فهرست نشریات علمی دسترسی آزاد ایران

The explosion of Internet of Things (IoT) devices has created enormous amounts of real-time data, requiring sophisticated Data Mining Methods (DMT) that can rapidly extract valuable insights. Managing the computational complexity of processing high data volumes, integrating various IoT data formats, and ensuring that the system can scale are among the most significant issues. Fuzzy Dynamic Adaptive Classifier Optimization Analysis (FDACOA) is a method that has been suggested as an approach to the difficulties caused by changes in data patterns, processing in real-time, and data heterogeneity. By incorporating Adaptive Fuzzy Logic (AFL) and heuristic optimization, FDACOA enhances data classification accuracy and efficiency while simultaneously assuring that the algorithm can adapt to changes in data streams. This adaptability is crucial in IoT applications, where data fluctuation might affect analysis quality. FDACOA uses dynamic adaptation to alter classifier parameters based on real-time feedback to improve prediction accuracy and reduce computing costs. An optimization layer fine-tunes fuzzy rules and membership functions to optimize performance across data situations. Simulation analyses proved the algorithm's capacity to classify with high accuracy and low computational cost. Smart healthcare, predictive maintenance in industrial IoT, and intelligent transportation systems use FDACOA for real-time decision-making and data-driven insights. FDACOA is a viable approach for dynamic data mining in IoT-enabled big data contexts because of its faster, more accurate, and more adaptable simulation results.