Paul, SuprovaPervez, TamannaRabiul Alam, Md. Golam2026-08-272026-08-272023-01-01M. M. R. N. Gazi, R. F. Nisa, N. S. Oishe, M. M. Fiona, S. M. A. Maruf and S. K. Ghosh, "Hybrid Deep Learning Framework for Rainfall Prediction: Integrating Wavelet-ARIMA, CEEMDANLSTM, and CNN-BiLSTM for Enhanced Climate Variability Analysis," 2025 International Conference on NexGen Networks and Cybernetics (IC2NC), Erode, India, 2025, pp. 781-788, doi: 10.1109/IC2NC67409.2025.11376471.97983503259042-s2.0-85166219735https://hdl.handle.net/10361/29539Since the outbreak of COVID-19, researchers around the world are trying to develop and vaccinate world communities. Selecting the suitable and cost-effective vaccine for a country is a Multi-Criteria Decision-Making (MCDM) problem involving several conflicting criteria on which the decision maker's knowledge is not precise. This work develops a Fuzzy TOPSIS approach in order to find a suitable COVID-19 vaccine. We used a total of eight well-known available vaccines and considered six main criteria based on various complexity, efficiency, and cost considerations. We evaluated the weights of numerous criteria and the ratings of each alternative vaccine by parameterizing a set of pre-defined linguistic variables using triangular fuzzy numbers. Final rankings of COVID-19 vaccines are obtained using the Fuzzy TOPSIS approach.6 Pagesen-USDeep learningAdaptation modelsClimate variabilityPredictive modelsWavelet analysisData modelsWater resourcesKeywords- rainfall predictionHybrid deep learningCEEMDAN-LSTMWavelet decompositionCNN-BiLSTMClimate variability analysisCOVID-19 (Disease)--Vaccination.Fuzzy logic.Conference Proceeding10.1109/IC3S57698.2023.10169848