A comprehensive exploration of machine learning techniques for EEG-based anxiety detection

PeerJ Computer Science, Journal Year: 2024, Volume and Issue: 10, P. e1829 - e1829

Published: Jan. 25, 2024

The performance of electroencephalogram (EEG)-based systems depends on the proper choice feature extraction and machine learning algorithms. This study highlights significance selecting appropriate algorithms for EEG-based anxiety detection. We explored different annotation/labeling, extraction, classification Two measurements, Hamilton rating scale (HAM-A) self-assessment Manikin (SAM), were used to label states. For EEG we employed discrete wavelet transform (DWT) power spectral density (PSD). To improve accuracy detection, compared ensemble methods such as random forest (RF), AdaBoost bagging, gradient bagging with conventional including linear discriminant analysis (LDA), support vector (SVM), k-nearest neighbor (KNN) classifiers. also evaluated classifiers using labeling (SAM HAM-A) (PSD DWT). Our findings demonstrated that HAM-A DWT-based features consistently yielded superior results across all Specifically, RF classifier achieved highest 87.5%, followed by Ada boost an 79%. outperformed other in terms accuracy, precision, recall.

Language: Английский

---

Exploring new horizons in neuroscience disease detection through innovative visual signal analysis

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

Published: Feb. 20, 2024

Abstract Brain disorders pose a substantial global health challenge, persisting as leading cause of mortality worldwide. Electroencephalogram (EEG) analysis is crucial for diagnosing brain disorders, but it can be challenging medical practitioners to interpret complex EEG signals and make accurate diagnoses. To address this, our study focuses on visualizing in format easily understandable by professionals deep learning algorithms. We propose novel time–frequency (TF) transform called the Forward–Backward Fourier (FBFT) utilize convolutional neural networks (CNNs) extract meaningful features from TF images classify disorders. introduce concept eye-naked classification, which integrates domain-specific knowledge clinical expertise into classification process. Our demonstrates effectiveness FBFT method, achieving impressive accuracies across multiple using CNN-based classification. Specifically, we achieve 99.82% epilepsy, 95.91% Alzheimer’s disease (AD), 85.1% murmur, 100% mental stress Furthermore, context naked-eye 78.6%, 71.9%, 82.7%, 91.0% AD, stress, respectively. Additionally, incorporate mean correlation coefficient (mCC) based channel selection method enhance accuracy further. By combining these innovative approaches, enhances visualization signals, providing with deeper understanding images. This research has potential bridge gap between image visual interpretation, better detection improved patient care field neuroscience.

Language: Английский

---

Brain activity patterns reflecting security perceptions of female cyclists in virtual reality experiments

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 4, 2025

Abstract Active transportation, such as cycling, improves mobility and general health. However, statistics reveal that in low- middle-income countries, male female cycling participation rates differ significantly. Existing literature highlights women’s willingness to use bicycles is significantly influenced by their perception of security. This study employs virtual reality (VR) simulation electroencephalography (EEG) analysis investigate factors influencing cyclists’ perceptions security Tehran. A total 52 participants took part four scenarios within a VR bicycle simulator, which simulates various environmental settings. In this experiment, participants’ brainwave signals are gathered through an EEG device, questionnaire with stated preferences filled out. The Gaussian mixture approach used cluster patterns based on from data. Subsequently, supervised machine learning methods, random forest, support vector machine, logistic regression, multilayer perceptron, utilized classify influential using clustered Consequently, the model, F1 score 0.74, appears be most effective technique for classification surveillance factors. Furthermore, SelectKBest algorithm determines presence obstacles like kiosks, routes passing tunnels underpasses, level incivility urban environment, informal have biggest impact perception.

Language: Английский

---

EEG-based anxiety emotion classification using an optimized convolutional neural network and transformer

Signal Image and Video Processing, Journal Year: 2025, Volume and Issue: 19(6)

Published: April 16, 2025

Language: Английский

---

Impact of varying levels of mental stress on phase information of EEG Signals: A study on the Frontal, Central, and parietal regions

Biomedical Signal Processing and Control, Journal Year: 2023, Volume and Issue: 86, P. 105236 - 105236

Published: July 8, 2023

Mental stress is a commonly occurring phenomenon that impacts people from diverse backgrounds and associated with numerous physical psychological illnesses. The brain plays vital role in how individuals perceive react to stress, including their physiological behavioral responses. In this study, our objective was investigate the impact of varying levels induced ranging mild severe, on activity. Our primary interest determine if mental would influence neural coordination, as assessed through intertrial phase clustering (ITPC). Furthermore, we hypothesized an increase perceived result reduced regional connectivity measured via phase-lag index (PLI). EEG data 41 participants (20 females, 21 males, age range 18 46; mean = 26.1; SD 7.06) were collected while they exposed three using parametric modulation study design. Following pre-processing, extracted two mentioned features performed statistical analysis. As additional analysis, discriminatory power these Random Forest classifier. Statistical analysis revealed significant decrease ITPCs over frontal, central, parietal regions accompanying increased stress. results obtained PLI showed frontocentral, frontoparietal, centroparietal regions. classification Forrest classifier predict 83.78% accuracy. These findings indicate phase-based could serve novel neurometric for quantifying vivo levels. contribute developing more precise tools measure objectively.

Language: Английский

---

EEG-based stress identification and classification using deep learning

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 83(14), P. 42703 - 42719

Published: Oct. 11, 2023

Language: Английский

---

Design of spatiotemporal variability index for climatic variables

Measurement, Journal Year: 2024, Volume and Issue: 231, P. 114577 - 114577

Published: March 28, 2024

Language: Английский

---

Identification of psychological stress from speech signal using deep learning algorithm

e-Prime - Advances in Electrical Engineering Electronics and Energy, Journal Year: 2024, Volume and Issue: 9, P. 100707 - 100707

Published: Aug. 7, 2024

Language: Английский

---

The Role of Frontal Electrodes in Human State Anxiety Detection Using Wavelet Features and Machine Learning

Published: May 12, 2024

Language: Английский

---

A Survey of EEG-Based Stress Detection Using Machine Learning and Deep Learning Techniques

Published: May 22, 2024

Language: Английский

---