Discovering Characteristic Actions from On-Body Sensor Data
- 1 October 2006
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2006 10th IEEE International Symposium on Wearable Computers
Abstract
We present an approach to activity discovery, the unsupervised identification and modeling of human actions embedded in a larger sensor stream. Activity discovery can be seen as the inverse of the activity recognition problem. Rather than learn models from hand-labeled sequences, we attempt to discover motifs, sets of similar subsequences within the raw sensor stream, without the benefit of labels or manual segmentation. These motifs are statistically unlikely and thus typically correspond to important or characteristic actions within the activity. The problem of activity discovery differs from typical motif discovery, such as locating protein binding sites, because of the nature of time series data representing human activity. For example, in activity data, motifs will tend to be sparsely distributed, vary in length, and may only exhibit intra-motif similarity after appropriate time warping. In this paper, we motivate the activity discovery problem and present our approach for efficient discovery of meaningful actions from sensor data representing human activity. We empirically evaluate the approach on an exercise data set captured by a wrist-mounted, three-axis inertial sensor. Our algorithm successfully discovers motifs that correspond to the real exercises with a recall rate of 96.3% and overall accuracy of 86.7% over six exercises and 864 occurrences.Keywords
This publication has 12 references indexed in Scilit:
- A generic motif discovery algorithm for sequential dataBioinformatics, 2005
- Analyzing features for activity recognitionPublished by Association for Computing Machinery (ACM) ,2005
- COOK’S COLLAGEPublished by Springer Science and Business Media LLC ,2005
- Using multiple sensors for mobile sign language recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- PERUSE: An unsupervised algorithm for finding recurring patterns in time seriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A symbolic representation of time series, with implications for streaming algorithmsPublished by Association for Computing Machinery (ACM) ,2003
- Unsupervised clustering of ambulatory audio and videoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Real-time American sign language recognition using desk and wearable computer based videoIeee Transactions On Pattern Analysis and Machine Intelligence, 1998
- Algorithms on Strings, Trees and SequencesPublished by Cambridge University Press (CUP) ,1997
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989