Analysis on dendritic deep learning model for AMR task DOI Creative Commons
Peng Yin, Shahong Zhu, Yang Yu

et al.

Cybersecurity, Journal Year: 2024, Volume and Issue: 7(1)

Published: Dec. 19, 2024

Abstract This study introduces a novel hybrid deep learning model featuring dendritic layer for enhancing the performance of automatic modulation recognition (AMR). By replacing fully connected layer, proposed demonstrates superior classification accuracy in AMR tasks. Comparative experiments with nine state-of-the-art models on RadioML2016.10a dataset reveal its consistent superiority. Statistical analyses, including Friedman test and Wilcoxon signed-rank test, confirm significant advantage HDM-D model.

Language: Английский

A multi-scale information fusion approach for brain network construction in epileptic EEG analysis DOI
Zhiwen Ren, Dingding Han

Physica A Statistical Mechanics and its Applications, Journal Year: 2025, Volume and Issue: unknown, P. 130415 - 130415

Published: Feb. 1, 2025

Language: Английский

Citations

0
Exploring temporal information dynamics in Spiking Neural Networks: Fast Temporal Efficient Training DOI

Changjiang Han,

Li‐Juan Liu,

Hamid Reza Karimi

et al.

Journal of Neuroscience Methods, Journal Year: 2025, Volume and Issue: unknown, P. 110401 - 110401

Published: Feb. 1, 2025

Language: Английский

Citations

0
Electroencephalographic Biomarkers for Neuropsychiatric Diseases: The State of the Art DOI Creative Commons
Nayeli Huidobro,

Roberto Meza-Andrade,

Ignacio Méndez‐Balbuena

et al.

Bioengineering, Journal Year: 2025, Volume and Issue: 12(3), P. 295 - 295

Published: March 14, 2025

Because of their nature, biomarkers for neuropsychiatric diseases were out the reach medical diagnostic technology until past few decades. In recent years, confluence greater, affordable computer power with need more efficient diagnoses and treatments has increased interest in possibility discovery. This review will focus on progress made over ten years regarding search electroencephalographic diseases. includes algorithms methods analysis, machine learning, quantitative electroencephalography as applied to neurodegenerative neurodevelopmental well traumatic brain injury COVID-19. Our findings suggest that there is a consensus among researchers classification most suit this field; slight disconnection between development increasingly sophisticated analysis what they actually be use clinical setting; finally, are favored type field caveats. The main goal state-of-the-art provide reader general panorama state art field.

Language: Английский

Citations

0
Soft sensing modeling of penicillin fermentation process based on local selection ensemble learning DOI Creative Commons

Feixiang Huang,

Longhao Li,

Chuanxiang Du

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Sept. 2, 2024

Language: Английский

Citations

1
Neurodynamic Characterization and Prediction of Schizophrenia Using Echo State Networks with Serotonin Modulation: A Temporal and Frequency Band Analysis Approach DOI Creative Commons

Anirudh Sowrirajan,

Pranav Sriniva,

Sundari Avanthikaa Sriniva

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 19, 2024

Abstract Schizophrenia is characterized by significant cognitive dysfunctions, with serotonin playing a crucial role in modulating neural processes. Analyzing the impact of on EEG patterns can provide important insights into distinguishing schizophrenic patients from healthy individuals. This study integrates serotonin-inspired modulation Echo State Networks (ESNs) to model nonlinear dynamics data patients, focus key brain regions such as frontal lobe and medial prefrontal cortex (mPFC). were preprocessed (0.1–40 Hz), ICA filtered, segmented, analyzed using ESNs, targeting 5 HT1A 5-HT2A receptors simulate effects mPFC regions. Principal Component Analysis (PCA) K-means clustering used classify samples. Results showed that schizophrenia exhibited elevated delta gamma band activity, diminished alpha beta activity. Serotonin enhanced performance ESNs reducing noise improving predictive accuracy, particularly The incorporation offers deeper understanding activity provides valuable disease-specific features, potentially advancing diagnostic approaches.

Language: Английский

Citations

0
Deep manifold learning for the reconstruction of spatiotemporal neural activity in brain cortex using electroencephalography signals DOI

Lingyun Wu,

Hu Zhi, Jing Liu

et al.

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 102, P. 107335 - 107335

Published: Dec. 18, 2024

Language: Английский

Citations

0
Analysis on dendritic deep learning model for AMR task DOI Creative Commons
Peng Yin, Shahong Zhu, Yang Yu

et al.

Cybersecurity, Journal Year: 2024, Volume and Issue: 7(1)

Published: Dec. 19, 2024

Abstract This study introduces a novel hybrid deep learning model featuring dendritic layer for enhancing the performance of automatic modulation recognition (AMR). By replacing fully connected layer, proposed demonstrates superior classification accuracy in AMR tasks. Comparative experiments with nine state-of-the-art models on RadioML2016.10a dataset reveal its consistent superiority. Statistical analyses, including Friedman test and Wilcoxon signed-rank test, confirm significant advantage HDM-D model.

Language: Английский

Citations

0