Robust human intensity-varying activity recognition using Stochastic Approximation in wearable sensors

Nabil Alshurafa, Wenyao Xu, Jason J. Liu, Ming Chun Huang, Bobak Mortazavi, Majid Sarrafzadeh, Christian Roberts

Research output: Chapter in Book/Report/Conference proceedingConference contribution

20 Scopus citations

Abstract

Detecting human activity independent of intensity is essential in many applications, primarily in calculating metabolic equivalent rates (MET) and extracting human context awareness from on-body inertial sensors. Many classifiers that train on an activity at a subset of intensity levels fail to classify the same activity at other intensity levels. This demonstrates weakness in the underlying activity model. Training a classifier for an activity at every intensity level is also not practical. In this paper we tackle a novel intensity-independent activity recognition application where the class labels exhibit large variability, the data is of high dimensionality, and clustering algorithms are necessary. We propose a new robust Stochastic Approximation framework for enhanced classification of such data. Experiments are reported for each dataset using two clustering techniques, K-Means and Gaussian Mixture Models. The Stochastic Approximation algorithm consistently outperforms other well-known classification schemes which validates the use of our proposed clustered data representation.

Original languageEnglish (US)
Title of host publication2013 IEEE International Conference on Body Sensor Networks, BSN 2013
DOIs
StatePublished - Oct 1 2013
Event2013 IEEE International Conference on Body Sensor Networks, BSN 2013 - Cambridge, MA, United States
Duration: May 6 2013May 9 2013

Publication series

Name2013 IEEE International Conference on Body Sensor Networks, BSN 2013

Other

Other2013 IEEE International Conference on Body Sensor Networks, BSN 2013
CountryUnited States
CityCambridge, MA
Period5/6/135/9/13

Keywords

  • Classification
  • Clustering
  • Intensity-Varying Activity
  • Mixture Models
  • Stochastic Approximation Model

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Robust human intensity-varying activity recognition using Stochastic Approximation in wearable sensors'. Together they form a unique fingerprint.

Cite this