Classification of Mental Workload Levels by Using EEG Signals

Abstract

Mental workload is amount of the required cognitive capacity during performing tasks. Electroencephalogram (EEG) is an objective monitoring technique used to evaluate mental workload. In this study, feature extraction methods based on Katz’s fractal dimension (KFD) and Higuchi’s fractal dimension; and error correcting output coding (ECOC) are proposed to classify mental workload levels through EEG signals, which were recorded during performing of the simultaneous tasks. ECOC, which is a classifier combination technique proposed for multiclass classification problems, is employed to classify mental workload as low, moderate and high level. ECOC was created based on one vs. all approach, by using support vector machines (SVM), k nearest neighbourhood and quadratic discriminant analysis. The performance of the proposed method is evaluated on Simultaneous Task EEG Workload (STEW) dataset collected from 48 subjects. By using KFD and HFD with respectively, the classification accuracy was determined as %78.44 and %95.39; and Cohen’s Kappa value was determined as 0.52 ve 0.89. The results indicate that combination of HFD and SVM-ECOC is a successful method in the multiclass classification of mental workload.

Keywords

• electroencephalography (EEG)
• mental workload (MWL)
• Katz’s fractal dimension
• Higuchi’s fractal dimension
• error coding output codes (ECOC)

EEG Sinyalleri Kullanılarak Zihinsel İş Yükü Seviyelerinin Sınıflandırılması

Abstract

Zihinsel iş yükü, bir görevi gerçekleştirmek için gerekli olan bilişsel kapasite miktarıdır. Elektroensefalogram (EEG), zihinsel iş yükünün objektif olarak değerlendirilebilmesi için kullanılan bir görüntüleme tekniğidir. Bu çalışmada, eşzamanlı görevlerin yerine getirilmesi sırasında kaydedilmiş EEG sinyallerinden zihinsel iş yükü seviyelerinin sınıflandırılması için, Katz fraktal boyut (KFB) ve Higuchi fraktal boyut (HFB) algoritmalarına dayalı öznitelik çıkarma yöntemleri ile hata düzelten çıkış kodlaması (HDÇK) yönteminin kullanılması önerilmiştir. Çok sınıflı sınıflandırma problemleri için önerilen bir sınıflandırıcı birleşim tekniği olan HDÇK, zihinsel iş yükünün düşük, orta ve yüksek seviye olarak sınıflandırılması için kullanılmıştır. HDÇK, destek vektör makineleri (DVM), k en yakın komşuluk ve kuadratik ayırtaç analizi yöntemleri kullanılarak bire-karşı-diğerleri yaklaşımı ile oluşturulmuştur. Önerilen yöntemin performansı, 48 katılımcıdan kaydedilen EEG sinyallerini içeren Eşzamanlı Görev EEG İş Yükü veri kümesi üzerinde değerlendirilmiştir. KFB ve HFB algoritmaları kullanılarak sınıflandırma doğrulukları sırasıyla %78.44 ve %95.39 ve Cohen’s Kappa değeri 0.52 ve 0.89 olarak belirlenmiştir. Sonuçlar, HFB ve DVM-HDÇK yöntemlerinin bir arada kullanımının zihinsel iş yükünün çok sınıflı sınıflandırılmasında başarılı bir yöntem olabileceğini göstermektedir.

Keywords

• elektroensefalogram (EEG)
• zihinsel iş yükü
• katz fraktal boyut
• higuchi fraktal boyut
• hata düzelten çıkış kodlaması (HDÇK)

References

1. [1] Stasi L.L.D., Antolí A., Cañas J.J., “Evaluating mental workload while interacting with computer-generated artificial environments”, Entertainment Computing, 4: 63–69, (2013).
2. [2] Charles R.L., Nixon J., “Measuring mental workload using physiological measures: A systematic review”, Applied Ergonomics, 74: 221–232, (2019).
3. [3] Acı Ç.İ., et.al., “Distinguishing mental attention states of humans via an EEG-based passive BCI using machine learning methods”, Expert Systems with Applications, 134: 153–166, (2019).
4. [4] Marinescu A., et.al. “Exploring the Relationship between Mental Workload, Variation in Performance and Physiological Parameters”, IFAC-PapersOnLine, 49(19): 591–596, (2016).
5. [5] Heine T., Lenis G., Reichensperger P., Beran T., Doessel O., Deml B., “Electrocardiographic features for the measurement of drivers' mental workload”, Applied Ergonomics, 61:31-43, (2017).
6. [6] Jaiswal D., Chowdhury A., Banerjee T., Chatterjee D., “Effect of Mental Workload on Breathing Pattern and Heart Rate for a Working Memory Task: A Pilot Study”, 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Germany, 2202-2206, 2019.
7. [7] Ruscio D., Bos A.J., Ciceri M.R., “Distraction or cognitive overload? Using modulations of the autonomic nervous system to discriminate the possible negative effects of advanced assistance system”, Accident Analysis and Prevention, 103: 105–111, (2017).
8. [8] Stuiver A., Brookhuis K.A., Waard D., Mulder B., “Short-term cardiovascular measures for driver support: Increasing sensitivity for detecting changes in mental workload”, International Journal of Psychophysiology, 92: 35–41, (2014).

