Technologies have driven big data collection across many fields, such as genomics and business intelligence. This results in a significant increase in variables and data points (observations) collected and stored. Although this presents opportunities to better model the relationship between predictors and the response variables, this also causes serious problems during data analysis, one of which is the multicollinearity problem. The two main approaches used to mitigate multicollinearity are variable selection methods and modified estimator methods. However, variable selection methods may negate efforts to collect more data as new data may eventually be dropped from modeling, while recent studies suggest that optimization approaches via machine learning handle data with multicollinearity better than statistical estimators. Therefore, this study details the chronological developments to mitigate the effects of multicollinearity and up-to-date recommendations to better mitigate multicollinearity.

No abstract

No abstract

Despite advancements in the Internet of Things (IoT) and social networks, developing an intelligent service discovery and composition framework in the Social IoT (SIoT) domain remains a challenge. In the IoT, a large number of things are connected together according to the different objectives of their owners. Due to this extensive connection of heterogeneous objects, generating a suitable recommendation for users becomes very difficult. The complexity of this problem exponentially increases when additional issues, such as user preferences, autonomous settings, and a chaotic IoT environment, must be considered. For the aforementioned reasons, this paper presents an SIoT architecture with a personalized recommendation framework to enhance service discovery and composition. The novel contribution of this study is the development of a unique personalized recommender engine that is based on the knowledge–desire–intention model and is suitable for service discovery in a smart community. Our algorithm provides service recommendations with high satisfaction by analyzing data concerning users’ beliefs and surroundings. Moreover, the algorithm eliminates the prevalent cold start problem in the early stage of recommendation generation. Several experiments and benchmarking on different datasets are conducted to investigate the performance of the proposed personalized recommender engine. The experimental precision and recall results indicate that the proposed approach can achieve up to an approximately 28% higher F-score than conventional approaches. In general, the proposed hybrid approach outperforms other methods.

No abstract