Wifi-based human activity recognition using Raspberry Pi.
Forbes, Glenn; Massie, Stewart; Craw, Susan
Doctor Stewart Massie email@example.com
Professor Susan Craw firstname.lastname@example.org
Ambient, non-intrusive approaches to smart home health monitoring, while limited in capability, are preferred by residents. More intrusive methods of sensing, such as video and wearables, can offer richer data but at the cost of lower resident uptake, in part due to privacy concerns. A radio frequency-based approach to sensing, Channel State Information (CSI),can make use of low cost off-the-shelf WiFi hardware. We have implemented an activity recognition system on the Raspberry Pi 4, one of the world’s most popular embedded boards. We have implemented an classiﬁcation system using the Pi to demonstrate its capability for activity recognition. This involves performing data collection, interpretation and windowing, before supplying the data to a classiﬁcation model. In this paper, the capabilities of the Raspberry Pi 4 at performing activity recognition on CSI data are investigated. We have developed and publicly released a data interaction framework, capable of interpreting, processing and visualising data from a range of CSI-capable hardware. Furthermore, CSI data captured for these experiments during various activity performances have also been made publically available. We then train a Deep Convolutional LSTM model to classify the activities. Our experiments, performed in a small apartment, achieve 92% average accuracy on 11 activity classes.
FORBES, G., MASSIE, S. and CRAW, S. 2020. Wifi-based human activity recognition using Raspberry Pi. In Alamaniotis, M. and Pan, S. (eds.) Proceedings of Institute of Electrical and Electronics Engineers (IEEE) 32nd Tools with artificial intelligence international conference 2020 (ICTAI 2020), 9-11 Nov 2020, [virtual conference]. Piscataway: IEEE [online], pages 722-730. Available from: https://doi.org/10.1109/ICTAI50040.2020.00115
|Conference Name||Institute of Electrical and Electronics Engineers (IEEE) 32nd Tools with artificial intelligence international conference 2020 (ICTAI 2020)|
|Conference Location||[virtual conference]|
|Start Date||Nov 9, 2020|
|End Date||Nov 11, 2020|
|Acceptance Date||Sep 1, 2020|
|Online Publication Date||Dec 24, 2020|
|Publication Date||Dec 31, 2020|
|Deposit Date||Sep 11, 2020|
|Publicly Available Date||Sep 11, 2020|
|Publisher||Institute of Electrical and Electronics Engineers|
|Book Title||Proceedings of IEEE 32nd Tools with artificial intelligence international conference (ICTAI 2020)|
|Keywords||Activity recognition; Smart home; IoT; RF|
FORBES 2020 Wifi-based
Publisher Licence URL
You might also like
Representing temporal dependencies in smart home activity recognition for health monitoring.
Representing temporal dependencies in human activity recognition.
Fall prediction using behavioural modelling from sensor data in smart homes.
Case based reasoning as a model for cognitive artificial intelligence.
FITsense: employing multi-modal sensors in smart homes to predict falls.