Animal family domain estimation method based on active learning

An active learning and animal technology, applied in computing, computer components, structured data retrieval, etc., can solve the problem of not being able to take into account the influence of terrain and obstacles, not being able to express the fuzzy boundaries of the animal's range of activities, and being difficult to take into account the anisotropy of animal activities, etc. problem, to achieve the effect of improving authenticity

Active Publication Date: 2020-10-13
TIANJIN NORMAL UNIVERSITY
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional kernel density estimation method is based on the Euclidean distance, which cannot fully take into account the influence of terrain and obstacles on the distance between space objects.
In other words, it is difficult for these methods to account for the anisotropy of animal activities
[0007] (3) The local convex hull method, the problem of this method is that it cannot express the fuzzy boundary of the animal's range of activities
Can not take into account the impact of terrain and obstacles

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
  • Animal family domain estimation method based on active learning
  • Animal family domain estimation method based on active learning
  • Animal family domain estimation method based on active learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] A variety of geographic information data (GPS point set, basic geographic information data, DEM data) is used as input data, among which the GPS point data set is the tracking data of animal activities; obstacles can be determined by basic geographic information data, and obstacles of different animals Animals may vary; DEM data were used to determine the impact of topography on animal activity. It should be noted that due to the diversity of animals, different animals may require different data. Rasterize the above three data with the same resolution and unify the coordinate system. Then use the cost distance calculation module to calculate the cost distance from each GPS tracking point to any point in the animal's activity area; use the possibility distribution calculation module to calculate the fuzzy probability distribution of the animal's activities in this area; use the home domain extraction module to pass The threshold is determined in advance to extract the c...

Embodiment 2

[0090] A simulated dataset such as Figure 5 Shown, the simulated animal is the sika deer, which prefers to live on the edge of forests and meadows, but not in dense forests or bushes; moreover, they prefer areas with little human disturbance, open spaces, and abundant water. The spatial resolution of the DEM data is 25m, and the elevation ranges from 689m to 2129m. In this example, the area above 1800m above sea level ( Figure 6Marked as A in ), the pond ( Figure 6 Marked as B in), expressway service area ( Figure 6 Marked as C), expressway ( Figure 6 marked D) and the farm ( Figure 6 Marked as E) is considered to be an obstacle to the activities of sika deer. Since animals prefer to live on flat terrain rather than rugged and steep areas, the terrain relief obtained by DEM was used to measure the cost distance in this area. Utilize the method of the present invention, obtain the fuzzy degree of membership of the family domain of simulation data set, such as Figu...

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 discloses an animal home domain estimation method based on active learning. A GPS point set, basic geographic information data, DEM data and other geographic information data are used asinput data, the GPS point set is animal activity tracking data, obstacles can be determined by the basic geographic information data, and the obstacles of different animals may be different; digitalelevation model (DEM) data is used for determining the influence of terrain on animal activities, and then a cost distance calculation module is used for calculating the cost distance between each GPStracking point location and any point in an activity area of an animal; a possibility distribution calculation module is utilized to calculate fuzzy possibility distribution of movement of the animalin the area; a home domain extraction module is used for extracting a core area and a non-core area (boundary area) of an animal activity range by determining a threshold value in advance, and home domain calculation is achieved.

Description

[0001] This application was supported by Tianjin Natural Science Foundation (17JCZDJC39700); National Natural Science Foundation of China (41971410). technical field [0002] The present invention relates to the modeling method of fuzzy geographic phenomenon in geographic information science and the method for determining animal home domain in ecology and animal behavior, and more specifically relates to the use of GPS tracker to obtain the position of animals, and the use of position data and basic geographic information data , DEM data, etc. to estimate the range of activities of animals. Background technique [0003] Home range (animal range) estimation is a central topic in the study of spatial ecology and is fundamental to understanding animal behavior. An animal's home range is generally defined as the percentage coverage of the range that encompasses all possible locations. Many complex factors influence the location and extent of a fauna's home range, such as an ani...

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): G06Q10/04G06F16/29G06K9/62G01S19/42
CPCG06Q10/04G06F16/29G01S19/42G06F18/22
Inventor 郭继发
Owner TIANJIN NORMAL UNIVERSITY
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