A Hybrid Trusted Knowledge Infusion Recommendation System for IoT-Based Applications
Partibha Ahlawat, Chhavi Rana · 2023
Technological evolutions always give substitute solutions for the betterment. In today”s ubiquitous web-based informatic scenario, it is very difficult to poke the purposeful information. But Recommender Systems as information filtering systems do this very effectively and significantly. There is a wide range of recommender systems applicable in many divergent areas. Internet of Things (IoT) as a seamlessly integrated platform of cyber world and physical world contributing an important role in business world, public and private sectors, maintenance and security, researches, healthcare, manufacturing sector and transportations etc. In IoT also, Recommender Systems can be applied to feature personalized and favorites things or services to the customers. Machine learning techniques are more desirable IoT-based recommendations because they can put together the attributes like dynamicity, scalability, and trust in recommendation. In this paper, firstly we introduce IoT Recommender Systems and their contrast nature with the traditional recommendations. We also propose a new hybrid framework for IoT recommendations using a trusted knowledge infusion model. We end the paper with the discussions of the results.