channels with preset template signals, and starting the shrimp acoustic parameter monitoring channels or outputting water quality environmental parameter abnormal information according to the comparison result;
the behavior sounding signal generated by shrimp aquatic organisms when the water quality is unchanged is received according to the length of a default input signal of the double-channel water quality acoustic comprehensive algorithm model, the behavior sounding signal generated by the shrimp aquatic organisms when the water quality is unchanged, which is originally collected in each water quality and acoustic parameter monitoring channel, is compared with a preset stress template signal, and stress response information of the shrimps, feeding-free behavior information of the shrimps, feeding behavior abnormal information of the shrimps or normal growth condition information of the shrimps is output.
The step S3 further comprises the steps of:
s31: judging the water quality parameters of the water quality and acoustic parameter monitoring channels, calculating the standard deviation of the water quality parameters of the water quality and acoustic parameter monitoring channels, judging the water quality parameters to be normal when the standard deviation of the water quality parameters is less than or equal to a preset threshold value, starting the shrimp acoustic parameter monitoring channels, carrying out next judgment, and otherwise, exiting the algorithm, outputting and reporting abnormal information of the water quality environment parameters;
s32: if the shrimp acoustic parameter monitoring channel is opened, judging shrimp sounding signals in the water quality and acoustic parameter monitoring channel, acquiring the shrimp sounding signals through a hydrophone, calculating the variation mean value of the shrimp sounding signals, judging that the shrimps have no stress reaction and entering the next judgment when the variation mean value of the shrimp sounding signals is greater than or equal to a second threshold value or less than or equal to a first threshold value; when the variation mean value of the shrimp sounding signals is smaller than a second threshold value and larger than a first threshold value, judging that the shrimps have stress reactions, exiting the algorithm, and outputting and reporting the stress reaction information of the shrimps;
s33: judging the shrimp sounding signals in the water quality and acoustic parameter monitoring channels, calculating the mean value of changes of the shrimp sounding signals, judging the shrimp eating behavior when the mean value of the changes of the shrimp sounding signals is larger than a second threshold value, and carrying out next judgment; when the variation mean value of the shrimp sounding signals is smaller than a first threshold value and is kept smaller than the first threshold value within 24 hours, judging that the shrimps do not generate the feeding behavior, exiting the algorithm, and outputting and reporting information of the shrimp non-feeding behavior;
s34: when the variation mean value of the shrimp sounding signals is larger than a second threshold value but the frequency appearing within 24 hours is smaller than a preset frequency threshold value, judging that the shrimp feeding behavior is abnormal, exiting the algorithm, and outputting and reporting information of the shrimp feeding behavior abnormality; otherwise, outputting and reporting normal information of the shrimp growth condition.
The step S4 further includes the steps of:
s41: counting the number of channels reporting the abnormal information of the water quality environmental parameters, and entering the next judgment when the number of the abnormal information of the water quality environmental parameters is less than 5; when the number of the abnormal information of the water quality environmental parameters is more than or equal to 5, the number of the channels reporting the abnormal information of the water quality environmental parameters exceeds 50 percent of the total number of the channels, the abnormal change of the water quality environmental parameters is judged to be detected, the algorithm is exited, and the output water quality environmental parameters are abnormal;
s42: counting the number of channels reporting the stress response information of the shrimps, entering next judgment when the number of the channels reporting the stress response information of the shrimps is less than 5, and judging that the shrimps have the morbidity when the number of the channels reporting the stress response information of the shrimps is more than 50% of the total number of the channels when the number of the channels reporting the stress response information of the shrimps is more than or equal to 5, exiting the algorithm, and outputting the morbidity of the shrimps;
s43: counting the number of channels reporting the information of the shrimp no-feeding behavior, entering next judgment when the number of the channels reporting the information of the shrimp no-feeding behavior is less than 5, and judging that the shrimp is likely to have the morbidity when the number of the channels reporting the information of the shrimp no-feeding behavior exceeds 50% of the total number of the channels when the number of the channels reporting the information of the shrimp no-feeding behavior is more than or equal to 5, wherein the algorithm is withdrawn at the moment, and outputting the possible morbidity of the shrimp;
s44: counting the number of channels reporting abnormal information of the feeding behaviors of the shrimps, entering next judgment when the number of the abnormal information of the feeding behaviors of the shrimps is less than 5, judging that the abnormal phenomenon of the growth conditions of the shrimps is detected when the number of the channels reporting the abnormal information of the feeding behaviors of the shrimps is more than or equal to 5 and the number of the channels reporting the abnormal information of the feeding behaviors of the shrimps is more than 50 percent of the total number of the channels, exiting the algorithm at this moment, and outputting abnormal growth conditions of the shrimps;
s45: counting the number of channels reporting stress response information of the shrimps, comparing the number of channels reporting the stress response information of the shrimps with the sum of the number of channels reporting no feeding behavior information of the shrimps and the number of channels reporting abnormal feeding behavior information of the shrimps, and when the number of channels reporting the stress response information of the shrimps is larger than or equal to the sum of the number of channels reporting no feeding behavior information of the shrimps and the number of channels reporting abnormal feeding behavior information of the shrimps, exiting the algorithm, outputting that the shrimps grow unhealthy, otherwise outputting that the growth condition of the shrimps is normal.
The signal acquisition unit records data for 30 minutes by default and records the data every 60 minutes.
Further comprising the steps of: and carrying out Fourier transform on the shrimp sounding signals of the water quality and acoustic parameter monitoring channels to obtain shrimp sounding pulse change signals, and taking the shrimp sounding pulse change signals as comparison signals.
And the multi-channel water quality acoustic comprehensive algorithm model outputs a report to a display unit and a terminal, and the display unit displays an analysis result in real time.
The water quality environmental parameter monitoring channel of the dual-channel water quality acoustic comprehensive algorithm model receives the water quality data of each channel recorded by the signal acquisition unit according to the default input signal template, the time length of the default recorded data is 30 minutes, the data is recorded every 60 minutes, the feedback analysis result is recorded, the water quality condition of each channel is judged respectively, and the water quality change condition of each channel is monitored online and timely. And performing discriminant analysis according to the integration of the water quality data in each channel, thereby obtaining the overall water quality environment condition and further deducing the survival state of the shrimps in the shrimp pond.
The shrimp acoustic behavior monitoring channel of the dual-channel water quality acoustic comprehensive algorithm model receives shrimp sounding signals of all channels recorded by a signal acquisition unit according to the default input signal length, the default input signal length is 45-60 minutes of data signals, 50-100 data signals are acquired every second, if the default input signal length is 55 minutes of data signals, 75 data signals are acquired every second, the single-channel shrimp behavior sounding algorithm model firstly judges the shrimp sounding signals input into all channels, judges the shrimp feeding condition and the stress condition of all channels respectively on the basis of the shrimp feeding sounding signals and the stress sounding signals, and monitors the shrimp growth condition of all channels on line in time. And performing discriminant analysis according to the integration of the acoustic data in each channel, thereby obtaining the overall activity condition of the shrimps in the shrimp pond and further deducing the survival state of the shrimps in the shrimp pond.
Referring to fig. 2, the dual-channel water quality acoustic comprehensive algorithm model of the present invention judges the water quality-acoustic signals input to each channel according to the following steps:
the invention firstly judges whether the water quality environmental parameters are normal or not, and the standard deviation is a measurement of the statistical distribution degree commonly used in probability statistics and can reflect the discrete degree between individual data in a data set.
Ideally, the water quality environment parameter should be a specific parameter, but because shrimps excrete and baits are fed manually, the real water quality environment parameter fluctuates in a small range near the determined parameter, so the standard deviation of the water quality environment parameter can be used as a mark for measuring whether the water quality environment parameter is abnormal or not, and is compared with a set threshold value, if the set threshold value is 0.05, when the standard deviation of the water quality environment parameter is less than or equal to the set threshold value, the water quality environment parameter is judged to be normal, and the next judgment is carried out; when the water quality environmental parameter is larger than the set threshold value, the water quality environmental parameter is judged to generate severe fluctuation, the channel is possibly interfered by shrimp excretion or artificial bait casting, the channel is not suitable to be used as the basis of the shrimp growth condition, the algorithm is exited, and the water quality environmental parameter abnormality is output and reported.
