|
Authors:
Angga Debby Frayudha, Totok Mulyono, Hamzah Agung, Riza Adya, Evy Nur Amalina, Ida Fitriana, Indonesia
|
|
Abstract:
Background - IoT research on intelligent service systems is
currently trending. IoT generates various kinds of data from sensors or
smartphones. The data generated from IoT can become more useful and actionable
if data analysis is performed.
Objective - Predictive analytics with IoT is a part of data
analysis that aims to predict a solution. The utilization of this analysis
produces innovative applications in various fields with various predictive
analytic methods or techniques.
Research Methodology - This research
uses Systematic Literature Review (SLR) to understand the research trends,
methods, and architectures used in predictive analytics with IoT. So the first
step is to determine the research question (RQ) then search for some literature
published in popular journal databases namely IEEE Xplore, Scopus and ACM from
2015 - 2023.
Findings - The results of the review of thirty (30) selected
articles, there are several research fields that are trending, namely
Transportation, Agriculture, Health, Industry, Smart Home, and Environment. The
most researched field is agriculture. Predictive analytics with IoT uses
methods that vary according to the data conditions used. There are five most
widely used methods, namely Bayesian Network (BN), Artificial Neural Network
(ANN), Recurrent Neural Network (RNN), Neural Network (NN), and Support Vector
Machines (SVM). Some studies have also proposed architectures that use
predictive analytics with IoT.
Managerial Implications - This research
can help the government in designing policies and regulations that support the
use of IoT technology in predictive analytics. This can help promote innovation
in public services, such as disaster prediction and mitigation, environmental
monitoring, and more efficient transportation management.
|
