Discrete data causal discovery method based on deterministic mechanism and noise interference
A technology of noise interference and discrete data, applied in data mining, electrical digital data processing, special data processing applications, etc., can solve the problem of low efficiency of discrete causal discovery, and achieve the goal of overcoming low discovery efficiency, overcoming identification difficulties, and increasing anti-interference. sexual effect
Inactive Publication Date: 2018-09-28
GUANGDONG UNIV OF TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In view of this, the present invention provides a discrete data causal discovery method based on deterministic mechanism and noise interference, which overcomes the defect of low efficiency of discrete causal discovery in the prior art
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
[0034] The embodiment of the present invention provides a discrete data causal discovery method based on a deterministic mechanism and noise interference.
[0035] Such as Figure 1-3 As shown, a discrete data causal discovery method based on deterministic mechanism and noise interference, the steps include:
[0036] S1. Preset model X→Y′→Y, defining a deterministic causal process; if there are two variables, X, Y, if X is the cause of Y, then we say, X→Y, where the causal model includes deterministic The first part is the deterministic mechanism. We believe that the dependent variable X to the fruit variable Y' in the real state is a deterministic mechanism, which can be expressed as Y'=f(x), where f is a discrete mapping function; the second part is the noise interference part, and Y' undergoes noise interference to obtain the observed fruit variable Y, that is, the process can be expressed as X→Y′→Y. In the embodiment of the present invention, the specific mapping relatio...
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 discrete data causal discovery method based on a deterministic mechanism and noise interference, comprising the following steps of: S1, presetting a model X-Y'-Y, and defining a deterministic causal process; S2, defining to obtain an initial scoring standard for evaluating the model X-Y'-Y; S3, calculating a final scoring standard used to evaluate the model; S4, using thegreedy strategy to estimate the state of Y' according to the score given by the final scoring standard, and obtaining the model M1: X-Y'-Y; S5, using the greedy strategy to estimate the state of theopposite X' according to the score given by the final scoring standard, and obtaining the model M2: Y-X'-X; and S6,scoring the S1 and S1 according to the comparison of M1 and M2, and outputting the causal direction. By introducing two parts of determinism and noise interference, the invention flexibly adapts to different deterministic mechanisms and noise mechanisms in the data, thereby increasinganti-interference, increasing the scope of application, overcoming the defects of low efficiency of discrete causal finding in the prior art, and achieving the purpose of improving the efficiency ofcausal discovery.
Description
technical field [0001] The invention relates to the technical field of data mining, and more specifically, relates to a causal discovery method of discrete data based on deterministic mechanism and noise interference. Background technique [0002] With the progress of society and the development of science and technology, the things people need to know become more and more complex. The causal relationship within the system exists objectively. Causal discovery is to mine the causal relationship contained in the data, so as to help people understand the relationship between things. objective law. [0003] In recent studies, causal discovery based on additive noise models has been generalized to discrete data for direction identification through the asymmetry of the independence of X from noise N: Y=f(X)+N, X⊥N ; an open question is whether, in discrete data, causal mechanisms satisfy the above model using additive operations. On the one hand, it has been argued that additive...
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 Applications(China)
IPC IPC(8): G06F17/30
CPCG06F2216/03
Inventor 乔杰蔡瑞初郝志峰温雯王丽娟陈炳丰
Owner GUANGDONG UNIV OF TECH