Judging the water quality environmental parameters in each channel, namely judging whether the water quality environmental parameters are abnormal or not, calculating the standard deviation of the water quality parameters of each channel, wherein the standard deviation of the water quality environmental parameters can also be used as a mark for judging whether the water quality environmental parameters are abnormal or not, comparing the standard deviation with a set threshold, and judging that the water quality environment is normal and entering the next step for judgment when the standard deviation of the water quality environmental parameters is less than the set threshold if the set threshold is 0.05; when the water quality environmental parameter is larger than or equal to the set threshold value, the environmental water quality state is judged to be abnormal, the algorithm is exited, and the water quality environmental parameter abnormality is output and reported.
The sound production behaviors of the shrimps in the channels are judged, the sound production behaviors of the shrimps in the channels are judged by the water quality acoustic comprehensive algorithm according to the two conditions, and the sound production signals of the shrimps in the channels are subjected to Fourier transform to obtain the sound production pulse change of the shrimps, wherein the pulse change is the electric signal change of the acoustic frequency.
When the mean value of the change of the electric signals of the acoustic frequency is less than the set first threshold value, the signals are weak, the shrimp vocalization behavior can not be judged by calculating the absolute difference of the signal values, whether the shrimp produces the stress vocalization behavior is judged by judging whether the shrimp produces the stress vocalization behavior or not by the proportion of the electric signals of the acoustic frequency greater than or less than the set first threshold value in the total signal length, the proportion of the set first threshold value in the total signal length is the existing data, the relation between the change term signal of the pulse change and the total change length of the threshold value is established by analyzing the known shrimp producing the stress vocalization frequency, the shrimp produces the stress response in the channel is judged, and when the mean value of the change of the electric signals of the acoustic frequency of the shrimp is less than the set second threshold value and greater than the set first threshold value, the algorithm exits, and the shrimp is output and reported to produce the stress response.
When the mean value of the change of the electric signal of the acoustic frequency is larger than or equal to the set second threshold value, the signal is strong, and the absolute difference between the maximum value and the mean value of the change range is smaller than the set second threshold value, the fact that the shrimps do not have feeding behaviors is meant, the absolute difference between the maximum value and the minimum value of the change range exceeding 24 hours in the channel is smaller than the set second threshold value, the algorithm is quitted, and the shrimp feeding-free behaviors are output and reported.
When the mean value of the change of the electric signals of the acoustic frequency is larger than or equal to the set second threshold value, the signals are strong, and the absolute differences between the maximum value and the mean value of the change range are larger than or equal to the set second threshold value, the shrimp is supposed to have feeding behaviors, the absolute differences between the maximum value and the minimum value and the mean value which are smaller than the two change ranges are larger than or equal to the set second threshold value within 24 hours in the channel, the algorithm is quitted, and the shrimp behavior abnormity is output and reported.
When the change of the electric signal of the acoustic frequency does not meet any condition, outputting and reporting that the growth condition of the shrimps is normal.
According to the invention, the single-channel water quality acoustic comprehensive algorithm model is used for comprehensively judging the output results of the water quality environmental parameter signals and the shrimp sounding signals of all channels, wherein the output results are the water quality environmental parameters, the shrimp possibly attacks diseases, the shrimp has stress reaction, the shrimp does not have ingestion behavior, the shrimp behavior is abnormal and the shrimp growth condition is normal, so that the reliability of system judgment is improved.
Referring to fig. 3, the multi-channel water quality acoustic comprehensive algorithm model of the present invention performs comprehensive decision according to the following steps:
counting the number of channels with abnormal water quality environmental parameters, firstly counting the channels reporting the abnormal water quality environmental parameters, and entering the next judgment when the number of the channels with abnormal water quality environmental parameters is less than 5; when the number of the abnormal water quality environmental parameters is more than or equal to 5, the number of the channels reporting the abnormal water quality environmental parameters exceeds 50 percent of the total number of the channels, the water area where the abnormal water quality environmental parameters are located is considered to be polluted, the algorithm is exited at the moment, and the output water quality environmental parameters are abnormal.
