Text Classification from Labeled and Unlabeled Documents using EM
Machine Learning - Special issue on information retrieval
SoundButton: Design of a Low Power Wearable Audio Classification System
ISWC '03 Proceedings of the 7th IEEE International Symposium on Wearable Computers
Mining models of human activities from the web
Proceedings of the 13th international conference on World Wide Web
A survey of mobile phone sensing
IEEE Communications Magazine
Audio-based context recognition
IEEE Transactions on Audio, Speech, and Language Processing
Recognizing Daily Life Context Using Web-Collected Audio Data
ISWC '12 Proceedings of the 2012 16th Annual International Symposium on Wearable Computers (ISWC)
Towards scalable activity recognition: adapting zero-effort crowdsourced acoustic models
Proceedings of the 12th International Conference on Mobile and Ubiquitous Multimedia
| Hi-index | 0.00 |
The growing ubiquity of sensors in mobile phones has opened many opportunities for personal daily activity sensing. Most context recognition systems require a cumbersome preparation by collecting and manually annotating training examples. Recently, mining online crowd-generated repositories for free annotated training data has been proposed to build context models. A crowd-generated dataset can capture a large variety both in terms of class number and in intra-class diversity, but may not cover all user-specific contexts. Thus, performance is often significantly worse than that of user-centric training. In this work, we exploit for the first time the combination of both crowd-generated audio dataset available in the web and unlabeled audio data obtained from users' mobile phones. We use a semi-supervised Gaussian mixture model to combine labeled data from the crowd-generated database and unlabeled personal recording data. Hereby we refine generic knowledge with data from the user to train a personalized model. This technique has been tested on 7 users on mobile phones with a total data of 14 days and up to 9 context classes. Preliminary results show that a semi-supervised model can improve the recognition accuracy up to 21%.