CN114041779A - Identification system and computer device for identifying respiratory diseases of livestock - Google Patents
Identification system and computer device for identifying respiratory diseases of livestock Download PDFInfo
- Publication number
- CN114041779A CN114041779A CN202111424289.6A CN202111424289A CN114041779A CN 114041779 A CN114041779 A CN 114041779A CN 202111424289 A CN202111424289 A CN 202111424289A CN 114041779 A CN114041779 A CN 114041779A
- Authority
- CN
- China
- Prior art keywords
- livestock
- neural network
- respiratory
- identification system
- identifying
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/0823—Detecting or evaluating cough events
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4803—Speech analysis specially adapted for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/40—Animals
-
- 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
- Y02A40/70—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in livestock or poultry
Abstract
The present invention provides an identification system, a computer device and a computer readable storage medium for identifying respiratory diseases of livestock, wherein the identification system comprises: the livestock respiratory sound processing system comprises a processing subsystem and a neural network subsystem, wherein the processing subsystem comprises a sub-processor, the neural network subsystem comprises a first neural network unit, a second neural network unit and a computer readable storage medium, the first neural network unit is used for receiving and processing respiratory sound data of livestock to obtain a symptom time sequence related to respiratory diseases of the livestock, and the symptom time sequence is the symptoms related to the respiratory diseases and the time sequence of occurrence of the symptoms of the livestock in a set time period; the second neural network unit is used for receiving and processing the symptom time sequence related to the respiratory disease of the livestock to obtain the respiratory disease suffered by the livestock. The technical scheme of the invention can improve the accuracy of identifying the respiratory diseases suffered by the livestock.
Description
Technical Field
The present invention relates generally to the field of livestock respiratory sound processing. More particularly, the invention relates to an identification system, a computer device and a computer readable storage medium for identifying respiratory diseases of livestock.
Background
Respiratory diseases are common diseases in livestock farms, and due to the characteristics of easy infection and difficult control, once livestock have respiratory diseases, if the respiratory diseases cannot be found and controlled in time, the respiratory diseases easily cause great economic loss to the livestock farms, the appetite of the livestock is reduced, the growth speed is reduced, and the livestock is killed in large quantity if the respiratory diseases are not found and controlled in time. Therefore, it is very important for the farm to find the livestock with respiratory diseases and take measures in time.
Currently, there are two methods for monitoring livestock for respiratory diseases. The first method is to monitor the livestock through a manual diagnosis mode, namely, workers regularly carry out health detection on the livestock in the farm to judge whether the livestock have respiratory diseases. Because of a large amount of livestock in the farm, the detection of the livestock one by one requires a large amount of labor cost and time cost, and the timeliness is poor, so that the livestock suffering from respiratory diseases cannot be found in time.
And secondly, adopting sound acquisition equipment to acquire cough sound signals of the livestock, then carrying out data processing by an artificial intelligence calculation method, and judging whether the livestock has respiratory diseases or not according to the cough sound signals of the livestock. The method has the advantages that whether the livestock are affected by the pathological changes can be monitored in real time, timeliness of detection of the respiratory diseases of the livestock can be guaranteed, detection labor cost and time cost are reduced, and the method has the defect that due to the fact that symptoms of the respiratory diseases are similar, the existing method cannot accurately identify the types of the respiratory diseases suffered by the livestock according to cough sound signals of the livestock, and accordingly reliability is poor.
In conclusion, the prior art has the problem of poor reliability when identifying the respiratory diseases of the livestock.
Disclosure of Invention
The invention provides an identification system, a computer device and a computer readable storage medium for identifying respiratory diseases of livestock, which at least solve the problem of poor reliability when identifying the respiratory diseases of the livestock.
To solve the above problems, in a first aspect, the present invention provides an identification system for identifying respiratory diseases of livestock, comprising: a processing subsystem comprising one or more processors; a neural network subsystem comprising a first neural network element and a second neural network element, and one or more computer-readable storage media storing program instructions implementing the neural network system that, when executed by the one or more processors, cause: the first neural network unit receives and processes breathing sound data of the livestock to obtain a symptom time sequence of the livestock, wherein the symptom time sequence is the symptoms of the livestock, which are related to the respiratory diseases and occur in a set time period, and the time sequence of the symptoms; and the second neural network unit receives and processes the symptom time sequence related to the respiratory disease of the livestock to obtain the respiratory disease of the livestock.
