Dr. Sarmad Fakhraldeen Ismail, a faculty member in the Department of Computer and Informatics Engineering at the College of Electronics Engineering, Ninevah University, has published a scientific research paper in collaboration with Prof. Dr. Erchan Aptoula of Sabancı University, Türkiye, entitled:
“Entropy-Guided Contrastive Learning for Remote Sensing Scene Classification”
The paper was published in IEEE Geoscience and Remote Sensing Letters, a journal published by the Institute of Electrical and Electronics Engineers (IEEE) and indexed in Scopus and the Web of Science Core Collection under the Science Citation Index Expanded (SCIE).
The research proposes a self-supervised contrastive learning approach that enables artificial intelligence models to learn distinctive features from satellite images without requiring manual labels during the initial training stage. The proposed method incorporates entropy, a measure of uncertainty, alongside feature similarity to improve discrimination between visually similar images and reduce classification errors in remote sensing scenes.
This scientific publication reflects the efforts of Ninevah University’s faculty members to produce specialized research that contributes to advancing artificial intelligence technologies and satellite image analysis, while expanding opportunities for research collaboration with international universities and scientific institutions.
Research Link:
https://ieeexplore.ieee.org/document/11733805