Computational Neuroscientist and Data Scientist Exploring EEG, Brain- Computer Interfaces, and AI

Biography

Khunsa Iftikhar is a research-focused computational neuroscientist and data scientist with an MSc (Distinction) in Big Data Science and Technology from the University of Bradford and a Bachelor’s degree in Software Engineering from COMSATS University Islamabad.

Her work lies at the intersection of neural signal processing, machine learning, and time-series analysis, with a strong focus on EEG-based brain–computer interfaces (BCIs) and human-centered AI systems.

Her research includes a published work on speech emotion recognition using deep learning (Springer LNCS, 2023), where she designed and evaluated convolutional neural network architectures across multi-dataset speech corpora. This work reflects her experience in deep learning model design, evaluation, and multi-source data integration.

She also has hands-on experience with EEG data acquisition, preprocessing, and feature extraction, working with non-invasive systems such as Emotiv Insight and Emotiv Epoc. Her work includes developing experimental pipelines for neural decoding, attention analysis, and cognitive state assessment.

During her MSc, she completed a dissertation on smart meter data analytics, applying unsupervised learning and time-series forecasting to large-scale energy consumption data. Conducted within the SAFI research project under Prof. Daniel Neagu’s AI research group, this work demonstrates her ability to work with high-dimensional, longitudinal datasets, a skill directly transferable to neural and biomedical data analysis.

Research Interests

Her research interests include:

Computational Neuroscience
Brain–Computer Interfaces (BCI)
EEG Signal Processing and Neural Decoding
Affective Computing and Emotion Recognition
Mental Health and Neurodevelopmental Disorders (e.g., ADHD)
Machine Learning for Biological and Human-Centered Data

She is particularly interested in understanding brain dynamics and developing data-driven models that translate neural signals into meaningful insights for real-world applications.

PhD Objective

She is actively seeking a fully funded PhD position to pursue interdisciplinary research at the intersection of computational neuroscience, machine learning, and artificial intelligence. Her primary research goal is to develop robust, generalizable models for neural signal decoding, with a focus on EEG-based cognitive and emotion recognition. She is particularly interested in affective computing, brain–computer interfaces (BCI), and multimodal learning frameworks that integrate neural, behavioral, and physiological data.

Her work aims to advance the understanding of human cognitive and emotional processes through data-driven modeling, while contributing to real-world applications in mental health, adaptive human–computer interaction, and intelligent neurotechnology systems. She is especially motivated to explore deep learning and representation learning approaches for cross-subject generalization, real-time inference, and personalized neuro-adaptive systems.

Let's Collaborate

If you are a faculty member, researcher, or collaborator working in neuroscience, machine learning, or interdisciplinary AI, she welcomes opportunities for collaboration and academic discussion.

Explore her projects, publications, and academic background, or reach out to discuss potential research directions.