System for automatically identifying children with autism based on eye movement technology and machine learning
A machine learning and autism technology, applied in the field of eye movement information capture and machine learning, can solve problems such as the ability to infer other people's intentions and the inability of autistic children to maintain attention, achieving less time-consuming, simple operation, and high application value Effect
Active Publication Date: 2019-04-16
PEKING UNIV
View PDF11 Cites 7 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
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
[0034] In this embodiment, the eye movement data of more than 70 autistic and normal children with high and low function in the visual following task were collected and analyzed in advance. Taking the coordinate mean, standard deviation, data skewness and slope of the eye movement data as the characteristic values of machine learning classification, it is found that these pre-collected data can well classify the three groups of children (normal children, high-school children, etc.) in classification verification. functional and low-functioning autistic children) and achieved a classification accuracy of over 80%. In actual use, for the children to be classified, the children need to complete the visual tracking task and obtain their original eye movement data, and classify the children to be classified according to the established classification model.
[0035] How to choose an appropriate visual-following task to better reveal the differences in the gaze patterns of autisti...
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 relates to a system for automatically identifying children with autism based on an eye movement technology and machine learning. A data collection module of the system is used for collecting eye movement coordinate data of child individuals in vision following tasks; a standardization conversion module is used for conducting standardization conversion on the position of a target picture and an interference picture in each task trying time; a characteristic value acquisition module for classification conducts data processing on the eye movement coordinate data according to the characteristic value kinds after the eye movement coordinate data is acquired and the standardization conversion module conducts processing, and the processed data is used as a final characteristic valuefor classification; a classification model training module uses a K-neighbor classifier and converts the collected eye movement coordinate data into characteristic value data, a classification modelis trained, and according to the established classification model, unknown children are automatically classified and identified. The system is easy to operate, short time is consumed, and the childrenwith autism different in function level can be identified.
Description
technical field [0001] The invention relates to the field of eye movement information capture and machine learning, in particular to a system for automatic identification of autistic children based on eye movement technology and machine learning. Background technique [0002] Autism Spectrum Disorder (ASD, hereinafter referred to as autism) is a neurodevelopmental disorder characterized by impairments in social interaction and language communication, narrow interests, and repetitive stereotyped behaviors (DSM-5; APA, 2013 ), generally onset in infants and young children, and the symptoms are highly heterogeneous and accompanied throughout life. The prevalence of autism is very high. According to a 2016 research report by the US Centers for Disease Control and Prevention, the prevalence of autism in the United States is as high as 14.7‰. The results of a sample survey of primary schools in the Beijing area found that the prevalence of autism in my country is similar to that ...
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 IPC IPC(8): A61B5/16A61B3/113
CPCA61B3/113A61B5/163
Inventor 魏坤琳易莉王乾东贺桥
Owner PEKING UNIV