Real-time AI-enabled multimedia networking in cloud-based digital learning systems requires high-quality, low-latency data transfer for effective, continuous learning. Managing changing traffic loads and delivering multimedia content like live lectures and video lessons requires adaptive fraudulent data control. Academic Fraudulent data management systems frequently have static parameter setting, inability to foresee traffic changes, and inadequate adaptation in various cloud environments. AI Neuro-Fuzzy Inference System (ANFIS)-Based Traffic Prediction and Fraudulent data Control Framework is proposed to overcome these difficulties. Historical traffic patterns and real-time QoS indicators help the ANFIS model anticipate fraudulent data and improve transmission settings. Neural networks' learning and fuzzy logic’s interpretability provide responsive, intelligent Academic Fraudulent data control in multimedia streams. Cloud-based digital learning environments use the suggested strategy to improve video streaming QoS. Experimental findings show that the framework dramatically lowers packet loss, delay, and jitter while enhancing bandwidth usage and learner experience. This proves the ANFIS-based algorithm’s real-time adaptive fraud data handling for scalable online education systems.
Yan Xing (Tue,) studied this question.