Neurocomputing in logistic management for education & science industry in unstable environments & in emergency contexts

Abstract

The paper examines the application of artificial neural networks (ANN) and hybrid neurocomputing technologies in logistics management for the education and science sectors under uncertainty and crisis conditions. Traditional analytical methods are often ineffective in dynamic and unstable environments. ANN, as adaptive and self-learning systems, enable intelligent forecasting, optimization, and decision support. Their use improves the efficiency, flexibility, and resilience of logistics processes in educational and research institutions. Hybrid neurocomputing models that integrate neural networks, fuzzy logic, evolutionary algorithms, and metaheuristics enhance resource management and risk prediction. These intelligent platforms form the basis for adaptive and crisis-resistant management, supporting sustainable development of education and science systems in the era of digital transformation.