Recognizing human motion with multiple acceleration sensors

Jani Mäntyjärvi, Johan Himberg, Tapio Seppänen

Research output: Contribution to journalArticleScientificpeer-review

292 Citations (Scopus)


In this paper experiments with acceleration sensors are described for human activity recognition of a wearable device user. The use of principal component analysis and independent component analysis with wavelet transform is tested for feature generation. Recognition of the human activity is examined with multilayer perceptron classifier. Best classification results for recognition of different human motions were 83-90%, and they were achieved by utilizing independent component analysis and principal component analysis. Difference between these methods turned out to be negligible.

Original languageEnglish
Pages (from-to)747-752
Number of pages6
JournalProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Publication statusPublished - 1 Jan 2001
MoE publication typeA1 Journal article-refereed


  • Accelerometer
  • Independent component analysis
  • Movement recognition
  • Principal component analysis
  • Wearable computing


Dive into the research topics of 'Recognizing human motion with multiple acceleration sensors'. Together they form a unique fingerprint.

Cite this