CN113591990A - Meteorological disaster early warning method based on agricultural Internet of things - Google Patents

Meteorological disaster early warning method based on agricultural Internet of things Download PDF

Info

Publication number
CN113591990A
CN113591990A CN202110879314.3A CN202110879314A CN113591990A CN 113591990 A CN113591990 A CN 113591990A CN 202110879314 A CN202110879314 A CN 202110879314A CN 113591990 A CN113591990 A CN 113591990A
Authority
CN
China
Prior art keywords
layer
agricultural
meteorological disaster
things
early warning
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.)
Withdrawn
Application number
CN202110879314.3A
Other languages
Chinese (zh)
Inventor
江煜
许飞云
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jinling Institute of Technology
Original Assignee
Jinling Institute of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jinling Institute of Technology filed Critical Jinling Institute of Technology
Priority to CN202110879314.3A priority Critical patent/CN113591990A/en
Publication of CN113591990A publication Critical patent/CN113591990A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Alarm Systems (AREA)

Abstract

A meteorological disaster early warning method based on an agricultural Internet of things comprises the following steps: step 1, building an agricultural meteorological disaster sensing layer based on STM32F 407; step 2, setting a network layer communication protocol; step 3, simulating the environmental noise of the data; step 4, extracting crop image features; step 5, training an agricultural meteorological disaster classifier; and 6, embedding the agricultural meteorological disaster classifier based on the BP neural network into a platform layer of the Internet of things, and connecting the agricultural meteorological disaster classifier with a sensing layer through a network layer to obtain the meteorological disaster early warning system of the agricultural Internet of things. The agricultural internet of things-based meteorological disaster early warning method is set up, various agricultural meteorological related data are collected through the sensing layer, the data are transmitted to the platform layer through the network layer, and meanwhile, the BP network agricultural meteorological disaster classification model is embedded into the platform, so that real-time monitoring and early warning are carried out on agricultural meteorological disasters, the crop disaster damage is reduced, and the crop yield is improved.

