CN112241951A - Agricultural monitoring method, system and computer equipment based on raspberry pi and LORA - Google Patents
Agricultural monitoring method, system and computer equipment based on raspberry pi and LORA Download PDFInfo
- Publication number
- CN112241951A CN112241951A CN202011118756.8A CN202011118756A CN112241951A CN 112241951 A CN112241951 A CN 112241951A CN 202011118756 A CN202011118756 A CN 202011118756A CN 112241951 A CN112241951 A CN 112241951A
- Authority
- CN
- China
- Prior art keywords
- neural network
- convolutional neural
- raspberry
- lora
- server side
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Catching Or Destruction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to an agricultural monitoring method, system, computer equipment and storage medium based on raspberry pi and LORA, wherein the method comprises the following steps: a convolutional neural network is set up in advance at a server side and used for carrying out pest and disease damage prediction on picture data; training the convolutional neural network at a server side to obtain a corresponding parameter file; transplanting the constructed convolutional neural network and the parameter file into a raspberry group in the gateway; when the gateway receives picture data sent by an LORA node, directly performing pest and disease damage prediction in the gateway through a convolutional neural network with trained parameters; and sending the prediction result of the convolutional neural network to a server side. According to the invention, only the pest and disease damage prediction is carried out on the picture data on the gateway formed by the raspberry group, and only the prediction result is sent to the server, so that the operation pressure of the server is greatly reduced, and the agricultural monitoring efficiency is improved.
Description
Technical Field
The invention relates to the technical field of intelligent monitoring, in particular to an agricultural monitoring method and system based on raspberry pi and LORA, computer equipment and a storage medium.
Background
The raspberry group is a microcomputer mainboard based on an ARM, an SD/MicroSD card is used as a memory hard disk, 1/2/4 USB interfaces and a 10/100 Ethernet interface (A type does not have a network port) are arranged around the mainboard of the card, the mainboard can be connected with a keyboard, a mouse and a network cable, and meanwhile, the raspberry group is provided with a television output interface of video analog signals and an HDMI high-definition video output interface.
At present, an intelligent agricultural monitoring system generally comprises nodes, gateways and servers. The nodes are used for collecting sensor data and forwarding the sensor data to the gateway, the gateway is used for receiving the data transmitted by the nodes and then transmitting the data to the server, and massive data are processed and calculated at the server side, so that the calculation pressure of the server side is greatly increased, the data processing of the server side needs to be reduced, and partial data processing is performed at the gateway side first. However, in the intelligent agricultural monitoring system, the neural network is adopted to predict the plant diseases and insect pests, but as a lot of time is consumed for training parameters of the neural network, the calculation capability of the raspberry in the gateway is not enough, so that the operation efficiency of the whole system is greatly reduced, and the prediction of the plant diseases and insect pests cannot be timely and effectively realized.
Disclosure of Invention
In view of the above, there is a need to provide a raspberry pi and LORA-based agricultural monitoring method, system, computer device and storage medium.
A raspberry pi and LORA based agricultural monitoring method, the method comprising:
a convolutional neural network is set up in advance at a server side and used for carrying out pest and disease damage prediction on picture data;
training the convolutional neural network at a server side to obtain a corresponding parameter file;
transplanting the constructed convolutional neural network and the parameter file into a raspberry group in the gateway;
when the gateway receives picture data sent by an LORA node, directly performing pest and disease damage prediction in the gateway through a convolutional neural network with trained parameters;
and sending the prediction result of the convolutional neural network to a server side.
In one embodiment, the step of building a convolutional neural network in advance at a server side, where the step of using the convolutional neural network to perform pest and disease damage prediction on picture data further includes:
a convolutional neural network is set up in advance at a server side, and the convolutional neural network comprises an input layer, an output layer and a hidden layer;
the input layer is composed of a plurality of input units and is used for receiving information from the external environment, and the input units can receive various characteristic information in the sample;
the hidden layer is arranged between the input layer and the output layer and is used for connecting the input layer variable and the output layer variable through a function;
the output layer is composed of a plurality of output units for generating the prediction result, and each output unit corresponds to a specific classification result.
