EEG-Based Processing Approach for Pain Detection

encephalogram-Based bear on Approach for Pain DetectionAbstract-To abide by the twinge based on encephalogram signals variability, several efforts has been made only no promising result has been achieved yet. In this study, we propose divergent gives to banish pan. electroencephalogram signals of 28 healthy volunteers were recorded continuously while they pass wound through the cognize ice-water paradigm. To access the de-correlated EEG extensions, In open portion Analysis(ICA) scheme was employ. Among them, the artifact and noise sources were removed and therefore suffer hooklike sources were obdurate and projected back. Before the assortment, some features were extracted from the EEG signal. To select the lift out features, sequential forward selection (SFS) was applied which also eliminates the redundancy. The compartmentalization results house 89% , 90% and 94% accuracy when one ne arest neighbour (1NN), 3NN and support sender machine (SVM) were use, re spectively.Keywords EEG sources, fuss in the ass dependent features, entropy, feature selection.IntroductionBackonja et al. 1 proposed an ice-water bath as a gradual painful stimulus, termed as the cold presser test (CPT). in this study, CPT is applied as the pain motivator paradigm. Some studies, inveatigated the changes during pain. The result of some previous studies2-5 was inform as an gain in the Delta and genus of import stripess and a decrease in the alpha mob during pain.In an separate(prenominal) study, a tonic pain stimulus 6 increase the motive of Delta, Beta-III and Gamma good deals and decreased the Theta, of import-I and Alpha-II band precedents. Intramuscular injection of hypertonic saline increases the Beta function7. In another question, inducing Capsaicin caused no square change in the EEG bands. Another study implied changes of Alpha band activities interact in pain-perception process 8. In another investigate, two levels of pain were classified by Nave Bayes classifier which produces 86.38.4% categorisation accuracy 21. In a different approach, fMRI images of the constituenticipants adept were detect while they were experiencing pain by heat induction which resulted in 94% accuracy 9.The close repeated findings of these studies is a general increase in the power of Beta band simultaneous to a decrease in the Alpha band with a possible coherence increases across different bands, as the brain response to pain.In naval division 2, the data enter and the preprocessing are explained In Section 3, the methods are described in detail in Section 4, the results are presented. Section 5 concludes the results.Data record and Preprocessing2.1. Data RecordingFor recording EEG signals, 30 electrodes were used by Scanlt EEG recording system. A cap based on 10-20 electrode placement system was used for recording. The impedance of every(prenominal) electrodes was less than 5 kilo ohms. The sampling count was ad neverthelessed at 25 0 hertz and a bandpass filter with cut-off frequencies adjusted in 0.5 and 47 hertz was implemented to the signal.In previous studies, laser, cuff pressure, baking hot/ice water, Electrocutaneous arousal 10-13, fetch been used to induce pain. In this study, the ice-water (also called CPT) was selected to give birth minimum side-effect. The recording procedure took place in a bland room. First, to achieve a baseline recording for distributively volunteer, a 30 second EEG signal were recorded in the resting position, which is called no-pain class. Then, by place their choke in the cold water (1.70.2centigrad) after a while, they reported the pain. The recording continues till the tolerating sentence for each subject.With respect to the fact of artifacts armorial bearing in the EEG signals and to record the noises with amplyer quality, some electrodes on the expect muscles were put to detect electromyogram artifacts. Also, EOG is one of the other artifact sources in EEG.2.2 . EEG Artifacts Eliminating Principal component analytic thinking (PCA) and regression methods14 are the methods used for eliminating the EEG artifacts such as muscle artifacts and eye artifacts. Also ICA has been introduced much effective for decomposing the recorded signals into uncorrelated sources 14 which is applied here to remove the EEG artifacts.2.2.1. free-living Component Analysis (ICA)The components x i displaystyle x_i of the observed random vector x = ( x 1 , , x m ) T displaystyle x=(x_1,ldots ,x_m)T are generated as a sum of the independent components s k displaystyle s_k x i = a i , 1 s 1 + + a i , k s k + + a i , n s n displaystyle x_i=a_i,1s_1+cdots +a_i,ks_k+cdots +a_i,ns_n weight down by the mixing weights a i , k displaystyle a_i,k 15X= AS (1)Where S is sources vector, X is the recorded signals (EEGs) matrix.To calculate its inverse or pseudo-inverse, termed