Feature selection and activity recognition from wearable sensors

Authors:
Susanna Pirttikangas;Kaori Fujinami;Tatsuo Nakajima
Affiliations:
Department of Electrical and Information Engineering, University of Oulu, Finland;Department of Computer Science, Waseda University, Japan;Department of Computer Science, Waseda University, Japan
Venue:
UCS'06 Proceedings of the Third international conference on Ubiquitous Computing Systems
Year:
2006

Citing 4
Cited 15

Introduction to statistical pattern recognition (2nd ed.)

Introduction to statistical pattern recognition (2nd ed.)
Citron: A Context Information Acquisition Framework for Personal Devices

RTCSA '05 Proceedings of the 11th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications
Analyzing features for activity recognition

Proceedings of the 2005 joint conference on Smart objects and ambient intelligence: innovative context-aware services: usages and technologies
Sentient artefacts: acquiring user’s context through daily objects

EUC'05 Proceedings of the 2005 international conference on Embedded and Ubiquitous Computing

Using physical activity for user behavior analysis

Proceedings of the 1st international conference on PErvasive Technologies Related to Assistive Environments
Implicit interaction with daily objects: applications and issues

Proceedings of the 3rd International Universal Communication Symposium
Distributed recognition of human actions using wearable motion sensor networks

Journal of Ambient Intelligence and Smart Environments
Discriminative temporal smoothing for activity recognition from wearable sensors

UCS'07 Proceedings of the 4th international conference on Ubiquitous computing systems
Nursing activity recognition using an inexpensive game controller: An application to infection control

Technology and Health Care
Activity recognition using biomechanical model based pose estimation

EuroSSC'10 Proceedings of the 5th European conference on Smart sensing and context
Improving the classification accuracy of streaming data using SAX similarity features

Pattern Recognition Letters
A rule-based approach to activity recognition

KICSS'10 Proceedings of the 5th international conference on Knowledge, information, and creativity support systems
Rejection of irrelevant human actions in real-time hidden Markov model based recognition systems for wearable computers

Proceedings of the 2nd Conference on Wireless Health
Simple and robust BSN-based activity classification: winning the first BSN contest

Proceedings of the 4th International Symposium on Applied Sciences in Biomedical and Communication Technologies
Daily living activity recognition based on statistical feature quality group selection

Expert Systems with Applications: An International Journal
Distributed recognition of human actions using wearable motion sensor networks

Journal of Ambient Intelligence and Smart Environments
Walk detection and step counting on unconstrained smartphones

Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing
On preserving statistical characteristics of accelerometry data using their empirical cumulative distribution

Proceedings of the 2013 International Symposium on Wearable Computers
Automatic detection of the onset of nursing activities using accelerometers and adaptive segmentation

Technology and Health Care

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe our data collection and results on activity recognition with wearable, coin-sized sensor devices. The devices were attached to four different parts of the body: right thigh and wrist, left wrist and to a necklace on 13 different testees. In this experiment, data was from 17 daily life examples from male and female subjects. Features were calculated from triaxial accelerometer and heart rate data within different sized time windows. The best features were selected with forward-backward sequential search algorithm. Interestingly, acceleration mean values from the necklace were selected as important features. Two classifiers (multilayer perceptrons and kNN classifiers) were tested for activity recognition, and the best result (90.61 % aggregate recognition rate for 4-fold cross validation) was achieved with a kNN classifier.