Head Movement-Based Visual Distraction Detection in Cyclists with Earables

Sidhharth Balakrishnan; Akhil Pallamreddy; Yanqiu Huang; Ozlem Durmaz Incel

doi:10.1145/3714394.3757261

Head Movement-Based Visual Distraction Detection in Cyclists with Earables

Sidhharth Balakrishnan
, Akhil Pallamreddy
, Yanqiu Huang
, Ozlem Durmaz Incel^*

^*Corresponding author for this work

Pervasive Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

21 Downloads (Pure)

Abstract

Visual distractions among cyclists significantly reduce their situational awareness, increasing the likelihood of accidents. This study introduces the use of an open-source OpenEarable device, equipped with onboard inertial measurement units (IMU), as an easy and non-invasive way to detect visual distractions by measuring head movements linked to such behaviors. Head movement data from 20 participants were collected during natural cycling situations using earable IMU sensors. Both classical machine learning and deep learning techniques are employed to analyze the data to detect visual distractions. Support Vector Machine (SVM) and Convolutional Neural Network (CNN) achieve weighted F1 scores of 0.85 and 0.87, and Cohen's Kappa scores of 0.74 and 0.59, respectively. These findings highlight the potential of earable devices in real-time distraction detection and establish a foundation for future wearable safety systems for cyclists.

Original language	English
Title of host publication	UbiComp Companion '25
Subtitle of host publication	Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing
Editors	Michael Beigl, Giulio Jacucci, Stephan Sigg, Yu Xiao, Jakob E. Bardram, Eirini Eleni Tsiropoulou, Chenren Xu
Place of Publication	New York
Publisher	Association for Computing Machinery, Inc
Pages	847-853
Number of pages	8
ISBN (Electronic)	979-8-4007-1477-1
DOIs	https://doi.org/10.1145/3714394.3757261
Publication status	Published - 12 Oct 2025
Event	ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2025 - Aalto University, Espoo, Finland Duration: 12 Oct 2024 → 16 Oct 2024 https://www.ubicomp.org/ubicomp-iswc-2025/

Conference

Conference	ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2025
Abbreviated title	UbiComp 2025
Country/Territory	Finland
City	Espoo
Period	12/10/24 → 16/10/24
Internet address	https://www.ubicomp.org/ubicomp-iswc-2025/

Keywords

earables
edge computing
head gestures
inertial measurement unit
neural networks

Access to Document

10.1145/3714394.3757261Licence: CC BY-NC-SA

Conference paperFinal published version, 1.56 MBLicence: CC BY-NC-SA

Cite this

Balakrishnan, S., Pallamreddy, A., Huang, Y., & Durmaz Incel, O. (2025). Head Movement-Based Visual Distraction Detection in Cyclists with Earables. In M. Beigl, G. Jacucci, S. Sigg, Y. Xiao, J. E. Bardram, E. E. Tsiropoulou, & C. Xu (Eds.), UbiComp Companion '25: Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing (pp. 847-853). Association for Computing Machinery, Inc. https://doi.org/10.1145/3714394.3757261

Balakrishnan, Sidhharth ; Pallamreddy, Akhil ; Huang, Yanqiu et al. / Head Movement-Based Visual Distraction Detection in Cyclists with Earables. UbiComp Companion '25: Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing. editor / Michael Beigl ; Giulio Jacucci ; Stephan Sigg ; Yu Xiao ; Jakob E. Bardram ; Eirini Eleni Tsiropoulou ; Chenren Xu. New York : Association for Computing Machinery, Inc, 2025. pp. 847-853

@inproceedings{e88eeca6977d46588c594020b427de26,

title = "Head Movement-Based Visual Distraction Detection in Cyclists with Earables",

abstract = "Visual distractions among cyclists significantly reduce their situational awareness, increasing the likelihood of accidents. This study introduces the use of an open-source OpenEarable device, equipped with onboard inertial measurement units (IMU), as an easy and non-invasive way to detect visual distractions by measuring head movements linked to such behaviors. Head movement data from 20 participants were collected during natural cycling situations using earable IMU sensors. Both classical machine learning and deep learning techniques are employed to analyze the data to detect visual distractions. Support Vector Machine (SVM) and Convolutional Neural Network (CNN) achieve weighted F1 scores of 0.85 and 0.87, and Cohen's Kappa scores of 0.74 and 0.59, respectively. These findings highlight the potential of earable devices in real-time distraction detection and establish a foundation for future wearable safety systems for cyclists.",

keywords = "earables, edge computing, head gestures, inertial measurement unit, neural networks",

author = "Sidhharth Balakrishnan and Akhil Pallamreddy and Yanqiu Huang and \{Durmaz Incel\}, Ozlem",

