Children hyperactivity behavior feature recognition algorithm based on deep learning

Abstract

The invention discloses a children hyperactivity behavior feature recognition algorithm based on deep learning, and relates to the technical field of recognition algorithms. The method comprises the following steps: step 1, acquiring and preprocessing an action image data set within the duration of the action of a to-be-recognized child; step 2, respectively inputting the data set obtained in the step 1 into a VGG16 convolutional neural network, a ResultNet50 convolutional neural network and an Inception-V4 convolutional neural network for classification and identification; step 3, processing the last layer of convolutional features of the three convolutional neural networks of VGG16, ResultNet50 and Inception-V4 through global average pooling operation; step 4, calculating the attention fusion weight of the VGG16 convolutional neural network, the ResultNet50 convolutional neural network and the Inception-V4 convolutional neural network through feature splicing; and 5, fusing the attention fusion weight and the feature values of the three models through inner product operation. The accuracy of an identification result is improved, the identification accuracy can be effectively improved, and medical workers are assisted in completing preliminary diagnosis of the hyperactivity of children.

Description

technical field [0001] The invention belongs to the technical field of feature recognition algorithms, in particular to a deep learning-based behavior feature recognition algorithm for children with ADHD. Background technique [0002] ADHD (abbreviated as ADHD), also known as Attention Deficit Hyperactivity Disorder (ADHD). It is a common abnormal behavior problem in children. The intelligence of these children is normal or close to normal, but they have defects in learning behavior and emotion. The main manifestations are difficulty in concentrating attention, narrowing attention span, short attention span, and excessive activities regardless of occasions. Hyperactivity, emotional impulsiveness, etc., often accompanied by cognitive impairment and learning difficulties. The disease starts before school and is a chronic process. The disease not only affects children's school, family and out-of-school life, but also easily leads to persistent learning difficulties, behavior...

AI Technical Summary

Problems solved by technology

The intelligence of these children is normal or close to normal, but they have defects in learning behavior and emotion. The main manifestations are that they are not commensurate with their age and developmental level. Excessive, emotional impulsiveness, etc., often accompanied by cognitive impairment and learning difficulties

Images