Vishwanath Kapoor and Mathew Wintters surveyed AI and machine learning (ML) integration within Internet of Things (IoT) ecosystems in their 2026 paper published in the International Journal For Multidisciplinary Research. The review categorizes common learning paradigms applied to IoT, such as supervised, unsupervised, and reinforcement learning, alongside deep learning, federated learning (decentralized training across devices), and TinyML (machine learning for resource-constrained hardware).

Practical applications span data analytics, predictive maintenance, and operational improvements in healthcare, industry, and smart cities. The authors highlight security enhancements, specifically intrusion and anomaly detection, as well as emerging uses of large language models (LLMs) and agentic systems for network management. Key challenges identified include data quality, resource limitations, privacy concerns, and autonomous system reliability.

Vishwanath Kapoor and Mathew Wintters surveyed AI and machine learning (ML) integration within Internet of Things (IoT) ecosystems in their 2026 paper published in the International Journal For Multidisciplinary Research. The review categorizes common learning paradigms applied to IoT, such as supervised, unsupervised, and reinforcement learning, alongside deep learning, federated learning (decentralized training across devices), and TinyML (machine learning for resource-constrained hardware).

Practical applications span data analytics, predictive maintenance, and operational improvements in healthcare, industry, and smart cities. The authors highlight security enhancements, specifically intrusion and anomaly detection, as well as emerging uses of large language models (LLMs) and agentic systems for network management. Key challenges identified include data quality, resource limitations, privacy concerns, and autonomous system reliability.