In one embodiment, the step of training the convolutional neural network at the server side to obtain a corresponding parameter file further includes:
sending a sample set collected in advance into the convolutional neural network;
adjusting a weight matrix in the convolutional neural network according to a difference between an actual output and a desired output of the convolutional neural network;
the above process is repeated for each sample until the overall error of the sample set does not exceed a preset specified range.
In one embodiment, the step of transplanting the constructed convolutional neural network and the parameter file into a raspberry pi in the gateway further includes:
training the convolutional neural network to obtain a weight parameter file consisting of weights;
directly running a convolutional neural network and a weight parameter file which are formed by codes on a java virtual machine in a raspberry group;
and receiving picture data sent by the LORA node, directly carrying out picture identification on the raspberry to obtain a corresponding pest and disease identification result, and sending the identification result to a server side.
A raspberry pi and LORA based agricultural monitoring system, the system comprising:
the server side is used for building a convolutional neural network in advance, and the convolutional neural network is used for predicting plant diseases and insect pests of the picture data; training the convolutional neural network at a server side to obtain a corresponding parameter file; transplanting the constructed convolutional neural network and the parameter file into a raspberry group in the gateway;
the LORA node is used for acquiring picture data and sending the picture data to a corresponding gateway;
the gateway is used for directly predicting the plant diseases and insect pests in the gateway through a convolutional neural network with trained parameters when receiving picture data sent by an LORA node; and sending the prediction result of the convolutional neural network to a server side.
In one embodiment, the server is further configured to:
a convolutional neural network is set up in advance at a server side, and the convolutional neural network comprises an input layer, an output layer and a hidden layer;
the input layer is composed of a plurality of input units and is used for receiving information from the external environment, and the input units can receive various characteristic information in the sample;
the hidden layer is arranged between the input layer and the output layer and is used for connecting the input layer variable and the output layer variable through a function;
the output layer is composed of a plurality of output units for generating the prediction result, and each output unit corresponds to a specific classification result.
In one embodiment, the server is further configured to:
sending a sample set collected in advance into the convolutional neural network;
adjusting a weight matrix in the convolutional neural network according to a difference between an actual output and a desired output of the convolutional neural network;
the above process is repeated for each sample until the overall error of the sample set does not exceed a preset specified range.
In one embodiment, the gateway is further configured to:
acquiring a weight parameter file consisting of weights obtained by training the convolutional neural network;
directly running a convolutional neural network and a weight parameter file which are formed by codes on a java virtual machine in a raspberry group;
and receiving picture data sent by the LORA node, directly carrying out picture identification on the raspberry to obtain a corresponding pest and disease identification result, and sending the identification result to a server side.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any of the above methods when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of any of the methods described above.
The agricultural monitoring method, the agricultural monitoring system, the computer equipment and the storage medium based on the raspberry pi and the LORA are characterized in that a convolutional neural network is constructed in advance at a server side, and the convolutional neural network is used for predicting plant diseases and insect pests of picture data; training the convolutional neural network at a server side to obtain a corresponding parameter file; transplanting the constructed convolutional neural network and the parameter file into a raspberry group in the gateway; when the gateway receives picture data sent by an LORA node, directly performing pest and disease damage prediction in the gateway through a convolutional neural network with trained parameters; and sending the prediction result of the convolutional neural network to a server side. The method takes the parameters of the constructed convolutional neural network into consideration at the server end, then stores the trained parameters in a file, then transplants the neural network containing the trained parameters into the raspberry group, carries out pest and disease prediction on the picture data transmitted by the nodes, finally carries out pest and disease prediction on the picture data on the gateway formed by the raspberry group, and only sends the prediction result to the server, thereby greatly reducing the operating pressure of the server and improving the efficiency of agricultural monitoring.
