Brain-controlled water drinking system based on dynamic convergence differential neural network

Abstract

The invention provides a brain-controlled water drinking system based on a dynamic convergence differential neural network. The system comprises the following steps: 1) performing data channel screening, band-pass filtering and independent component analysis on electroencephalogram data acquired by emotiv electroencephalogram equipment; 2) training, identifying and classifying the data set obtained in the step 1) through a dynamic convergence differential neural network; 3) combining the P300 identification classification result obtained in the step 2) with a user interface to obtain a final target object number; 4) sending the number of the target object obtained in the step 3) to a visual mechanical arm system, grabbing the cup and sending the cup to the mouth of the user, and completing a water drinking task.

Description

technical field [0001] The invention belongs to the field of electroencephalogram signal recognition control, in particular to a brain-controlled water drinking system based on a dynamic convergence differential neural network. Background technique [0002] Brain Computer Interface (BCI) is an information transmission channel that directly communicates with a computer without relying on other organs and peripheral nerves of the human body. It provides a new way for severely disabled patients to communicate with the outside world. Severely disabled patients often sit in wheelchairs or stay in bed for a long time due to their limited mobility, and it is difficult for others to accurately know their intention of action. They have very limited means of communicating with the outside world. [0003] At present, there are also some existing research attempts to combine brain-computer interface technology with robotic arm technology. The publication number is CN102198660A, and th...

AI Technical Summary

Problems solved by technology

The invention patent applications mentioned above only complete some simple or even preset tasks of manipulator motion control through EEG signals. The tasks completed by the manipulator are not specific and cannot reflect the advantages of the manipulator.

And most of its classification networks are completed using simple machine learning methods, which take a long time to calculate

Images