L-CAS domotic sensors Dataset


This dataset contains domotic sensor data recorded at Lincoln Centre for Autonomous Systems (L-CAS) at the University of Lincoln, UK. Data was continuously recorded in two mongo databases, one for 2016 ( from 1st of Jul to 12th of October) and one for 2017 (from 25 Jan).  Each database contains one collection with data from zwave sensors and an uniscan multisensor connected to the domotic network.


This dataset provides:

    Environmental data with more than 800k data entries

    Ground truth is provided by Long-Term activity image datasets  under request.


If you are considering using this data, please reference the following:

Fernandez-Carmona M., Cosar S., Coppola C. and Bellotto N. (2017) “Entropy-based Abnormal Activity Detection Fusing RGB-D and Domotic Sensors”. IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2017). [BibTeX] [©]

Recording platform:

Recordings were made using OpenHAB 1.8.3, with the following sensors:

Sensor Item field prefix location
Fibaro Wall Plug Sensor Kitchen_Plug_ Coffee machine
Fibaro Multi Sensor Kitchen_Multi_ Kitchen
Fibaro Door Sensor Toilet_Door_ Toilet door
Everspring Door Sensor Fridge_Door_ Fridge
Philio Multi Sensor Workshop_Multi_ Workshop door
Zenhou Wall Plug Sensor Printer_Plug_ Printer
Everspring Door Sensor External_Door_ External main door
Fibaro motion Sensor Lounge_Multi_ Lounge
Aeotec Multi Sensor 6 Office1_Multi_ Office area
Philio multi sensor Entry_Multi_ Entry door
Uniscan environmental sensor Env_ Robot

Download and Related Software*

Mongo databases can be downloaded here: 2016 Database and 2017 Database. Additionally, we use this dataset to develop models of human activity. A ROS implementation is available here: Wavelet-based Temporal Forecasting Action Server

*If you consider using these, please send us an email (Manuel Fernandez-Carmona or Nicola Bellotto) telling a little more about your ideas.


This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

Copyright (c) 2016 Manuel Fernandez-Carmona, and Nicola Bellotto.


This work was funded in part by the EU Horizon 2020 project ENRICHME, H2020-ICT-2014-1, Grant agreement no.: 643691.