note = "Publisher Copyright: {\textcopyright} 2025 Owner/Author.; ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2025, UbiComp 2025 ; Conference date: 12-10-2024 Through 16-10-2024",

year = "2025",

month = oct,

day = "12",

doi = "10.1145/3714394.3757261",

language = "English",

pages = "847--853",

editor = "Michael Beigl and Giulio Jacucci and Stephan Sigg and Yu Xiao and Bardram, \{Jakob E.\} and Tsiropoulou, \{Eirini Eleni\} and Chenren Xu",

booktitle = "UbiComp Companion '25",

publisher = "Association for Computing Machinery, Inc",

url = "https://www.ubicomp.org/ubicomp-iswc-2025/",

}

Balakrishnan, S, Pallamreddy, A, Huang, Y & Durmaz Incel, O 2025, Head Movement-Based Visual Distraction Detection in Cyclists with Earables. in M Beigl, G Jacucci, S Sigg, Y Xiao, JE Bardram, EE Tsiropoulou & C Xu (eds), UbiComp Companion '25: Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc, New York, pp. 847-853, ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2025, Espoo, Finland, 12/10/24. https://doi.org/10.1145/3714394.3757261

Head Movement-Based Visual Distraction Detection in Cyclists with Earables. / Balakrishnan, Sidhharth; Pallamreddy, Akhil; Huang, Yanqiu et al.
UbiComp Companion '25: Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing. ed. / Michael Beigl; Giulio Jacucci; Stephan Sigg; Yu Xiao; Jakob E. Bardram; Eirini Eleni Tsiropoulou; Chenren Xu. New York: Association for Computing Machinery, Inc, 2025. p. 847-853.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Head Movement-Based Visual Distraction Detection in Cyclists with Earables

AU - Balakrishnan, Sidhharth

AU - Pallamreddy, Akhil

AU - Huang, Yanqiu

AU - Durmaz Incel, Ozlem

PY - 2025/10/12

Y1 - 2025/10/12

N2 - Visual distractions among cyclists significantly reduce their situational awareness, increasing the likelihood of accidents. This study introduces the use of an open-source OpenEarable device, equipped with onboard inertial measurement units (IMU), as an easy and non-invasive way to detect visual distractions by measuring head movements linked to such behaviors. Head movement data from 20 participants were collected during natural cycling situations using earable IMU sensors. Both classical machine learning and deep learning techniques are employed to analyze the data to detect visual distractions. Support Vector Machine (SVM) and Convolutional Neural Network (CNN) achieve weighted F1 scores of 0.85 and 0.87, and Cohen's Kappa scores of 0.74 and 0.59, respectively. These findings highlight the potential of earable devices in real-time distraction detection and establish a foundation for future wearable safety systems for cyclists.

AB - Visual distractions among cyclists significantly reduce their situational awareness, increasing the likelihood of accidents. This study introduces the use of an open-source OpenEarable device, equipped with onboard inertial measurement units (IMU), as an easy and non-invasive way to detect visual distractions by measuring head movements linked to such behaviors. Head movement data from 20 participants were collected during natural cycling situations using earable IMU sensors. Both classical machine learning and deep learning techniques are employed to analyze the data to detect visual distractions. Support Vector Machine (SVM) and Convolutional Neural Network (CNN) achieve weighted F1 scores of 0.85 and 0.87, and Cohen's Kappa scores of 0.74 and 0.59, respectively. These findings highlight the potential of earable devices in real-time distraction detection and establish a foundation for future wearable safety systems for cyclists.

KW - earables

KW - edge computing

KW - head gestures

KW - inertial measurement unit

KW - neural networks

UR - https://www.scopus.com/pages/publications/105027031451

U2 - 10.1145/3714394.3757261

DO - 10.1145/3714394.3757261

M3 - Conference contribution

AN - SCOPUS:105027031451

SP - 847

EP - 853

BT - UbiComp Companion '25

A2 - Beigl, Michael

A2 - Jacucci, Giulio

A2 - Sigg, Stephan

A2 - Xiao, Yu

A2 - Bardram, Jakob E.

A2 - Tsiropoulou, Eirini Eleni

A2 - Xu, Chenren

PB - Association for Computing Machinery, Inc

CY - New York

T2 - ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2025

Y2 - 12 October 2024 through 16 October 2024

ER -

Balakrishnan S, Pallamreddy A, Huang Y , Durmaz Incel O. Head Movement-Based Visual Distraction Detection in Cyclists with Earables. In Beigl M, Jacucci G, Sigg S, Xiao Y, Bardram JE, Tsiropoulou EE, Xu C, editors, UbiComp Companion '25: Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing. New York: Association for Computing Machinery, Inc. 2025. p. 847-853 doi: 10.1145/3714394.3757261

Head Movement-Based Visual Distraction Detection in Cyclists with Earables

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this