Water quality instability is a major constraint in giant freshwater prawn farming, particularly in land-based systems where fluctuations in environmental conditions can reduce survival and productivity. This study applied an integrated CRITIC–TOPSIS framework to evaluate alternative water quality management strategies for giant freshwater prawn farming under multiple operational and production criteria. Four alternatives, representing different levels of management sophistication from conventional monitoring to a full IoT-based real-time monitoring system, were assessed using five criteria: Cost, Labor, Energy, Survival, and Yield. The CRITIC method was used to determine objective criterion weights, while TOPSIS was employed to rank the alternatives according to their relative closeness to the ideal solution. The CRITIC results indicated that Cost (0.2523) and Energy (0.2506) were the most influential criteria, followed by Labor (0.1681), whereas Survival and Yield each received a weight of 0.1645. The TOPSIS results showed that Alternative 4 was the most suitable option, with the highest closeness coefficient (0.5534), followed by Alternative 3 (0.5084), Alternative 2 (0.4583), and Alternative 1 (0.4466). Alternative 4 also achieved the best production performance, with 93% survival, 4.65 kg yield, and the lowest labor requirement (17 h), although it required the highest cost (13,746 Baht) and energy consumption (35 kWh). Compared with the conventional strategy, Alternative 4 improved survival by 11 percentage points, increased yield by 0.55 kg, and reduced labor by 18 h. The findings demonstrate that the integrated CRITIC–TOPSIS framework can serve as an effective decision-support tool for selecting water quality management strategies in freshwater prawn farming by balancing resource requirements and production outcomes. Under the present evaluation framework, the IoT-based real-time monitoring strategy was identified as the most suitable alternative for land-based giant freshwater prawn farming.

Fake news has become a major problem affecting people, society, the economy and national security. This work proposes a combined deep learning model based on the ideal distance weighting method for fake news detection. The proposed model was validated on the ISOT and COVID-19 fake news datasets. Firstly, the ISOT and COVID-19 fake news datasets were collected. Secondly, the training-based models were used to provide accuracy values. After that, these values were transformed into criteria weights using the new ideal distance weighting method. Finally, the prediction value of the proposed model is calculated by the criteria weights. The results show that the proposed method is effective to distinguish the fake news datasets.