Functional magnetic resonance imaging (fMRI) based category concepts similarity calculation method
A category and concept technology, applied in the field of similarity calculation between category concepts based on functional magnetic resonance, can solve the problems of inability to obtain similarity and difficulty in obtaining category concept similarity, and achieve the effect of high accuracy
Inactive Publication Date: 2016-06-08
XUANWU HOSPITAL OF CAPITAL UNIV OF MEDICAL SCI
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, no matter using corpus or semantic web, how to collect and manage a large amount of corpus or semantic vocabulary is a huge challenge, and there are still many technical difficulties
Furthermore, this method models the entire population based on its assumptions, and cannot model the similarity between category concepts at the individual level
[0006] In summary, no matter which of the above methods is used to calculate the similarity between category concepts, there is a certain degree of subjectivity, and it is difficult to obtain a large number of similarities between category concepts
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
[0036] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and examples.
[0037] In order to objectively and easily obtain a large amount of similarity degree information between category concepts and improve accuracy, the present invention applies fMRI technology to the similarity calculation process between category concepts. The similarity of category concept images is directly judged. The similarity calculations between category concepts are all calculated based on the brain region image information collected by fMRI when the subjects recognize the category concept pictures, so that a large number of category concepts can be obtained with fewer judgments and lower cognitive load. similarity information. Moreover, it is an objective method to calculate the similarity between category concepts directly based on the activat...
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 present invention discloses a functional magnetic resonance imaging (fMRI) based category concepts similarity calculation method. The method specifically comprises steps of firstly, when each category concept image is identified, collecting, by using fMRI, brain area activation image information when each tested person identifies each category concept image, and then, calculating based on the collected image information to obtain an activation level vector of a set activation brain area when each tested person identifies each category concept image; and finally, calculating an average variance of activation level vectors corresponding to every two category concept images of each tested person, then, normalizing the obtained average variance so as to obtain a similarity value of every two category concepts. According to the method, similarity degrees of a lot of category concepts can be obtained easily and objectively, and the accuracy is high.
Description
technical field [0001] The present invention relates to the fields of artificial intelligence and cognitive neuroscience, in particular to a similarity calculation method between category concepts based on functional magnetic resonance (fMRI, functional magnetic resonance imaging). Background technique [0002] In the field of artificial intelligence and network intelligence, it is often necessary to evaluate the similarity between category concepts, for example: the similarity between category concepts such as "apple-pear" or "apple-potato", so that the similarity between the evaluated category concepts Applied in intelligent search engine or intelligent question answering system. How to evaluate the similarity between category concepts objectively, rationally and quantitatively is very important for the research and development in the field of intelligence. [0003] At present, there are two main methods for calculating the similarity between category concepts: the first ...
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): G06F19/00
CPCG16Z99/00
Inventor 梁佩鹏李坤成
Owner XUANWU HOSPITAL OF CAPITAL UNIV OF MEDICAL SCI