Example Analysis of TensorFlow processing Motion Imagination Classification Task

TensorFlow deals with the sample analysis of motion imagination classification tasks. In view of this problem, this article introduces the corresponding analysis and solutions in detail, hoping to help more partners who want to solve this problem to find a more simple and feasible method.

The method in this paper is EEG source imaging (ESI) + Morlet wavelet joint time-frequency analysis (JTFA) + convolution neural network (CNN). The raw data has been processed using Matlab ToolkitBrainstorm. After the ESI + JTFA process, CNN is used to classify the EEG data.

EEG Motor Imagery Signals (Tasks) Classificationvia Convolutional Neural Networks (CNN)

Code address:

Https://github.com/SuperBruceJia/EEG-Motor-Imagery-Classification-CNNs-TensorFlow installation and use

Python file: PhysioNet_MI_Dataset/MIND_Get_EDF.py

-download all the EEG Motor Movement/Imagery Dataset .edf files from here!

(Under Any Python Environment) $python MIND_Get_EDF.py

Python file: Read_Raw_Data_Save_Into_Matlab_Files.py

-Read the edf Raw data of different channels and save them into matlab .m files

-At this stage, the Python file must be processed under a Python 2 environment (I recommend to use Python 2. 7 version).

(Under Python 2.7Environment) $python Read_Raw_Data_Save_Into_Matlab_Files.py

Matlab file: Saved_Matlab_Data/Preprocessing_Raw_Data.m

-Pre-process the dataset (Data Normalization mainly) and save matlab .m files into Excel .xlsx Files

Python file: MI_Proposed_CNNs_Architecture.py

-the proposed CNNs architecture

-based on TensorFlow 1.12.0 with CUDA 9.0 or TensorFlow 1.13.1 with CUDA 10.0

-The trained results are saved in the Tensorboard

-Open the Tensorboard and save the results into Excel .csv files

-Draw the graphs using Matlab or Origin

(Under Python 3.6Environment) $python MI_Proposed_CNNs_Architecture.py

CNN Network Architecture Code: MI_Proposed_CNNs_Architecture

This is the answer to the sample analysis of TensorFlow's handling of motion imagination classification tasks. I hope the above content can be of some help to you. If you still have a lot of doubts to be solved, you can follow the industry information channel for more related knowledge.