A Multi-source Heterogeneous Data Association Method
A multi-source heterogeneous data and multi-data source technology, applied in the field of data fusion, can solve problems such as the difficulty of directly establishing association relationships, and achieve the effects of promoting association discrimination, improving accuracy, and strengthening associations
Active Publication Date: 2022-03-15
中国人民解放军91977部队
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In view of this, the present invention provides a multi-source heterogeneous data association method, the main purpose of which is to solve the problem in the prior art that multi-source heterogeneous data are in different probability distribution spaces and feature spaces, and it is difficult to directly establish an association relationship
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0018] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0019] The present invention mainly solves the problem in the prior art that in the multi-source heterogeneous data, there is a "heterogeneity gap" between information of different modalities, so effective association cannot be performed.
[0020] The present invention constructs a multi-source heterogeneous data association model, uses a deep neural network to perform nonlinear mapping on the multi-source heterogeneous data, and co...
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
Login to View More Abstract
The invention discloses a method for associating multi-source heterogeneous data, which belongs to the technical field of data fusion and mainly solves the problem of heterogeneous gaps between information of different modalities in multi-source heterogeneous data in the prior art. The method constructs a multi-source heterogeneous data association model, uses a deep neural network to perform nonlinear mapping on the multi-source heterogeneous data, and constructs an association relationship between different modal information. This method integrates the common features and unique features of each data source, and makes full use of the unique features to contain complementary information between data sources, which has a positive role in promoting the association and discrimination between multi-source heterogeneous data.
Description
technical field [0001] The invention relates to the technical field of data fusion, in particular to a multi-source heterogeneous data association method. Background technique [0002] In recent years, with the rapid development of various data detection platforms, the types and quantities of sensors have continued to grow, and the accumulation of detection data has reached the scale of big data. Taking the two types of information, image and location, as examples, the acquisition of image data generally has the characteristics of wide detection range, long revisit cycle, high positioning accuracy, and obvious visual features, which can be used for large-scale early warning in the early warning detection process and terminal identification; radar, AIS and other location data have the characteristics of strong real-time performance but weak visual features, and can be used for target tracking, situation generation and intention judgment in the early warning and detection proc...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/215G06F16/28G06K9/62G06N3/04G06N3/08
CPCG06F16/215G06F16/284G06N3/08G06N3/045G06F18/253
Inventor 吕亚飞张筱晗石敏江志浩王雅芬黄猛涂卫红
Owner 中国人民解放军91977部队