Description

Meteorological disaster early warning method based on agricultural Internet of things
Technical Field
The invention relates to the field of meteorological disaster early warning, in particular to a meteorological disaster early warning method based on an agricultural Internet of things.
Background
Agriculture is an important industry in China, agricultural production is closely related to meteorological conditions, the requirements of different growth and development stages of crops on meteorological elements such as precipitation, temperature, sunlight, wind direction and wind speed are different, and meteorological changes directly affect the yield and quality of the crops. China has large climate environment change, often appears extreme weather, seriously influences crop production and threatens grain safety.
Therefore, agricultural meteorological early warning service work is well done, the agricultural meteorological early warning service work has an important effect on enhancing the agricultural disaster defense capability and reducing the agricultural disaster damage loss, and in order to enhance the rapid and accurate detection and early warning of the meteorological disasters, the agricultural Internet of things-based meteorological disaster early warning method is provided, so that more time is strived for users to adjust the agricultural production management scheme according to the field conditions and the disaster conditions, the agricultural meteorological disaster coping capability is enhanced, and the agricultural meteorological early warning method has important significance on realizing agricultural production and income increase.
Disclosure of Invention
In order to solve the problems, the agricultural Internet of things-based meteorological disaster early warning method is set up, various agricultural meteorological related data are collected through the sensing layer, the data are transmitted to the platform layer through the network layer, and meanwhile, the BP network agricultural meteorological disaster classification model is embedded into the platform, so that real-time monitoring and early warning are carried out on agricultural meteorological disasters, the crop disaster damage is reduced, and the crop yield is improved. To achieve the purpose, the invention provides a meteorological disaster early warning method based on an agricultural Internet of things, which comprises the following specific steps:
step 1, building an agricultural meteorological disaster sensing layer based on STM32F 407: detecting information such as agricultural land images, temperature and humidity, wind power, rainfall and the like of a land to be collected through various sensors, and storing the collected data in real time;
step 2, setting a network layer communication protocol: the method for setting the data communication mode and the communication data format comprises the following steps: the platform layer receives related data sent by the STM32 by sending different types of command codes;
step 3, simulating environmental noise of data: salt and pepper noise is added to the crop image collected by the sensing layer, and interference borne by the agricultural land image during collection is simulated;
step 4, extracting crop image features, performing smoothing filtering processing on the collected crop images, and extracting color features in the images;
step 5, training an agricultural meteorological disaster classifier: the color features extracted from the training samples, humidity, temperature and rainfall are used as input, the freezing injury level of crops is used as output, and an agricultural meteorological disaster classifier based on a BP neural network is trained;
and 6, embedding the agricultural meteorological disaster classifier based on the BP neural network into a platform layer of the Internet of things, and connecting the agricultural meteorological disaster classifier with a sensing layer through a network layer to obtain the meteorological disaster early warning system of the agricultural Internet of things.
Further, the process of constructing the agricultural meteorological disaster sensing layer based on the STM32F407 in the step 1 is represented as follows:
the agricultural Internet of things system for meteorological disaster early warning comprises the following components: perception layer, network layer, wherein the perception layer is with STM32F407 controller as the core, and the perception layer includes: the system comprises temperature and humidity data collected by a temperature and humidity detection sensor, wind data collected by a wind speed sensor, rainfall data collected by a rainfall sensor and crop image data collected by an image collection sensor, wherein each sensor node is independent; the STM32F407 controller passes through DMA circuit, AD converting circuit, drive circuit, various data of filter amplifier circuit collection perception layer to utilize serial ports communication, bluetooth module to link to each other with the network layer, with the data transmission who gathers to thing networking platform layer, thing networking platform layer does further processing analysis to the data that detect simultaneously.
Further, the procedure of setting the network layer communication protocol in step 2 is represented as follows:
setting a data communication mode and a communication data format in a network communication layer of the Internet of things, wherein commands in command codes comprise: command codes for parameter setting and offset calibration of various sensors, sending command codes for data of various sensors, command codes for processing various meteorological disasters and the like.
Further, the process of extracting the crop image features in step 4 is represented as follows:
