Farwa is a postdoctoral researcher at Adeliade University and South Australian Health and Medical Research Institute (SAHMRI) working at the intersection of cognitive and computational neuroscience and healthcare technologies. Her research interests span biomedical and statistical signal processing, convex optimization, machine learning, and deep learning, with a particular focus on interpretable AI for clinical translation. Through this work, she aims to develop healthcare solutions that are trustworthy, usable, and impactful in real-world settings. She completed her doctoral studies in the Department of Electrical and Electronic Engineering at Imperial College London, where she worked in the Communications and Signal Processing Research Group. Her doctoral research focused on advanced signal processing models and learning-based methods for biomedical applications. Prior to her doctoral studies, Farwa worked for more than three years as a Research Associate at the Center of Artificial Intelligence and Computational Science (CACTuS) Lab at the Information Technology University (ITU), Lahore, Pakistan. She received her Master’s degree in Electrical Engineering from Lahore University of Management Sciences (LUMS) in 2019, specializing in Signal Processing and Machine Learning, and completed her Bachelor’s degree in Electrical Engineering from the University of Engineering and Technology (UET), Lahore in 2017.

Beyond research, Farwa is deeply passionate about science communication, education, and advocating for underrepresented voices in science. She is strongly committed to closing the gender gap in STEM and believes that early exposure to science, particularly for young girls, can be transformative. Through teaching, outreach, and public engagement, she aims to make science more inclusive, engaging, and empowering, while contributing meaningful, data-driven innovations and helping shape a more equitable and diverse scientific community.

Her specific research insterests are as follows:

Biomedical and Statistical Signal Processing: Development of signal processing methodologies for the analysis of multimodal biomedical data such as EEG, sEMG, MEG, and MRI. This includes statistical signal modeling, source localization, and feature extraction techniques aimed at understanding neural dynamics and identifying clinically relevant biomarkers in neurological and movement disorders.

Computational Modeling of Neural Systems: Mathematical and computational modeling of neural population dynamics using differential equations and stochastic systems, with the goal of linking physiological mechanisms to observable signals and imaging data.

Neuromodulation and Data-Driven Neuroscience: Analysis of non-invasive brain stimulation data (e.g., TMS) to study neuroplasticity and working memory, using signal processing, biophysical modeling, and machine learning techniques to characterize brain-state dependent effects, individual variability and pharmacological effects on neuroplasticity.

Inverse Problems and Imaging: Inverse problems arising in biomedical imaging and neurophysiology, including the reconstruction of latent neural sources and physiological states from indirect, noisy, and high-dimensional measurements. This includes theoretical and computational approaches to ill-posed inverse problems in neuroimaging and related modalities.

Deep Learning for Image and Signal Reconstruction: Strong interest in deep learning based approaches for image and signal reconstruction, particularly hybrid model-based and data-driven methods. This includes neural architectures for accelerated and robust reconstruction in biomedical imaging, as well as learning priors and representations that improve generalization and interpretability in inverse problems.

Convex Optimization and Structured Signal Representations: Convex optimization methods for learning low-rank, sparse, and structured representations of signals and images. This spans optimization algorithms, regularization techniques, and theoretical guarantees for recovering meaningful structure in high-dimensional biomedical data, with applications to imaging, neural signal analysis, and connectivity modeling.