Neural and statistical techniques for remote sensing image classification

• Veröffentlicht in: PROBLEMS IN PROGRAMMING
• Datum: 2026
• Heft: 2-3
• Сторінки: 577-583
• ISSN: 1727-4907
• Автори та афіліації: Iu. Grypych — Space Research Institute NASU-NSAU; N. Kussul — NTUU "KPI"; O. Kussul — NTUU "KPI"
• Hauptverfasser: Grypych, Iu., Kussul, N., Kussul, O.
• Format: Artikel
• Sprache: Englisch
• Veröffentlicht: PROBLEMS IN PROGRAMMING 2026
• Schlagworte: UDC 52(15).003
• Online Zugang: https://pp.isofts.kiev.ua/index.php/ojs1/article/view/956
• Назва журналу: Problems in programming

This paper examines different approaches to remote sensing images classification. Included in the study are statistical approach, in particular Gaussian maximum likelihood classifier, and two different neural networks paradigms: multilayer perceptron trained with EDBD algorithm, and ARTMAP neural ne...