According to one embodiment of the invention, the symptoms associated with respiratory tract disease include at least one of dry cough, wet cough and sneezing.
According to another embodiment of the present invention, the respiratory disease includes at least one of mycoplasma, blue ear, influenza and pseudorabies.
According to yet another embodiment of the invention, the one or more computer-readable storage media further store program instructions to perform mel-frequency spectrum processing that, when executed by the one or more processors, cause: and carrying out Mel frequency spectrum processing on the respiratory tract sound data of the livestock.
According to another embodiment of the invention, the program instructions, when executed by the one or more processors, further cause: the second neural network unit acquires the severity of the respiratory disease of the livestock.
According to yet another embodiment of the invention, the severity level comprises a light level, a medium level and a heavy level.
According to another embodiment of the invention, a sound collector is further included, and the one or more computer-readable storage media further store program instructions for controlling the sound collector which, when executed by the one or more processors, cause: the sound collector obtains the breathing sound of the livestock.
According to a further embodiment of the invention, the sound collector obtaining the breathing sound of the animals for a set period of time comprises: the breathing sound of the livestock is acquired once every set time interval.
In a second aspect, the present invention also provides a computing device comprising the identification system according to any one of the above embodiments.
In a third aspect, the invention further provides a computer-readable storage medium comprising a computer program for identifying respiratory diseases of livestock, which, when executed by one or more processors of an apparatus, causes the apparatus to perform the operations of the identification system of any one of the embodiments described above.
According to the technical scheme provided by the invention, the first neural network unit can obtain the symptoms related to respiratory diseases and the time sequence of the symptoms generated by the livestock according to the breathing sound data of the livestock in a set time period; the second neural network unit can identify the respiratory diseases suffered by the livestock according to the symptoms related to the respiratory diseases generated by the livestock and the generation symptom time sequence. According to the technical scheme, the second neural network unit can identify the respiratory diseases of the livestock according to the symptoms related to the respiratory diseases and the occurrence symptom time sequence of the livestock in a set time period, so that the method has the advantage of high accuracy of identification results, and the reliability of identifying the respiratory diseases of the livestock can be improved.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the present invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which like reference numerals refer to similar or corresponding parts and in which:
FIG. 1 is a diagram of the architecture of a system for identifying respiratory diseases in livestock according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of acquiring a disorder timing sequence according to an embodiment of the present invention; and
fig. 3 is a block diagram of an apparatus for identifying respiratory diseases of livestock according to an embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the embodiments described herein are only some of the embodiments of the invention provided to facilitate a clear understanding of the concepts and legal requirements, and that not all embodiments of the invention may be practiced. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed in the present specification without inventive step, are within the scope of the present invention.
Referring to fig. 1, fig. 1 is a diagram illustrating an architecture of a system for identifying respiratory diseases of livestock according to an embodiment of the present invention. According to the system architecture shown in fig. 1, the identification system for identifying respiratory diseases of livestock of the invention comprises a processor subsystem and a neural network subsystem, wherein the processor subsystem may comprise one or more processors, and the neural network subsystem may comprise a first neural network unit and a second neural network unit.
As an example, the first and second neural network elements of the present invention described above may be implemented as program instructions stored on a computer-readable storage medium. Depending on the application scenario, the computer-readable storage medium may be one or more of, and may be any type of storage medium capable of storing program instructions. During execution of the identification tasks of the invention, the processor may execute program instructions stored on the computer-readable storage medium such that execution of the program instructions results in operations performed by the first and second neural network units of the invention.
Specifically, when the processor executes the one or more program instructions, the first neural network element of the present invention may be configured to receive and process the respiratory tract sounds of the livestock to obtain respiratory tract disease-related symptoms occurring in the livestock, and the second neural network element may be configured to receive and process a timing sequence of respiratory tract disease-related symptoms occurring in the livestock to obtain respiratory tract disease suffered by the livestock.
The symptom time sequence is a time sequence of symptoms related to respiratory diseases of the livestock in a set time, after the breathing sounds of the livestock in the set time are obtained, the first neural network unit firstly identifies the symptoms related to the respiratory diseases of the livestock in the set time according to the breathing sounds, and then arranges the symptoms according to the appearing time sequence to obtain the symptom time sequence related to the respiratory diseases of the livestock in the set time.
The first neural network element and the second neural network element are described in detail below, and it is understood that the first neural network element and the second neural network element are exemplary and not restrictive, and the neural network models used by the first neural network element and the second neural network element can be selected according to actual requirements.
In this embodiment, the first Neural Network unit adopts a CRNN (Convolutional Recurrent Neural Network) Neural Network model, that is, the CRNN Neural Network model is trained by adopting a first training data set, and the trained CRNN Neural Network model is used as the first Neural Network unit. The method comprises the steps that data stored in a first training data set are a plurality of breathing sound segments of livestock, when a first data training set is adopted to train a CRNN neural network model, firstly, the symptom types, the symptom starting time and the symptom ending time of the breathing sound segments in the first training data set are marked, then, the marked breathing sound segments are used as input quantities to train the CRNN neural network model, and training is received until the error of the output quantity of the CRNN neural network model is smaller than a first set error, so that the trained CRNN neural network model is obtained.
The first neural network unit can receive the breathing sound of the livestock in a set time period, process the breathing sound data, identify the symptoms of the livestock related to respiratory diseases in the set time period, obtain the starting time and the ending time of each symptom of the livestock in the set time period, and further obtain the time sequence of each symptom of the livestock in the set time period. In addition, the first neural network unit receives the breathing sound data of the livestock within a set time, and can receive the breathing sound data from a sound collecting device connected with a processor or other devices in a communication mode. After receiving the breathing sound data of the received livestock within the set time, the breathing sound data is identified, so that the symptoms related to the respiratory diseases of the livestock in the set time period can be obtained.
The second neural network Unit adopts a Gate Recovery Unit (GRU) neural network model, that is, the GRU neural network model is trained by adopting a second training data set, and the trained GRU neural network model is used as the second neural network Unit. And when the GRU neural network model is trained by adopting the second training data set, firstly marking the data in the second training data set, namely marking the respiratory disease type corresponding to each data, then training the GRU neural network model by taking the data in the marked second training data set as an input quantity, and ending the training until the error of the GRU neural network model is smaller than a second set error to obtain the trained GRU neural network model.
The second neural network unit can receive and process symptoms related to the respiratory diseases of the livestock in a set time period to obtain the respiratory diseases suffered by the livestock. The second neural network unit receives the symptom time sequence which is generated by the livestock in a set time period and is related to the respiratory disease, namely the processing result of the first neural network unit to the breathing sound data of the livestock in the set time period is received. When the first neural network unit processes breathing sound data of the livestock in a set time period to obtain a symptom time sequence which occurs to the livestock and is related to respiratory diseases in the set time period, the second neural network unit obtains the symptom time sequence which occurs to the livestock and is related to the respiratory diseases in the set time period in a data calling mode, and then the respiratory diseases suffered by the livestock are obtained according to the symptom time sequence which occurs to the livestock and is related to the respiratory diseases in the set time period.
In summary, according to the technical scheme provided by the invention, the first neural network unit is adopted to identify the respiratory tract disease-related symptom time sequence of the livestock in the set time period, and the second neural network unit can identify the respiratory tract disease of the livestock according to the respiratory tract disease-related symptom time sequence of the livestock in the set time period. Since the livestock have respiratory diseases, even if the types of the diseases are different, the symptoms are similar, but the occurrence frequency and the occurrence sequence of the symptoms are different. According to the technical scheme provided by the invention, when the respiratory diseases of the livestock are identified, the respiratory diseases of the livestock can be identified by combining symptoms related to the respiratory diseases and a time sequence of the symptoms generated by the livestock within a set time, so that compared with a mode of identifying the respiratory diseases of the livestock only according to the symptoms in the prior art, the identification result has higher accuracy, and the reliability of the identification mode is higher.
The technical solution of the present invention is introduced in the above, and is explained in detail below with reference to specific application scenarios.
