Learning from Life-Logging Data by Hybrid HMM: A Case Study on Active States Prediction

Created by W.Langdon from gp-bibliography.bib Revision:1.4192

  author =       "Ji Ni and Tryphon Lambrou and Xujiong Ye",
  title =        "Learning from Life-Logging Data by Hybrid HMM: A Case
                 Study on Active States Prediction",
  booktitle =    "12th international Conference on Biomedical
                 Engineering Biomedical Engineering (BioMed 2016)",
  year =         "2016",
  editor =       "Arnold Baca",
  address =      "Innsbruck, Austria",
  month =        feb # " 15-16",
  organisation = "IASTED",
  keywords =     "genetic algorithms, genetic programming, SVM, ehealth,
                 machine learning, wearable sensor, life-logging data",
  bibsource =    "OAI-PMH server at eprints.lincoln.ac.uk",
  language =     "en",
  oai =          "oai:eprints.lincoln.ac.uk:23092",
  relation =     "10.2316/P.2016.832-019",
  type =         "Conference or Workshop contribution; NonPeerReviewed",
  URL =          "http://eprints.lincoln.ac.uk/23092/",
  URL =          "http://eprints.lincoln.ac.uk/23092/1/832-019.pdf",
  URL =          "http://www.actapress.com/Abstract.aspx?paperId=456195",
  DOI =          "doi:10.2316/P.2016.832-019",
  abstract =     "In this paper, we have proposed employing a hybrid
                 classifier-hidden Markov model (HMM) as a supervised
                 learning approach to recognise daily active states from
                 sequential life-logging data collected from wearable
                 sensors. We generate synthetic data from real dataset
                 to cope with noise and incompleteness for training
                 purpose and, in conjunction with HMM, propose using a
                 multiobjective genetic programming (MOGP) classifier in
                 comparison of the support vector machine (SVM) with
                 variant kernels. We demonstrate that the system with
                 either algorithm works effectively to recognise
                 personal active states regarding medical reference. We
                 also illustrate that MOGP yields generally better
                 results than SVM without requiring an ad hoc kernel.",

Genetic Programming entries for Ji Ni Tryphon Lambrou Xujiong Ye