Using Large Language Models to Enhance the Reusability of Sensor Data
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10045/139617
Title: | Using Large Language Models to Enhance the Reusability of Sensor Data |
---|---|
Authors: | Berenguer, Alberto | Morejón, Adriana | Tomás, David | Mazón, Jose-Norberto |
Research Group/s: | Web and Knowledge (WaKe) | Procesamiento del Lenguaje y Sistemas de Información (GPLSI) |
Center, Department or Service: | Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos |
Keywords: | Internet of Things | Sensor data | Interoperability | Data reusability | Data processing |
Issue Date: | 6-Jan-2024 |
Publisher: | MDPI |
Citation: | Berenguer A, Morejón A, Tomás D, Mazón J-N. Using Large Language Models to Enhance the Reusability of Sensor Data. Sensors. 2024; 24(2):347. https://doi.org/10.3390/s24020347 |
Abstract: | The Internet of Things generates vast data volumes via diverse sensors, yet its potential remains unexploited for innovative data-driven products and services. Limitations arise from sensor-dependent data handling by manufacturers and user companies, hindering third-party access and comprehension. Initiatives like the European Data Act aim to enable high-quality access to sensor-generated data by regulating accuracy, completeness, and relevance while respecting intellectual property rights. Despite data availability, interoperability challenges impede sensor data reusability. For instance, sensor data shared in HTML formats requires an intricate, time-consuming processing to attain reusable formats like JSON or XML. This study introduces a methodology aimed at converting raw sensor data extracted from web portals into structured formats, thereby enhancing data reusability. The approach utilises large language models to derive structured formats from sensor data initially presented in non-interoperable formats. The effectiveness of these language models was assessed through quantitative and qualitative evaluations in a use case involving meteorological data. In the proposed experiments, GPT-4, the best performing LLM tested, demonstrated the feasibility of this methodology, achieving a precision of 93.51% and a recall of 85.33% in converting HTML to JSON/XML, thus confirming its potential in obtaining reusable sensor data. |
Sponsor: | This research was funded by MCIN/AEI/10.13039/501100011033 and by the European Union Next Generation EU/PRTR as part of the projects TED2021130890B-C21 and PID2021-122263OB-C22. Alberto Berenguer has a contract for predoctoral training with “Generalitat Valenciana” and the European Social Fund, funded by grant number ACIF/2021/507. |
URI: | http://hdl.handle.net/10045/139617 |
ISSN: | 1424-8220 |
DOI: | 10.3390/s24020347 |
Language: | eng |
Type: | info:eu-repo/semantics/article |
Rights: | © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
Peer Review: | si |
Publisher version: | https://doi.org/10.3390/s24020347 |
Appears in Collections: | INV - GPLSI - Artículos de Revistas INV - WaKe - Artículos de Revistas |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
![]() | 453,59 kB | Adobe PDF | Open Preview | |
Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.