step 4.1, after adding salt and pepper noise to the crop image, firstly performing smooth filtering processing on the image to remove the salt and pepper noise in the image;
step 4.2, extracting color features of the crop image:
converting the RGB color of the filtered image data into HSV space through color space, and extracting the color characteristic G of the image by using the following formula:
G＝QsQvH+QvS+V (1)
and Qs and Qv are respectively the quantization series of the saturation S and the brightness V of the color space, H represents the hue value of the color space, and the color characteristics extracted from the training sample, temperature and humidity, wind power, rainfall and crop disaster labels form a crop training sample characteristic set.
Further, the process of training the agricultural weather hazard classifier in step 5 is represented as follows:
step 5.1, constructing an agricultural meteorological disaster BP neural network model, which is composed of three layers of structures, wherein the three layers are respectively as follows: the crop disaster prevention system comprises an input layer, a hidden layer and an output layer, wherein the number of nodes of the input layer is the dimension of input data characteristics, the number of layers of the output layer is 1 dimension, and the type of crop disaster is represented by a 1-dimensional output vector label;
step 5.2, setting an objective function, wherein the objective of the BP neural network is to minimize the total error of each node of an output layer, and the error formula is as follows:
Figure BDA0003191435840000031
Okis the output value of k nodes of the output layer, YkIs the actual value of the sample;
step 5.3, inputting training samples, updating weight values and threshold values of each layer:
Figure BDA0003191435840000041
Figure BDA0003191435840000042
Figure BDA0003191435840000043
Figure BDA0003191435840000044
where η is the learning rate of the neural network, VijAnd wjkRespectively representing the weight from the ith neuron node of the input layer to the jth node of the hidden layer and the weight from the jth neuron node of the hidden layer to the kth node of the output layer, thetajIs a network hidden layer node threshold, phikIs a network output layer node threshold;
and 5.4, obtaining the trained agricultural meteorological disaster BP neural network classification model.
Further, the process of the practical application of the meteorological disaster early warning of the agricultural internet of things in the step 6 is represented as follows:
the meteorological disaster early warning system of the agricultural Internet of things collects various parameters such as humidity, temperature, precipitation and wind power related to crops through the sensing layer, displays the parameters on the platform layer after the parameters are communicated through the network layer, sets a threshold value to monitor and early warn various parameters, outputs the freezing condition of the crops through the agricultural meteorological disaster BP neural network classification model, and scientifically prevents and treats different disaster-suffered conditions.
The meteorological disaster early warning method based on the agricultural Internet of things has the beneficial effects that: the invention has the technical effects that:
1. the agricultural Internet of things-based meteorological disaster early warning method is set up, various data related to crops are collected by using the sensing layer, and meanwhile, the data are transmitted to the network layer by using the DMA module, so that the load of a CPU (central processing unit) of an STM32 controller is reduced, and the operation efficiency of the controller is improved;
2. the method effectively simulates the interference of the crop image in the noise environment when the crop image collects data, and trains the BP classification model by using the data simulating noise, thereby enhancing the robustness and stability of the model in the noise environment;
3. according to the invention, real-time monitoring and early warning are carried out on agricultural weather through the agricultural Internet of things, so that the disaster damage of crops can be reduced, and the crop yield is improved.
Drawings
Fig. 1 is a control structure diagram of the present invention.
Detailed Description
The invention is described in further detail below with reference to the following detailed description and accompanying drawings:
the invention provides a meteorological disaster early warning method based on an agricultural Internet of things, and aims to obtain an agricultural Internet of things system capable of monitoring and early warning agricultural meteorology in real time, reduce crop disaster damage and improve crop yield. Fig. 1 is a control structure diagram of the present invention. The steps of the present invention will be described in detail below with reference to the control structure diagram.
Step 1, building an agricultural meteorological disaster sensing layer based on STM32F 407: detecting information such as agricultural land images, temperature and humidity, wind power, rainfall and the like of a land to be collected through various sensors, and storing the collected data in real time;
the process of building an agricultural meteorological disaster sensing layer based on STM32F407 in step 1 can be represented as follows:
