Eeg based smart emotion recognition using meta heuristic optimization and hybrid deep learning techniques DOI Creative Commons

M. Karthiga,

E. Suganya,

S. Sountharrajan

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Дек. 4, 2024

Язык: Английский

MelNet: An End-to-End Adaptive Network with Adjustable Frequency for Preprocessing-Free Broadband Acoustic Emission Signals DOI
Jing Huang, Rui Qin, Zhifen Zhang

и другие.

Information Fusion, Год журнала: 2025, Номер unknown, С. 103229 - 103229

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0

Study on real-time warning system of blind path for the visually impaired based on improved deep residual shrinkage network DOI Creative Commons

Zhezhou Yu,

Fuwang Wang

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 29, 2025

Visually impaired individuals often face various obstacles when navigating blind roads, such as road disconnections, obstructions, and more complex emergencies, which can leave them in difficult situations. Traditional early warning methods suffer from low accuracy lack real-time capabilities. Therefore, this study proposes a novel system for traffic jams on roads. By analyzing the emotional state (normal, mild anxiety, extreme anxiety) electroencephalogram (EEG) signals of visually they are trapped, determine whether distress require assistance. Additionally, considering complexity environment fact that EEG prone to external interference during acquisition, introduces an improved deep residual shrinkage network based dense blocks (DB-DRSN). DB-DRSN replaces convolutional hidden layer original module with integrates connections optimize use both shallow features. The results show achieves 96.72% recognizing difficulties faced by impaired, significantly outperforming traditional models. Compared other methods, proposed offers quicker assistance individuals. demonstrated strong performance detecting about jams, greatly enhancing safety enabling timely detection intervention.

Язык: Английский

Процитировано

0

Multi-source domain separation adversarial domain adaptation for EEG emotion recognition DOI
Qingsong Ai, Chenhuan Wang, Kun Chen

и другие.

Biomedical Signal Processing and Control, Год журнала: 2025, Номер 109, С. 108016 - 108016

Опубликована: Май 17, 2025

Процитировано

0

Automated depression detection via cloud based EEG analysis with transfer learning and synchrosqueezed wavelet transform DOI Creative Commons
Sara Bagherzadeh,

Mohammad Reza Norouzi,

Amirhesam Ghasri

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Май 23, 2025

Язык: Английский

Процитировано

0

Multimodal Insights into Granger Causality Connectivity: Integrating Physiological Signals and Gated Eye-Tracking Data for Emotion Recognition Using Convolutional Neural Network DOI Creative Commons

Javid Farhadi Sedehi,

Nader Jafarnia Dabanloo, Keivan Maghooli

и другие.

Heliyon, Год журнала: 2024, Номер 10(16), С. e36411 - e36411

Опубликована: Авг. 1, 2024

Highlights•Introduces ECG-EEG integration with eye-tracking for emotion recognition.•Employs pupil diameter metrics to refine emotional data accuracy.•Innovative Granger causality approach study brain-heart interaction.•Utilizes ResNet-18 high accuracy: 91 % and AUC of 0.97.•Outperforms state-of-the-art enhancement.AbstractThis introduces a groundbreaking method enhance the accuracy reliability recognition systems by combining electrocardiogram (ECG) electroencephalogram (EEG) data, using an gated strategy. Initially, we propose technique filter out irrelevant portions employing from data. Subsequently, introduce innovative estimating effective connectivity capture dynamic interaction between brain heart during states happiness sadness. (GC) is estimated utilized optimize input highly pre-trained convolutional neural network (CNN), specifically ResNet-18. To assess this methodology, employed EEG ECG publicly available MAHNOB-HCI database, 5-fold cross-validation approach. Our achieved impressive average area under curve (AUC) 91.00 0.97, respectively, GC-EEG-ECG images processed Comparative analysis studies clearly shows that augmenting refining strategy significantly enhances performance across various emotions.

Язык: Английский

Процитировано

2

A radial basis deformable residual convolutional neural model embedded with local multi-modal feature knowledge and its application in cross-subject classification DOI
Jingjing Li, Yanhong Zhou, Tiange Liu

и другие.

Expert Systems with Applications, Год журнала: 2024, Номер 257, С. 125089 - 125089

Опубликована: Авг. 13, 2024

Язык: Английский

Процитировано

1

EEG emotion recognition approach using multi-scale convolution and feature fusion DOI
Yong Zhang,

Qingguo Shan,

Wen‐Yun Chen

и другие.

The Visual Computer, Год журнала: 2024, Номер unknown

Опубликована: Сен. 19, 2024

Язык: Английский

Процитировано

1

Study on multidimensional emotion recognition fusing dynamic brain network features in EEG signals DOI
Yan Wu, Tianyu Meng, Qi Li

и другие.

Biomedical Signal Processing and Control, Год журнала: 2024, Номер 100, С. 107054 - 107054

Опубликована: Окт. 15, 2024

Язык: Английский

Процитировано

1

Review of: "EEG-based Emotion Classification using Deep Learning: Approaches, Trends and Bibliometrics" DOI Creative Commons
Sara Bagherzadeh

Опубликована: Март 22, 2024

Язык: Английский

Процитировано

0

Advanced functional connectivity analysis with integrated EEG signal enhancement and GTW-EEG-GAN for emotion detection DOI
Nirmal Varghese Babu, E. Grace Mary Kanaga

International Journal of Computers and Applications, Год журнала: 2024, Номер unknown, С. 1 - 14

Опубликована: Окт. 23, 2024

Emotion recognition is crucial in human-computer interaction and psychological research, utilizing modalities such as facial expressions, voice intonations, EEG signals. This research investigates AI-driven techniques by employing Graph Neural Networks (GNNs) on functional connectivity matrices derived from data to advance emotion recognition. Our approach integrates sophisticated preprocessing methods, including Integrated Signal Enhancement (IESE) novel augmentation Gaussian Time Warping Generative Adversarial Network (GTW-EEG-GAN). integration aims at enhancing quality diversity. decomposition using EMD-Wavelet Hybrid Decomposition further refines feature extraction, enabling robust analysis of Functional metrics capture critical neural interactions intended for precise characterization. The GNN architecture effectively processes these features, achieving significant accuracy improvements. Evaluations the DEAP dataset demonstrate promising results, attaining 94.5% before hyperparameter tuning improving 98.6% after tuning, highlighting system's efficacy. methodology showcases advanced signal processing with AI, offering a comprehensive framework future studies. findings advocate potential applications areas personalized mental health monitoring, adaptive learning environments, responsive gaming experiences, demonstrating broad impact versatility EEG-based

Язык: Английский

Процитировано

0