Human motion detection in daily activity tasks using wearable sensors

Olga Politi, Iosif Mporas, Vasileios Megalooikonomou

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

13 Citations (Scopus)


In this article we present a human motion detection frame-work, based on data derived from a single tri-axial accel-erometer. The framework uses a set of different pre-processing methods that produce data representations which are respectively parameterized by statistical and physical features. These features are then concatenated and classified using well-known classification algorithms for the problem of motion recognition. Experimental evaluation was carried out according to a subject-dependent scenario, meaning that the classification is performed for each subject separately using their own data and the average accuracy for all indi-viduals is computed. The best achieved detection perfor-mance for 14 everyday human motion activities, using the USC-HAD database, was approximately 95%. The results compare favorably are competitive to the best reported per-formance of 93.1% for the same database.

Original languageEnglish
Title of host publication2014 Proceedings of the 22nd European Signal Processing Conference, EUSIPCO 2014
PublisherEuropean Signal Processing Conference, EUSIPCO
Number of pages5
ISBN (Electronic)9780992862619
Publication statusPublished - 10 Nov 2014
Externally publishedYes
Event22nd European Signal Processing Conference, EUSIPCO 2014 - Lisbon, Portugal
Duration: 1 Sept 20145 Sept 2014

Publication series

NameEuropean Signal Processing Conference
ISSN (Print)2219-5491


Conference22nd European Signal Processing Conference, EUSIPCO 2014


  • Accelerometers
  • daily activity
  • human motion recognition
  • movement classification
  • wearable sensors


Dive into the research topics of 'Human motion detection in daily activity tasks using wearable sensors'. Together they form a unique fingerprint.

Cite this