Leveraging mist and fog for big data analytics in IoT environment. Issue 7 (27th July 2020)

• Record Type: Journal Article
• Authors: El‐Hasnony, Ibrahim M.; Mostafa, Reham R.; Elhoseny, Mohamed; Barakat, Sherif I.
• Is Part Of: Transactions on emerging telecommunications technologies. Volume 32:Issue 7(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-07-27
• Subjects: Telecommunication -- Periodicals; 384.05
• DOI: 10.1002/ett.4057
• Languages: English
• ISSNs: 2161-5748

Abstract

Abstract: Internet of Things (IoT) emerged as one of the leading technological advancements of our days. IoT generates enormous quantities of valuable data that need on time processing, resulting in reliable, and accurate decisions based on the Internet of Things vision. The quality of the generated data is inadequate, incomplete, uncertain, and produced from multiple sources. Although cloud servers can analyze and store enormous data, they need a lot of time to send full‐size data for storage and analysis as well as the high overhead they have that not satisfactory in many applications. This article provides a systematic way to review the IoT environment according to big data analytics together with limitations and challenges. Moreover, a cloud‐fog‐mist combination for handling IoT data concerning centralized and distributed data mining is explained. A proposed hybrid real‐time remote patient monitoring framework introduced that consists of the integration among the mist, fog, and cloud for healthcare treatment, which remote‐monitors patients continuously. In addition, Reduced‐Error Pruning tree (REPtree), MultiLayer Perceptron, naïve Bayes, and Sequential Minimal Optimization algorithms have applied to "Gas sensors for home activity monitoring" dataset to demonstrate the feasibility of traditional data mining algorithms to IoT data. The results showed that the REPtree algorithm achieved better accuracy against others with accuracy ranged between 90.66% and 93.6% according to the size of the data used in the study. Still, for the time metric, naive Bayes outperformed them with the lowest time between 1 and 18 seconds for building the model. Abstract : This article provides a systematic way to review the IoT environment according to big data analytics together with a proposed framework for patient monitoring using the mist and fog computing. Moreover, different machine learning models are applied to "Gas sensors for home activity monitoring" dataset and resulted in the superiority of REPtree and naive Bayes thorough the accuracy and the time, respectively.