Counting the number of channels with stress reaction of the shrimps, counting the number of channels reporting the stress reaction of the shrimps, entering next judgment when the number of the channels with stress reaction of the shrimps is less than 5, and judging that the number of the channels with stress reaction of the shrimps is more than 50% of the total number of the channels when the number of the channels with stress reaction of the shrimps is more than or equal to 5, wherein the judgment detects that the shrimps have a disease occurrence phenomenon, and then exiting the algorithm and outputting that the shrimps have the disease.
Counting the number of channels without ingestion behaviors of the shrimps, counting the number of channels reporting no ingestion behaviors of the shrimps, entering next judgment when the number of channels without ingestion behaviors of the shrimps is less than 5, judging that the number of channels reporting no ingestion behaviors of the shrimps exceeds 50% of the total number of channels when the number of channels without ingestion behaviors of the shrimps is more than or equal to 5, judging that the shrimps possibly have morbidity, exiting the algorithm at the moment, and outputting that the shrimps possibly have morbidity.
Counting the number of channels with abnormal shrimp feeding behaviors, counting the number of channels reporting abnormal shrimp feeding behaviors, entering next judgment when the number of channels with abnormal shrimp feeding behaviors is less than 5, and judging that the number of channels with abnormal shrimp feeding behaviors exceeds 50 percent of the total number of channels when the number of channels with abnormal shrimp feeding behaviors is more than or equal to 5, and exiting the algorithm to output abnormal shrimp growth conditions when judging that the abnormal shrimp growth conditions occur.
Comparing the number of the channels with stress reaction of the shrimps, comparing the sum of the number of the channels reporting the stress reaction of the shrimps, the number of the channels reporting no feeding behavior of the shrimps and the number of the channels with abnormal feeding behavior of the shrimps, and when the number of the channels with stress reaction of the shrimps is more than or equal to the sum of the number of the channels with no feeding behavior of the shrimps and the number of the channels with abnormal feeding behavior of the shrimps, exiting the algorithm, outputting that the shrimps grow healthily, otherwise, outputting that the shrimp grow normally.
The multi-channel comprehensive decision algorithm model outputs reports to the display unit and the terminal, and the display unit analyzes results in real time.
While the present invention has been described in detail and with reference to the embodiments thereof as illustrated in the accompanying drawings, it will be apparent to one skilled in the art that various changes and modifications can be made therein. Therefore, certain details of the embodiments are not to be interpreted as limiting, and the scope of the invention is to be determined by the appended claims.
Claims (7)
1. A method for predicting the onset of diseases of cultured shrimps by combining water quality parameters and behavior sounding comprises the following steps:
s1: nine independent water quality and acoustic parameter monitoring channels are established by arranging a plurality of independent signal acquisition units in the shrimp pond, wherein each signal acquisition unit comprises a microprocessor, and a water quality detector and a hydrophone which are connected with the microprocessor; a signal analysis unit is connected with each signal acquisition unit;
s2: collecting and recording original signals through the signal collecting unit, wherein the original signals comprise water quality parameters collected by the water quality detector and behavior sounding signals generated by shrimp aquatic organisms collected by the hydrophone when the water quality is unchanged;
s3: the microprocessor comprises a double-channel water quality acoustic comprehensive algorithm model, and the original signals are analyzed and judged by using the double-channel water quality acoustic comprehensive algorithm model to obtain the environment and shrimp state information of each acoustic parameter monitoring channel; the environment and shrimp state information comprises water quality environment parameter abnormal information, shrimp stress response information, shrimp non-ingestion behavior information and shrimp ingestion behavior abnormal information;
s4: the signal analysis unit comprises a multi-channel water quality acoustic comprehensive algorithm model; and judging whether the growth conditions of the shrimps in the shrimp pond are normal or not according to the multi-channel water quality acoustic comprehensive algorithm model and the environment and shrimp state information.
2. The method for predicting the onset of shrimps in culture according to the combination of water quality parameters and behavioral vocalization of claim 1, wherein in the step S3, the two-channel water quality acoustic integrated algorithm model receives the water quality parameters according to the length of default input signals, and the water quality parameters include dissolved oxygen, pH value, temperature and salinity; comparing the original collected signals of the water quality and acoustic parameter monitoring channels with preset template signals, and opening shrimp acoustic parameter monitoring channels or outputting water quality environmental parameter abnormal information according to comparison results;
the two-channel water quality acoustic comprehensive algorithm model receives behavior sounding signals generated by the shrimp aquatic organisms when the water quality is unchanged according to the length of a default input signal, compares the behavior sounding signals generated by the shrimp aquatic organisms when the water quality is unchanged and originally collected by each water quality and acoustic parameter monitoring channel with preset stress template signals, and outputs stress response information of the shrimps, feeding-free behavior information of the shrimps, feeding behavior abnormal information of the shrimps or normal growth condition information of the shrimps.
