Skip to main content
Fadoua Khmaissia

Fadoua Khmaissia

Research Scientist

Murray Hill, NJ, USA

New Image

Biography

Fadoua Khmaissia is a researcher in the Decentralized Systems Research group at Nokia Bell Labs in Murray Hill, NJ. She holds a Computer Science PhD from the University of Louisville, KY. She has a rich experience in both theoretical and applied machine learning research. Her PhD focuses on leveraging generative modeling and data augmentation to improve semi-supervised computer vision in low data regime. She has a track record collaborating with multidisciplinary teams to solve ambiguous research questions. She also led and contributed to several applied machine learning projects including; automatic target recognition from visible and infrared images, buried objects detection using ground penetration radar data and, data-driven modeling of materials’ properties for renewable energy applications. Her research interests include Machine learning, Computer vision, Deep learning with limited labeled data, AI for Climate Change, and AI for Social Good.

Education
  • 2023: Ph.D. in Computer Science, University of Louisville, KY, USA
  • 2017: MS.C. in Computer Science, University of Louisville, KY, USA
  • 2015: B.Eng. in Telecommunication Engineering, Sup'Com, University of Carthage, Ariana, Tunisia
  • 2012: A.S. in Applied Physics, IPEST, University of Carthage, Tunis, Tunisia
Selected Articles and Publications
  • Khmaissia, Fadoua, and Hichem Frigui. "Improving Automatic Target Recognition in Low Data Regime Using Semi-Supervised Learning and Generative Data Augmentation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023.
  • Khmaissia, Fadoua, et al. "An Unsupervised Machine Learning Approach to Assess the ZIP Code Level Impact of COVID-19 in NYC.", Healthcare Systems, Population Health, and the Role of Health-Tech, ICML 2020.
  • Khmaissia, Fadoua, et al. "Accelerating band gap prediction for solar materials using feature selection and regression techniques." Computational Materials Science 147 (2018): 304-315.
  • Khmaissia, Fadoua, et al. "Data driven modeling of magnetism in dilute magnetic semiconductors: correlation between the magnetic features of diluted magnetic semiconductors and electronic properties of the constituent atoms." Journal of Physics: Condensed Matter 31.44 (2019): 445901.
  • Frigui, Hichem, Fadoua Khmaissia, and Andrew Karem. "Feature extraction for predicting the probability of detecting buried explosive objects using GPR data." Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXIV. Vol. 11012. SPIE, 2019.
Patents

F. Khmaissia et al., Multiple input machine learning framework for anomaly detection, Application #US17/515,163

On this page