the agricultural Internet of things system for meteorological disaster early warning comprises the following components: perception layer, network layer, wherein the perception layer is with STM32F407 controller as the core, and the perception layer includes: the system comprises temperature and humidity data collected by a temperature and humidity detection sensor, wind data collected by a wind speed sensor, rainfall data collected by a rainfall sensor and crop image data collected by an image collection sensor, wherein each sensor node is independent; the STM32F407 controller passes through DMA circuit, AD converting circuit, drive circuit, various data of filter amplifier circuit collection perception layer to utilize serial ports communication, bluetooth module to link to each other with the network layer, with the data transmission who gathers to thing networking platform layer, thing networking platform layer does further processing analysis to the data that detect simultaneously.
Step 2, setting a network layer communication protocol: the method for setting the data communication mode and the communication data format comprises the following steps: the platform layer receives related data sent by the STM32 by sending different types of command codes;
the process of setting the network layer communication protocol in step 2 may be represented as follows:
setting a data communication mode and a communication data format in a network communication layer of the Internet of things, wherein commands in command codes comprise: command codes for parameter setting and offset calibration of various sensors, sending command codes for data of various sensors, command codes for processing various meteorological disasters and the like.
Step 3, simulating environmental noise of data: salt and pepper noise is added to the crop image collected by the sensing layer, and interference borne by the agricultural land image during collection is simulated;
step 4, extracting crop image features, performing smoothing filtering processing on the collected crop images, and extracting color features in the images;
the process of extracting the crop image features in step 4 can be expressed as follows:
step 4.1, after adding salt and pepper noise to the crop image, firstly performing smooth filtering processing on the image to remove the salt and pepper noise in the image;
step 4.2, extracting color features of the crop image:
converting the RGB color of the filtered image data into HSV space through color space, and extracting the color characteristic G of the image by using the following formula:
G＝QsQvH+QvS+V (1)
and Qs and Qv are respectively the quantization series of the saturation S and the brightness V of the color space, H represents the hue value of the color space, and the color characteristics extracted from the training sample, temperature and humidity, wind power, rainfall and crop disaster labels form a crop training sample characteristic set.
Step 5, training an agricultural meteorological disaster classifier: the color features extracted from the training samples, humidity, temperature and rainfall are used as input, the freezing injury level of crops is used as output, and an agricultural meteorological disaster classifier based on a BP neural network is trained;
the process of training the agro-meteorological disaster classifier in step 5 can be represented as follows:
step 5.1, constructing an agricultural meteorological disaster BP neural network model, which is composed of three layers of structures, wherein the three layers are respectively as follows: the crop disaster prevention system comprises an input layer, a hidden layer and an output layer, wherein the number of nodes of the input layer is the dimension of the input data characteristic, the number of layers of the output layer is 1 dimension, and the type of crop disaster is represented by a 1-dimension output vector label;
step 5.2, setting an objective function, wherein the objective of the BP neural network is to minimize the total error of each node of an output layer, and the error formula is as follows:
Figure BDA0003191435840000071
Okis the output value of k nodes of the output layer, YkIs the actual value of the sample;
step 5.3, inputting training samples, updating weight values and threshold values of each layer:
Figure BDA0003191435840000072
Figure BDA0003191435840000073
Figure BDA0003191435840000074
Figure BDA0003191435840000075
where η is the learning rate of the neural network, VijAnd wjkRespectively representing the weight value from the ith neuron node of the input layer to the jth node of the hidden layer and the weight value from the jth neuron node of the hidden layer to the kth node of the output layer, thetajIs a network hidden layer node threshold value, phikIs a network output layer node threshold;
and 5.4, obtaining the trained agricultural meteorological disaster BP neural network classification model.
Step 6, embedding the agricultural meteorological disaster classifier based on the BP neural network into a platform layer of the Internet of things, and connecting the agricultural meteorological disaster classifier with a sensing layer through a network layer to obtain a meteorological disaster early warning system of the agricultural Internet of things;
the process of the practical application of the meteorological disaster early warning of the agricultural internet of things in the step 6 can be expressed as follows:
the meteorological disaster early warning system of the agricultural Internet of things collects various parameters such as humidity, temperature, precipitation and wind power related to crops through the sensing layer, displays the parameters on the platform layer after the parameters are communicated through the network layer, sets a threshold value to monitor and early warn various parameters, outputs the freezing condition of the crops through the agricultural meteorological disaster BP neural network classification model, and scientifically prevents and treats different disaster-suffered conditions.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, but any modifications or equivalent variations made according to the technical spirit of the present invention are within the scope of the present invention as claimed.

