Skip to main content

A study on multi-class anxiety detection using wearable EEG headband

Abstract

In this paper, we present a trait anxiety detection framework using resting-state electroencephalography (EEG) data. Our proposed framework consists of EEG data acquisition, pre-processing, feature extraction and selection, and classification stages. EEG data of 65 participants is recorded in an eye-open state for the duration of two minutes. The trait anxiety scores are gathered using the state-trait anxiety inventory questionnaire, which is used to label the participant’s EEG data into two (non-anxious and anxious) and three (non-anxious, low anxious, and highly anxious) classes. Pre-processing of the recorded EEG data is performed using the onboard noise cancellation scheme of the MUSE EEG headband. Channel selection is performed by applying a t-test and analysis of variance on the power spectral densities for two and three classes of anxiety respectively. Five time-domain features are extracted from the selected EEG channels. The wrapper method for feature selection is applied for selecting an optimum subset of features, which are used to classify the trait anxiety. The highest classification accuracy of \(87.69\%\) and \(83.07\%\) using random forest classifier is achieved for two and three class anxiety classification respectively. Our proposed trait anxiety detection scheme outperforms existing schemes in terms of higher classification accuracy and reduced feature vector length.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Notes

  1. https://sites.google.com/site/simplrgp/resources.

References

  • Adam A, Shapiai MI, Mohd Tumari MZ, Mohamad MS, Mubin M (2014) Feature selection and classifier parameters estimation for EEG signals peak detection using particle swarm optimization. Sci World J 2014:1–13

    Article  Google Scholar 

  • Arsalan A, Majid M, Butt AR, Anwar SM (2019b) Classification of perceived mental stress using a commercially available EEG headband. IEEE J Biomed Health Inform 23(6):2257–2264

    Article  Google Scholar 

  • Arsalan A, Majid M, Anwar SM (2019a) Electroencephalography based machine learning framework for anxiety classification. In: International conference on intelligent technologies and applications. Springer, pp 187–197

  • Asif A, Majid M, Anwar SM (2019) Human stress classification using EEG signals in response to music tracks. Comput Biol Med 107:182–196

    Article  Google Scholar 

  • Association AP et al (2013) Diagnostic and statistical manual of mental disorders (DSM-5®). American Psychiatric Pub 5:1–947

    Google Scholar 

  • Baghdadi A, Aribi Y, Fourati R, Halouani N, Siarry P, Alimi AM (2019) DASPS: a database for anxious states based on a psychological stimulation. arXiv:190102942

  • Bradt J, Teague A (2018) Music interventions for dental anxiety. Oral Dis 24(3):300–306

    Article  Google Scholar 

  • Breiman L (2001) Random forests. Mach Learn 45(1):5–32

    Article  Google Scholar 

  • Caballo VE, Salazar IC, Arias B, Jesús M (2010) Validation of the social anxiety questionnaire for adults (SAQ-A30) with Spanish university students: similarities and differences among degree subjects and regions. Behav Psychol 18(1):5–34

    Google Scholar 

  • Chalmers JA, Quintana DS, Abbott MJ, Kemp AH et al (2014) Anxiety disorders are associated with reduced heart rate variability: a meta-analysis. Front Psychiatry 5(80):1–11

    Google Scholar 

  • Emdin CA, Odutayo A, Wong CX, Tran J, Hsiao AJ, Hunn BH (2016) Meta-analysis of anxiety as a risk factor for cardiovascular disease. Am J Cardiol 118(4):511–519

    Article  Google Scholar 

  • EngElS AS, Heller W, Spielberg JM, Warren SL, Sutton BP, Banich MT, Miller GA (2010) Co-occurring anxiety influences patterns of brain activity in depression. Cogn Affect Behav Neurosci 10(1):141–156

    Article  Google Scholar 

  • Giannakakis G, Pediaditis M, Manousos D, Kazantzaki E, Chiarugi F, Simos PG, Marias K, Tsiknakis M (2017) Stress and anxiety detection using facial cues from videos. Biomed Signal Process Control 31:89–101

    Article  Google Scholar 

  • Giannakakis G, Grigoriadis D, Tsiknakis M (2015) Detection of stress/anxiety state from EEG features during video watching. In: 2015 37th IEEE annual international conference of the engineering in medicine and biology society (EMBC). IEEE, pp 6034–6037

  • Harrewijn A, Van der Molen M, Westenberg P (2016) Putative EEG measures of social anxiety: comparing frontal alpha asymmetry and delta-beta cross-frequency correlation. Cogn Affect Behav Neurosci 16(6):1086–1098

    Article  Google Scholar 

  • Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer, New York, pp 1–745

    Book  Google Scholar 

  • Hek K, Direk N, Newson RS, Hofman A, Hoogendijk WJ, Mulder CL, Tiemeier H (2013) Anxiety disorders and salivary cortisol levels in older adults: a population-based study. Psychoneuroendocrinology 38(2):300–305

    Article  Google Scholar 

  • Jayakkumar S, Chong E, Yeow C et al (2017) A wearable, EEG-based massage headband for anxiety alleviation. In: 2017 39th IEEE annual international conference of the engineering in medicine and biology society (EMBC). IEEE, pp 3557–3560

  • Julian LJ (2011) Measures of anxiety. Arthritis Care Res 63(0 11):1–11

    Google Scholar 

  • Kalatzis I, Piliouras N, Ventouras E, Papageorgiou CC, Rabavilas AD, Cavouras D (2004) Design and implementation of an svm-based computer classification system for discriminating depressive patients from healthy controls using the p600 component of erp signals. Comput Methods Progr Biomed 75(1):11–22

    Article  Google Scholar 

  • Kayikcioglu O, Bilgin S, Seymenoglu G, Deveci A (2017) State and trait anxiety scores of patients receiving intravitreal injections. Biomed Hub 2(2):1–5

    Article  Google Scholar 

  • Khanade K, Sasangohar F (2017) Efficacy of using heart rate measurements as an indicator to monitor anxiety disorders: a scoping literature review. In: Proceedings of the human factors and ergonomics society annual meeting, Los Angeles, vol 61. SAGE Publications, Sage, pp 1783–1787

  • Klados MA, Simos P, Micheloyannis S, Margulies D, Bamidis PD (2015) ERP measures of math anxiety: how math anxiety affects working memory and mental calculation tasks? Front Behav Neurosci 9:282

    Article  Google Scholar 

  • Kollia N, Panagiotakos D, Georgousopoulou E, Chrysohoou C, Yannakoulia M, Stefanadis C, Chatterji S, Haro JM, Papageorgiou C, Pitsavos C et al (2017) Exploring the path between depression, anxiety and 10-year cardiovascular disease incidence, among apparently healthy Greek middle-aged adults: the Attica study. Maturitas 106:73–79

    Article  Google Scholar 

  • Leichsenring F, Leweke F (2017) Social anxiety disorder. N Engl J Med 376(23):2255–2264

    Article  Google Scholar 

  • Lvd Maaten, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(86):2579–2605

    MATH  Google Scholar 

  • Newman MG, Llera SJ, Erickson TM, Przeworski A, Castonguay LG (2013) Worry and generalized anxiety disorder: a review and theoretical synthesis of evidence on nature, etiology, mechanisms, and treatment. Annu Rev Clin Psychol 9:275–297

    Article  Google Scholar 

  • Omerhodzic I, Avdakovic S, Nuhanovic A, Dizdarevic K (2010) Energy distribution of EEG signals: EEG signal wavelet-neural network classifier. Int J Biomed Biol Eng 4(1):35–40

    Google Scholar 

  • Pinkney V, Wickens R, Bamford S, Baldwin DS, Garner M (2014) Defensive eye-blink startle responses in a human experimental model of anxiety. J Psychopharmacol 28(9):874–880

    Article  Google Scholar 

  • Resalat SN, Saba V (2016) A study of various feature extraction methods on a motor imagery based brain computer interface system. Basic Clin Neurosci 7(1):13

    Google Scholar 

  • Reynolds GO, Hanna KK, Neargarder S, Cronin-Golomb A (2017) The relation of anxiety and cognition in Parkinson’s disease. Neuropsychology 31(6):596–604

    Article  Google Scholar 

  • Rosebrock LE, Hoxha D, Norris C, Cacioppo JT, Gollan JK (2016) Skin conductance and subjective arousal in anxiety, depression, and comorbidity. J Psychophysiol 31(4):145–157

    Article  Google Scholar 

  • Saeed U, Muhammad S, Anwar SM, Majid M, Awais M, Alnowami M (2018) Selection of neural oscillatory features for human stress classification with single channel EEG headset. BioMed Res Int 2018:1–9

    Article  Google Scholar 

  • Spielberger CD (2010) State-trait anxiety inventory. In: The Corsini encyclopedia of psychology, p 1

  • Spielberger CD, Gonzalez-Reigosa F, Martinez-Urrutia A, Natalicio LF, Natalicio DS (2017) The state-trait anxiety inventory. Interam J Psychol 5:3–4

    Google Scholar 

  • Tarrant JM, Viczko J, Cope H (2018) Virtual reality for anxiety reduction demonstrated by quantitative EEG: a pilot study. Front Psychol 9:1280

    Article  Google Scholar 

  • Von der Embse N, Jester D, Roy D, Post J (2018) Test anxiety effects, predictors, and correlates: a 30-year meta-analytic review. J Affect Disord 227:483–493

    Article  Google Scholar 

  • Wang Y, Chai F, Zhang H, Liu X, Xie P, Zheng L, Yang L, Li L, Fang D (2016) Cortical functional activity in patients with generalized anxiety disorder. BMC Psychiatry 16(1):217

    Article  Google Scholar 

  • Wiederhold BK, Miller IT, Wiederhold MD (2018) Using virtual reality to mobilize health care: mobile virtual reality technology for attenuation of anxiety and pain. IEEE Consum Electron Mag 7(1):106–109

    Article  Google Scholar 

  • Witten IH, Frank E, Hall MA, Pal CJ (2016) Data mining: practical machine learning tools and techniques. Morgan Kaufmann, vol 4, pp 1–578

  • Wright RE (1995) Logistic regression: reading and understanding multivariate statistics. Am Psychol Assoc 1995:217–244

    Google Scholar 

  • Zanetti M, Mizumoto T, Faes L, Fornaser A, De Cecco M, Maule L, Valente M, Nollo G (2019) Multilevel assessment of mental stress via network physiology paradigm using consumer wearable devices. J Ambient Intell Humaniz Comput 5:1–10

    Google Scholar 

  • Zhang Y, Wang B, Jing J, Zhang J, Zou J, Nakamura M (2017) A comparison study on multidomain EEG features for sleep stage classification. Comput Intell Neurosci 2017:1–8

    Google Scholar 

  • Zheng Y, Wong TC, Leung BH, Poon CC (2016) Unobtrusive and multimodal wearable sensing to quantify anxiety. IEEE Sens J 16(10):3689–3696

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Muhammad Majid.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Arsalan, A., Majid, M. A study on multi-class anxiety detection using wearable EEG headband. J Ambient Intell Human Comput (2021). https://doi.org/10.1007/s12652-021-03249-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s12652-021-03249-y

Keywords

  • Trait anxiety
  • Anxiety detection
  • Wearable sensors
  • Electroencephalography
  • Feature extraction
  • Multi-class classification