Improving human motion identification using motion dependent classification

Evangelia Pippa, Iosif Mporas, Vasileios Megalooikonomou

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

Abstract

In this article, we present a new methodology for human motion identification based on motion dependent binary classifiers that afterwards fuse their decisions to identify an Activity of Daily Living (ADL). Temporal and spectral features extracted from the sensor signals (accelerometer and gyroscope) and concatenated to a single feature vector are used to train motion dependent binary classification models. Each individual model is capable to recognize one motion versus all the others. Afterwards the decisions are combined by a fusion function using as weights the sensitivity values derived from the evaluation of each motion dependent classifier on the provided training set. The proposed methodology was evaluated using SVMs for the motion dependent classifiers and is compared against the common multiclass classification approach optimized using either feature selection or subject dependent classification. The classification accuracy of the proposed methodology reaches 99% offering competitive performance comparing to the other approaches.
Original languageEnglish
Title of host publicationInformation and Communication Technologies for Ageing Well and e-Health
Subtitle of host publicationSecond International Conference, ICT4AWE 2016, Rome, Italy, April 21-22, 2016, Revised Selected Papers
PublisherSpringer Nature Link
Pages49-65
Number of pages17
Volume736
ISBN (Electronic)9783319627045
ISBN (Print)9783319627038
DOIs
Publication statusE-pub ahead of print - 20 Jul 2017
Event2nd International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2016 - Rome, Italy
Duration: 21 Apr 201622 Apr 2016

Publication series

NameCommunications in Computer and Information Science
Volume736
ISSN (Print)18650929

Conference

Conference2nd International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2016
Country/TerritoryItaly
CityRome
Period21/04/1622/04/16

Keywords

  • Accelerometers
  • ADLs
  • Classification
  • Feature extraction
  • Fusion
  • Gyroscopes
  • Human motion identification

Fingerprint

Dive into the research topics of 'Improving human motion identification using motion dependent classification'. Together they form a unique fingerprint.

Cite this