IoT Wallet: Machine Learning-based Sensor Portfolio Application

Sep 23, 2020·
Petar Šolić
,
Ante Lojić Kapetanović
,
Tomislav Županović
,
Ivo Kovačević
Toni Perković
Toni Perković
,
Petar Popovski

Abstract

In this paper an application for building sensor wallet is presented. Currently, given system collects sensor data from The Things Network (TTN) cloud system, stores the data into the Influx database and presents the processed data to the user dashboard. Based on the type of the user, data can be viewed-only, controlled or the top user can register the sensor to the system. Moreover, the system can notify users based on the rules that can be adjusted through the user interface. The special feature of the system is the machine learning service that can be used in various scenarios and is presented throughout the case study that gives a novel approach to estimate soil moisture from the signal strength of a given underground LoRa beacon node.

Type

Publication

International Conference on Smart and Sustainable Technologies (SpliTech), 1–5

Status

Peer-reviewed Open access
publications
Toni Perković
Authors
Toni Perković
Full Professor
I am a Full Professor in the Department of Electronics and Computing at the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture (FESB), University of Split, Croatia, where I teach wireless network security, wireless communication networks, data science and reinforcement learning. My research spans information security, applied cryptography and the Internet of Things. Before returning to FESB in 2020, I was an assistant and then associate professor at the University Department of Forensic Sciences in Split. I co-founded the SpliTech international conference and serve on the editorial board of the Journal of Communications Software and Systems.