Abstract

Processing of accelerometer data for recognizing short duration hand movements is a challenging problem. This paper focuses on characterization of acceleration data corresponding to hand movements (lift to mouth, scoop, stir, pour, unscrew cap) using aggregate statistical features and histograms computed from raw acceleration and derivative of the acceleration data. Data collected from an accelerometer placed on the wrist of subjects was used to perform the analysis. Supplementing the statistical features with raw acceleration histograms had a very marginal effect on the classification performance. However, the addition of derivative histograms resulted in a considerable improvement in the classification accuracy by nearly 8%. The effect of bin size of the derivative histograms was also conducted. It was observed that having a small number of bins decreased the classification accuracy by 3%. We thus show that adding features that capture the distribution of the changes in the acceleration data improve the classification performance.

Original languageEnglish (US)
Title of host publicationProceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009
Pages1700-1703
Number of pages4
DOIs
StatePublished - 2009
Event2009 IEEE International Conference on Multimedia and Expo, ICME 2009 - New York, NY, United States
Duration: Jun 28 2009Jul 3 2009

Other

Other2009 IEEE International Conference on Multimedia and Expo, ICME 2009
CountryUnited States
CityNew York, NY
Period6/28/097/3/09

Fingerprint

Accelerometers
Bins
Derivatives
Processing

Keywords

  • Accelerometer
  • Feature extraction
  • Histograms

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications
  • Hardware and Architecture
  • Software

Cite this

Krishnan, N. C., Pradhan, G. N., & Panchanathan, S. (2009). Recognizing short duration hand movements from accelerometer data. In Proceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009 (pp. 1700-1703). [5202848] https://doi.org/10.1109/ICME.2009.5202848

Recognizing short duration hand movements from accelerometer data. / Krishnan, Narayanan C.; Pradhan, Gaurav N.; Panchanathan, Sethuraman.

Proceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009. 2009. p. 1700-1703 5202848.

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

Krishnan, NC, Pradhan, GN & Panchanathan, S 2009, Recognizing short duration hand movements from accelerometer data. in Proceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009., 5202848, pp. 1700-1703, 2009 IEEE International Conference on Multimedia and Expo, ICME 2009, New York, NY, United States, 6/28/09. https://doi.org/10.1109/ICME.2009.5202848
Krishnan NC, Pradhan GN, Panchanathan S. Recognizing short duration hand movements from accelerometer data. In Proceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009. 2009. p. 1700-1703. 5202848 https://doi.org/10.1109/ICME.2009.5202848
Krishnan, Narayanan C. ; Pradhan, Gaurav N. ; Panchanathan, Sethuraman. / Recognizing short duration hand movements from accelerometer data. Proceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009. 2009. pp. 1700-1703
@inproceedings{8be1abe5266e48678be6928fcda9f502,
title = "Recognizing short duration hand movements from accelerometer data",
abstract = "Processing of accelerometer data for recognizing short duration hand movements is a challenging problem. This paper focuses on characterization of acceleration data corresponding to hand movements (lift to mouth, scoop, stir, pour, unscrew cap) using aggregate statistical features and histograms computed from raw acceleration and derivative of the acceleration data. Data collected from an accelerometer placed on the wrist of subjects was used to perform the analysis. Supplementing the statistical features with raw acceleration histograms had a very marginal effect on the classification performance. However, the addition of derivative histograms resulted in a considerable improvement in the classification accuracy by nearly 8{\%}. The effect of bin size of the derivative histograms was also conducted. It was observed that having a small number of bins decreased the classification accuracy by 3{\%}. We thus show that adding features that capture the distribution of the changes in the acceleration data improve the classification performance.",
keywords = "Accelerometer, Feature extraction, Histograms",
author = "Krishnan, {Narayanan C.} and Pradhan, {Gaurav N.} and Sethuraman Panchanathan",
year = "2009",
doi = "10.1109/ICME.2009.5202848",
language = "English (US)",
isbn = "9781424442911",
pages = "1700--1703",
booktitle = "Proceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009",

}

TY - GEN

T1 - Recognizing short duration hand movements from accelerometer data

AU - Krishnan, Narayanan C.

AU - Pradhan, Gaurav N.

AU - Panchanathan, Sethuraman

PY - 2009

Y1 - 2009

N2 - Processing of accelerometer data for recognizing short duration hand movements is a challenging problem. This paper focuses on characterization of acceleration data corresponding to hand movements (lift to mouth, scoop, stir, pour, unscrew cap) using aggregate statistical features and histograms computed from raw acceleration and derivative of the acceleration data. Data collected from an accelerometer placed on the wrist of subjects was used to perform the analysis. Supplementing the statistical features with raw acceleration histograms had a very marginal effect on the classification performance. However, the addition of derivative histograms resulted in a considerable improvement in the classification accuracy by nearly 8%. The effect of bin size of the derivative histograms was also conducted. It was observed that having a small number of bins decreased the classification accuracy by 3%. We thus show that adding features that capture the distribution of the changes in the acceleration data improve the classification performance.

AB - Processing of accelerometer data for recognizing short duration hand movements is a challenging problem. This paper focuses on characterization of acceleration data corresponding to hand movements (lift to mouth, scoop, stir, pour, unscrew cap) using aggregate statistical features and histograms computed from raw acceleration and derivative of the acceleration data. Data collected from an accelerometer placed on the wrist of subjects was used to perform the analysis. Supplementing the statistical features with raw acceleration histograms had a very marginal effect on the classification performance. However, the addition of derivative histograms resulted in a considerable improvement in the classification accuracy by nearly 8%. The effect of bin size of the derivative histograms was also conducted. It was observed that having a small number of bins decreased the classification accuracy by 3%. We thus show that adding features that capture the distribution of the changes in the acceleration data improve the classification performance.

KW - Accelerometer

KW - Feature extraction

KW - Histograms

UR - http://www.scopus.com/inward/record.url?scp=70449623344&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449623344&partnerID=8YFLogxK

U2 - 10.1109/ICME.2009.5202848

DO - 10.1109/ICME.2009.5202848

M3 - Conference contribution

AN - SCOPUS:70449623344

SN - 9781424442911

SP - 1700

EP - 1703

BT - Proceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009

ER -