Detecting activities from body-worn accelerometers via instance-based algorithms

Authors:
Nicola Bicocchi;Marco Mamei;Franco Zambonelli
Affiliations:
Dipartimento di Scienze e Metodi dell'Ingegneria, University of Modena and Reggio, Emilia 42100, Italy;Dipartimento di Scienze e Metodi dell'Ingegneria, University of Modena and Reggio, Emilia 42100, Italy;Dipartimento di Scienze e Metodi dell'Ingegneria, University of Modena and Reggio, Emilia 42100, Italy
Venue:
Pervasive and Mobile Computing
Year:
2010

Citing 19
Cited 3

Machine learning in automated text categorization

ACM Computing Surveys (CSUR)
Activity and Location Recognition Using Wearable Sensors

IEEE Pervasive Computing
Context Awareness by Analyzing Accelerometer Data

ISWC '00 Proceedings of the 4th IEEE International Symposium on Wearable Computers
What Shall We Teach Our Pants?

ISWC '00 Proceedings of the 4th IEEE International Symposium on Wearable Computers
Detecting outliers using transduction and statistical testing

Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
Enhancing instance-based classification with local density: a new algorithm for classifying unbalanced biomedical data

Bioinformatics
On Detecting an Emerging Class

GRC '07 Proceedings of the 2007 IEEE International Conference on Granular Computing
Gesture spotting with body-worn inertial sensors to detect user activities

Pattern Recognition
The Mobile Sensing Platform: An Embedded Activity Recognition System

IEEE Pervasive Computing
Discovery of activity patterns using topic models

UbiComp '08 Proceedings of the 10th international conference on Ubiquitous computing
80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Rise of People-Centric Sensing

IEEE Internet Computing
Sensing meets mobile social networks: the design, implementation and evaluation of the CenceMe application

Proceedings of the 6th ACM conference on Embedded network sensor systems
rfid in pervasive computing: State-of-the-art and outlook

Pervasive and Mobile Computing
Body Area Sensor Networks: Challenges and Opportunities

Computer
Pervasive Self-Learning with Multi-modal Distributed Sensors

SASOW '08 Proceedings of the 2008 Second IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshops
Activity recognition from accelerometer data

IAAI'05 Proceedings of the 17th conference on Innovative applications of artificial intelligence - Volume 3
Human Activity Recognition and Pattern Discovery

IEEE Pervasive Computing
Eigensolver methods for progressive multidimensional scaling of large data

GD'06 Proceedings of the 14th international conference on Graph drawing

"All-about" diaries: concepts and experiences

Proceedings of the 5th International Conference on Communication System Software and Middleware
Augmenting mobile localization with activities and common sense knowledge

AmI'11 Proceedings of the Second international conference on Ambient Intelligence
ADR-SPLDA: Activity discovery and recognition by combining sequential patterns and latent Dirichlet allocation

Pervasive and Mobile Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The automatic and unobtrusive identification of user activities is one of the most challenging goals of context-aware computing. This paper discusses and experimentally evaluates instance-based algorithms to infer user activities on the basis of data acquired from body-worn accelerometer sensors. We show that instance-based algorithms can classify simple and specific activities with high accuracy. In addition, due to their low requirements, we show how they can be implemented on severely resource-constrained devices. Finally, we propose mechanisms to take advantage of the temporal dimension of the signal, and to identify novel activities at run time.