In one embodiment, symptoms associated with respiratory illness include dry cough, wet cough, and sneezing. When the first neural network unit is trained, dividing each sound segment in the first training data set into a plurality of sub-segments, and when the data in the first training data set is labeled, if no symptom occurs in the sub-segments, marking the sub-segments as 0; if a dry cough occurs within a sub-segment, the sub-segment is marked 1; if there is a wet cough occurring within a sub-segment, the sub-segment is marked 2; if a sub-segment sneezes, the sub-segment is marked with 3, so that a symptom sequence corresponding to each sound segment is obtained, and then the symptom sequences of each sound segment in the first training data set are used as output to train the first neural network unit. For example, as shown in fig. 2, assuming that the duration of a sound segment is 10 seconds, the duration of a sub-segment is 1 second, if the livestock has dry cough in the 3 rd second, wet cough in the 6 th second, sneeze in the 7 th second, and no symptom occurs in other sub-segments, the corresponding symptom sequence for the sound segment is [0, 0, 1, 0, 0, 2, 3, 0, 0, 0 ]; if the livestock had dry cough in the 3 rd and 4 th seconds, wet cough in the 6 th second, sneeze in the 7 th and 8 th seconds, and no symptom occurred in the other sub-segments, the symptom sequence corresponding to the sound segment was [0, 0, 1, 1, 0, 2, 3, 3, 0, 0 ]. Similarly, after the first neural network unit processes the breathing sound data of the livestock in the set time period, the symptoms related to the respiratory diseases of the livestock in the set time period are identified, the time of the livestock in generating the symptoms can be obtained, and the symptoms are sorted according to the generated time, so that the time sequence of the symptoms related to the respiratory diseases of the livestock in the set time period can be obtained.
In another embodiment, respiratory diseases include mycoplasma, blue ear, influenza, and pseudorabies. A plurality of samples, including samples with mycoplasma, samples with blue ears, samples with influenza, samples with pseudorabies, and samples without disease, are stored in a second training dataset. When the second neural network unit is trained, the samples in the second training data set are labeled with the disease types, and then the labeled data are adopted for training. After the first neural network unit obtains the symptoms related to the respiratory diseases of the livestock in a set time period, the second neural network unit can judge the respiratory diseases of the livestock according to the symptoms.
The respiratory tract-related symptoms and types of respiratory tract diseases are described in detail above, and the respiratory tract sound data are described in detail below with reference to specific application scenarios.
In one application scenario, the one or more computer readable storage media further stores program instructions for mel-frequency spectrum processing, which when executed by the one or more processors, causes mel-frequency spectrum processing of animal respiratory tract sound data over a set period of time. The Mel frequency spectrum is a method for processing audio signals, through Mel frequency spectrum processing, the breathing sound of livestock in a set time period can be converted into a frequency spectrum diagram of corresponding Mel scales, the frequency spectrum diagram can be used as the input quantity of a first neural network unit, and the first neural network unit identifies the symptoms of the livestock in the set time period and the time of the symptoms. The arrangement mode of the embodiment is equivalent to that the sound of the livestock in the set time period is preprocessed, and the breathing sound of the livestock in the set time period is converted into the frequency spectrum signal from the audio signal, so that the convenience of receiving and processing the data by the first neural network unit can be improved.
The preprocessing method of the breathing sound is described in detail above, and the second neuron network is described in detail below with reference to specific application scenarios.
In one application scenario, the program, when executed by the one or more processors, further causes the second neural network element to obtain a severity of respiratory illness of the livestock. When livestock suffer from respiratory diseases, the severity of the diseases is different, and the time sequence of the symptoms is different. For example, the more flu livestock have, the more sneezing it has occurred within a set time. Therefore, after the symptom time sequence of the livestock in the set time is obtained, the severity of the livestock suffering from the diseases can be judged according to the symptom time sequence. In order to make the obtained second neural network unit recognize the severity of the respiratory disease of the livestock according to the symptom sequence of the livestock within the set time period, in the embodiment, when the second neural network unit is trained, the respiratory disease type and the severity of the disease of each data in the second training data set are firstly marked, and then the second neural network is trained by using the data in the marked second training data set.
