Yazar "Jafarifarmand, Aysa" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    A Comparative Study of Classical Spectral and Spatial Feature Extraction Methods for Fatigue Detection via EEG Signals
    (Institute of Electrical and Electronics Engineers Inc., 2025) Zahid, Arslan Mohammad; Subasi, Yavuz Giray; Jafarifarmand, Aysa
    Driving fatigue detection using electroencephalography (EEG) is an emerging application of smart systems with marked implication in transportation safety, healthcare and human-machine interaction. This study proposes a machine learning-based framework for binary mental fatigue classification, utilizing and comparing two established feature extraction methods-Power Spectral Density (PSD) and Common Spatial Pattern (CSP). A comparative evaluation was conducted across four traditional classifiers: k-Nearest Neighbors (kNN), Linear Support Vector Machine (SVM), Radial Basis Function (RBF) SVM, and Random Forest, using an open access EEG dataset. Four independent approaches were considered for this study: PSD-based features with all features considered, feature selection of the most informative PSD features, CSP features with all components considered, and selected CSP components. Each approach considered utilizing all four classifiers. Experimental results revealed that in general, CSP-based spatial features outperformed PSD in three out of four classifiers, specifically in non-linear models. Notably, RBF SVM with selected CSP components yielded an accruacy of 91.13%, comparable to kNN with all CSP components (91.63%) while outperforming both PSD-based approaches. These findings highlight the effectiveness of CSP-based spatial filtering combined with ML for EEGsignal classification representing a promising step towards the development of real-time, intelligent fatigue monitoring systems. © 2025 IEEE.
  • Küçük Resim Yok
    Öğe
    EEG Band Power Feature Based Electrode Combination Analysis for Epilepsy Detection
    (Institute of Electrical and Electronics Engineers Inc., 2025) Sargin, Serhat Ismet; Jafarifarmand, Aysa
    Epilepsy is a chronic neurological disorder characterised by seizures caused by abnormal electrical activity in the brain. Today, the diagnosis of epilepsy is largely based on the analysis of electroencephalogram (EEG) signals. However, the nonlinear and chaotic nature of EEG signals makes visual inspection a time-consuming, labour-intensive, and specialised process. In this context, this study proposes a computer-aided diagnostic method that aims to analyse EEG signals more efficiently. Within the scope of the study, power values belonging to different frequency bands were obtained from EEG signals collected from 121 participants through 35 electrodes. In determining the electrode combinations, the individual classification performance of each electrode was analysed, the electrode with the highest performance was selected and combined with the other electrodes in the vector space, thus creating effective electrode combinations. The resulting feature vectors were presented as input to the decision tree classifier, and the model's performance was evaluated with metrics such as accuracy, F1 score, sensitivity, and specificity. Using a combination of theta band power features obtained from F3C3, C3P3, T6O2, T5O1, FP2A2, O2A2 and P4A2 electrodes, the model showed a high success in epilepsy detection with 84.6% accuracy and 81.1% F1 score. © 2025 IEEE.
  • Küçük Resim Yok
    Öğe
    Microwave Medical Diagnosis System With a Framework to Optimize the Antenna Configuration and Frequency of Operation Using Neural Networks
    (IEEE-Inst Electrical Electronics Engineers Inc, 2022) Jafarifarmand, Aysa; Yilmaz, Tuba; Akduman, Ibrahim
    Using artificial neural networks (NNs) in microwave medical diagnosis is recently of great interest in various problems such as early breast cancer detection, brain stroke, and leukemia monitoring. NNs facilitate the process by directly assessing the presence and properties of the tissues based on the scattered field values. Although the reported studies obtained successful results through the application of NNs to microwave diagnostic problems, they used large numbers of input data. The NN input, referred to as features, for microwave diagnosis is composed of scattered fields namely antenna transmission and reflections at the frequency of choice. Large input data increase both the number of required training samples and computational cost. Optimizing the number of antennas and frequency of operation is therefore critical to improving the performance of NN-based medical diagnosis. This work considers the correlations between the effects of different frequencies and receiver/transmitter (Rx/Tx) antennas separately in order to objectively reduce the number of features. Optimized feed-forward NNs are applied to detect the presence of object(s) with permittivity value above the predefined level within the solution domain. It is performed by designating various permittivity values to the internal object(s). Promising results were obtained by reducing the number of features approximately seven times.