Pain Level Measurement Using Discrete Wavelet Transform

Vatankhah, Maryam; Toliyat, Amir

doi:10.7763/ijet.2016.v8.917

Cited by 18 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be noted that the data in some studies were gathered via EEG. The results of Vatankhah et al [21,22], Alazrai et al [23], and Nezam et al [24] are in line with those of the present study which were obtained based on cold pressor test (CPT), for causing pain to individuals. Mansoor et al [25] caused pain using coldness and heating stimulus, and differed pain from non-pain states via KNN and SVM classifiers.…”

Section: Introductionsupporting

confidence: 91%

“…It should be mentioned that previous studies applied EEG signal processing and its relevant methods for automatic pain detection. For instance, Vatankhah et al [21,22], Alazrai et al [23], and Nezam et al [24] used CPT, similar to the present study, for inducing pain in participants and the data were recorded using EEG. In study by Vatankhah et al [21], accuracy of the classifier for detecting pain and non-pain states based on nonlinear features was 89 and 93% and based on spectral features, detection accuracy was 75 and 80% using SVM and ANFIS-SVM classifiers, respectively.…”

Section: Discussionmentioning

confidence: 85%

“…In study by Vatankhah et al [21], accuracy of the classifier for detecting pain and non-pain states based on nonlinear features was 89 and 93% and based on spectral features, detection accuracy was 75 and 80% using SVM and ANFIS-SVM classifiers, respectively. Vatankhah et al [22] differentiated pain from the non-pain state based on registered spectral features, and then detected three levels of pain with a wavelet via 95% accuracy. In another study by Alazrai et al [23], the best accuracy in pain and non-pain detection was 93.86% based on the registered features of the beta frequency band and using the SVM classifier.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Dynamic Analysis of Human Brain in the Pain State by Electroencephalography

Tavasoli

Einalou

Akhondzadeh

2021

Preprint

View full text Add to dashboard Cite

Objective Pain is an unpleasant sensation that is important in all therapeutic conditions. So far, some studies have focused on pain assessment and cognition through different tests and methods. Considering the occurrence of pain causes, along with the activation of a long network in brain regions, recognizing the dynamical changes of the brain in pain states is helpful for pain detection using the electroencephalogram (EEG) signal. Therefore, the present study addressed the above-mentioned issue by applying EEG at the time of inducing phasic pain. Results Phasic pain was produced using coldness and then dynamical features via EEG were analyzed by the Recurrence Quantification Analysis (RQA) method, and finally, the Rough neural network classifier was utilized for achieving accuracy regarding detecting and categorizing pain and non-pain states, which was 95.25\(\pm\)4%. The simulation results confirmed that cerebral behaviors are detectable during pain. In addition, the high accuracy of the classifier for evaluating the dynamical features of the brain during pain occurrence is one of the most merits of the proposed method. Eventually, pain detection can improve medical methods.

show abstract

Section: Introductionsupporting

confidence: 91%

Section: Discussionmentioning

confidence: 85%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Analysis of Human Brain in the Pain State by Electroencephalography

Tavasoli

Einalou

Akhondzadeh

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The results show that the variations in the power associated with different frequency bands of the EEG signals can be used to analyze the perception mechanism of tonic cold pain. In another study, Vatankhah and Toliyat [11] proposed an approach that employs the wavelet coherency to estimate the tonic cold pain level. In particular, first-and second-order statistical features were extracted from the wavelet coherency of the EEG signals and used to construct two classifiers-an SVM classifier with radial basis function (RBF) kernel and a hidden Markov model (HMM) classifier.…”