Further, in another application scenario, the severity of respiratory illness in livestock includes mild, moderate and severe. When the second neural network unit is trained, firstly, the respiratory disease types and the severity of the data in the second training data set belong to light level, medium level or heavy level, then the second neural network unit is trained by adopting the marked second training data set, and the trained second neural network unit not only can identify the respiratory diseases suffered by the livestock, but also can judge whether the severity of the respiratory diseases suffered by the livestock belongs to light level, medium level or heavy level. The arrangement mode of the embodiment can not only obtain the severity of the respiratory diseases suffered by the livestock, but also reduce the complexity of data processing.
The second neural network unit is introduced in detail above, and the method for acquiring the breathing sounds of the livestock is described in detail below with reference to specific application scenarios.
In one application scenario, the recognition system further comprises a sound collector, and the one or more computer-readable storage media further store program instructions for controlling the sound collector, which when executed by the one or more processors, cause the sound collector to capture the breathing sounds of the animal over a set period of time.
The sound collector in the identification system can comprise a microphone array and a sound collection card which are arranged in four channels, wherein the microphone array is arranged in the position with a set height from the ground in the center of the breeding house and is used for collecting the breathing sound of livestock in the breeding house; the sound collection card is connected with the microphone array, can receive the livestock breath sound that four-channel microphone array gathered to can breathe the sound to the livestock of gathering and fuse, with noise and reverberation in the reduction breed house to the influence of sound quality. In addition, in order to guarantee the comprehensiveness that detects livestock breathing sound in the plant, the quantity of sound collectors can be set according to the size of breeding house area, and the area of breeding house is big more, and the quantity of sound collectors arranged therein is big more, for example, can install a sound collector in the area scope of settlement to make identification system can acquire the breathing sound of all livestock in the plant.
Further, in another application scenario, when the sound collector acquires the breathing sound of the livestock within a set time period, the adopted method comprises the following steps: and acquiring the breathing sound of the livestock once every set time interval in a set time period. In order to reduce the data volume of the respiratory sound of gathering, can gather the respiratory sound of livestock in the specific time quantum every day, for example can only gather the respiratory sound of livestock in the time quantum of 20 o 'clock to 8 o' clock next day every day, because the respiratory disease of livestock is comparatively obvious at night, consequently the respiratory sound of livestock in this time quantum, not only can improve the accuracy to livestock respiratory disease discernment, data bulk when can also reduce discernment livestock respiratory disease, improve the work efficiency of discernment livestock respiratory disease.
In the recognition system of the present invention, the time period from 20 o 'clock to 8 o' clock of the next day may be set as the set time period, or the time period may be divided into a plurality of time periods on average, and each time period may be set as the set time period. In addition, in order to further reduce the data volume when identifying respiratory diseases of livestock, the embodiment controls the sound collector to obtain the respiratory sound of the livestock once at set time intervals within a set time period, for example, the respiratory sound of the livestock can be collected for 3 minutes, then the time is suspended for three minutes, then the respiratory sound of the livestock is collected for 3 minutes, and so on, and the respiratory sound collection within the set time period is completed. The data volume when not only can reducing discernment livestock respiratory disease of the mode that sets up of this embodiment, it is the integrality of data volume when also can guaranteeing to discern livestock respiratory disease, consequently both can improve the work efficiency who discerns livestock respiratory, can improve the accuracy of discernment again.
With the identification system according to the embodiment of the present invention, the first neural network unit processes the breathing sounds of the livestock within the set time period to obtain the symptom time sequence related to the respiratory diseases of the livestock within the set time period, and the second neural network unit processes the symptom time sequence to obtain the respiratory diseases suffered by the livestock. For example, the collected respiratory sounds of livestock in the farm can be input into the identification and evaluation system of the invention, so that the types of respiratory diseases suffered by the livestock can be directly obtained, and measures can be taken in time to intervene to prevent the infection and spread of diseases.
Fig. 3 is a block diagram illustrating an apparatus 1100 for identifying respiratory illness of livestock according to an embodiment of the invention. As shown in fig. 3, device 1100 may include a central processing unit ("CPU") 1111, which may be a general purpose CPU, a special purpose CPU, or other execution unit where information processing and programming operates. Further, the device 1100 may also include a mass storage 1112 and a read only memory ("ROM") 1113, wherein the mass storage 1112 may be configured to store various types of data including, for example, various image data identifying respiratory ailments of livestock, algorithm data, intermediate results, and various programs needed to operate the device 1100. A read only memory ("ROM") 1113 may be configured to store power-on self-test for the device 1100, initialization of various functional blocks in the system, drivers for basic input/output of the system, and data required to boot the operating system.
Optionally, the device 1100 may also include other hardware platforms or components, such as the illustrated tensor processing unit ("TPU") 1114, field programmable gate array ("FPGA") 1115, and machine learning unit ("MLU") 1116. It is to be understood that although various hardware platforms or components are illustrated in the apparatus 1100 of the present invention, such is for illustration and not limitation, and one skilled in the art can add or remove corresponding hardware as may be required. For example, the device 1100 may include only a CPU to implement the respiratory illness identification operation of the present invention.
In some embodiments, to facilitate the transfer and interaction of data with external networks, the device 1100 of the present invention further comprises a communication interface 1117 such that it may be connected to a local area network/wireless local area network ("LAN/WLAN") 1105 via the communication interface 1117, and may in turn be connected to a local server 1106 via the LAN/WLAN or to the Internet ("Internet") 1107. Alternatively or additionally, device 1100 of the present invention may also be directly connected to the internet or a cellular network via communication interface 1118 based on a wireless communication technology, such as a 3 rd generation ("3G"), 4 th generation ("4G"), or 5 th generation ("5G") based wireless communication technology. In some application scenarios, the device 1100 of the present invention may also access the server 1108 and possibly the database 1109 of the external network as needed in order to obtain various known neural network models, data and modules, and may remotely store various data, such as various types of data for presenting or identifying respiratory diseases of livestock.
The peripheral devices of the apparatus 1100 of the present invention may include a display device 1102, an input device 1103, and a data transmission interface 1104. In one embodiment, the display device 1102 may include, for example, one or more speakers and/or one or more visual displays configured to provide voice prompts and/or visual displays of the operational procedures or final results of the present invention for displaying images of lesion areas. The input device 1103 may include, for example, a keyboard, mouse, microphone, gesture capture camera, or other input buttons or controls configured to receive an input of animal breathing sounds and/or user instructions. The data transfer interface 1104 may include, for example, a serial interface, a parallel interface, or a universal serial bus interface ("USB"), a small computer system interface ("SCSI"), serial ATA, FireWire ("FireWire"), PCI Express, and a high-definition multimedia interface ("HDMI"), which are configured for data transfer and interaction with other devices or systems. In accordance with aspects of the present invention, the data transfer interface 1104 may receive animal breathing sounds from the sound collectors and transmit data and results including animal breathing sounds or various other types to the device 1100.
The above-described CPU 1111, mass storage 1112, read only memory ROM 1113, TPU 1114, FPGA 1115, MLU 1116 and communication interface 1117 of the device 1100 of the present invention may be interconnected via bus 1119, and data interaction may be achieved with peripheral devices via this bus. Through the bus 1119, the CPU 1111 may control other hardware components and their peripherals in the device 1100, in one embodiment.
An apparatus for identifying respiratory diseases of livestock that may be used to carry out the present invention is described above in connection with fig. 3. It is to be understood that the device architectures or architectures herein are merely exemplary, and that the implementations and implementation entities of the present invention are not limited thereto, but may be varied without departing from the spirit of the invention.
It should also be appreciated that any module, unit, component, server, computer, terminal, or device executing instructions of the examples of the invention may include or otherwise have access to a computer-readable medium, such as a storage medium, computer storage medium, or data storage device (removable) and/or non-removable, such as a magnetic disk, optical disk, or tape. Computer storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules or other data.
In addition, the terms "first" or "second", etc. used in this specification are used to refer to numbers or ordinal terms for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the feature. In the description of the present specification, "a plurality" means at least two, for example, two, three or more, and the like, unless specifically defined otherwise.
While various embodiments of the present invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, changes, and substitutions will occur to those skilled in the art without departing from the spirit and scope of the present invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention. It is intended that the following claims define the scope of the invention and that the module compositions, equivalents, or alternatives falling within the scope of these claims be covered thereby.