3. The method for predicting the onset of the shrimps cultured by combining the water quality parameter with the behavior sounding according to claim 1, wherein the step S3 further comprises the steps of:
s31: judging the water quality parameters of the water quality and acoustic parameter monitoring channels, calculating the standard deviation of the water quality parameters of the water quality and acoustic parameter monitoring channels, judging the water quality parameters to be normal and starting shrimp acoustic parameter monitoring channels when the standard deviation of the water quality parameters is less than or equal to a preset threshold value, and judging the next step, otherwise, exiting the algorithm and outputting and reporting the water quality environment parameter abnormal information;
s32: if the shrimp acoustic parameter monitoring channel is opened, judging shrimp sounding signals in the water quality and acoustic parameter monitoring channels, acquiring the shrimp sounding signals through the hydrophone, calculating the variation mean value of the shrimp sounding signals, judging that the shrimps have no stress response when the variation mean value of the shrimp sounding signals is greater than or equal to a second threshold value or less than or equal to a first threshold value, and entering the next judgment; when the average change value of the shrimp sounding signals is smaller than the second threshold value and larger than the first threshold value, judging that the shrimps have stress reactions, exiting the algorithm, and outputting and reporting the information of the stress reactions of the shrimps;
s33: judging the shrimp sounding signals in the water quality and acoustic parameter monitoring channels, calculating the mean value of the change of the shrimp sounding signals, judging the shrimp eating behavior when the mean value of the change of the shrimp sounding signals is greater than the second threshold value, and performing the next judgment; when the average change value of the shrimp sounding signals is smaller than the first threshold value and is kept smaller than the first threshold value within 24 hours, judging that the shrimps do not generate feeding behaviors, exiting the algorithm, and outputting and reporting information of the shrimps on no feeding behaviors;
s34: when the variation mean value of the shrimp sounding signals is larger than the second threshold value but the frequency appearing within 24 hours is smaller than a preset frequency threshold value, judging that the shrimp feeding behavior is abnormal, exiting the algorithm, and outputting and reporting the shrimp feeding behavior abnormal information; otherwise, outputting and reporting the information that the shrimp growth condition is normal.
4. The method for predicting the onset of shrimps in culture according to claim 1, wherein the step S4 further comprises the steps of:
s41: counting the number of channels reporting the abnormal information of the water quality environmental parameters, and entering the next judgment when the number of the abnormal information of the water quality environmental parameters is less than 5; when the number of the abnormal water quality environmental parameter information is more than or equal to 5, reporting that the number of the channels of the abnormal water quality environmental parameter information exceeds 50% of the total number of the channels, judging that the abnormal change of the water quality environmental parameter is detected, exiting the algorithm, and outputting that the water quality environmental parameter is abnormal;
s42: counting the number of channels reporting the stress response information of the shrimps, entering next judgment when the number of the channels reporting the stress response information of the shrimps is less than 5, judging that the shrimps are detected to have a disease occurrence phenomenon when the number of the channels reporting the stress response information of the shrimps is more than 50% of the total number of the channels when the number of the channels reporting the stress response information of the shrimps is more than or equal to 5, exiting the algorithm, and outputting that the shrimps have the disease occurrence;
s43: counting the number of channels reporting the information of the shrimp non-ingestion behavior, entering next judgment when the number of the channels reporting the information of the shrimp non-ingestion behavior is less than 5, and judging that the shrimp is possibly attacked when the number of the channels reporting the information of the shrimp non-ingestion behavior is more than or equal to 5 and the number of the channels reporting the information of the shrimp non-ingestion behavior exceeds 50 percent of the total number of the channels;
s44: counting the number of channels reporting the abnormal information of the shrimp feeding behavior, entering next judgment when the number of the abnormal information of the shrimp feeding behavior is less than 5, judging that the abnormal phenomenon of the shrimp growth condition is detected when the number of the channels reporting the abnormal information of the shrimp feeding behavior is more than or equal to 5 and the number of the channels reporting the abnormal information of the shrimp feeding behavior exceeds 50 percent of the total number of the channels, and exiting the algorithm at the moment to output the abnormal shrimp growth condition;
s45: counting the number of channels reporting the stress response information of the shrimps, comparing the number of channels reporting the stress response information of the shrimps with the sum of the number of channels reporting no feeding behavior information of the shrimps and the number of channels reporting abnormal feeding behavior information of the shrimps, when the number of channels reporting the stress response information of the shrimps is more than or equal to the sum of the number of channels reporting no feeding behavior information of the shrimps and the number of channels reporting abnormal feeding behavior information of the shrimps, exiting the algorithm, outputting that the shrimps grow unhealthy, and otherwise outputting that the growth condition of the shrimps is normal.
