Bicycle behavior recognition using 3-axis acceleration sensor and 3-axis gyro sensor equipped with smartphone

Yuri Usami, Kazuaki Ishikawa, Toshinori Takayama, Masao Yanagisawa, Nozomu Togawa

Research output: Contribution to journalArticle

Abstract

It becomes possible to prevent accidents beforehand by predicting dangerous riding behavior based on recognition of bicycle behaviors. In this paper, we propose a bicycle behavior recognition method using a three-axis acceleration sensor and three-axis gyro sensor equipped with a smartphone when it is installed on a bicycle handlebar. We focus on the periodic handlebar motions for balancing while running a bicycle and reduce the sensor noises caused by them. After that, we use machine learning for recognizing the bicycle behaviors, effectively utilizing the motion features in bicycle behavior recognition. The experimental results demonstrate that the proposed method accurately recognizes the four bicycle behaviors of stop, run straight, turn right, and turn left and its F-measure becomes around 0.9. The results indicate that, even if the smartphone is installed on the noisy bicycle handlebar, our proposed method can recognize the bicycle behaviors with almost the same accuracy as the one when a smartphone is installed on a rear axle of a bicycle on which the handlebar motion noises can be much reduced.

Original languageEnglish
Pages (from-to)953-965
Number of pages13
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE102A
Issue number8
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Bicycles
Smartphones
Sensor
Sensors
Motion
Periodic Motion
Accidents
Rear axles
Balancing
Straight
Machine Learning
Learning systems
Experimental Results
Demonstrate

Keywords

  • Acceleration sensor
  • Behavior recognition
  • Bicycle
  • Gyro sensor
  • Smartphone

ASJC Scopus subject areas

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

Bicycle behavior recognition using 3-axis acceleration sensor and 3-axis gyro sensor equipped with smartphone. / Usami, Yuri; Ishikawa, Kazuaki; Takayama, Toshinori; Yanagisawa, Masao; Togawa, Nozomu.

In: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E102A, No. 8, 01.01.2019, p. 953-965.

Research output: Contribution to journalArticle

@article{55c193b69a8b462c81501a60a7471ff6,
title = "Bicycle behavior recognition using 3-axis acceleration sensor and 3-axis gyro sensor equipped with smartphone",
abstract = "It becomes possible to prevent accidents beforehand by predicting dangerous riding behavior based on recognition of bicycle behaviors. In this paper, we propose a bicycle behavior recognition method using a three-axis acceleration sensor and three-axis gyro sensor equipped with a smartphone when it is installed on a bicycle handlebar. We focus on the periodic handlebar motions for balancing while running a bicycle and reduce the sensor noises caused by them. After that, we use machine learning for recognizing the bicycle behaviors, effectively utilizing the motion features in bicycle behavior recognition. The experimental results demonstrate that the proposed method accurately recognizes the four bicycle behaviors of stop, run straight, turn right, and turn left and its F-measure becomes around 0.9. The results indicate that, even if the smartphone is installed on the noisy bicycle handlebar, our proposed method can recognize the bicycle behaviors with almost the same accuracy as the one when a smartphone is installed on a rear axle of a bicycle on which the handlebar motion noises can be much reduced.",
keywords = "Acceleration sensor, Behavior recognition, Bicycle, Gyro sensor, Smartphone",
author = "Yuri Usami and Kazuaki Ishikawa and Toshinori Takayama and Masao Yanagisawa and Nozomu Togawa",
year = "2019",
month = "1",
day = "1",
doi = "10.1587/transfun.E102.A.953",
language = "English",
volume = "E102A",
pages = "953--965",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "8",

}

TY - JOUR

T1 - Bicycle behavior recognition using 3-axis acceleration sensor and 3-axis gyro sensor equipped with smartphone

AU - Usami, Yuri

AU - Ishikawa, Kazuaki

AU - Takayama, Toshinori

AU - Yanagisawa, Masao

AU - Togawa, Nozomu

PY - 2019/1/1

Y1 - 2019/1/1

N2 - It becomes possible to prevent accidents beforehand by predicting dangerous riding behavior based on recognition of bicycle behaviors. In this paper, we propose a bicycle behavior recognition method using a three-axis acceleration sensor and three-axis gyro sensor equipped with a smartphone when it is installed on a bicycle handlebar. We focus on the periodic handlebar motions for balancing while running a bicycle and reduce the sensor noises caused by them. After that, we use machine learning for recognizing the bicycle behaviors, effectively utilizing the motion features in bicycle behavior recognition. The experimental results demonstrate that the proposed method accurately recognizes the four bicycle behaviors of stop, run straight, turn right, and turn left and its F-measure becomes around 0.9. The results indicate that, even if the smartphone is installed on the noisy bicycle handlebar, our proposed method can recognize the bicycle behaviors with almost the same accuracy as the one when a smartphone is installed on a rear axle of a bicycle on which the handlebar motion noises can be much reduced.

AB - It becomes possible to prevent accidents beforehand by predicting dangerous riding behavior based on recognition of bicycle behaviors. In this paper, we propose a bicycle behavior recognition method using a three-axis acceleration sensor and three-axis gyro sensor equipped with a smartphone when it is installed on a bicycle handlebar. We focus on the periodic handlebar motions for balancing while running a bicycle and reduce the sensor noises caused by them. After that, we use machine learning for recognizing the bicycle behaviors, effectively utilizing the motion features in bicycle behavior recognition. The experimental results demonstrate that the proposed method accurately recognizes the four bicycle behaviors of stop, run straight, turn right, and turn left and its F-measure becomes around 0.9. The results indicate that, even if the smartphone is installed on the noisy bicycle handlebar, our proposed method can recognize the bicycle behaviors with almost the same accuracy as the one when a smartphone is installed on a rear axle of a bicycle on which the handlebar motion noises can be much reduced.

KW - Acceleration sensor

KW - Behavior recognition

KW - Bicycle

KW - Gyro sensor

KW - Smartphone

UR - http://www.scopus.com/inward/record.url?scp=85072672225&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072672225&partnerID=8YFLogxK

U2 - 10.1587/transfun.E102.A.953

DO - 10.1587/transfun.E102.A.953

M3 - Article

AN - SCOPUS:85072672225

VL - E102A

SP - 953

EP - 965

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 8

ER -