Drawings
FIG. 1 is a schematic flow diagram of a raspberry pi and LORA based agricultural monitoring method in one embodiment;
FIG. 2 is a diagram of an application environment of a Raspberry pie and LORA based agricultural monitoring method in one embodiment;
FIG. 3 is a schematic flow diagram of a raspberry pi and LORA based agricultural monitoring method in another embodiment;
FIG. 4 is a schematic flow diagram of a raspberry pi and LORA based agricultural monitoring method in yet another embodiment;
FIG. 5 is a schematic flow chart of a raspberry pi and LORA based agricultural monitoring method according to yet another embodiment;
FIG. 6 is a diagram illustrating the structure of a convolutional neural network in one embodiment;
FIG. 7 is a block diagram of a raspberry pi and LORA based agricultural monitoring system in one embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, there is provided a raspberry pi and LORA based agricultural monitoring method comprising:
102, a convolutional neural network is set up in advance at a server side and used for predicting plant diseases and insect pests of picture data;
104, training the convolutional neural network at a server side to obtain a corresponding parameter file;
step 106, transplanting the constructed convolutional neural network and the parameter file into a raspberry group in the gateway;
108, when the gateway receives the picture data sent by the LORA node, directly performing pest and disease damage prediction in the gateway through a convolutional neural network with trained parameters;
and step 110, sending the prediction result of the convolutional neural network to a server side.
At present, an existing intelligent agricultural monitoring system comprises nodes, a gateway and a server, wherein the nodes are used for collecting sensor data and forwarding the sensor data to the gateway, the gateway is used for receiving the data transmitted by the nodes and then transmitting the data to the server, and massive data are processed and calculated at the server end, so that the calculation pressure of the server end is greatly increased, the data processed by the server end needs to be reduced, and partial data processing is firstly performed at the gateway end.
In the embodiment, an agricultural monitoring method based on raspberry pi and LORA is provided, and the method can be applied to the application environment shown in fig. 2. Specifically, the server is connected with the gateway through a network (4G), and the gateway and the node communicate through a LORA module. The image data are collected through the camera at the LORA node and sent to the gateway to carry out pest and disease damage prediction through adopting the neural network, but because the parameter of the training neural network needs to consume a large amount of time, the calculation capability of the raspberry group is not enough, so the method of taking is that the parameter of the constructed convolutional neural network is trained at the server end first, the trained parameter is stored in a file, then the neural network containing the trained parameter is transplanted to the raspberry group, the pest and disease damage prediction is carried out on the image data transmitted by the node, finally, the pest and disease damage prediction is carried out on the image data on the gateway formed by the raspberry group, only the prediction result needs to be sent to the server, and the operation pressure of the server is greatly reduced.
In the embodiment, a convolutional neural network is set up in advance at a server side and used for predicting plant diseases and insect pests of picture data; training the convolutional neural network at a server side to obtain a corresponding parameter file; transplanting the constructed convolutional neural network and the parameter file into a raspberry group in the gateway; when the gateway receives picture data sent by an LORA node, directly performing pest and disease damage prediction in the gateway through a convolutional neural network with trained parameters; and sending the prediction result of the convolutional neural network to a server side. The convolutional neural network parameter training method based on the Raspberry dispatching comprises the steps that the parameter training of the constructed convolutional neural network is conducted at the server side, the trained parameter is stored in a file, then the neural network including the trained parameter is transplanted into the Raspberry dispatching, the pest and disease damage prediction is conducted on the picture data transmitted from the nodes, finally, the pest and disease damage prediction is conducted on the picture data only on the gateway formed by the Raspberry dispatching, only the prediction result is sent to the server, the operating pressure of the server is greatly reduced, and the agricultural monitoring efficiency is improved.
