EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Decoding Cognitive States and Emotions Using the Electroencephalogram

Ihsan Ullah, Raheel Zafar, Hammad Dilpazir, Muhammad Javvad Ur Rehman, Abdullah Waqas, Rana Fayyaz Ahmad

International Journal of Innovations in Science and Technology · 23.11.2025 · 2842

DOI: 10.33411/ijist/1652 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovations in Science and Technology, online erschienen am 23.11.2025. Verfasst von Ihsan Ullah und 5 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Emotions are essential in human communication, social interaction, and decision-making. However, accurately classifying emotions is difficult with many applications in various domains such as psychology, psychiatry, neuroscience, and human-computer interaction. Emotion detection is one of the key challenges in current research, especially when emotional words are used. It is already known that positive and negative words have an impact on human behaviour and emotions, but very rare study that focus on emotions based on the words. In this study, we propose a novel approach for emotion classification based on electroencephalogram (EEG) data elicited by text stimuli, which are various English words. Text stimuli can evoke rich and diverse emotions, but they have been less explored than other modalities for emotion elicitation. In this study, EEG data of 25 participants were used, which were collected using a 128-channel EGI system. The collected data was pre-processed, and features were extracted using four methods: Convolutional Neural Network (CNN), Wavelet Transform (WT), Power Spectral Density (PSD), and the raw data itself was used as features. The results showed that CNN features achieved an average accuracy of 80%, followed by WT with 75%, PSD with 72%, and raw data with 65%. Our study shows the feasibility and effectiveness of using CNN, PSD, and WT with SVM for emotion classification based on EEG data and text stimuli. Lastly, a hybrid model was proposed based on the combination of CNN for feature extraction and SVM for classification.

Zitieren

APA

Ullah, I., Zafar, R., Dilpazir, H., Rehman, M. J. U., Waqas, A., & Ahmad, R. F. (2025). Decoding Cognitive States and Emotions Using the Electroencephalogram. International Journal of Innovations in Science and Technology, 2842. https://doi.org/10.33411/ijist/1652

Vancouver

Ullah I, Zafar R, Dilpazir H, Rehman MJU, Waqas A, Ahmad RF. Decoding Cognitive States and Emotions Using the Electroencephalogram. International Journal of Innovations in Science and Technology. 2025:2842. doi:10.33411/ijist/1652

BibTeX
@article{Ullah2025,
  author = {Ullah, Ihsan and Zafar, Raheel and Dilpazir, Hammad and Rehman, Muhammad Javvad Ur and Waqas, Abdullah and Ahmad, Rana Fayyaz},
  title = {Decoding Cognitive States and Emotions Using the Electroencephalogram},
  journal = {International Journal of Innovations in Science and Technology},
  year = {2025},
  pages = {2842},
  doi = {10.33411/ijist/1652}
}
Kostenlos starten →