EEG-based tonic cold pain recognition system using wavelet transform
- Springer (part of Springer Nature)
- Publication Type:
- Journal Article
- Neural Computing and Applications, 2019, 31, (7), pp. 3187-3200
- Issue Date:
|Alazrai2019_Article_EEG-basedTonicColdPainRecognit.pdf||Published version||1.02 MB|
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
© 2017, The Natural Computing Applications Forum. Developing an objective pain identification system can provide caregivers with a second opinion to improve the treatment of patients who are unable to verbally communicate their pain. In this study, we present a new EEG-based approach for pain recognition. The proposed approach is employed to identify four different states that a human can feel during tonic cold pain stimulation. These states are the relax state, relax-to-pain state (RPS), pain state (PS), and pain-to-relax state (PRS). A sliding window has been used to decompose the EEG signals into overlapping segments. Each EEG segment is analyzed using the discrete wavelet transform to construct a time–frequency representation of the EEG signals and extract a set of nonlinear features. These features are used to construct a two-layer hierarchical classification framework that can identify the aforementioned four pain states. The first layer identifies whether an EEG segment is relax or pain segment. In the second layer, the pain segments are classified into one of the three pain states (i.e., RPS, PS, and PRS). To evaluate the performance of the proposed approach, we recorded EEG data for 24 healthy subjects who were exposed to tonic cold pain stimulation. Three procedures were employed to evaluate the capability of the approach to detect the four states associated with tonic cold pain stimulation. The experimental results demonstrate the efficacy of our approach for accurate tonic cold pain identification. Moreover, these promising results suggest the feasibility of expanding the proposed approach to characterize clinical pain, such as cancer-related pain.
Please use this identifier to cite or link to this item: