Skip to main content

2025 | OriginalPaper | Buchkapitel

Ensemble Classifier for EEG-Based Stress Classification: An Empirical Study on Stacking Classifiers

verfasst von : Shikha Shikha, Divyashikha Sethia, S. Indu

Erschienen in: Proceedings of Third International Conference on Computational Electronics for Wireless Communications

Verlag: Springer Nature Singapore

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

In the last few years, combining multiple algorithms to improve the performance of machine learning models has been a common practice. However, its application to stress detection still needs to be explored. This paper uses a stacking ensemble technique to introduce a novel stress classification approach using electroencephalogram (EEG) signals. Specifically, the study evaluates the effectiveness of various classifiers, including Random Forest (RF), K-Nearest Neighbor (KNN), Gradient Boosting (GB), Naive Bayes (NB), Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), and Adaboost (AB), individually and in combination with RF as the base model, for stress classification tasks. The paper uses the SAM40 Dataset consisting of 32-channel EEG data to extract features in time and frequency domains for stress classification. The results show that the stacked classifiers outperform single classifiers, with RF + KNN providing the highest accuracy of 98.55%. The findings suggest that a stacked classifier is a promising approach for stress classification, as it can leverage the strengths of different algorithms and improve generalization performance. It holds promising future applicability in personalized stress management, healthcare interventions, and addressing societal concerns related to mental well-being.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Papathanasiou IV et al (2015) Stress: concepts, theoretical models and nursing interventions. Am J Nurs Sci 4(2–1):45–50CrossRef Papathanasiou IV et al (2015) Stress: concepts, theoretical models and nursing interventions. Am J Nurs Sci 4(2–1):45–50CrossRef
2.
Zurück zum Zitat Aigrain J et al (2016) Multimodal stress detection from multiple assessments. IEEE Trans Affect Comput 9(4):491–506CrossRef Aigrain J et al (2016) Multimodal stress detection from multiple assessments. IEEE Trans Affect Comput 9(4):491–506CrossRef
3.
Zurück zum Zitat Giannakakis G et al (2019) Review on psychological stress detection using biosignals. IEEE Trans Affect Comput 13(1):440–460CrossRef Giannakakis G et al (2019) Review on psychological stress detection using biosignals. IEEE Trans Affect Comput 13(1):440–460CrossRef
4.
Zurück zum Zitat Fernández JRM et al (2018) Mental stress detection using bioradar respiratory signals. Biomedl Signal Process Control 43:244–249 Fernández JRM et al (2018) Mental stress detection using bioradar respiratory signals. Biomedl Signal Process Control 43:244–249
5.
Zurück zum Zitat Nirabi A et al (2022) EEG signal analysis for mental stress classification: a review. J Theor Appl Inf Technol 100(20):6199–6214 Nirabi A et al (2022) EEG signal analysis for mental stress classification: a review. J Theor Appl Inf Technol 100(20):6199–6214
6.
Zurück zum Zitat Chatterjee S et al (2022) EEG-based emotion classification using stacking ensemble approach. Sensors 22(21):8550CrossRef Chatterjee S et al (2022) EEG-based emotion classification using stacking ensemble approach. Sensors 22(21):8550CrossRef
7.
Zurück zum Zitat Novak D et al (2012) A survey of methods for data fusion and system adaptation using autonomic nervous system responses in physiological computing. Interact Comput 24(3):154–172CrossRef Novak D et al (2012) A survey of methods for data fusion and system adaptation using autonomic nervous system responses in physiological computing. Interact Comput 24(3):154–172CrossRef
8.
Zurück zum Zitat Arpaia P et al (2020) A wearable EEG instrument for real-time frontal asymmetry monitoring in worker stress analysis. IEEE Trans Instrum Meas 69(10):8335–8343CrossRef Arpaia P et al (2020) A wearable EEG instrument for real-time frontal asymmetry monitoring in worker stress analysis. IEEE Trans Instrum Meas 69(10):8335–8343CrossRef
9.
Zurück zum Zitat Malviya L, et al (2021) EEG data analysis for stress detection. In: 2021 10th IEEE international conference on communication systems and network technologies (CSNT). IEEE 2021:148–152 Malviya L, et al (2021) EEG data analysis for stress detection. In: 2021 10th IEEE international conference on communication systems and network technologies (CSNT). IEEE 2021:148–152
10.
Zurück zum Zitat Arsalan A et al (2022) A study on multi-class anxiety detection using wearable EEG headband. J Ambient Intell Hum Comput 13(12):5739–5749CrossRef Arsalan A et al (2022) A study on multi-class anxiety detection using wearable EEG headband. J Ambient Intell Hum Comput 13(12):5739–5749CrossRef
11.
Zurück zum Zitat Hasan MJ et al (2019) A hybrid feature pool-based emotional stress state detection algorithm using EEG signals. Brain Sci 9(12):376CrossRef Hasan MJ et al (2019) A hybrid feature pool-based emotional stress state detection algorithm using EEG signals. Brain Sci 9(12):376CrossRef
12.
Zurück zum Zitat Attallah O (2020) An effective mental stress state detection and evaluation system using minimum number of frontal brain electrodes. Diagnostics 10(5):292CrossRef Attallah O (2020) An effective mental stress state detection and evaluation system using minimum number of frontal brain electrodes. Diagnostics 10(5):292CrossRef
13.
Zurück zum Zitat Ghosh R et al (2022) SAM 40: dataset of 40 subject EEG recordings to monitor the induced-stress while performing stroop color-word test, arithmetic task, and mirror image recognition task. Data Brief 40:107772CrossRef Ghosh R et al (2022) SAM 40: dataset of 40 subject EEG recordings to monitor the induced-stress while performing stroop color-word test, arithmetic task, and mirror image recognition task. Data Brief 40:107772CrossRef
14.
Zurück zum Zitat Bird JJ, Manso LJ, Ribeiro EP, Ekart A, Faria DR (2018) A study on mental state classification using eeg-based brain-machine interface. In: 2018 international conference on intelligent systems (IS). IEEE 2018:795–800 Bird JJ, Manso LJ, Ribeiro EP, Ekart A, Faria DR (2018) A study on mental state classification using eeg-based brain-machine interface. In: 2018 international conference on intelligent systems (IS). IEEE 2018:795–800
Metadaten
Titel
Ensemble Classifier for EEG-Based Stress Classification: An Empirical Study on Stacking Classifiers
verfasst von
Shikha Shikha
Divyashikha Sethia
S. Indu
Copyright-Jahr
2025
Verlag
Springer Nature Singapore
DOI
https://doi.org/10.1007/978-981-97-1943-3_34