Novel Architecture For EEG Emotion Classification Using Neurofuzzy Spike Net

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Jan. 7, 2025

Emotion recognition from Electroencephalogram (EEG) signals is one of the fastest-growing and challenging fields, with a huge prospect for future application in mental health monitoring, human-computer interaction, personalized learning environments. Conventional Neural Networks (CNN) traditional signal processing techniques have usually been performed EEG emotion classification, which face difficulty capturing complicated temporal dynamics inherent uncertainty signals. The proposed work overcomes challenges using new architecture merging Spiking (SNN) Fuzzy Hierarchical Attention Membership (FHAM), NeuroFuzzy SpikeNet (NFS-Net). NFS-Net takes advantage SNNs' event-driven nature signals, are treated independently as asynchronous, spike-based events like biological neurons. It allows patterns data high precision, rather important correct recognition. local spiking feature SNNs encourages sparse coding, making whole system computational power energy highly effective it very suitable wearable devices real-time applications.

Language: Английский

Research hotspots and trends in the application of electroencephalography for assessment of disorders of consciousness: a bibliometric analysis

Frontiers in Neurology, Journal Year: 2025, Volume and Issue: 15

Published: Jan. 27, 2025

Objective Disorders of consciousness (DoC) result from severe traumatic brain injury and hypoxia or ischemia tissues, leading to impaired perceptual abilities. Electroencephalography (EEG) is a non-invasive widely applicable technology used for assessing DoC. We aimed identify the research hotspots in this field through systematic analysis. Methods Relevant studies published January 1, 2004 December 31, 2023 were retrieved Web Science Core Collection database. The data analyzed visualized using CiteSpace, VOSviewer, SCImago Graphica. Results In total, 1,639 relevant publications retrieved. country with highest number was United States, most productive institution Harvard University, journal output Clinical Neurophysiology , total citations Neurology . author Steven Laureys common keyword “vegetative state.” Conclusion undergoing rapid development, characterized by proliferation advanced technologies an increased emphasis on international collaboration. document offers impartial perspective advancements study benefit researchers.

Language: Английский

Advancing Sleep Disorder Diagnostics: A Transformer-based EEG Model for Sleep Stage Classification and OSA Prediction

IEEE Journal of Biomedical and Health Informatics, Journal Year: 2024, Volume and Issue: 29(2), P. 878 - 886

Published: Dec. 9, 2024

Sleep disorders, particularly Obstructive Apnea (OSA), have a considerable effect on an individual's health and quality of life. Accurate sleep stage classification prediction OSA are crucial for timely diagnosis effective management disorders. In this study, we develop sequential network that enhances by incorporating self-attention mechanisms Conditional Random Fields (CRF) into deep learning model comprising multi-kernel Convolutional Neural Networks (CNNs) Transformer-based encoders. The mechanism enables the to focus most discriminative features extracted from single-channel electroencephalography (EEG) recordings, while CRF module captures temporal dependencies between stages, improving model's ability learn more plausible sequences. Moreover, explore relationship stages severity utilizing predicted train various regression models Apnea-Hypopnea Index (AHI) prediction. Our experiments demonstrate improved performance 78.7%, datasets with diverse AHI values, highlight potential leveraging information monitoring OSA. By employing advanced techniques, thoroughly intricate apnea, laying foundation precise automated diagnostics

Language: Английский