Intelligent Computing
Machine learning, deep learning, and generative AI for reliable analysis, prediction, and decision support.
Reliable AI · Security · Sensing
RANA Lab develops and evaluates intelligent computing systems for consequential, real-world settings. We bring AI, algorithm design, and careful measurement to challenges in cybersecurity, health, sustainable agriculture, and computational biology.
Research areas
We combine AI, algorithms, and systems research to help make decisions from complex, incomplete, or uncertain data.
Machine learning, deep learning, and generative AI for reliable analysis, prediction, and decision support.
AI-driven security, privacy protection, adversarial testing, and trustworthy systems built to withstand misuse.
AI for healthcare, biomedical informatics, multimodal sensing, and non-invasive measurement.
Smart farming, precision agriculture, and environmental intelligence from connected field data.
Bioinformatics, genomics, and biological data science for insight into complex life-science data.
Efficient, robust algorithms for learning, optimization, data integration, and real-world decisions.
Research programs
We connect computational methods to measured signals and careful evaluation.
A Raman–NIR digital-twin effort studies spectral features, calibration, and uncertainty for future non-invasive glucose monitoring.
We examine manipulated media, cross-generator detection, and multimodal evidence under realistic sharing conditions.
Our work explores adversarial testing, privacy, and resilient AI in cyber-physical and sensor-rich environments.
How we work
A result matters when its assumptions, data, uncertainty, and failure cases are visible. We pair technical development with disciplined evaluation.
Ground models in meaningful signals and well-defined targets.
Test across sources, operating conditions, and potential attacks.
Make assumptions, uncertainty, and failure modes understandable.
Research showcase
Recent conference presentations and research posters from the lab.
A growing record of research shared with academic and community audiences.
Toward Reliable Non-Invasive Glucose Monitoring: A COMSOL-Based Raman–BRS Digital Twin
A research talk and poster on spectral modeling, glucose calibration, and measurement uncertainty for a non-invasive sensing digital twin.
Toward Reliable Non-Invasive Glucose Monitoring: A COMSOL-Based Raman–BRS Digital Twin
Poster presentation featuring a physics-based digital twin for Raman–NIR spectral modeling and glucose calibration.
No seminar entries yet. New presentations will appear here.
People
Our student researchers work across AI, cybersecurity, health, and data-driven systems.
Assistant Professor in the School of Computing at Georgia Southern University. His research develops reliable AI and computational methods for security, health, biology, and sustainable systems.
Email Dr. RanaA four-person student team across three degree levels.
Student profiles and project details can be added as the team grows.
Connect with us
Students interested in research and colleagues exploring collaboration are welcome to get in touch.