as W, the equation(3) is usedS =WX, where W=A-1 (2)2.2.2. EOG Artifact To remove the most outsta nding EEG artifacts, which are EOG and EMG artifacts, the similar process was done. As the Fp1 highroad is the most contained EEG channel, the correlativity of this channel with all determined sources, was mensurable Eq.4 is the correlation formula. If the value exceeded 0.7, the corresponding source was selected as the suspicious EOG source16. (3)Where Ri is the correlation of the ith source with the recorded signal at Fp1.Fig.1 shows the spectral defend of the determined EOG source which is mostly on foreahed space.Shanon Entropy (4)Fractal DimensionL(k)= (5)Fig. 1. Spectral lay out of EOG component2.2.3. EMG ArtifactsTo remove the EMG artifacts, the correlation of all sources with the facadeis and temporalis muscle channels were computed and the ones which were more than 0.7 were considered as the probable EMG sources. Commonly, EMG sources have higher power at high frequencies. Therefore, to precisely detect EMG sources, in addition to the correlation criterion, their brai n role were investigated17. The scalp map and power spectrum of one of the detected EMG artifacts is shown in Fig. 2.(b)Fig. 2. An EMG source (a)Scalp map,(b) Activity Power SpectralMethodsThis study is started from the data acquisition part in which 28 healthy subjects participated. We record their EEG signals through the resting pin down (without imposing any pain stimulus) and pain condition.Due to the presence of artifact and noise in the recorded signals, we apply independent component abstract (ICA) to EEG in order to remove the effect of electrooculogram (EOG), electromyogram (EMG) and suit artifacts. Non-artifact sources were projected back to electrode space and various features were extracted from them. To remove the redundancy and change magnitude the discriminability, an approach for selecting discriminative ones, Sequential earlier Selection(SFS) was applied. The candidate classifiers were support vector machine (SVM) and one nearest neighbor (1NN).3.1. FeaturesTh e features used in this re bet are as follows band power of the pain sources in pentad bands (Delta, Theta, Alpha, Beta, Gamma), fractal dimension, Shannon entropy, approximate entropy and spectral entropy.As a brief definition to the features, Five frequency bands including Delta (0-4 Hz), Theta (4-8 Hz), Alpha (8-13 Hz), Beta (13-30 Hz), and Gamma (30Hz) were elicited for each time frame, from each channel. 17.Shannon entropy 18 measures the amount of irregularity in a distribution.Fractal dimensionmeasures the irregularity or roughness of a signal in a time frame19.The table below, demonstrates the brief procedure of calculating the features.Where P()are the probabilities occurred in the ith bin.is thethe average out length, L(k) is the average length.3.2. Feature selectionThe high number of features extracted in this study, from 30 channels within each time frame caused a high amount of redundancy.Search strategies need an objective function to select the fitting sub mend of features. This objective function is usually a statistical/ information/ surmount based criterion or the classifiers feedback, which are called filter and housecoat, respectively. Filter methods are fast and does not bias to the classifier type, while wrapper methods usually render better results at high computational complexity cost.3.2.1. Sequential Forward Selection (SFS)Sequential forward selection mechanism starts with empty set of features and repeatedly adds the most significant features to reach the criterion20.Here the criterion is selected as the sort accuracy with the objective of SFS selects the most discriminative algorithm.3.3. ClassifiersTwo well-known(a) classifiers, 1-NN and SVM, were used in this study. 1-NN is a local and nonlinear classifier, which is proper for classifying multimodal distributed samples41. From another angle, SVM with a suitable kernel is capable of classifying samples of two classes with overlap, which suffers a heavy(p) generalization p roperty21.3.4. classificationInvestigating brain map through CPT gives us valuable information about the classification possibility. Two frequency ranges, come to at 2Hz (Delta) and 9.8Hz (Alpha), are observed as the most pain dependent features 3-5,8,22,23. The average brain map over all the subjects, in the Delta (Fig. 3) and Alpha (Fig. 4) bands, are exhibited in pain and no pain class.abFig. 3. The average brain map of subjects at 2Hz (Delta band) a) Non-pain, b) painabFig. 4. The average brain map of subjects at 9.8Hz (Alpha band) a) Non-pain, b)painFig. 