Akademik Məlumat İdarəetmə Sistemi
7th International Conference on Intelligent and Fuzzy Systems, INFUS 2025, İstanbul, Turkey, 29 - 31 July 2025, vol.1531 LNNS, pp.465-473, (Full Text)
In this study, a hybrid model based on fuzzy logic and artificial neural networks (ANN) was proposed to predict and optimize the storage and transportation conditions of pharmaceutical products. The model effectively accounts for both the uncertainty of environmental and logistical variables using fuzzy inference, as well as the complex nonlinear relationships between them using ANN. The integration of fuzzy logic allows for the semantic interpretation of expert knowledge by evaluating input data such as temperature, humidity, trajectory, and storage conditions. The defazzified risk value obtained using the fuzzy system is then used as additional input data for the neural network, which increases the model’s learning ability and prediction accuracy. The experimental results showed that the model is able to accurately predict short-term changes in temperature and humidity under various operating scenarios. In addition, the model is responsive to changes in the level of risk, which is important for timely intervention in pharmaceutical logistics. The proposed approach not only increases the efficiency of forecasting, but also increases the interpretability of the decision-making process, which makes it widely applicable for real-world use in pharmaceutical applications.