Using Large Language Models to Enhance the Reusability of Sensor Data.

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.

Usefulness of open data to determine the incidence of COVID-19 and its relationship with atmospheric variables in Spain during the 2020 lockdown.

The SARS-CoV-2 pandemic and the spread of the COVID-19 disease led to a lockdown being imposed in Spain to minimise contagion from 16 March 2020 to 1 May 2020. Over this period, measures were taken to reduce population mobility (a key factor in disease transmission). The scenario thus created enabled us to examine the impact of factors other than mobility (in this case, meteorological conditions) on the incidence of the disease, and thus to identify which environmental variables played the biggest role in the pandemic's evolution. Worthy of note, the data required to perform the study was entirely extracted from governmental open data sources. The present work therefore demonstrates the utility of such data to conduct scientific research of interest to society, leading to studies that are also fully reproducible. The results revealed a relationship between temperatures and the spread of COVID-19. The trend was that of a slightly lower disease incidence as the minimum temperature rises, i.e. the lower the minimum temperature, the greater the number of cases. Furthermore, a link was found between the incidence of the disease and other variables, such as altitude and proximity to the sea. There were no indications, however, in the study's data, of a relationship between incidence and precipitation or wind.