dc.contributor.author | Casagrande, Flavia Dias | |
dc.contributor.author | Zouganeli, Evi | |
dc.date.accessioned | 2019-12-03T15:31:44Z | |
dc.date.accessioned | 2019-12-09T14:36:22Z | |
dc.date.available | 2019-12-03T15:31:44Z | |
dc.date.available | 2019-12-09T14:36:22Z | |
dc.date.issued | 2019 | |
dc.identifier.citation | Casagrande FDC, Zouganeli E P. Activity Recognition and Prediction in Real Homes. Springer, Cham; 2019. 12 p.. Communications in Computer and Information Science | en |
dc.identifier.isbn | 978-3-030-35664-4 | |
dc.identifier.uri | https://hdl.handle.net/10642/7878 | |
dc.description.abstract | In this paper, we present work in progress on activity recognition and prediction in real homes using either binary sensor data or depth video data. We present our field trial and set-up for collecting and storing the data, our methods, and our current results. We compare the accuracy of predicting the next binary sensor event using probabilistic methods and Long Short-Term Memory (LSTM) networks, include the time information to improve prediction accuracy, as well as predict both the next sensor event and its time of occurrence using one LSTM model. We investigate transfer learning between apartments and show that it is possible to pre-train the model with data from other apartments and achieve good accuracy in a new apartment straight away. In addition, we present preliminary results from activity recognition using low resolution depth video data from seven apartments, and classify four activities – no movement, standing up, sitting down, and TV interaction – by using a relatively simple processing method where we apply an Infinite Impulse Response (IIR) filter to extract movements from the frames prior to feeding them to a convolutional LSTM network for the classification. | en |
dc.description.sponsorship | Financed by the Norwegian Research Council under the SAMANSVAR programme (247620/O70). | en |
dc.language.iso | en | en |
dc.publisher | Springer Natue | en |
dc.relation.ispartofseries | Nordic Artificial Intelligence Research and Development: Third Symposium of the Norwegian AI Society, NAIS 2019, Trondheim, Norway, May 27–28, 2019, Proceedings; | |
dc.relation.ispartofseries | Communications in Computer and Information Science;Volume 1056 | |
dc.rights | | en |
dc.subject | Smart homes | en |
dc.subject | Sequence predictions | en |
dc.subject | Time predictions | en |
dc.subject | Binary sensors | en |
dc.subject | Recurrent neural networks | en |
dc.subject | Probabilistic Methods | en |
dc.title | Activity Recognition and Prediction in Real Homes | en |
dc.type | Chapter | en |
dc.type | Peer reviewed | en |
dc.date.updated | 2019-12-03T15:31:44Z | |
dc.description.version | acceptedVersion | en |
dc.identifier.doi | https://dx.doi.org/10.1007/978-3-030-35664-4 | |
dc.identifier.cristin | 1756239 | |
dc.source.isbn | 978-3-030-35664-4 | |