In one embodiment, as shown in fig. 3, an agricultural monitoring method based on raspberry pi and LORA is provided, in which a convolutional neural network is set up in advance at a server, and the step of using the convolutional neural network for pest and disease damage prediction of picture data further includes:
302, a convolutional neural network is set up in advance at a server end, and the convolutional neural network comprises an input layer, an output layer and a hidden layer;
step 304, the input layer is composed of a plurality of input units and used for receiving information from the external environment, and the input units can receive various different characteristic information in the sample;
step 306, the hidden layer is arranged between the input layer and the output layer, and the hidden layer is in function connection with the input layer variable and the output layer variable;
in step 308, the output layer is composed of a plurality of output units for generating the prediction result, and each output unit corresponds to a specific classification result.
In the embodiment, an agricultural monitoring method based on raspberry pi and LORA is provided, wherein an input layer is adopted for building a neural network and only receives information from an external environment, and the input layer is composed of input units, and the input units can receive various different characteristic information in a sample. Each neuron of this layer behaves as an independent variable, and passes information only for the next layer without performing any computation. The hidden layer is interposed between the input layer and the output layer, these layers being fully used for analysis, whose function links the input layer variables and the output layer variables to make them more data-adaptive. Finally, the output layer generates the final result, each output unit corresponds to a specific classification and is the result value sent to the external system by the network, and the whole network achieves the purpose of learning by a program for adjusting the link strength. As shown in fig. 6, the input unit receives different image characteristic information, and the output unit is used for outputting different pest and disease prediction results.
In an embodiment, as shown in fig. 4, there is provided a raspberry pi and LORA-based agricultural monitoring method, in which the step of training the convolutional neural network at a server side to obtain a corresponding parameter file further includes:
step 402, sending a sample set collected in advance into the convolutional neural network;
step 404, adjusting a weight matrix in the convolutional neural network according to the difference between the actual output and the expected output of the convolutional neural network;
step 406, the above process is repeated for each sample until the overall error of the sample set does not exceed a preset specified range.
In this embodiment, a method for agricultural monitoring based on raspberry pi and LORA is provided, in which a set of training sets collected in advance is sent to a network for a training process of a neural network, and connection weights are adjusted according to a difference between an actual output and an expected output of the network. The trained model can have a better monitoring effect, and the specific training model comprises the following steps:
first, one sample (Ai, Bi) of the sample set is selected, Ai being data and Bi being a label (belonging to a category). Then, the data is sent to a convolutional neural network, and the actual output Y of the neural network is calculated, wherein the weights in the network should be random quantities. Then, error calculation, i.e., how much the predicted value differs from the actual value, is performed, and the weight matrix is adjusted according to the error. Finally, the above process is repeated for each sample until the error does not exceed the specified range for the entire sample set.
In one embodiment, as shown in fig. 5, there is provided a raspberry pi and LORA-based agricultural monitoring method, in which the step of transplanting the constructed convolutional neural network and the parameter file into the raspberry pi in the gateway further includes:
502, training a convolutional neural network to obtain a weight parameter file consisting of weights;
step 504, directly running the convolutional neural network formed by the codes and the weight parameter file on a java virtual machine in the raspberry pi;
and step 506, receiving the picture data sent by the LORA node, directly carrying out picture recognition on the raspberry to obtain a corresponding pest and disease identification result, and sending the identification result to a server side.
In this embodiment, an agricultural monitoring method based on a raspberry pi and a LORA is provided, where the method is trained to obtain a parameter file composed of weights, then a neural network model composed of codes and the weight parameter file are directly run on a java virtual machine in the raspberry pi, and then a picture transmitted by the LORA is used to directly perform picture recognition on the raspberry pi to determine whether cotton is diseased or not and what kind of disease is specific. And finally, the raspberry group sends the prediction result to a server.
The specific usage scenario is illustrated as follows: in actual work, a camera in a node sends image data of a cotton field to a gateway formed by a raspberry group, whether plant diseases and insect pests exist is predicted by utilizing a neural network in the gateway, and then a prediction result is transmitted to a server, so that prediction of the plant diseases and insect pests can be realized in the gateway, participation of the server is not needed, and pressure of the server is greatly reduced.
It should be understood that although the various steps in the flow charts of fig. 1-5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 7, there is provided a raspberry pi and LORA based agricultural monitoring system 700, comprising:
the server 701 is used for building a convolutional neural network in advance, and the convolutional neural network is used for predicting plant diseases and insect pests of the picture data; training the convolutional neural network at a server side to obtain a corresponding parameter file; transplanting the constructed convolutional neural network and the parameter file into a raspberry group in the gateway;
the LORA node 703 is used for acquiring picture data and sending the picture data to a corresponding gateway;
the gateway 702 is used for directly predicting plant diseases and insect pests in the gateway through a convolutional neural network with trained parameters when picture data sent by an LORA node is received; and sending the prediction result of the convolutional neural network to a server side.
In one embodiment, the server 701 is further configured to:
a convolutional neural network is set up in advance at a server side, and the convolutional neural network comprises an input layer, an output layer and a hidden layer;
the input layer is composed of a plurality of input units and is used for receiving information from the external environment, and the input units can receive various characteristic information in the sample;
the hidden layer is arranged between the input layer and the output layer and is used for connecting the input layer variable and the output layer variable through a function;
the output layer is composed of a plurality of output units for generating the prediction result, and each output unit corresponds to a specific classification result.
In one embodiment, the server 701 is further configured to:
sending a sample set collected in advance into the convolutional neural network;
adjusting a weight matrix in the convolutional neural network according to a difference between an actual output and a desired output of the convolutional neural network;
the above process is repeated for each sample until the overall error of the sample set does not exceed a preset specified range.
In one embodiment, the gateway 702 is further configured to:
acquiring a weight parameter file consisting of weights obtained by training the convolutional neural network;
directly running a convolutional neural network and a weight parameter file which are formed by codes on a java virtual machine in a raspberry group;
and receiving picture data sent by the LORA node, directly carrying out picture identification on the raspberry to obtain a corresponding pest and disease identification result, and sending the identification result to a server side.
For specific limitations of the raspberry pi and LORA based agricultural monitoring system, reference may be made to the above limitations of the raspberry pi and LORA based agricultural monitoring method, which are not described herein again.
In one embodiment, a computer device is provided, the internal structure of which may be as shown in FIG. 8. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a raspberry pi and LORA based agricultural monitoring method.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method embodiments when executing the computer program.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the above respective method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A raspberry pi and LORA based agricultural monitoring method, the method comprising:
a convolutional neural network is set up in advance at a server side and used for carrying out pest and disease damage prediction on picture data;
training the convolutional neural network at a server side to obtain a corresponding parameter file;
transplanting the constructed convolutional neural network and the parameter file into a raspberry group in the gateway;
when the gateway receives picture data sent by an LORA node, directly performing pest and disease damage prediction in the gateway through a convolutional neural network with trained parameters;
and sending the prediction result of the convolutional neural network to a server side.
2. The agricultural monitoring method based on the raspberry pi and the LORA according to claim 1, wherein a convolutional neural network is pre-established at a server side, and the step of the convolutional neural network for performing pest and disease damage prediction on picture data further comprises:
a convolutional neural network is set up in advance at a server side, and the convolutional neural network comprises an input layer, an output layer and a hidden layer;
the input layer is composed of a plurality of input units and is used for receiving information from the external environment, and the input units can receive various characteristic information in the sample;
the hidden layer is arranged between the input layer and the output layer and is used for connecting the input layer variable and the output layer variable through a function;
the output layer is composed of a plurality of output units for generating the prediction result, and each output unit corresponds to a specific classification result.
3. The raspberry pi and LORA-based agricultural monitoring method of claim 1, wherein the step of training the convolutional neural network at a server end to obtain a corresponding parameter file further comprises:
sending a sample set collected in advance into the convolutional neural network;
adjusting a weight matrix in the convolutional neural network according to a difference between an actual output and a desired output of the convolutional neural network;
the above process is repeated for each sample until the overall error of the sample set does not exceed a preset specified range.
