Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Emotion recognition from EEG signals has
become one of well-known research directions in affective
computing because EEG signals can provide a direct
perspective into how humans feel emotions. In this paper, we
build a deep learning system that finds out the people’s
emotional states by using an EEG recordings in the SEED
dataset. This dataset has EEG recordings from several
channels and it matches to three emotions: negative, positive
and as well as neutral.To prepare the data for model training,
the EEG signals are down sampled and normalized before
being used as input to a one-dimensional convolutional neural
network (CNN). The CNN automatically learns discriminative
patterns from the EEG signals without requiring manual
feature engineering.
For getting signals ready for the training phase, the EEG
signals are first down sampled, then normalization is applied
before sending as input to one-dimensional CNN. The CNN can
pick up important patterns from EEG signals automatically
and does not rely on manual feature processing. To check how
model fits data from different persons, Leave-One-Subject-Out
(LOSO) cross-validation is used.The experiments show the
CNN-based model is able to differentiate between emotional
states using EEG and still provides pretty constant results even
when used on new people
Keywords:
EEG, Emotion Recognition, Deep Learning, Convolutional Neural Network, SEED Dataset,LOSO
Cite Article:
"EEG-Based Emotion Recognition Using Convolutional Neural Networks", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2456-3315, Vol.11, Issue 4, page no.c28-c33, April-2026, Available :http://www.ijrti.org/papers/IJRTI2604277.pdf
Downloads:
000205506
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator