Recognizing human motion with multiple acceleration sensors

Jani Mäntyjärvi; Johan Himberg; Tapio Seppänen

doi:10.1109/ICSMC.2001.973004

Recognizing human motion with multiple acceleration sensors

Jani Mäntyjärvi, Johan Himberg, Tapio Seppänen

Not published at VTT

Research output: Contribution to journal › Article › Scientific › peer-review

298 Citations (Scopus)

Abstract

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 language	English
Pages (from-to)	747-752
Number of pages	6
Journal	Proceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume	2
DOIs	https://doi.org/10.1109/ICSMC.2001.973004
Publication status	Published - 1 Jan 2001
MoE publication type	A1 Journal article-refereed

Keywords

Accelerometer
Independent component analysis
Movement recognition
Principal component analysis
Wearable computing

Access to Document

10.1109/ICSMC.2001.973004

Cite this

@article{36e5a6bef57e462c96961dc6bf0f190d,

title = "Recognizing human motion with multiple acceleration sensors",

abstract = "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.",

keywords = "Accelerometer, Independent component analysis, Movement recognition, Principal component analysis, Wearable computing",

author = "Jani M{\"a}ntyj{\"a}rvi and Johan Himberg and Tapio Sepp{\"a}nen",

year = "2001",

month = jan,

day = "1",

doi = "10.1109/ICSMC.2001.973004",

language = "English",

volume = "2",

pages = "747--752",

journal = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",

issn = "0884-3627",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

}

TY - JOUR

T1 - Recognizing human motion with multiple acceleration sensors

AU - Mäntyjärvi, Jani

AU - Himberg, Johan

AU - Seppänen, Tapio

PY - 2001/1/1

Y1 - 2001/1/1

N2 - 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.

AB - 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.

KW - Accelerometer

KW - Independent component analysis

KW - Movement recognition

KW - Principal component analysis

KW - Wearable computing

UR - http://www.scopus.com/inward/record.url?scp=0035723662&partnerID=8YFLogxK

U2 - 10.1109/ICSMC.2001.973004

DO - 10.1109/ICSMC.2001.973004

M3 - Article

AN - SCOPUS:0035723662

SN - 0884-3627

VL - 2

SP - 747

EP - 752

JO - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

JF - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

ER -

Recognizing human motion with multiple acceleration sensors

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this