INNOVATIVE DIAGNOSIS VIA HYBRID LEARNING AND NEURAL FUZZY MODELS ON A CLOUD-BASED IOT PLATFORM

Abstract

Background Information: Cloud computing, artificial intelligence, and the Internet of Things have changed healthcare by providing real-time monitoring and diagnosis. Hybrid learning models combined with neural fuzzy systems improve healthcare diagnoses, especially when it comes to handling uncertainty in massive amounts of medical data gathered from IoT devices. Methods: Fuzzy logic and neural networks were combined to create a hybrid neural fuzzy learning model. Using machine learning techniques, the system gathers real-time data from Internet of Things devices, interprets it through cloud-based platforms, and forecasts normal or abnormal health situations. Medical datasets were used for the model's training and validation. Objectives: In addition to assessing the scalability of real-time data processing and the efficacy of hybrid learning models in enhancing diagnostic accuracy, the study intends to investigate the integration of IoT, cloud computing, and AI for healthcare diagnostics. Results: The hybrid model outperformed traditional AI-based diagnostic techniques, achieving 96.40% precision, 98.25% recall, and 97.89% diagnostic accuracy. Conclusion: The accuracy and efficiency of the proposed method's processing increases real- time healthcare diagnostics. Enabling dependable patient monitoring and prompt decision- making, its versatility and scalability make it appropriate for wider healthcare applications.