Boosting EEG and ECG Classification with Synthetic Biophysical Data Generated via Generative Adversarial Networks DOI Creative Commons
Archana Venugopal, Diego R. Faria

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(23), P. 10818 - 10818

Published: Nov. 22, 2024

This study presents a novel approach using Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP) to generate synthetic electroencephalography (EEG) and electrocardiogram (ECG) waveforms. The EEG data represent concentration relaxation mental states, while the ECG correspond normal abnormal states. By addressing challenges of limited biophysical data, including privacy concerns restricted volunteer availability, our model generates realistic waveforms learned from real data. Combining datasets improved classification accuracy 92% 98.45%, highlighting benefits dataset augmentation for machine learning performance. WGAN-GP achieved 96.84% representing states optimal when classified fusion convolutional neural networks (CNNs). A 50% combination yielded highest 98.48%. For signals, consisted 60-s recordings across four channels (TP9, AF7, AF8, TP10) individuals, providing approximately 15,000 points per subject state. contained 1200 samples, each comprising 140 points, outperformed basic generative adversarial network (GAN) in generating reliable support vector (SVM) classifier an 98% 95.8% Synthetic random forest (RF) classifier’s 97% alone 98.40% combined Statistical significance was assessed Wilcoxon signed-rank test, demonstrating robustness model. Techniques such as discrete wavelet transform, downsampling, upsampling were employed enhance quality. method shows significant potential scarcity advancing applications assistive technologies, human-robot interaction, health monitoring, among other medical applications.

Language: Английский

Impact of Virtual Reality on Brain–Computer Interface Performance in IoT Control—Review of Current State of Knowledge DOI Creative Commons
Adrianna Piszcz, Izabela Rojek, Dariusz Mikołajewski

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(22), P. 10541 - 10541

Published: Nov. 15, 2024

This article examines state-of-the-art research into the impact of virtual reality (VR) on brain–computer interface (BCI) performance: how use can affect brain activity and neural plasticity in ways that improve performance interfaces IoT control, e.g., for smart home purposes. Integrating BCI with VR improves control by providing immersive, adaptive training environments increase signal accuracy user control. offers real-time feedback simulations help users refine their interactions systems, making more intuitive responsive. combination ultimately leads to greater independence, efficiency, ease use, especially mobility issues, managing IoT-connected devices. The integration shows great potential transformative applications ranging from neurorehabilitation human–computer interaction cognitive assessment personalized therapeutic interventions a variety neurological disorders. literature review highlights significant advances multifaceted challenges this rapidly evolving field. Particularly noteworthy is emphasis importance processing techniques, which are key enhancing overall immersion experienced individuals environments. value multimodal integration, technology combined complementary biosensors such as gaze tracking motion capture, also highlighted. incorporation advanced artificial intelligence (AI) techniques will revolutionize way we approach diagnosis treatment neurodegenerative conditions.

Language: Английский

Citations

0
Boosting EEG and ECG Classification with Synthetic Biophysical Data Generated via Generative Adversarial Networks DOI Creative Commons
Archana Venugopal, Diego R. Faria

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(23), P. 10818 - 10818

Published: Nov. 22, 2024

This study presents a novel approach using Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN-GP) to generate synthetic electroencephalography (EEG) and electrocardiogram (ECG) waveforms. The EEG data represent concentration relaxation mental states, while the ECG correspond normal abnormal states. By addressing challenges of limited biophysical data, including privacy concerns restricted volunteer availability, our model generates realistic waveforms learned from real data. Combining datasets improved classification accuracy 92% 98.45%, highlighting benefits dataset augmentation for machine learning performance. WGAN-GP achieved 96.84% representing states optimal when classified fusion convolutional neural networks (CNNs). A 50% combination yielded highest 98.48%. For signals, consisted 60-s recordings across four channels (TP9, AF7, AF8, TP10) individuals, providing approximately 15,000 points per subject state. contained 1200 samples, each comprising 140 points, outperformed basic generative adversarial network (GAN) in generating reliable support vector (SVM) classifier an 98% 95.8% Synthetic random forest (RF) classifier’s 97% alone 98.40% combined Statistical significance was assessed Wilcoxon signed-rank test, demonstrating robustness model. Techniques such as discrete wavelet transform, downsampling, upsampling were employed enhance quality. method shows significant potential scarcity advancing applications assistive technologies, human-robot interaction, health monitoring, among other medical applications.

Language: Английский

Citations

0