Claims (6)

1. A meteorological disaster early warning method based on an agricultural Internet of things comprises the following specific steps:
step 1, building an agricultural meteorological disaster sensing layer based on STM32F 407: detecting information such as agricultural land images, temperature and humidity, wind power, rainfall and the like of a land to be collected through various sensors, and storing the collected data in real time;
step 2, setting a network layer communication protocol: the method for setting the data communication mode and the communication data format comprises the following steps: the platform layer receives related data sent by the STM32 by sending different types of command codes;
step 3, simulating environmental noise of data: salt and pepper noise is added to the crop image collected by the sensing layer, and interference borne by the agricultural land image during collection is simulated;
step 4, extracting crop image features, performing smoothing filtering processing on the collected crop images, and extracting color features in the images;
step 5, training an agricultural meteorological disaster classifier: the color features extracted from the training samples, humidity, temperature and rainfall are used as input, the freezing injury level of crops is used as output, and an agricultural meteorological disaster classifier based on a BP neural network is trained;
and 6, embedding the agricultural meteorological disaster classifier based on the BP neural network into a platform layer of the Internet of things, and connecting the agricultural meteorological disaster classifier with a sensing layer through a network layer to obtain the meteorological disaster early warning system of the agricultural Internet of things.
2. The agricultural internet of things-based meteorological disaster early warning method according to claim 1, wherein the agricultural internet of things-based meteorological disaster early warning method comprises the following steps: the process of building the agricultural meteorological disaster sensing layer based on the STM32F407 in the step 1 is represented as follows:
the agricultural Internet of things system for meteorological disaster early warning comprises the following components: perception layer, network layer, wherein the perception layer is with STM32F407 controller as the core, and the perception layer includes: the system comprises temperature and humidity data collected by a temperature and humidity detection sensor, wind data collected by a wind speed sensor, rainfall data collected by a rainfall sensor and crop image data collected by an image collection sensor, wherein each sensor node is independent; the STM32F407 controller passes through DMA circuit, AD converting circuit, drive circuit, various data of filter amplifier circuit collection perception layer to utilize serial ports communication, bluetooth module to link to each other with the network layer, with the data transmission who gathers to thing networking platform layer, thing networking platform layer does further processing analysis to the data that detect simultaneously.
3. The agricultural internet of things-based meteorological disaster early warning method according to claim 1, wherein the agricultural internet of things-based meteorological disaster early warning method comprises the following steps: the process of setting the network layer communication protocol in step 2 is represented as follows:
setting a data communication mode and a communication data format in a network communication layer of the Internet of things, wherein commands in command codes comprise: command codes for parameter setting and offset calibration of various sensors, sending command codes for data of various sensors, command codes for processing various meteorological disasters and the like.
4. The agricultural internet of things-based meteorological disaster early warning method according to claim 1, wherein the agricultural internet of things-based meteorological disaster early warning method comprises the following steps: the process of extracting the crop image features in step 4 is represented as follows:
step 4.1, after adding salt and pepper noise to the crop image, firstly performing smooth filtering processing on the image to remove the salt and pepper noise in the image;
step 4.2, extracting color features of the crop image:
converting the RGB color of the filtered image data into HSV space through color space, and extracting the color characteristic G of the image by using the following formula:
G＝QsQvH+QvS+V (1)
and Qs and Qv are respectively the quantization series of the saturation S and the brightness V of the color space, H represents the hue value of the color space, and the color characteristics extracted from the training sample, temperature and humidity, wind power, rainfall and crop disaster labels form a crop training sample characteristic set.
5. The agricultural internet of things-based meteorological disaster early warning method according to claim 1, wherein the agricultural internet of things-based meteorological disaster early warning method comprises the following steps: the process of training the agricultural weather hazard classifier in step 5 is represented as follows:
step 5.1, constructing an agricultural meteorological disaster BP neural network model, which is composed of three layers of structures, wherein the three layers are respectively as follows: the crop disaster prevention system comprises an input layer, a hidden layer and an output layer, wherein the number of nodes of the input layer is the dimension of the input data characteristic, the number of layers of the output layer is 1 dimension, and the type of crop disaster is represented by a 1-dimension output vector label;
step 5.2, setting an objective function, wherein the objective of the BP neural network is to minimize the total error of each node of an output layer, and the error formula is as follows:
Figure FDA0003191435830000031
Okis the output value of k nodes of the output layer, YkIs the actual value of the sample;
step 5.3, inputting training samples, updating weight values and threshold values of each layer:
Figure FDA0003191435830000032
Figure FDA0003191435830000033
Figure FDA0003191435830000034
Figure FDA0003191435830000035
where η is the learning rate of the neural network, VijAnd wjkRespectively representing the weight from the ith neuron node of the input layer to the jth node of the hidden layer and the weight from the jth neuron node of the hidden layer to the kth node of the output layer, thetajIs a network hidden layer node threshold, phikIs a network output layer node threshold;
and 5.4, obtaining the trained agricultural meteorological disaster BP neural network classification model.
6. The agricultural internet of things-based meteorological disaster early warning method according to claim 1, wherein the agricultural internet of things-based meteorological disaster early warning method comprises the following steps: the process of the practical application of the meteorological disaster early warning of the agricultural Internet of things in the step 6 is expressed as follows:
the meteorological disaster early warning system of the agricultural Internet of things collects various parameters such as humidity, temperature, precipitation and wind power related to crops through the sensing layer, displays the parameters on the platform layer after the parameters are communicated through the network layer, sets a threshold value to monitor and early warn various parameters, outputs the freezing condition of the crops through the agricultural meteorological disaster BP neural network classification model, and scientifically prevents and treats different disaster-suffered conditions.
CN202110879314.3A 2021-08-02 2021-08-02 Meteorological disaster early warning method based on agricultural Internet of things Withdrawn CN113591990A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110879314.3A CN113591990A (en) 2021-08-02 2021-08-02 Meteorological disaster early warning method based on agricultural Internet of things