9. [9] Marquart G., Cabrall C., “Winter J., Review of eye-related measures of drivers’ mental workload”, Procedia Manufacturing, 3: 2854 – 2861, (2015).
10. [10] Wang S., Gwizdka J., Chaovalitwongse W.A., “Using Wireless EEG Signals to Assess Memory Workload in the n-Back Task”, IEEE Transactıons on Human-Machıne Systems, 46(3): 424-435, (2016).
11. [11] Lohani M., Payne B.R., Strayer D.L., “A Review of Psychophysiological Measures to Assess Cognitive States in Real-World Driving”, Frontiers in Human Neuroscience, 13:57, (2019).
12. [12] Alonso L.F.N., Gil J.G., “Brain Computer Interfaces, a Review”, Sensors, 12:1211-1279, (2012).
13. [13] Duru A.D., “Determination of Increased Mental Workload Condition From EEG by the Use of Classification Techniques”, International Journal of Advances in Engineering and Pure Sciences, 1: 47-52, (2019).
14. [14] Gianluca Di Flumeri G.D., et.al., “EEG-Based Mental Workload Neurometric to Evaluate the Impact of Different Traffic and Road Conditions in Real Driving Settings”, Frontiers in Human Neuroscience, 12:509, (2018).
15. [15] Wang S., Gwizdka J., Chaovalitwongse W. A., “Using Wireless EEG Signals to Assess Memory Workload in the n-Back Task”, IEEE Transactions on Human-Machine Systems, 46(3): 424-435, (2016).
16. [16] Qu H., Shan Y., Liu Y., Pang L., Fan Z., Zhang J., Wanyan X., “Mental Workload Classification Method Based on EEG Independent Component Features”, Applied Science, 10: 3036, (2020).
17. [17] Chin Z.Y., et.al. “EEG-based discrimination of different cognitive workload levels from mental arithmetic”, 40th Annual International Conference of the IEEE (EMBC), Honolulu, 1984-1987, (2018).
18. [18] Lim W. L., Sourina O., Wang L. P., “STEW: Simultaneous Task EEG Workload Data Set”, IEEE Transactıons on Neural Systems and Rehabılıtatıon Engıneerıng, 26 (11): 2106-2114, (2018).
19. [19] Chakladar D.D., Dey S., Roy P.P., Dogra D.P., “EEG-based mental workload estimation using deep BLSTM-LSTMnetwork and evolutionary algorithm”, Biomedical Signal Processing and Control, 60 101989, (2020).
20. [20] Jacob J.E., Nair G.K., Cherian A., Iype T., “Application of fractal dimension for EEG based diagnosis of encephalopathy”, Analog Integrated Circuits and Signal Processing, 100:429–436, (2019).
21. [21] Esteller R., Vachtsevanos G., Echauz J., Litt B., “A Comparison of Waveform Fractal Dimension Algorithms”, IEEE Transactions on Circuits and Systems—I: Fundamental Theory and Applıcatıons, 48(2):177-183, (2001).
22. [22] Higuchi T., “Approach to an Irregular Time Series on the Basis of the Fractal Theory”, Physica D, 31: 277-283, (1988).
23. [23] Khosrowabadi R., Quek C., Ang K.K., Tung S.W., Heijnen M., “A Brain-Computer Interface for classifying EEG correlates of chronic mental stress”, International Joint Conference on Neural Networks, USA, 575-562, (2011).
24. [24] Guler İ., Ubeyli E.D., “Multiclass Support Vector Machines for EEG-Signals Classification”, IEEE Transactions on Information Technology in Biomedicine, 11(2):117-126, (2007).
25. [25] Joutsijoki H., et.al., “Error-Correcting Output Codes in Classification of Human Induced Pluripotent Stem Cell Colony Images”, BioMed Research International, 2016: 3025057, (2016).
26. [26] Cortes, C., Vapnik, V., “Support-vector networks”, Machine Learning, 20: 273-297, (1995).
27. [27] Bhattacharyya S, Khasnobish A., Chatterjee S., Konar A., Tibarewala D.N., “Performance Analysis of LDA, QDA and KNN Algorithms in Left-Right Limb Movement Classification from EEG Data”, International Conference on Systems in Medicine and Biology, India, 126- 131, (2010).
28. [28] Naseer N., Qureshi N.K., Noori F.M., Hong K.S., “Analysis of Different Classification Techniques for Two-Class Functional Near-Infrared Spectroscopy-Based Brain-Computer Interface”, Computational Intelligence and Neuroscience 2016: 5480760, (2016).
29. [29] Aydin E.A., Bay O.F., Guler I., “P300-Based Asynchronous Brain Computer Interface for Environmental Control System”, IEEE Journal of Bıomedıcal and Health Informatıcs, 22(3): 653-663, (2018).
30. [30] Kılıç S., “Kappa Testi”, Journal of Mood Disorders, 5(3):142-144, (2015).
31. [31] Sim J., Wright C.C., “The Kappa Statistic in Reliability Studies: Use, Interpretation, and Sample Size Requirements”, Physical Therapy, 85(3), 257–268, (2005).