Claims (10)
1. An identification system for identifying respiratory diseases in livestock, comprising:
a processing subsystem comprising one or more processors;
a neural network subsystem comprising a first neural network element and a second neural network element, an
One or more computer-readable storage media storing program instructions implementing the neural network system that, when executed by the one or more processors, cause:
the first neural network unit receives and processes breathing sound data of the livestock to obtain a symptom time sequence of the livestock, wherein the symptom time sequence is the symptoms of the livestock, which are related to the respiratory diseases and occur in a set time period, and the time sequence of the symptoms; and
the second neural network unit receives and processes the symptom time sequence related to the respiratory disease of the livestock to obtain the respiratory disease of the livestock.
2. An identification system for identifying respiratory diseases in livestock according to claim 1, wherein said symptoms associated with respiratory diseases comprise at least one of dry cough, wet cough and sneezing.
3. The identification system for identifying respiratory illness in livestock according to claim 1, wherein said respiratory illness includes at least one of mycoplasma, blue ear, influenza and pseudorabies.
4. The identification system for identifying livestock respiratory disease of claim 1, wherein said one or more computer readable storage media further stores program instructions for mel-frequency spectrum processing, which when executed by said one or more processors, causes: and carrying out Mel frequency spectrum processing on the livestock respiratory tract sound data.
5. The identification system for identifying livestock respiratory disease of claim 1, wherein said program instructions, when executed by said one or more processors, further cause: the second neural network unit acquires the severity of the respiratory disease of the livestock.
6. An identification system for identifying respiratory illness in livestock according to claim 5, wherein said severity levels include light, medium and heavy levels.
7. The identification system for identifying livestock respiratory disease of claim 1 further comprising a sound collector, and said one or more computer readable storage media further storing program instructions for controlling a sound collector, which when executed by said one or more processors, causes: the sound collector obtains the breathing sound of the livestock.
8. The identification system for identifying respiratory illness of livestock according to claim 7, wherein said sound collector acquiring said livestock breathing sounds comprises: the breathing sound of the livestock is acquired once every set time interval.
9. A computing device characterised in that it comprises an identification system according to any one of claims 1-8.
10. A computer-readable storage medium, characterized in that it comprises a computer program for identifying respiratory diseases of livestock, which when executed by one or more processors of a device, causes the device to perform the operations of the identification system according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111424289.6A CN114041779A (en) | 2021-11-26 | 2021-11-26 | Identification system and computer device for identifying respiratory diseases of livestock |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111424289.6A CN114041779A (en) | 2021-11-26 | 2021-11-26 | Identification system and computer device for identifying respiratory diseases of livestock |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114041779A true CN114041779A (en) | 2022-02-15 |
Family
ID=80211361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111424289.6A Pending CN114041779A (en) | 2021-11-26 | 2021-11-26 | Identification system and computer device for identifying respiratory diseases of livestock |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114041779A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104321015A (en) * | 2012-03-29 | 2015-01-28 | 昆士兰大学 | A method and apparatus for processing patient sounds |
| CN108135534A (en) * | 2015-08-26 | 2018-06-08 | 瑞思迈传感器技术有限公司 | Monitoring and the System and method for of management chronic disease |
| CN108935188A (en) * | 2018-07-05 | 2018-12-07 | 平安科技（深圳）有限公司 | Pig disease identification method, apparatus and electronic equipment |
| CN109431507A (en) * | 2018-10-26 | 2019-03-08 | 平安科技（深圳）有限公司 | Cough disease identification method and device based on deep learning |
