Haar-like filtering for human activity recognition using 3D accelerometer

Yuya Hanai, Jun Nishimura, Tadahiro Kuroda

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

36 Citations (Scopus)

Abstract

In this paper, novel 2 one-dimensional (1D) Haar-like filtering techniques are proposed as a new and low calculation cost feature extraction method suitable for 3D acceleration signals based human activity recognition. Proposed filtering method is a simple difference filter with variable filter parameters. Our method holds a strong adaptability to various classification problems which no previously studied features (mean, standard deviation, etc.) possessed. In our experiment on human activity recognition, the proposed method achieved both the highest recognition accuracy of 93.91% while reducing calculation cost to 21.22% compared to previous method.

Original languageEnglish
Title of host publication2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009, Proceedings
Pages675-678
Number of pages4
DOIs
Publication statusPublished - 2009
Event2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009 - Marco Island, FL, United States
Duration: 2009 Jan 42009 Jan 7

Other

Other2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009
CountryUnited States
CityMarco Island, FL
Period09/1/409/1/7

Fingerprint

Accelerometers
Feature extraction
Costs
Experiments

Keywords

  • 1D haar-like filtering
  • Accelerometer
  • Human activity recognition
  • Sensornet

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Hanai, Y., Nishimura, J., & Kuroda, T. (2009). Haar-like filtering for human activity recognition using 3D accelerometer. In 2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009, Proceedings (pp. 675-678). [4786008] https://doi.org/10.1109/DSP.2009.4786008

Haar-like filtering for human activity recognition using 3D accelerometer. / Hanai, Yuya; Nishimura, Jun; Kuroda, Tadahiro.

2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009, Proceedings. 2009. p. 675-678 4786008.

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

Hanai, Y, Nishimura, J & Kuroda, T 2009, Haar-like filtering for human activity recognition using 3D accelerometer. in 2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009, Proceedings., 4786008, pp. 675-678, 2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009, Marco Island, FL, United States, 09/1/4. https://doi.org/10.1109/DSP.2009.4786008
Hanai Y, Nishimura J, Kuroda T. Haar-like filtering for human activity recognition using 3D accelerometer. In 2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009, Proceedings. 2009. p. 675-678. 4786008 https://doi.org/10.1109/DSP.2009.4786008
Hanai, Yuya ; Nishimura, Jun ; Kuroda, Tadahiro. / Haar-like filtering for human activity recognition using 3D accelerometer. 2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009, Proceedings. 2009. pp. 675-678
@inproceedings{904c8d6f53444308ad4be1385e506cd6,
title = "Haar-like filtering for human activity recognition using 3D accelerometer",
abstract = "In this paper, novel 2 one-dimensional (1D) Haar-like filtering techniques are proposed as a new and low calculation cost feature extraction method suitable for 3D acceleration signals based human activity recognition. Proposed filtering method is a simple difference filter with variable filter parameters. Our method holds a strong adaptability to various classification problems which no previously studied features (mean, standard deviation, etc.) possessed. In our experiment on human activity recognition, the proposed method achieved both the highest recognition accuracy of 93.91{\%} while reducing calculation cost to 21.22{\%} compared to previous method.",
keywords = "1D haar-like filtering, Accelerometer, Human activity recognition, Sensornet",
author = "Yuya Hanai and Jun Nishimura and Tadahiro Kuroda",
year = "2009",
doi = "10.1109/DSP.2009.4786008",
language = "English",
isbn = "9781424436774",
pages = "675--678",
booktitle = "2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009, Proceedings",

}

TY - GEN

T1 - Haar-like filtering for human activity recognition using 3D accelerometer

AU - Hanai, Yuya

AU - Nishimura, Jun

AU - Kuroda, Tadahiro

PY - 2009

Y1 - 2009

N2 - In this paper, novel 2 one-dimensional (1D) Haar-like filtering techniques are proposed as a new and low calculation cost feature extraction method suitable for 3D acceleration signals based human activity recognition. Proposed filtering method is a simple difference filter with variable filter parameters. Our method holds a strong adaptability to various classification problems which no previously studied features (mean, standard deviation, etc.) possessed. In our experiment on human activity recognition, the proposed method achieved both the highest recognition accuracy of 93.91% while reducing calculation cost to 21.22% compared to previous method.

AB - In this paper, novel 2 one-dimensional (1D) Haar-like filtering techniques are proposed as a new and low calculation cost feature extraction method suitable for 3D acceleration signals based human activity recognition. Proposed filtering method is a simple difference filter with variable filter parameters. Our method holds a strong adaptability to various classification problems which no previously studied features (mean, standard deviation, etc.) possessed. In our experiment on human activity recognition, the proposed method achieved both the highest recognition accuracy of 93.91% while reducing calculation cost to 21.22% compared to previous method.

KW - 1D haar-like filtering

KW - Accelerometer

KW - Human activity recognition

KW - Sensornet

UR - http://www.scopus.com/inward/record.url?scp=63649152771&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=63649152771&partnerID=8YFLogxK

U2 - 10.1109/DSP.2009.4786008

DO - 10.1109/DSP.2009.4786008

M3 - Conference contribution

SN - 9781424436774

SP - 675

EP - 678

BT - 2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, DSP/SPE 2009, Proceedings

ER -