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110879314.3A CN113591990A (en) 2021-08-02 2021-08-02 Meteorological disaster early warning method based on agricultural Internet of things

Publications (1)

Publication Number Publication Date
CN113591990A true CN113591990A (en) 2021-11-02

Family

ID=78253601

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110879314.3A Withdrawn CN113591990A (en) 2021-08-02 2021-08-02 Meteorological disaster early warning method based on agricultural Internet of things

Country Status (1)

Country Link
CN (1) CN113591990A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114239849A (en) * 2021-11-30 2022-03-25 支付宝(杭州)信息技术有限公司 Weather disaster prediction and model training method, device, equipment and storage medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114239849A (en) * 2021-11-30 2022-03-25 支付宝(杭州)信息技术有限公司 Weather disaster prediction and model training method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN106971152B (en) Method for detecting bird nest in power transmission line based on aerial images
CN111563431A (en) Plant leaf disease and insect pest identification method based on improved convolutional neural network
CN106991666B (en) A kind of disease geo-radar image recognition methods suitable for more size pictorial informations
CN111127423B (en) Rice pest and disease identification method based on CNN-BP neural network algorithm
CN110083096A (en) A kind of silo intelligent monitoring method
WO2018120634A1 (en) Method and apparatus for identifying disease and insect damage
CN104007733B (en) It is a kind of that the system and method being monitored is produced to intensive agriculture
CN112286263A (en) Crop regulation and control method, device and system and communication equipment
CN116034904B (en) Pig health monitoring system and method based on track type inspection robot
CN116058195B (en) Illumination regulation and control method, system and device for leaf vegetable growth environment
CN113591990A (en) Meteorological disaster early warning method based on agricultural Internet of things
CN109874584A (en) A kind of fruit tree growing way monitoring system based on deep learning convolutional neural networks
CN114460080A (en) Rice disease and pest intelligent monitoring system
Dharmasena et al. Autonomous cloud robotic system for smart agriculture
Yuan et al. Sensitivity examination of YOLOv4 regarding test image distortion and training dataset attribute for apple flower bud classification
CN109828623B (en) Production management method and device for greenhouse crop context awareness
CN116560946A (en) Soil pollution data pushing system based on cloud computing
CN209330740U (en) A kind of early warning system based on machine vision Citrus Huanglongbing pathogen
CN116452358B (en) Intelligent agriculture management system based on Internet of things
CN112036470A (en) Cloud transmission-based multi-sensor fusion cucumber bemisia tabaci identification method
Abdulla et al. Agriculture based on internet of things and deep learning
CN113627258B (en) Apple leaf pathology detection method
CN112800877A (en) Pest control method based on agricultural Internet of things
CN113420623B (en) 5G base station detection method and system based on self-organizing mapping neural network
CN115063602A (en) Crop pest and disease identification method based on improved YOLOX-S 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
WW01 Invention patent application withdrawn after publication

Application publication date: 20211102

WW01 Invention patent application withdrawn after publication