Comprehensive evaluation of human activity classification based on inertia measurement unit with air pressure sensor

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

1 Citation (Scopus)

Abstract

This paper focuses on accuracy improvement of human activities detection and classification by using single Inertia Measurement Unit sensor (IMU sensor: an acceleration sensor, a gyro sensor, a magnetometer, and an air pressure sensor) which is a type of the wearable sensors. Generally, performance of classification model is determined by these methodologies; number and type of sensors, coordinate transformation, time window, time-frequency domain analysis, and machine learning algorithms. The contributions of this paper are summarized in the following three points. Firstly, a pressure sensor is additionally utilized to improve the accuracy of human activities estimation. This information is effective to estimate up/down motion by stair and elevator. Secondly, comprehensive evaluation of the combinations using different methodologies is conducted to find an optimal classification model. Thirdly, ensemble learning is performed to improve estimation accuracy. It shows superior performance with over 95 % accuracy of human activity estimation.

Original languageEnglish
Title of host publication2017 24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
Volume2017-December
ISBN (Electronic)9781509065462
DOIs
Publication statusPublished - 2017 Dec 14
Event24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017 - Auckland, New Zealand
Duration: 2017 Nov 212017 Nov 23

Other

Other24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017
CountryNew Zealand
CityAuckland
Period17/11/2117/11/23

Fingerprint

Pressure Sensor
Comprehensive Evaluation
Units of measurement
Pressure sensors
Inertia
Sensor
Unit
Sensors
Air
Frequency domain analysis
Stairs
Elevators
Frequency Domain Analysis
Ensemble Learning
Magnetometers
Time-frequency Analysis
Methodology
Learning algorithms
Coordinate Transformation
Time Windows

Keywords

  • Activity Classification
  • Feature Selection
  • Inertia Measurement Unit
  • Machine Learning

ASJC Scopus subject areas

  • Mechanical Engineering
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Control and Optimization

Cite this

Ishikawa, T., Hayami, H., & Murakami, T. (2017). Comprehensive evaluation of human activity classification based on inertia measurement unit with air pressure sensor. In 2017 24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017 (Vol. 2017-December, pp. 1-6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/M2VIP.2017.8211471

Comprehensive evaluation of human activity classification based on inertia measurement unit with air pressure sensor. / Ishikawa, Takahiro; Hayami, Hitoshi; Murakami, Toshiyuki.

2017 24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017. Vol. 2017-December Institute of Electrical and Electronics Engineers Inc., 2017. p. 1-6.

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

Ishikawa, T, Hayami, H & Murakami, T 2017, Comprehensive evaluation of human activity classification based on inertia measurement unit with air pressure sensor. in 2017 24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017. vol. 2017-December, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017, Auckland, New Zealand, 17/11/21. https://doi.org/10.1109/M2VIP.2017.8211471
Ishikawa T, Hayami H, Murakami T. Comprehensive evaluation of human activity classification based on inertia measurement unit with air pressure sensor. In 2017 24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017. Vol. 2017-December. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1-6 https://doi.org/10.1109/M2VIP.2017.8211471
Ishikawa, Takahiro ; Hayami, Hitoshi ; Murakami, Toshiyuki. / Comprehensive evaluation of human activity classification based on inertia measurement unit with air pressure sensor. 2017 24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017. Vol. 2017-December Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1-6
@inproceedings{9900092d735b4599a821d9f02f361eae,
title = "Comprehensive evaluation of human activity classification based on inertia measurement unit with air pressure sensor",
abstract = "This paper focuses on accuracy improvement of human activities detection and classification by using single Inertia Measurement Unit sensor (IMU sensor: an acceleration sensor, a gyro sensor, a magnetometer, and an air pressure sensor) which is a type of the wearable sensors. Generally, performance of classification model is determined by these methodologies; number and type of sensors, coordinate transformation, time window, time-frequency domain analysis, and machine learning algorithms. The contributions of this paper are summarized in the following three points. Firstly, a pressure sensor is additionally utilized to improve the accuracy of human activities estimation. This information is effective to estimate up/down motion by stair and elevator. Secondly, comprehensive evaluation of the combinations using different methodologies is conducted to find an optimal classification model. Thirdly, ensemble learning is performed to improve estimation accuracy. It shows superior performance with over 95 {\%} accuracy of human activity estimation.",
keywords = "Activity Classification, Feature Selection, Inertia Measurement Unit, Machine Learning",
author = "Takahiro Ishikawa and Hitoshi Hayami and Toshiyuki Murakami",
year = "2017",
month = "12",
day = "14",
doi = "10.1109/M2VIP.2017.8211471",
language = "English",
volume = "2017-December",
pages = "1--6",
booktitle = "2017 24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Comprehensive evaluation of human activity classification based on inertia measurement unit with air pressure sensor

AU - Ishikawa, Takahiro

AU - Hayami, Hitoshi

AU - Murakami, Toshiyuki

PY - 2017/12/14

Y1 - 2017/12/14

N2 - This paper focuses on accuracy improvement of human activities detection and classification by using single Inertia Measurement Unit sensor (IMU sensor: an acceleration sensor, a gyro sensor, a magnetometer, and an air pressure sensor) which is a type of the wearable sensors. Generally, performance of classification model is determined by these methodologies; number and type of sensors, coordinate transformation, time window, time-frequency domain analysis, and machine learning algorithms. The contributions of this paper are summarized in the following three points. Firstly, a pressure sensor is additionally utilized to improve the accuracy of human activities estimation. This information is effective to estimate up/down motion by stair and elevator. Secondly, comprehensive evaluation of the combinations using different methodologies is conducted to find an optimal classification model. Thirdly, ensemble learning is performed to improve estimation accuracy. It shows superior performance with over 95 % accuracy of human activity estimation.

AB - This paper focuses on accuracy improvement of human activities detection and classification by using single Inertia Measurement Unit sensor (IMU sensor: an acceleration sensor, a gyro sensor, a magnetometer, and an air pressure sensor) which is a type of the wearable sensors. Generally, performance of classification model is determined by these methodologies; number and type of sensors, coordinate transformation, time window, time-frequency domain analysis, and machine learning algorithms. The contributions of this paper are summarized in the following three points. Firstly, a pressure sensor is additionally utilized to improve the accuracy of human activities estimation. This information is effective to estimate up/down motion by stair and elevator. Secondly, comprehensive evaluation of the combinations using different methodologies is conducted to find an optimal classification model. Thirdly, ensemble learning is performed to improve estimation accuracy. It shows superior performance with over 95 % accuracy of human activity estimation.

KW - Activity Classification

KW - Feature Selection

KW - Inertia Measurement Unit

KW - Machine Learning

UR - http://www.scopus.com/inward/record.url?scp=85048496701&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048496701&partnerID=8YFLogxK

U2 - 10.1109/M2VIP.2017.8211471

DO - 10.1109/M2VIP.2017.8211471

M3 - Conference contribution

AN - SCOPUS:85048496701

VL - 2017-December

SP - 1

EP - 6

BT - 2017 24th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -