Home
Home
    • Home
    • About us
      • About CTAC
      • Organization
      • Regulation
    • People
      • Members
      • Positions available
    • Research
      • Vision
      • Research Areas
        • Construction Materials and Technologies
        • Hydraulics and Environment
        • Territory
      • Ongoing Research Projects
      • Research Projects 2018-2022
      • Past Projects
    • Facilities
      • Construction Materials and Technologies
      • Hydraulics and Environment
      • Territory
    • Publications
      • All
      • Books
      • Book Chapters
      • Papers in Scientific Journals
      • Conference Comunications
      • PhD Thesis
      • Masters Thesis
      • Journal
      • RepositoriUM
    • Education
      • Doctoral Programme Infrarisk
      • Doctoral Programme in Civil Engineering
      • Doctoral Programme in Eco Construction and Rehabilitation
      • Doctoral Programme of Solid Waste Management and Treatment
      • International Doctorate in Sustainable Built Environment
        • International Doctorate in Sustainable Built Environment
      • Master's Degree in Civil Engineering
      • Master's Degree in Sustainable Built Environment
      • Master's Degree in Urban Engineering
      • Master´s Degree in Sustainable Construction and Rehabilitation
    • Partners
    • Events
    • News
    • SITAC
    Filter

    Publications

    Papers in International JournalsChapters/ Papers in International BooksChapters/ Papers in National BooksCommunications in International ConferencesCommunications in National ConferencesMSc ThesesBooksProceedingsPatentsTechnical/ Scientific ReportsPhD Theses

    Deviation prediction and correction on low-cost atmospheric pressure sensors using a machine-learning algorithm

    TitleDeviation prediction and correction on low-cost atmospheric pressure sensors using a machine-learning algorithm
    Publication TypeCommunications in International Conferences
    Year of Publication2020
    AuthorsC. de Araújo T., Silva L. T., and Moreira A. J. C.
    Abstract

    Atmospheric pressure sensor s are important devices for several applications, incl uding environment
    monitoring and indoor positioning tracking systems. This paper proposes a method to enhance the quality of
    data obtained from low-cost atmospheric pressure sensors using a mach ine learning algorithm to predict the
    error behaviour. By using the extremely Randomized Trees algorithm, a model was trained with a reference
    sensor data for temperature and humidity and with all low-cost sensor datasets that were co-located into an
    artificial climatic chamber that simulated different climatic situations. Fifteen low-cost environmental sensor
    units, composed by five different models, were considered. They measure – together – temperature, relative
    humidity and atmospheric pressure. In the evaluation, three categories of output metrics were considered:
    raw; trained by the independent sensor data; and traine d by the low-cost sensor data. The model trained by
    the reference sensor was able to reduce the Mean Absolute Error (MAE) between atmospheric pressure sensor
    pairs by up to 67%, while the same ensemble trained with all low-cost data was able to reduce the MAE by
    up to 98%. These results suggest that low-cost environmental sensors can be a good asset if their data are
    properly processed

    Conference NameSENSORNETS
    JournalProceedings of the 9th International Conference on Sensor Networks
    Pagination41-51
    Date Published2020-02-29
    PublisherACM SIGMETRICS, IFSA and IET
    Conference LocationMalta
    DOIDoi:....
    URLhttps://www.scitepress.org/Papers/2020/89684/89684.pdf
    KeywordsCollaborative Sensing, Data Quality, Environmental monitoring, low-cost sensors, Machine learning
    RightsopenAccess
    Peer reviewedyes
    Statuspublished
    • Google Scholar
    • BibTex
    • RTF
    • XML

    About CTAC

    The Centre for Territory, Environment and Construction (CTAC) is a research unit of the School of Engineering of University of Minho (UMinho), recognised by the “FCT – Fundação para a Ciência e Tecnologia” (Foundation for Science and Technology), associated to the Department of Civil Engineering (DEC), with whom it shares resources and namely human resources.

    Currently CTAC aggregates 25 researchers holding a PhD of which 20 are faculty professors of the Civil Engineering Department. Read more


    Watch the CTAC Institutional Video

    Journal

    Research Areas of Competence

    Construction Materials and Technologies
    Hydraulics and Environment
    Territory

    News

    Contact us

    Centro de Território, Ambiente e Construção
    Escola de Engenharia da Universidade do Minho
    Campus de Azurém
    4800-058 Guimarães, Portugal

    Phone: + 351 253 510 200 (517 206)
    Fax: + 351 253 510 217

    Email: geral@ctac.uminho.pt


    Copyright 2014 CTAC Research Group in Territory, Environment and Construction
    Website Credits