3 illustrates an increase in the power of Delta band by savour the pain, which changes the activity focus area from top to the right hemisphere. These findings were previously reported 3-5, 23. In contrast, by feeling more pain, the power of Alpha band is decreased in the frontal lobe and increased in occipital lobes, as shown in Fig. 4, which is as the results obtained in former studies 3-5, 8, 22-23.It is noted that the b ase of the classifier was just built up harmonize to the detected differences on the spacial distribution of these two band power features. To use the other EEG features and find a discriminate subset of features, SFS was run. Therefore, by adding the other features, which were selected by SFS, it was expected to achieve a higher classification accuracy.ResultsEEG signals from 30 electrodes were recorded and then EOG and EMG artifacts were removed by the ICA method, described in Section 2. Through the preprocessing, EMG or EOG sources and the sources caused by the bad connection of an electrode on the scalp, was projected outward of the brain.The base of the classifier was just established upon the significant changes in the spatial distribution of band power features through feeling pain (Fig. 4). since reality is that applying just the selected band power features does not provide convincing results, the structure while considering the other features was proposed. The results of pain classification by the proposed structure and those band power features, which were selected through optic inspection, is shown in Table I. For now and on, all of the presented classification results in this study is achieved by ten-times ten-folds cross validation was executed for the cross validation phase. The classification accuracies are illustrated in Table IV, once SVM was considered for all nodes and the other time 1-NN classifier was assigned.Table I. The pain classification results of only the selected band power features mixed bag1-NN3-NNSVMPain Versus Non-pain686654Table II shows the classification accuracies achieved by applying svm to the features that is introduced as the discriminative ones in previous studies 6-8, 10, 23-24.Table II. The relative results of pain and non-pain classification by applying the previous suggested features6-8, 10, 23-24.Suggested Band Power Features in the Previous StudiesClassification Accuracy (%)Alpha band65Beta and Alpha bands61 Delta and Alpha and Beta bands68Theta and Alpha bands57Delta and Beta bands61Alpha and Gamma bands62Delta, Beta and Alpha Gamma bands59These numerous features, in each time frame, were concatenated into nonparallel feature vectors and therefore the classifiers were encountered with high-dimensional vectors. To remove the redundancy and customize an optimized subset of features , SFS was adopted, to select the pain dependent features and therefore improve the final results.Nevertheless, while using wrapper method, the selected feature set depends on the classifier, the selected subsets of features are not necessary correspond for SVM and 1-NN. SFS was run for each classifier separately. Also, since the test and train sets are changed through different folds, the selected features in different validation folds are not identical. As all of the reports which use wrapper approach, to demonstrate the list of selected features, the common features through folds were reported. The selecte d features by SFS at each node are listed in Table III. and for deploying SVM at all nodes presented and the 1NN features are listed in Table IV.Table III. The selected features by SFS for SVM and 1-NNClassifier call of the selected featuresSVMAlpha, Delta, Beta and Gamma bands, Shannon entropy, and fractal dimensionK-NNAlpha, Delta, Beta bands and Shannon entropyThe achieved classification results by applying the EEG features, customized using SFS, are illustrated in Table VI.Table VI. Classification accuracy of the painAccuracy (%)ClassifierStage94SVMPain vs. Non-Pain891-NN903-NNAs it is stated the list of selected features depends on the type of classifier. tidingsEEG signals is the only non-invasive physiological-base measuring data that quantitatively records the brain activity. Also, the research in pain measurement is still in the beginning compared to other applications such as speech processing.As it is mentioned, among the artifact removal schemes such as regression with P CA, adaptive filter and match filter, the best known method is still ICA. It provides this opportunity to eliminate different noise and artifact roots in the ICA space, where all of the sources were statistically independent. Some constraints were considered to assure us that the suspicious noisy sources were correctly selected. In other words, the variation of spatial distribution of the Delta and Alpha bands are visualized by brain map images through the time and this variation was translated into a succesfull classification.We tried to select edifying features to reveal the pain changes as highlight as possible. In this regard, rather of eliciting features from the