5. The method for predicting the onset of the shrimps in culture by combining the water quality parameters with the behavioral vocalization as claimed in claim 1, wherein the signal acquisition unit is used for recording data for 30 minutes by default and recording the data every 60 minutes.
6. The method for predicting the onset of the shrimps cultured by combining the water quality parameters with the behavior sounding according to claim 3, further comprising the steps of: and carrying out Fourier transform on the shrimp sounding signals of the water quality and acoustic parameter monitoring channels to obtain shrimp sounding pulse change signals, and taking the shrimp sounding pulse change signals as comparison signals.
7. The method for predicting the onset of shrimps in culture by combining water quality parameters with behavior sounding according to claim 1, wherein the multi-channel water quality acoustic comprehensive algorithm model outputs a report to a display unit and a terminal, and the display unit displays the analysis result in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110345830.8A CN115136912B (en) | 2021-03-31 | Method for predicting disease occurrence of cultured shrimps by combining water quality parameters and behavioral sounding |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110345830.8A CN115136912B (en) | 2021-03-31 | Method for predicting disease occurrence of cultured shrimps by combining water quality parameters and behavioral sounding |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115136912A true CN115136912A (en) | 2022-10-04 |
| CN115136912B CN115136912B (en) | 2024-05-10 |
Family
ID=
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117084200A (en) * | 2023-08-22 | 2023-11-21 | 盐城工业职业技术学院 | Aquaculture dosing control system applying big data analysis |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000003586A2 (en) * | 1998-07-15 | 2000-01-27 | Eco-Fish Ltd. | Fish feeding control in aquaculture on the basis of sound emitted by fish |
| CN105746394A (en) * | 2016-03-01 | 2016-07-13 | 中国科学院南海海洋研究所 | Method for judging survival ability of crassostrea hongkongensis |
| WO2017003113A1 (en) * | 2015-06-30 | 2017-01-05 | 주식회사 글로비트 | System for preventing diseases of flatfish through sound and image analysis |
| CN106625681A (en) * | 2017-02-23 | 2017-05-10 | 福建强闽信息科技有限公司 | Aquatic animal disease diagnosis robot device and implementation method |
| CN109009129A (en) * | 2018-08-20 | 2018-12-18 | 南京农业大学 | Sow respiratory disease method for early warning based on acoustic analysis |
| CN109566478A (en) * | 2018-10-18 | 2019-04-05 | 厦门大学 | The on-line monitoring method of aquaculture organisms body health status |
| CN111583962A (en) * | 2020-05-12 | 2020-08-25 | 南京农业大学 | Sheep rumination behavior monitoring method based on acoustic analysis |
| CN111951289A (en) * | 2020-08-13 | 2020-11-17 | 江苏东印智慧工程技术研究院有限公司 | BA-Unet-based underwater sonar image data segmentation method |
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000003586A2 (en) * | 1998-07-15 | 2000-01-27 | Eco-Fish Ltd. | Fish feeding control in aquaculture on the basis of sound emitted by fish |
| WO2017003113A1 (en) * | 2015-06-30 | 2017-01-05 | 주식회사 글로비트 | System for preventing diseases of flatfish through sound and image analysis |
| CN105746394A (en) * | 2016-03-01 | 2016-07-13 | 中国科学院南海海洋研究所 | Method for judging survival ability of crassostrea hongkongensis |
| CN106625681A (en) * | 2017-02-23 | 2017-05-10 | 福建强闽信息科技有限公司 | Aquatic animal disease diagnosis robot device and implementation method |
| CN109009129A (en) * | 2018-08-20 | 2018-12-18 | 南京农业大学 | Sow respiratory disease method for early warning based on acoustic analysis |
| CN109566478A (en) * | 2018-10-18 | 2019-04-05 | 厦门大学 | The on-line monitoring method of aquaculture organisms body health status |
