Potentialities of data processing in internet of things applications
by Arturo Cardenas_Rivero; Reyneris De_la_Paz; Jorge Portal; Cristian Duran-Faundez; Ivan Santana
International Journal of Embedded Systems (IJES), Vol. 14, No. 5, 2021

Abstract: This paper proposes an internet of things application with intelligent data processing, which can be applied in several industrial sectors. The designed application allows the data collection, storage and visualisation. An IoT gateway is implemented on a Raspberry Pi and functions as a local server. The IoT gateway allows access to the information from the sensor nodes, even without an internet connection. The information processing is performed on a big data server in the cloud, using Apache Spark, Apache Kafka and the IoT ThingsBoard platform. In previous work, the IoT application architecture was implemented in tomato crop greenhouses and a database was obtained. The objective of this research is to evaluate the potentialities of processing the acquired data using the proposed IoT application architecture. Additionally, two public databases are used for experimental tests of the intelligent data processing. Different machine learning algorithms available in Spark was applied and a selection of those that provide the best results is made.

Online publication date: Thu, 13-Jan-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Embedded Systems (IJES):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com