| CN110265041A (en) * | 2019-07-01 | 2019-09-20 | 河南牧业经济学院 | A kind of method and system for the song behavior collected, analyze pig |
| CN110338092A (en) * | 2019-07-01 | 2019-10-18 | 河南牧业经济学院 | A kind of pig Activity recognition method and system based on sound |
| CN110751942A (en) * | 2018-07-20 | 2020-02-04 | 北京京东金融科技控股有限公司 | Method and device for identifying characteristic sound |
| CN111629663A (en) * | 2017-12-21 | 2020-09-04 | 昆士兰大学 | Method for diagnosing respiratory system disease by analyzing cough sound using disease characteristics |
| CN113488071A (en) * | 2021-07-16 | 2021-10-08 | 河南牧原智能科技有限公司 | Pig cough recognition method, device, equipment and readable storage medium |
-
2021
- 2021-11-26 CN CN202111424289.6A patent/CN114041779A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104321015A (en) * | 2012-03-29 | 2015-01-28 | 昆士兰大学 | A method and apparatus for processing patient sounds |
| CN108135534A (en) * | 2015-08-26 | 2018-06-08 | 瑞思迈传感器技术有限公司 | Monitoring and the System and method for of management chronic disease |
| CN111629663A (en) * | 2017-12-21 | 2020-09-04 | 昆士兰大学 | Method for diagnosing respiratory system disease by analyzing cough sound using disease characteristics |
| CN108935188A (en) * | 2018-07-05 | 2018-12-07 | 平安科技（深圳）有限公司 | Pig disease identification method, apparatus and electronic equipment |
| CN110751942A (en) * | 2018-07-20 | 2020-02-04 | 北京京东金融科技控股有限公司 | Method and device for identifying characteristic sound |
| CN109431507A (en) * | 2018-10-26 | 2019-03-08 | 平安科技（深圳）有限公司 | Cough disease identification method and device based on deep learning |
| CN110265041A (en) * | 2019-07-01 | 2019-09-20 | 河南牧业经济学院 | A kind of method and system for the song behavior collected, analyze pig |
| CN110338092A (en) * | 2019-07-01 | 2019-10-18 | 河南牧业经济学院 | A kind of pig Activity recognition method and system based on sound |
| CN113488071A (en) * | 2021-07-16 | 2021-10-08 | 河南牧原智能科技有限公司 | Pig cough recognition method, device, equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Using a CNN-LSTM for basic behaviors detection of a single dairy cow in a complex environment | |
| KR102168641B1 (en) | System and Method for managing barn | |
| WO2021085313A1 (en) | Disease prediction system, insurance fee calculation system, and disease prediction method | |
| CN112580552B (en) | Murine behavior analysis method and device | |
| JP2020036633A (en) | Abnormality determination program, abnormality determination method and abnormality determination device | |
| Tian et al. | Real-time behavioral recognition in dairy cows based on geomagnetism and acceleration information | |
| KR102265809B1 (en) | Method and apparatus for detecting behavior pattern of livestock using acceleration sensor | |
| CN110111815A (en) | Animal anomaly sound monitoring method and device, storage medium, electronic equipment | |
| CN107495971A (en) | Morbidity's alarm medical system and its detection method based on skeleton identification | |
| KR102425523B1 (en) | Method and appartus for checking symptom of pig and managing cloud service | |
| CN112906734A (en) | Intelligent livestock breeding method and device, computer equipment and storage medium | |
| CN115830490A (en) | Multi-target tracking and behavior statistical method for herd health pigs | |
| CN202815842U (en) | Cloud computing-based intermediate system of traditional Chinese medicine diagnostic method data collection and diagnosis | |
| CN109276243A (en) | Brain electricity psychological test method and terminal device | |
| CN109949272A (en) | Identify the collecting method and system of skin disease type acquisition human skin picture | |
| CN114041779A (en) | Identification system and computer device for identifying respiratory diseases of livestock | |
| CN110751092B (en) | Agricultural monitoring method and device based on Internet of things, storage medium and electronic equipment | |
| CN110123484B (en) | Livestock delivery detection method and device | |
| WO2023216609A1 (en) | Target behavior recognition method and apparatus based on visual-audio feature fusion, and application | |
| CN116824626A (en) | Artificial intelligent identification method for abnormal state of animal | |
| CN113516139A (en) | Data processing method, device, equipment and storage medium | |
| CN115830078A (en) | Live pig multi-target tracking and behavior recognition method, computer equipment and storage medium | |
| KR102341715B1 (en) | Apparatus and method for livestock monitoring | |
| CN113068657B (en) | Intelligent efficient pig raising method and system | |
| CN110008874B (en) | Data processing method and device, computer system and readable medium |
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 |