Maryam Abo-Tabik

Maryam Abo-Tabik serves as a Lecturer in Computer Science within the School of Engineering and Computing, where she applies interdisciplinary expertise to develop machine learning solutions for health behaviour prediction. Her work bridges computer science and public health through innovative mobile health applications, particularly targeting smoking cessation interventions using real-world smartphone data.

Her research interests center on deep learning architectures and behavioural modelling techniques for health monitoring, with emphasis on predicting smoking lapses through movement dynamics and physiological signals. This includes pioneering work on 1D-CNN models for time-series analysis of hand movements and smartphone sensor data, advancing the field of just-in-time adaptive interventions in digital therapeutics.

Analysis of her publication trajectory reveals consistent focus on translating machine learning innovations into practical cessation tools, evolving from foundational biometric research to specialized health applications. Her methodology integrates mobile sensing with predictive analytics to create personalized, real-time behavioural support systems.

Professional recognition includes:

• HEA Fellow

Dr Abo-Tabik actively supervises advanced student projects in health technology development, guiding interdisciplinary research that combines technical implementation with behavioural science principles for next-generation mobile health solutions.