4. The raspberry pi and LORA-based agricultural monitoring method of claim 3, wherein the step of transplanting the constructed convolutional neural network and parameter file into the raspberry pi in the gateway further comprises:
training the convolutional neural network to obtain a weight parameter file consisting of weights;
directly running a convolutional neural network and a weight parameter file which are formed by codes on a java virtual machine in a raspberry group;
and receiving picture data sent by the LORA node, directly carrying out picture identification on the raspberry to obtain a corresponding pest and disease identification result, and sending the identification result to a server side.
5. An agricultural monitoring system based on raspberry pi and LORA, the system comprising:
the server side is used for building a convolutional neural network in advance, and the convolutional neural network is used for predicting plant diseases and insect pests of the picture data; training the convolutional neural network at a server side to obtain a corresponding parameter file; transplanting the constructed convolutional neural network and the parameter file into a raspberry group in the gateway;
the LORA node is used for acquiring picture data and sending the picture data to a corresponding gateway;
the gateway is used for directly predicting the plant diseases and insect pests in the gateway through a convolutional neural network with trained parameters when receiving picture data sent by an LORA node; and sending the prediction result of the convolutional neural network to a server side.
6. The raspberry pi and LORA based agricultural monitoring system of claim 5, wherein the server side is further configured to:
a convolutional neural network is set up in advance at a server side, and the convolutional neural network comprises an input layer, an output layer and a hidden layer;
the input layer is composed of a plurality of input units and is used for receiving information from the external environment, and the input units can receive various characteristic information in the sample;
the hidden layer is arranged between the input layer and the output layer and is used for connecting the input layer variable and the output layer variable through a function;
the output layer is composed of a plurality of output units for generating the prediction result, and each output unit corresponds to a specific classification result.
7. The raspberry pi and LORA based agricultural monitoring system of claim 5, wherein the server side is further configured to:
sending a sample set collected in advance into the convolutional neural network;
adjusting a weight matrix in the convolutional neural network according to a difference between an actual output and a desired output of the convolutional neural network;
the above process is repeated for each sample until the overall error of the sample set does not exceed a preset specified range.
8. The raspberry pi and LORA based agricultural monitoring system of claim 7, wherein the gateway is further configured to:
acquiring a weight parameter file consisting of weights obtained by training the convolutional neural network;
directly running a convolutional neural network and a weight parameter file which are formed by codes on a java virtual machine in a raspberry group;
and receiving picture data sent by the LORA node, directly carrying out picture identification on the raspberry to obtain a corresponding pest and disease identification result, and sending the identification result to a server side.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 4 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011118756.8A CN112241951A (en) | 2020-10-19 | 2020-10-19 | Agricultural monitoring method, system and computer equipment based on raspberry pi and LORA |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011118756.8A CN112241951A (en) | 2020-10-19 | 2020-10-19 | Agricultural monitoring method, system and computer equipment based on raspberry pi and LORA |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112241951A true CN112241951A (en) | 2021-01-19 |
Family
ID=74169123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011118756.8A Pending CN112241951A (en) | 2020-10-19 | 2020-10-19 | Agricultural monitoring method, system and computer equipment based on raspberry pi and LORA |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112241951A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112714410A (en) * | 2021-01-25 | 2021-04-27 | 中北大学 | Agricultural monitoring method with movable nodes |
| CN112714411A (en) * | 2021-01-25 | 2021-04-27 | 中北大学 | Agricultural monitoring device with movable nodes |
