Salma Tayeb

About

Salma Tayeb is a researcher whose work lies at the intersection of neuroscience and machine learning, with a primary focus on brain-machine interfaces (BMI). Her research centers on decoding neural activity—specifically electroencephalography (EEG) signals—to enable direct control of external devices through thought alone. Tayeb’s major contributions involve the efficient classification of imagined hand movements, a critical step for developing assistive technologies for individuals with motor impairments. In her most-cited work (2016, 19 citations), she pioneered the use of a Radial Basis Function (RBF) kernel Support Vector Machine (SVM) to accurately discriminate between left and right imagined hand movements from EEG data. Building on this, her 2017 study (9 citations) refined the approach by integrating a joint Continuous Wavelet Transform and Principal Component Analysis (CWT_PCA) feature extraction method, further enhancing classification performance. These contributions have helped advance the practical viability of non-invasive BMI systems, demonstrating that robust motor imagery decoding is achievable with relatively simple, efficient algorithms. Tayeb’s work is particularly notable for its emphasis on computational efficiency, making her methods more accessible for real-time applications. Her research continues to inspire students and engineers working toward seamless human-machine integration.

Research Focus

Key Achievements

Top Papers

1. 1
   EEG efficient classification of imagined hand movement using RBF kernel SVM

   19 citations · 2016
2. 2
   EEG efficient classification of imagined right and left hand movement using RBF kernel SVM and the joint CWT_PCA

   9 citations · 2017

Key Collaborators

Contact & Links