Sharing training data among different activity classes

Authors:
Quan Kong;Takuya Maekawa
Affiliations:
Osaka University, Osaka, Japan;Osaka University, Osaka, Japan
Venue:
Proceedings of the 2013 ACM conference on Pervasive and ubiquitous computing adjunct publication
Year:
2013

Citing 8
Cited 0

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
Exploring semi-supervised and active learning for activity recognition

ISWC '08 Proceedings of the 2008 12th IEEE International Symposium on Wearable Computers
Semi-Supervised Learning

Semi-Supervised Learning
Unsupervised Activity Recognition with User's Physical Characteristics Data

ISWC '11 Proceedings of the 2011 15th Annual International Symposium on Wearable Computers
Enabling large-scale human activity inference on smartphones using community similarity networks (csn)

Proceedings of the 13th international conference on Ubiquitous computing
Optimizing the cauchy-schwarz PDF distance for information theoretic, non-parametric clustering

EMMCVPR'05 Proceedings of the 5th international conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Object-based activity recognition with heterogeneous sensors on wrist

Pervasive'10 Proceedings of the 8th international conference on Pervasive Computing
On the use of brain decoded signals for online user adaptive gesture recognition systems

Pervasive'10 Proceedings of the 8th international conference on Pervasive Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a new activity recognition system for the daily activity by using a generative/discriminative hybrid model that can learn an activity classification model with small quantities of training data by sharing training data among different activity classes. Many existing activity recognition studies employ a supervised machine learning approach and thus require an end user's labeled training data, this approach places a large burden on the user. In this study, we assume that a user wears sensors (accelerometers) on several parts of the body such as the wrist, waist, and thigh, and by sharing sensor data obtained from only selected accelerometers (e.g., only waist and thigh sensors) among two different activity classes based on a sensor data similarity measure, the quantities of training data can be increased. For further reduction of the burden on the user, we also adopt semi-supervised approach to train the classifier in our study.