Mobile Ad Hoc Networks: A Public Adoption and Risk Management Model Leveraging the Axiom Methodology and Machine Learning Optimization

A Mobile Ad Hoc Network (MANET) is a decentralized wireless network of mobile nodes that self-configure without fixed infrastructure. Initially deployed for military and emergency scenarios, recent research highlights MANETs' potential as an alternative to traditional Internet Service Providers (ISPs), particularly during crises like the COVID-19 pandemic. This paper advances the MANET Axiom Risk Methodology, refining its risk assessment framework with machine learning optimization and dynamic weighting mechanisms. By leveraging Decision Tree and Naive Bayes algorithms, the optimized methodology achieves a 20% improvement in risk assessment accuracy and a 30% reduction in computational overhead, enabling real-time operation in low-resource environments. The resulting system combines robust risk profiling with an intuitive interface, empowering users to evaluate MANET connections confidently. This approach enhances security, scalability, and accessibility, positioning MANETs as a resilient alternative for public adoption during critical network disruptions.