Section: Introductionmentioning

confidence: 99%

Tonic Cold Pain Detection Using Choi–Williams Time-Frequency Distribution Analysis of EEG Signals: A Feasibility Study

et al. 2019

View full text Add to dashboard Cite

Detecting pain based on analyzing electroencephalography (EEG) signals can enhance the ability of caregivers to characterize and manage clinical pain. However, the subjective nature of pain and the nonstationarity of EEG signals increase the difficulty of pain detection using EEG signals analysis. In this work, we present an EEG-based pain detection approach that analyzes the EEG signals using a quadratic time-frequency distribution, namely the Choi–Williams distribution (CWD). The use of the CWD enables construction of a time-frequency representation (TFR) of the EEG signals to characterize the time-varying spectral components of the EEG signals. The TFR of the EEG signals is analyzed to extract 12 time-frequency features for pain detection. These features are used to train a support vector machine classifier to distinguish between EEG signals that are associated with the no-pain and pain classes. To evaluate the performance of our proposed approach, we have recorded EEG signals for 24 healthy subjects under tonic cold pain stimulus. Moreover, we have developed two performance evaluation procedures—channel- and feature-based evaluation procedures—to study the effect of the utilized EEG channels and time-frequency features on the accuracy of pain detection. The experimental results show that our proposed approach achieved an average classification accuracy of 89.24% in distinguishing between the no-pain and pain classes. In addition, the classification performance achieved using our proposed approach outperforms the classification results reported in several existing EEG-based pain detection approaches.

show abstract

“…ese distributions can be obtained by computing joint timefrequency parameters. In wavelet domain analysis, multiscale feature representation is used and each scale has unique thickness [20]. Each level comprises both down-sampling and filtration stage, i.e., designed using high pass and low pass filters.…”

Section: Wavelet Domain Frequency Domain Parameters Do Not Contain Tmentioning

confidence: 99%

Variations in Electrocortical Activity due to Surgical Incision in Anaesthetized Cardiac Patients: Electroencephalogram-Based Quantitative Analysis

Kaur

Prakash

Kalra

et al. 2020

Journal of Healthcare Engineering

View full text Add to dashboard Cite

is study examines the alterations in scalp recorded cortical activity due to surgical incision in anaesthetized cardiac patients using electroencephalogram (EEG) patterns. e primary aim was to compare the changes in electrocortical activity after surgical incision. e secondary aim was to compare the changes in time, frequency, and wavelet domain parameters after loss of consciousness (LoC) and after intubation. Real-time EEG data were recorded from 19 patients undergoing cardiac surgery and signals were quantified with time, frequency, and wavelet domain parameters. An increase in hjorth activity, hjorth complexity, rms value, total band power, relative delta band power, standard deviation and maxima of approximation coefficients (a 5 ), minima of detail coefficients (d 5 , d 4 , and d 3 ) and decrease in hjorth mobility; approximate entropy; relative theta, alpha, and beta band power; specentropy; median, spectral edge, and mean frequency; mean of detail coefficients (d 4 ); standard deviation of detail coefficients (d 5 , d 4 , and d 3 ); maxima of detail coefficients (d 5 ); and minima of approximation coefficients (a 5 ) were observed during LoC. Decrease in hjorth activity; hjorth mobility; rms value; total band power; relative theta band power; median frequency; standard deviation of coefficients (a 5 , d 5 , d 4 , and d 3 ); and maxima of coefficients (a 5 , d 5 , d 4 , and d 3 ) and increase in hjorth complexity; mean of detail coefficients (d 5 ); and minima of coefficients (a 5 , d 5 , d 4 , and d 3 ) were observed after intubation. Significant decrease in hjorth activity; hjorth mobility; total band power; relative alpha band power; specentropy; median and mean frequency; standard deviation and maxima of detail coefficients (d 5 , d 4 , and d 3 ) and increase in rms value; relative delta band power; mean of coefficients (a 5 and d 5 ); and minima of coefficients (d 5 , d 4 , and d 3 ) were observed due to surgical incision. It can be concluded that different spectral and temporal parameters of EEG signals are highly sensitive to induction, intubation, and surgical incision which are potentially informative for measuring the depth of anaesthesia or efficacy of anaesthetic agents.

show abstract

Pain Level Measurement Using Discrete Wavelet Transform

Cited by 18 publications

References 16 publications

Dynamic Analysis of Human Brain in the Pain State by Electroencephalography

Dynamic Analysis of Human Brain in the Pain State by Electroencephalography

Tonic Cold Pain Detection Using Choi–Williams Time-Frequency Distribution Analysis of EEG Signals: A Feasibility Study

Variations in Electrocortical Activity due to Surgical Incision in Anaesthetized Cardiac Patients: Electroencephalogram-Based Quantitative Analysis

Contact Info

Product

Resources

About