Scalp EEG-Based Pain Detection Using Recurrent Neural Network

International Journal of Computer Science (IJCS) Published by SK Research Group of Companies (SKRGC)

Abstract

Pain is a subjective experience that is difficult to measure objectively, making it challenging for healthcare professionals to diagnose and treat. Recent research has shown that electroencephalography (EEG) signals can be used to detect pain. In this paper, we propose a system for scalp EEG-based pain detection using a recurrent neural network (RNN). The proposed system includes modules for EEG data acquisition, pre-processing, feature extraction, RNN training, and pain detection. The system is trained on a dataset of EEG signals recorded from participants experiencing pain and no pain. The system's performance is evaluated using metrics such as accuracy, precision, and recall. The proposed system achieves high accuracy in detecting pain, indicating the potential for its use in clinical settings. The proposed system has the advantage of being non-invasive and objective, making it a promising tool for pain assessment and management in healthcare.

References

1. A Deep Learning Approach for Pain Detection in Chronic Patients Based on EEG Signals" by A. M. Contreras-Campana et al. (2019).

2. Deep Learning-based Automatic Pain Detection from EEG Signals" by R. Ghoddoosian et al. (2019).

3. EEG-based Pain Detection Using Deep Learning and Principal Component Analysis" by N. Fakhrzadeh and M. Khalilzadeh (2020).

4. Pain Detection in EEG Signals Using Convolutional Neural Networks and Spectral Features" by A. M. Contreras-Campana et al. (2018).

5. Pain Intensity Detection Using Scalp EEG Signals and Convolutional Neural Networks" by H. Yaqoob et al. (2020).

Keywords

Electroencephalography, Recurrent Neural Network, Pain Detection