The application of artificial intelligence and the Internet of Things in optimizing the effectiveness of agile teaching

Agile teaching requires adaptability, personalization, efficiency. Dynamic changes are made possible by integrating Internet of Things (IoT) and artificial intelligence (AI) technology. This ensures optimal educational delivery and promotes interactive, student-centered smart learning environments. Research aims to maximize the effectiveness of Agile teaching by leveraging the integration of AI and IoT. Classroom data were collected using IoT devices, including smart boards, environmental sensors, student wearables, alongside digital learning systems. Raw IoT and interaction data were preprocessed using Kalman filtering to remove noise, followed by normalization to ensure uniformity and synchronization across multiple channels. Principal Component Analysis (PCA) was applied to extract key features, reducing dimensionality while retaining essential information. This research proposes the Addax optimization-mutated Tri-Autoencoder Ensemble Machine (AO-TAEM) approach to improve prediction accuracy, capture temporal dependencies, and enhance anomaly detection in learning behaviors, while Addax optimization improves convergence and accuracy. TAEM provides a robust computational framework for adaptive and intelligent learning environments. MATLAB-based implementation demonstrated significant improvements in predicting student performance, engagement, and adaptive teaching strategies. The results demonstrate that the AO-TAEM technique outperforms multimodal baseline topologies, yielding noteworthy outcomes with F1-score, precision, accuracy, and recall ranging between 90 and 95%. The integration of AI and IoT systems optimizes autoencoder ensembles for agile teaching. Unlike existing AI-IoT-based agile teaching models, the proposed AO-TAEM uniquely integrates AO with a tri-autoencoder ensemble, enabling adaptive weight mutation, enhanced temporal learning, and improved convergence for real-time educational analytics. Model establishes a scalable, intelligent education model, ensuring dynamic personalization, real-time responsiveness, and sustainable improvements in modern learning environments.