| CN111583962A (en) * | 2020-05-12 | 2020-08-25 | 南京农业大学 | Sheep rumination behavior monitoring method based on acoustic analysis |
| CN111951289A (en) * | 2020-08-13 | 2020-11-17 | 江苏东印智慧工程技术研究院有限公司 | BA-Unet-based underwater sonar image data segmentation method |
Non-Patent Citations (1)
| Title |
|---|
| 曹正良等: "南美白对虾养殖虾塘中水下声景的应用研宄初探", 声学技术, vol. 38, no. 2, pages 379 - 381 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117084200A (en) * | 2023-08-22 | 2023-11-21 | 盐城工业职业技术学院 | Aquaculture dosing control system applying big data analysis |
| CN117084200B (en) * | 2023-08-22 | 2024-01-19 | 盐城工业职业技术学院 | Aquaculture dosing control system applying big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pistorio et al. | Acoustic analysis of vocal development in a New World primate, the common marmoset (Callithrix jacchus) | |
| Burkett et al. | VoICE: A semi-automated pipeline for standardizing vocal analysis across models | |
| Ruiz-Velazco et al. | Management of stocking density, pond size, starting time of aeration, and duration of cultivation for intensive commercial production of shrimp Litopenaeus vannamei | |
| Searby et al. | Acoustic recognition in macaroni penguins: an original signature system | |
| Lavender et al. | Ontogenetic investigation of underwater hearing capabilities in loggerhead sea turtles (Caretta caretta) using a dual testing approach | |
| CN110169375B (en) | Method and device for monitoring ingestion behavior and ingestion amount of dairy cows | |
| JP6558786B1 (en) | Method, computer system, and program for predicting target characteristics | |
| Funk et al. | Elevational speciation in action? Restricted gene flow associated with adaptive divergence across an altitudinal gradient | |
| Siracusa et al. | North American red squirrels mitigate costs of territory defence through social plasticity | |
| CN112526097A (en) | Aquaculture water body environment intelligent monitoring management system based on big data analysis | |
| CN109566478B (en) | Online monitoring method for health state of aquaculture organism | |
| Rabl et al. | Quantitative evaluation of orofacial motor function in mice: the pasta gnawing test, a voluntary and stress-free behavior test | |
| CN116611000B (en) | Intelligent hairy crab culture environment monitoring system based on machine learning | |
| Hassan et al. | Fish as a source of acoustic signal measurement in an aquaculture tank: acoustic sensor based time frequency analysis. | |
| CN115136912A (en) | Disease incidence prediction method for cultured shrimps by combining water quality parameters and behavior sounding | |
| CN115136912B (en) | Method for predicting disease occurrence of cultured shrimps by combining water quality parameters and behavioral sounding | |
| Caldwell et al. | Frequency information in the vibration-cued escape hatching of red-eyed treefrogs | |
| Fontana et al. | Broiler vocalisation to predict the growth | |
| Phillips et al. | Geographical divergence of acoustic signals in Cyprinella galactura, the whitetail shiner (Cyprinidae) | |
| US11576354B2 (en) | Method for customized monitoring of sounds caused by respiratory distress | |
| CN112380486B (en) | Dynamic monitoring and evaluating method and system for sea water ornamental fish culture state | |
| Lemasson et al. | A new methodological approach to context analysis of call production | |
| Repenning et al. | Distinguishing females of capuchino seedeaters: call repertoires provide evidence for species-level diagnosis | |
| Rahman et al. | Application of machine learning techniques in aquaculture | |
| Rauber et al. | Effect of group size and experience on the ontogeny of sentinel calling behaviour in meerkats |
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 | ||
| GR01 | Patent grant |