| CN113008742A (en) * | 2021-02-23 | 2021-06-22 | 中国农业大学 | Method and system for detecting deposition amount of fog drops |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109272108A (en) * | 2018-08-22 | 2019-01-25 | 深圳市亚博智能科技有限公司 | Control method for movement, system and computer equipment based on neural network algorithm |
| CN109784153A (en) * | 2018-12-10 | 2019-05-21 | 平安科技（深圳）有限公司 | Emotion identification method, apparatus, computer equipment and storage medium |
| CN111107530A (en) * | 2019-12-06 | 2020-05-05 | 深圳大学 | Agricultural disease and pest control system based on LoRa technology |
| CN111367773A (en) * | 2020-02-29 | 2020-07-03 | 苏州浪潮智能科技有限公司 | Method, system, equipment and medium for detecting network card of server |
-
2020
- 2020-10-19 CN CN202011118756.8A patent/CN112241951A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109272108A (en) * | 2018-08-22 | 2019-01-25 | 深圳市亚博智能科技有限公司 | Control method for movement, system and computer equipment based on neural network algorithm |
| CN109784153A (en) * | 2018-12-10 | 2019-05-21 | 平安科技（深圳）有限公司 | Emotion identification method, apparatus, computer equipment and storage medium |
| CN111107530A (en) * | 2019-12-06 | 2020-05-05 | 深圳大学 | Agricultural disease and pest control system based on LoRa technology |
| CN111367773A (en) * | 2020-02-29 | 2020-07-03 | 苏州浪潮智能科技有限公司 | Method, system, equipment and medium for detecting network card of server |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112714410A (en) * | 2021-01-25 | 2021-04-27 | 中北大学 | Agricultural monitoring method with movable nodes |
| CN112714411A (en) * | 2021-01-25 | 2021-04-27 | 中北大学 | Agricultural monitoring device with movable nodes |
| CN112714410B (en) * | 2021-01-25 | 2023-04-07 | 中北大学 | Agricultural monitoring method with movable nodes |
| CN113008742A (en) * | 2021-02-23 | 2021-06-22 | 中国农业大学 | Method and system for detecting deposition amount of fog drops |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112241951A (en) | Agricultural monitoring method, system and computer equipment based on raspberry pi and LORA | |
| Zhang et al. | Estimation of a generalized fishery model: A two-stage approach | |
| KR102367409B1 (en) | Method, server and computer program for predicting it service failure using pre-learned failure prediction model | |
| JP2021018821A (en) | Data intelligent prediction method, device, computer device, and storage medium | |
| CN115829297B (en) | Work package generation method, device, terminal and storage medium for assembly type building | |
| CN116310914B (en) | Unmanned aerial vehicle monitoring method and system based on artificial intelligence | |
| CN112132278A (en) | Model compression method and device, computer equipment and storage medium | |
| CN114647525A (en) | Diagnostic method, diagnostic device, terminal and storage medium | |
| CN113723956A (en) | Abnormity monitoring method, device, equipment and storage medium | |
| CN112988538A (en) | Artificial intelligence development platform monitoring alarm data prediction method, device and medium | |
| CN113705685A (en) | Disease feature recognition model training method, disease feature recognition device and disease feature recognition equipment | |
| CN112181659A (en) | Cloud simulation memory resource prediction model construction method and memory resource prediction method | |
| CN115409153A (en) | Attention LSTM-based animal husbandry index prediction method and prediction system | |
| CN111679970B (en) | Method for predicting running environment state of robot software system | |
| CN114219177A (en) | Computer room environment regulation and control method and device, electronic equipment and storage medium | |
| CN115730660B (en) | Link generation method and related device based on causal decoupling | |
| CN116521344B (en) | AI algorithm scheduling method and system based on resource bus | |
| CN115409217B (en) | Multitasking predictive maintenance method based on multi-expert hybrid network | |
| Morales-García et al. | SEPARATE: A tightly coupled, seamless IoT infrastructure for deploying AI algorithms in smart agriculture environments | |
| CN110766231A (en) | Crime prediction method and system based on multi-head neural network | |
| CN114242196B (en) | Automatic generation method and device for clinical medical record | |
| CN112000428B (en) | JVM optimization method and device based on machine learning and electronic device | |
| CN114334029A (en) | Compound activity prediction method, network training method, device, medium, and apparatus | |
| CN114782758B (en) | Image processing model training method, system, computer device and storage medium | |
| CN113098707B (en) | Virtual network function demand prediction method in edge network |
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 |