Indoor Occupancy Detection and Estimation using Machine Learning and Measurements from an IoT LoRa-based Monitoring System

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

12 Downloads (Pure)

Resumé

In this paper, we present results on the application of machine learning to the detection of human presence and estimation of the number of occupants in our offices using data from an IoT LoRa-based indoor environment monitoring system at Aalborg University, Denmark. We cast the problem as either binary or multi-class classification and apply a two-layer feed forward neural network to the data. The data used for training, validation and testing of the network comprises of environmental data from the IoT sensors and manual recordings of the door and window states. Results show that the classifier is able to correctly determine occupancy of our offices from the IoT sensor measurements with accuracy up to 94.6% and 91.5% for the binary (presence or absence of persons) and multi-class (no person, one person or two or more persons) problems, respectively. Our analysis also shows that occupancy detection with a network trained either in another room or with single environmental parameter is also possible but with less accuracy.
OriginalsprogEngelsk
Titel2019 Global IoT Summit (GIoTS)
Antal sider5
ForlagIEEE
Publikationsdato18 jun. 2019
ISBN (Trykt)978-1-7281-2172-7
ISBN (Elektronisk)978-1-7281-2171-0
DOI
StatusUdgivet - 18 jun. 2019
Begivenhed2019 Global IoT Summit - Aarhus, Danmark
Varighed: 17 jun. 201921 jun. 2019
https://www.globaliotsummit.org/

Konference

Konference2019 Global IoT Summit
LandDanmark
ByAarhus
Periode17/06/201921/06/2019
Internetadresse

Fingerprint

Learning systems
Monitoring
Feedforward neural networks
Sensors
Classifiers
Testing
Internet of things

Emneord

    Citer dette

    @inproceedings{6063b599c1c14f0d9505c26002922944,
    title = "Indoor Occupancy Detection and Estimation using Machine Learning and Measurements from an IoT LoRa-based Monitoring System",
    abstract = "In this paper, we present results on the application of machine learning to the detection of human presence and estimation of the number of occupants in our offices using data from an IoT LoRa-based indoor environment monitoring system at Aalborg University, Denmark. We cast the problem as either binary or multi-class classification and apply a two-layer feed forward neural network to the data. The data used for training, validation and testing of the network comprises of environmental data from the IoT sensors and manual recordings of the door and window states. Results show that the classifier is able to correctly determine occupancy of our offices from the IoT sensor measurements with accuracy up to 94.6{\%} and 91.5{\%} for the binary (presence or absence of persons) and multi-class (no person, one person or two or more persons) problems, respectively. Our analysis also shows that occupancy detection with a network trained either in another room or with single environmental parameter is also possible but with less accuracy.",
    keywords = "Machine Learning, Occupancy detection, IoT applications, LoRa, Neural networks",
    author = "Adeogun, {Ramoni Ojekunle} and Ignacio Rodriguez and Mohammad Razzaghpour and Gilberto Berardinelli and Christensen, {Per Hartmann} and Preben Mogensen",
    year = "2019",
    month = "6",
    day = "18",
    doi = "10.1109/GIOTS.2019.8766374",
    language = "English",
    isbn = "978-1-7281-2172-7",
    booktitle = "2019 Global IoT Summit (GIoTS)",
    publisher = "IEEE",
    address = "United States",

    }

    Indoor Occupancy Detection and Estimation using Machine Learning and Measurements from an IoT LoRa-based Monitoring System. / Adeogun, Ramoni Ojekunle; Rodriguez, Ignacio; Razzaghpour, Mohammad; Berardinelli, Gilberto; Christensen, Per Hartmann; Mogensen, Preben.

    2019 Global IoT Summit (GIoTS). IEEE, 2019.

    Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

    TY - GEN

    T1 - Indoor Occupancy Detection and Estimation using Machine Learning and Measurements from an IoT LoRa-based Monitoring System

    AU - Adeogun, Ramoni Ojekunle

    AU - Rodriguez, Ignacio

    AU - Razzaghpour, Mohammad

    AU - Berardinelli, Gilberto

    AU - Christensen, Per Hartmann

    AU - Mogensen, Preben

    PY - 2019/6/18

    Y1 - 2019/6/18

    N2 - In this paper, we present results on the application of machine learning to the detection of human presence and estimation of the number of occupants in our offices using data from an IoT LoRa-based indoor environment monitoring system at Aalborg University, Denmark. We cast the problem as either binary or multi-class classification and apply a two-layer feed forward neural network to the data. The data used for training, validation and testing of the network comprises of environmental data from the IoT sensors and manual recordings of the door and window states. Results show that the classifier is able to correctly determine occupancy of our offices from the IoT sensor measurements with accuracy up to 94.6% and 91.5% for the binary (presence or absence of persons) and multi-class (no person, one person or two or more persons) problems, respectively. Our analysis also shows that occupancy detection with a network trained either in another room or with single environmental parameter is also possible but with less accuracy.

    AB - In this paper, we present results on the application of machine learning to the detection of human presence and estimation of the number of occupants in our offices using data from an IoT LoRa-based indoor environment monitoring system at Aalborg University, Denmark. We cast the problem as either binary or multi-class classification and apply a two-layer feed forward neural network to the data. The data used for training, validation and testing of the network comprises of environmental data from the IoT sensors and manual recordings of the door and window states. Results show that the classifier is able to correctly determine occupancy of our offices from the IoT sensor measurements with accuracy up to 94.6% and 91.5% for the binary (presence or absence of persons) and multi-class (no person, one person or two or more persons) problems, respectively. Our analysis also shows that occupancy detection with a network trained either in another room or with single environmental parameter is also possible but with less accuracy.

    KW - Machine Learning

    KW - Occupancy detection

    KW - IoT applications

    KW - LoRa

    KW - Neural networks

    U2 - 10.1109/GIOTS.2019.8766374

    DO - 10.1109/GIOTS.2019.8766374

    M3 - Article in proceeding

    SN - 978-1-7281-2172-7

    BT - 2019 Global IoT Summit (GIoTS)

    PB - IEEE

    ER -