An Intelligent Disaster Prediction in Communication Network Using OAN-ANFIS Technique Based on TEM Feature Selection Approach

Abstract

Abstract: Due to facility damage and a lack of power, natural disasters disrupt vital services. When the main nodes of a hierarchical network, such as a cellular communication system, are compromised or overloaded, major communication failures frequently happen over a large geographic area. High throughput satellite (HTS) is one of the best options for disaster management as an alternate communication capability since it offers effective communication for a large area regardless of the availability of conventional terrestrial infrastructures. Conventional HTS, on the other hand, uses fixed beam bandwidth and connections for relaying data, making it ineffective when communication demand spikes in a disaster area. Therefore, the work has developed an Intelligent Disaster prediction in a communication network that alters and empowers the decision-making process to avoid a False alarm rate toward transmitting data to the digital world in a better way using the OAN-ANFIS technique based on the TEM Feature selection approach. To limit the likelihood of inaccuracy, the suggested framework first preprocesses the data by transforming unstructured data into arranged manner. The preprocessing technique handles missing values, scaling, and addressing imbalanced data. Following that, the preprocessed data is subjected to Feature selection using the TEM technique, which combines three metaheuristic algorithms, namely Xinit-FSO, LCV-ChoA, and AL-HDC, to pick the optimum feature to train the node recognition model. To obtain a high accuracy rate, the proposed Feature selection technique captures the most known feature to train the model. Finally, OAN-ANFIS predicts the various Disaster limitations of communication. The tentative outcome suggests that the proposed framework has high adaptive predictive compression approaches and achieves higher accuracy than existing strategies.