Improving Experience Sampling with Multi-view User-driven Annotation Prediction (bibtex)
by Liono, Jonathan, Salim, Flora D., van Berkel, Niels, Kostakos, Vassilis and Qin, Alex Kai
Abstract:
A fundamental challenge in real-time labelling of activity data is user burden. The Experience Sampling Method (ESM) is widely used to obtain such labels for sensor data. However, in an in-situ deployment, it is not feasible to expect users to precisely label the start and end time of each event or activity. For this reason, time-point based experience sampling (without an actual start and end time) is prevalent. We present a framework that applies multi-instance and semi-supervised learning techniques to perform to predict user annotations from multiple mobile sensor data streams. Our proposed framework estimates users' annotations in ESM-based studies progressively, via an interactive pipeline of co-training and active learning. We evaluate our work using data collected from an in-the-wild data collection.
Reference:
J. Liono, F. D. Salim, N. van Berkel, V. Kostakos, A. K. Qin, "Improving Experience Sampling with Multi-view User-driven Annotation Prediction", in Proceedings of IEEE International Conference on Pervasive Computing and Communications (PerCom'19), 2019, 22-32.
Bibtex Entry:
@inproceedings{Liono2019ESMAnnotationPrediction,
	Abstract = {A fundamental challenge in real-time labelling of activity data is user burden. The Experience Sampling Method (ESM) is widely used to obtain such labels for sensor data. However, in an in-situ deployment, it is not feasible to expect users to precisely label the start and end time of each event or activity. For this reason, time-point based experience sampling (without an actual start and end time) is prevalent. We present a framework that applies multi-instance and semi-supervised learning techniques to perform to predict user annotations from multiple mobile sensor data streams. Our proposed framework estimates users' annotations in ESM-based studies progressively, via an interactive pipeline of co-training and active learning. We evaluate our work using data collected from an in-the-wild data collection.},
	Author = {Liono, Jonathan and Salim, Flora D. and van Berkel, Niels and Kostakos, Vassilis and Qin, Alex Kai},
	Booktitle = {Proceedings of IEEE International Conference on Pervasive Computing and Communications},
	Doi = {10.1109/PERCOM.2019.8767394},
	Location = {PerCom'19},
	Pages = {22-32},
	Title = {Improving Experience Sampling with Multi-view User-driven Annotation Prediction},
	Type = {Conference Paper},
	Url = {https://nielsvanberkel.com/files/publications/percom2019a.pdf},
	Year = {2019}}
Powered by bibtexbrowser