Mental fatigue recognition study based on 1D convolutional neural network and short-term ECG signals

Area of Science:

• Biomedical Engineering
• Machine Learning
• Neuroscience

Background:

• Mental fatigue is a significant health concern contributing to accidents.
• Traditional machine learning methods for fatigue detection are inefficient and lack real-time accuracy.

Purpose of the Study:

• To develop an accurate and real-time mental fatigue recognition model.
• To overcome limitations of traditional machine learning in fatigue detection.

Main Methods:

• A 1D Convolutional Neural Network (1D-CNN) model was developed.
• The model processes 5-second raw Electrocardiogram (ECG) sequences.
• A dataset of ECG signals from 22 subjects across three time periods was used for training and testing.

Main Results:

• The 1D-CNN model achieved high performance in recognizing mental fatigue.
• Accuracy, precision, recall, and F1 score reached 98.44%, 98.47%, 98.41%, and 98.44%, respectively.

Conclusions:

• The proposed 1D-CNN model effectively recognizes multi-level mental fatigue.
• This approach enhances accuracy and real-time performance for fatigue monitoring.
• Provides theoretical support for practical, real-time fatigue monitoring in daily life.