@article {10.3844/jcssp.2025.2834.2849,
article_type = {journal},
title = {Latent Feature-Based Trust-Aware Model for Service Delegation in Social Internet of Things (SIoT)},
author = {Rahul, and Venkatesh, and Basapur, Satish B},
volume = {21},
number = {12},
year = {2026},
month = {Jan},
pages = {2834-2849},
doi = {10.3844/jcssp.2025.2834.2849},
url = {https://thescipub.com/abstract/jcssp.2025.2834.2849},
abstract = {The integration of social networking concepts into the Internet of Things (IoT) paradigm has given rise to Social IoT (SIoT) ecosystems, aiming to address challenges related to network navigation, service discovery, and service composition. A fundamental issue in SIoT is the careful selection of trustworthy devices that provide services. A service provider can offer multiple and diverse services, and different service providers may offer the same services with varying parameters, making it difficult for service requesters to navigate and identify the best service provider that meets their requirements. Moreover, heterogeneous devices and dynamic social relationships in SIoT networks pose challenges in recommending reliable service providers. This research focuses on identifying and recommending consistent and trustworthy service providers in SIoT. The proposed trust model evaluates interactions, friendships, community similarity, cooperativeness, hidden features of service providers and their services, and predicts uncertainties associated with service providers while assessing their trustworthiness. A set of research experiments is conducted on an available dataset to demonstrate the effectiveness and efficiency of the proposed method. The trust model leverages device interactions, cooperativeness, trustworthy relationships, usage patterns, and uncertainty features of service providers. The Root Mean Square Error (RMSE) and Mean Square Error (MSE) metrics are used to evaluate the accuracy of service provider recommendations in the SIoT environment. The proposed model achieves lower RMSE and MSE values, indicating improved recommendation performance. Additionally, the Normalized Discounted Cumulative Gain (NDCG) metric is employed to assess the quality and efficiency of the recommended service providers. The proposed trust model achieves an NDCG score of approximately 90%, demonstrating its ability to recommend highly trusted service providers effectively.},
journal = {Journal of Computer Science},
publisher = {Science Publications}
}