Enhancing intrusion detection using wireless sensor networks: A novel ahp-madm aggregated multiple type 3 fuzzy logic-based k-barriers prediction system

In an evolving defense landscape with persistent security threats, enhancing Wireless Sensor Networks (WSN) for border security and advancing Intrusion Detection Systems (IDS) are vital for national defense and data integrity. In this research, we present a structured and innovative Analytical Hierarchy Process (AHP) Multi attribute Decision Making (MADM) Aggregated Multiple Type 3 Fuzzy Logic (IT3FLS) approach for the accurate prediction of the number of k-barriers for fast intrusion detection and prevention within WSN. Four possible features—the rectangular region, the detecting sensors range, the transmission range of the sensors, and the number of sensors for uniform sensor distribution—were used in the training and evaluation of the suggested model. Using Monte Carlo simulation, these traits are retrieved. This methodology outlined in four-stages. In Stage 1, it constructs Multiple IT3FLS through data collected from simulations. Stage 2 rigorously evaluates IT3FLS models using statistical measures, culminating in a performance matrix. Stage 3 integrates this matrix, enhancing understanding via the AHP-MADM to assign weights. In Stage 4, these weights optimize predictions through a weighted aggregation method. The system's results significantly enhance the accuracy of k-barrier predictions in intrusion detection. The model demonstrates its proficiency with a remarkable correlation coefficient (R) of 0.997, a minimal root mean square error (RMSE) of 5.36 and low bias of 1.7. Furthermore, the research assesses the proposed system's performance against multiple benchmark methods, confirming its superior accuracy and computational efficiency.