correlated EEG signals on the scalp electrodes, variety of the known features were extracted from the pain dependent EEG source signals. Moreover, instead of ad-hoc methods, a heuristic search strategy, called as SFS, was employed to automatically select the suitable features. The high classification result demnstara tes the propriety of the whole process.References1 C.S. Cleeland, Y. Nakamura, E.W. Howland, N. R. Morgan, B. A. Edwards, M. Backonja, Effects of oral morphine on cold pressor tolerance time and neuropsychological performance, Neuropsychopharmacology, vol. 15, pp. 252-262, 1996.2 A.C.N. Chen, P. Rappelsberger, wag and homophile Pain Topographic EEG Amplitude and Coherence Mapping, Brain Topography, vol. 7, pp.196-205, 1994.3 A.C.N. Chen, P. Rappelsberger, O. Filz, topographic anatomy of EEG Coherence Changes May Reflect Differential Neural profit Activation in Cold and Pain Perception, Brain Topography, vol. 11 , pp. 125-132 , 1998.4 S. Ferracuti, S. Seri , D. Mattia , G. Cruccu, duodecimal EEG modifications during the cold water pressor test hemispheric and hand differences, Int. ledger of Psychophysiology, vol. 17, pp.261-268, 1992.5 A.C.N. Chen, S.F. Dworkin, J. Haug, J. Gehrig, Topographic brain measures of human pain and pain responsivity, Pain, vol. 37 , pp.129-140, 1989. 6 P. Veerasarn, C.S.Stohler, The effect of experimental muscle pain on the background galvanic brain activity, Pain, vol. 49 , pp.349-360, 1992.7 P.-F Chang, L. Arendt-Nielsen, T. Graven-Nielsen, P. Svensson, A.C.N. Chen, Topographic effects of tonic cutaneious nociceptive stimulation on human electroencephalograph, Neuroscience Letters, vol. 35 , pp. 49-52, 2001.8 W. Penga, C. Babiloni, Y. Maod, Y. Hua, Subjective pain perception negociate by alpha rhythms, Biological psychology , vol. 109 ,pp. 141-150, 2015.9 T. Wager, L. Atlas, M. Lindquist, M. Roy, C. Woo, E. Kross. An fMRI-Based Neurologic Signatureof Physical Pain, The red-hot england journal of medicine, vol. 368, pp. 1388-1397, 2013.10 E. Schulz , A. Zherdin , L. Tiemann, C. Plant , M. Ploner , Decoding an individuals sensitivity to pain from the multivariate analysis of EEG data, Cereb Cortex, vol. 22, pp. 18-23, 2012.11 P, Ravn , R. Frederiksen , A. Skovsen , LL. Christrup , Mu. Werner , Prediction of pain sensitivit y in healthy volunteers, Journal of Pain Research, vol. 5, pp. 326-313, Aug. 2012.12 S. Walter, S. Gruss, K. Limbrecht-Ecklundt, H. C. Traue, P. Werner, A. Al-Hamadi, N. Diniz, G. Moreira da Silva, A. O. Andrade Automatic pain quantification using autonomic parameters, Psychology Neuroscience, vol. 7 , pp.363-380, Nov. 2014.13 S.Gruss , R.Treister , P.Werner , S .Crawcour , A .Andrade , S .Walter ,Pain Intensity recognition rank via Biopotential Feature Patterns with Support Vector Machines, Biopotential Pattern of Pain via Machine Learning, vol. 10, oct. 2015.14 S. Makeig, AJ. Bell, T-P. Jung, TJ.Sejnowski, Independent component analysis of electroencephalographic data, Advances in Neural Information Processing Systems, vol. 8 , pp.145-151, 1996.15 Sheng-Hsiou Hsu, Tim R. Mullen, Tzyy-Ping Jung, Gert Cauwenberghs, Real-Time Adaptive EEG Source Separation exploitation Online recursive Independent Component Analysis, IEEE Trans Neural Syst Rehabil Eng, vol. 24, 3, March 2016.16 T .Jung, S.Makeig, C.Humphries, T.Martin, J. Vicente , T.Sejnowski, Removing electroencephalographic artifacts by blind source separation, Psychophysiology, vol. 37 , pp. 163-178, 2000.17 F.Ghassemi, Independent Component Analysis of ERP for levelingVisual continue Attention, Amirkabir University of Technology , 2007.18 I. A. Rezek, S. J. Roberts, Stochastic complexity measures for 33 D. Abasolo1, R. Hornero1, P. Espino, D. A lvarez1, J.Poza, Entropy analysis of the EEG background activity in Alzheimers disease patients, Physiol Meas, vol.27, pp.241-253, 2006.19M. Sabeti, S. Katebi, R.Boostani, Entropy and complexity measures for EEG signal classification of schizophrenic and control participants, Elsevier Journal of Artificial intelligence service in medicine, vol. 47 , pp.263-274, , 2009.20 S. Enshaeifar, S. Kouchaki, C. Cheong Took, and S. Sanei, Quaternion Singular Spectrum Analysis of Electroencephalogram with industry in Sleep Analysis, IEEE Trans Neural Syst Rehabil Eng. Vol . 24, 1, Jan. 2016.21 M. Gram, C. Graversen, S.S. Olesen, A.M. Drewes, Dynamic spectral indices of the electroencephalogram provide new insights into tonic pain. Clinical Neurophysiology, vol. 126, pp. 763-771, April 2015.22 M. Huber , J. Bartling, D. Pachur, S.Woikowsky, S. Lautenbacher, EEG responses to tonic heat pain, Exp Brain Res, vol. 173, pp. 14-24, 2006.23 R. Dowman, D. Rissacher, S. Schuckers, EEG indices of tonic pain-related activity in the somatosensory cortices,See comment in PubMed Commons belowClinical Neurophysiology, vol. 119 , pp. 1201-1212 , 2008.