Skip to main content

A technological framework for data-driven IoT systems: application on landslide monitoring.

Karunarathne, S.M., Dray, M., Popov, L., Butler, M., Pennington, C. and Angelopoulos, C.M., 2020. A technological framework for data-driven IoT systems: application on landslide monitoring. Computer Communications, 154 (March), 298-312.

Full text available as:

[img] PDF
A technological framework for data driven IoT systems.pdf - Accepted Version
Restricted to Repository staff only until 15 March 2021.

3MB

Abstract

The emergence of the paradigm of the Internet of Things has underpinned the development of data-driven cyber-physical systems that collect and process data that is dense both in space and time. The application areas of such data-driven IoT systems are numerous and their socio-economic impact of great importance as they enable the monitoring and management of processes in sectors ranging from urban management to management of the natural environment. In this work, we introduce and detail an end-to-end technological framework for data-driven IoT systems for landslide monitoring. The framework is articulated in three tiers – namely data acquisition, data curation and data presentation. For each tier we present and detail its design and development aspects; from the IoT hardware design and the wireless communication technologies of choice, to how Big Data infrastructure and Machine Learning components can be combined to support a sophisticated presentation tier that delivers the true added value of a system to its final users. The framework is validated, extended and fine-tuned by means of two pilots at locations experiencing the impact of different landslide types and activity. This work qualitatively improves upon existing methods of landslide monitoring and showcases how data-driven IoT systems can pave new pathways for interdisciplinary research as well as generate positive impact on modern societies.

Item Type:Article
ISSN:0140-3664
Group:Faculty of Science & Technology
ID Code:33508
Deposited By: Unnamed user with email symplectic@symplectic
Deposited On:25 Feb 2020 16:32
Last Modified:28 Apr 2020 15:55

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -