An outlier detection method based on agricultural big data

A detection method and technology for outliers, applied in structured data retrieval, digital data information retrieval, database indexing, etc., can solve the problem of poor outlier detection effect, etc. Computationally expensive effects

Inactive Publication Date: 2019-02-15
GUANGDONG KINGPOINT DATA SCI & TECH CO LTD
View PDF4 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide an outlier detection method based on agricultural big data, which uses a distributed system combined with an isolated forest algorithm model to detect outliers in agricultural big data, and solves the problem that the outlier detection effect in the prior art is not good. question

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An outlier detection method based on agricultural big data
  • An outlier detection method based on agricultural big data
  • An outlier detection method based on agricultural big data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Such as figure 1 Shown: An outlier detection method based on agricultural big data, including:

[0031] The data acquisition step is to collect agricultural production data, agricultural soil data and agricultural meteorological resource data, and train the data by means of sampling training. After the training, several isolated trees are obtained, and the collection of isolated trees constitutes a training data set;

[0032] The step of building an iTree tree is to select m sample points from the training data set, continuously randomly select split attributes and split points, and complete the construction of the iTree tree when the termination condition is reached;

[0033] The step of constructing the isolated forest algorithm model is to initialize the number t of iTree trees in the isolated forest algorithm model and the sub-sample set m extracted when constructing the iTree tree, enter the step of cyclically constructing the iTree tree, construct mutually indepen...

Embodiment 2

[0060] Such as Figure 4 Shown: An outlier detection system based on agricultural big data, including an input module, an output module, and a server. The input module, output module, and server communicate through a wireless communication module network, and the wireless communication module uses Niye AMW006-A1U WiFi module;

[0061] 1. Input terminals include:

[0062] The data input module is used for the tester to input the specific value of the test data x and send the test data to the server.

[0063] 2. Output terminals include:

[0064] The data output module is used for receiving the abnormal value judgment result of the server and displaying the result.

[0065] 3. The server includes:

[0066] The data receiving module receives the test data of the input terminal;

[0067] The database contains pre-stored agricultural production data, agricultural soil data and agricultural meteorological resource data, and extracts 100 data for training. After training, 100 is...

Embodiment 3

[0079] In this embodiment, five comparative examples are listed, and outlier detection simulation experiments are performed on the five comparative examples and the first embodiment, and the experimental results of the comparative examples are compared with the experimental results of the first embodiment.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to the field of agricultural outlier detection, in particular to an outlier detection method based on agricultural big data. The method comprises the following steps: a data collection step of collecting agricultural production data, agricultural soil data and agrometeorological resource data, and integrating the data into a training data set; The step of constructing iTree tree is to select m sample points from the training dataset and continuously randomly select splitting attributes and splitting points until the termination condition is reached; the step of constructing iTree tree is to select m sample points from the training dataset. Constructing an isolated forest algorithm model, initializing the number t of iTree trees in the isolated forest and the set m ofsubsamples taken when constructing the iTree trees, entering the step of constructing the iTree trees in a loop, and constructing mutually independent iTree trees, wherein the set of all iTree trees constitutes the isolated forest algorithm model; An outlier judging step of calculating an outlier score s (x), and judging whether the test data x is an outlier by the outlier score s (x). The invention applies the isolated forest algorithm model to the outlier detection of the agricultural big data, and can effectively improve the detection effect of the outlier of the agricultural big data.

Description

technical field [0001] The invention relates to the field of agricultural outlier detection, in particular to an outlier detection method based on agricultural big data. Background technique [0002] Information management is an inevitable trend of agricultural economic development and an inevitable process of transforming traditional agriculture into modern agriculture. With the development of agricultural informatization, agricultural big data is becoming another focus of big data applications. Agricultural big data is cross-professional and cross-industry data analysis and mining. Combining big data with relevant scientific research in the field of agriculture can provide new methods and new ideas for government decision-making, agricultural research and development of agriculture-related enterprises. development prospects. [0003] Outliers refer to the measured values ​​that deviate from the mean value by more than two standard deviations in a set of measured values, ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/06G06Q50/02G06F16/2458G06F16/22
CPCG06Q10/0635G06Q50/02
Inventor 简宋全何佳宁赵轩秦于钦张清瑞
Owner GUANGDONG KINGPOINT DATA SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap