Electroencephalogram-Based Pain Classification Using Artificial Neural Networks

Abstract

This study investigates the variations in electroencephalogram (EEG) signals due to pain stimuli and proposes an optimal network configuration of the multilayer perceptron neural network (MLPNN) for pain state detection. EEG signals were recorded from 39 volunteers under the normal resting state and by applying external pain stimuli. Time, frequency, and wavelet domain parameters were computed and analysed. Decrease in Hjorth mobility, relative alpha power, minima of approximation coefficients (a₅), mean and median frequency; increase in Hjorth complexity, root mean square value, relative delta power along with standard deviation, and maxima of approximation coefficients (a₅) were observed at all the electrode positions. Several combinations of backpropagation algorithms and error functions were investigated to find the optimal configuration of MLPNN. We had classified pain state with an accuracy of 87.53%, 90.25%, 93.34%, and 90.62% in FP₁, FP₂, P₃, and P₄ electrode positions, respectively.

Keywords:

• Cold water test
• Daubechies mother wavelet
• Electroencephalogram/graphy (EEG)
• K-fold cross-validation
• Lempel-Ziv complexity
• Multilayer perceptron neural network (MLPNN)

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This research did not receive funding, as it was performed as part of Ph.D. research work.

Notes on contributors

Manpreet Kaur

Manpreet Kaur, currently working as a research scholar in Centre of Excellence (Industrial and Product Design), Punjab Engineering College, Chandigarh, received her Bachelor of Technology and Master of Technology in electronics and communication engineering from Haryana College of Technology and Management, Kaithal, Haryana, India, in 2010 and 2012, respectively. She is working on the projects related to human engineering. Corresponding Author. Email: [email protected]

Neelam Rup Prakash

Neelam Rup Prakash, working as professor in Punjab Engineering College, Chandigarh, received her BE degree in ECE from Panjab University (PU) in 1987. She served industry for 3 years and joined as faculty in PEC in 1990. She completed her masters in electronics from PU in 1996 and was awarded certificate of Merit for the first position in University. She completed her PhD also from PU in 2002. Her memberships are in IEEE, IEI, and IETE. She has undertaken projects like Centre of Excellence (Industrial and Product Design), Embedded Curriculum and Lab Based on Intel Atom, Night Watch Miniaturization (Philips-II). Email: [email protected]

Parveen Kalra

Parveen Kalra received his bachelor degree in mechanical engineering from Panjab University, Chandigarh. He completed his master’s degree from Memorial University of Newfoundland, Canada, and PhD degree from Punjab University, Chandigarh. He has a vast experience in industry/research labs and has been teaching in Punjab Engineering College, Chandigarh since 1990. He is currently the coordinator of Centre of Excellence in Industrial and Product Design setup in 2013 by NPIU, Noida (MHRD unit), under Technical Education Quality Improvement Programme (TEQIP) Phase-II, a World Bank assisted Project in Technical Education. Email: [email protected]

Goverdhan Dutt Puri

Goverdhan Dutt Puri is the head of Department of Anaesthesia and Intensive Care, PGIMER, Chandigarh. He completed his MBBS from MDU, Rohtak, in 1979, MD and PhD in Anaesthesia from PGIMER in 1982 and 1994, respectively. He was professor and head of Department of Anaesthesia at SGPGIMS, Lucknow, for about 2 years. He has numerous awards like British Journal of Anaesthesia scholar for 2 months in the UK in 1989 and has been a visiting scientist under PN Berry Scholarship for 2 months at Cardiothoracic Centre, AIIMS New Delhi in 1993, Cornell Medical Centre and Memorial Sloan Kettering Cancer Institute, New York, in June–July 1997 and June 2000, Klinikum Kassel, Kassel, Germany, May 2001 and December 2004, and fellow of National Academy of Medical Sciences, New Delhi, India. He is also involved in development of Automated Closed Loop Arterial Pressure control System funded by DST, Delhi. Email: [email protected]