Mobile-based Kernel-Fuzzy-C-Means-Wavelet for Driver Fatigue Prediction with Cloud Computing

Boon Giin Lee; Jae Hee Park; Chuan Chin Pu; Wan Young Chung

doi:10.1109/ICSENS.2014.6985233

Mobile-based Kernel-Fuzzy-C-Means-Wavelet for Driver Fatigue Prediction with Cloud Computing

Boon Giin Lee
, Jae Hee Park
, Chuan Chin Pu
, Wan Young Chung

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

5 Citations (Scopus)

Abstract

A driver fatigue monitoring system with high precision could be a monetary countermeasure to reduce the road accidents. This study focuses on delivering fatigue prediction based on photoplethysmogram (PPG) and electrocardiogram (ECG) wavelet spectrum analysis. Specifically, an adaptive threshold method is utilized for PPG and ECG artifacts removal, peak and onset detection. Subsequently, the wavelet coefficients generated are further composed into very low frequency, low frequency and high frequency bands. Autonomous rule extraction is performed by using Kernel Fuzzy C-Means (Kernel FCM) with "if-then" rules to train the dataset for classifying driver vigilance level. By developing the hierarchical prediction model in smartphone device, it enabled the sensing data collection, fatigue level analysis, and warning sounded to driver when low arousal is detected, thus provide a safe and non-obstructive driving environment. Collected and analyzed data is uploaded to cloud server for remote monitoring. The experimental results validated prediction accuracy can be achieved at 96% to 98% on average across subjects.

Original language	English
Title of host publication	IEEE SENSORS 2014, Proceedings
Editors	Francisco J. Arregui
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1236-1239
Number of pages	4
Edition	December
ISBN (Electronic)	9781479901616
DOIs	https://doi.org/10.1109/ICSENS.2014.6985233
Publication status	Published - 15 Dec 2014
Externally published	Yes
Event	13th IEEE SENSORS Conference, SENSORS 2014 - Valencia, Spain Duration: 2 Nov 2014 → 5 Nov 2014

Publication series

Name	Proceedings of IEEE Sensors
Number	December
Volume	2014-December
ISSN (Print)	1930-0395
ISSN (Electronic)	2168-9229

Conference

Conference	13th IEEE SENSORS Conference, SENSORS 2014
Country/Territory	Spain
City	Valencia
Period	2/11/14 → 5/11/14

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Free Keywords

Adaptive threshold
Cloud server
ECG
Fatigue prediction
Kernel fuzzy cmeans
PPG
Wavelet spectrum

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1109/ICSENS.2014.6985233

Cite this

Lee, B. G., Park, J. H., Pu, C. C., & Chung, W. Y. (2014). Mobile-based Kernel-Fuzzy-C-Means-Wavelet for Driver Fatigue Prediction with Cloud Computing. In F. J. Arregui (Ed.), IEEE SENSORS 2014, Proceedings (December ed., pp. 1236-1239). Article 6985233 (Proceedings of IEEE Sensors; Vol. 2014-December, No. December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSENS.2014.6985233

@inproceedings{ba35c14b41c3437f97348a37e7cd2fbf,

title = "Mobile-based Kernel-Fuzzy-C-Means-Wavelet for Driver Fatigue Prediction with Cloud Computing",

abstract = "A driver fatigue monitoring system with high precision could be a monetary countermeasure to reduce the road accidents. This study focuses on delivering fatigue prediction based on photoplethysmogram (PPG) and electrocardiogram (ECG) wavelet spectrum analysis. Specifically, an adaptive threshold method is utilized for PPG and ECG artifacts removal, peak and onset detection. Subsequently, the wavelet coefficients generated are further composed into very low frequency, low frequency and high frequency bands. Autonomous rule extraction is performed by using Kernel Fuzzy C-Means (Kernel FCM) with {"}if-then{"} rules to train the dataset for classifying driver vigilance level. By developing the hierarchical prediction model in smartphone device, it enabled the sensing data collection, fatigue level analysis, and warning sounded to driver when low arousal is detected, thus provide a safe and non-obstructive driving environment. Collected and analyzed data is uploaded to cloud server for remote monitoring. The experimental results validated prediction accuracy can be achieved at 96\% to 98\% on average across subjects.",

keywords = "Adaptive threshold, Cloud server, ECG, Fatigue prediction, Kernel fuzzy cmeans, PPG, Wavelet spectrum",

author = "Lee, \{Boon Giin\} and Park, \{Jae Hee\} and Pu, \{Chuan Chin\} and Chung, \{Wan Young\}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 13th IEEE SENSORS Conference, SENSORS 2014 ; Conference date: 02-11-2014 Through 05-11-2014",

year = "2014",

month = dec,

day = "15",

doi = "10.1109/ICSENS.2014.6985233",

language = "English",

series = "Proceedings of IEEE Sensors",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "December",

pages = "1236--1239",

editor = "Arregui, \{Francisco J.\}",

booktitle = "IEEE SENSORS 2014, Proceedings",

address = "United States",

edition = "December",

}

Lee, BG, Park, JH, Pu, CC & Chung, WY 2014, Mobile-based Kernel-Fuzzy-C-Means-Wavelet for Driver Fatigue Prediction with Cloud Computing. in FJ Arregui (ed.), IEEE SENSORS 2014, Proceedings. December edn, 6985233, Proceedings of IEEE Sensors, no. December, vol. 2014-December, Institute of Electrical and Electronics Engineers Inc., pp. 1236-1239, 13th IEEE SENSORS Conference, SENSORS 2014, Valencia, Spain, 2/11/14. https://doi.org/10.1109/ICSENS.2014.6985233

Mobile-based Kernel-Fuzzy-C-Means-Wavelet for Driver Fatigue Prediction with Cloud Computing. / Lee, Boon Giin; Park, Jae Hee; Pu, Chuan Chin et al.
IEEE SENSORS 2014, Proceedings. ed. / Francisco J. Arregui. December. ed. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1236-1239 6985233 (Proceedings of IEEE Sensors; Vol. 2014-December, No. December).

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

TY - GEN

T1 - Mobile-based Kernel-Fuzzy-C-Means-Wavelet for Driver Fatigue Prediction with Cloud Computing

AU - Lee, Boon Giin

AU - Park, Jae Hee

AU - Pu, Chuan Chin

AU - Chung, Wan Young

PY - 2014/12/15

Y1 - 2014/12/15

N2 - A driver fatigue monitoring system with high precision could be a monetary countermeasure to reduce the road accidents. This study focuses on delivering fatigue prediction based on photoplethysmogram (PPG) and electrocardiogram (ECG) wavelet spectrum analysis. Specifically, an adaptive threshold method is utilized for PPG and ECG artifacts removal, peak and onset detection. Subsequently, the wavelet coefficients generated are further composed into very low frequency, low frequency and high frequency bands. Autonomous rule extraction is performed by using Kernel Fuzzy C-Means (Kernel FCM) with "if-then" rules to train the dataset for classifying driver vigilance level. By developing the hierarchical prediction model in smartphone device, it enabled the sensing data collection, fatigue level analysis, and warning sounded to driver when low arousal is detected, thus provide a safe and non-obstructive driving environment. Collected and analyzed data is uploaded to cloud server for remote monitoring. The experimental results validated prediction accuracy can be achieved at 96% to 98% on average across subjects.

AB - A driver fatigue monitoring system with high precision could be a monetary countermeasure to reduce the road accidents. This study focuses on delivering fatigue prediction based on photoplethysmogram (PPG) and electrocardiogram (ECG) wavelet spectrum analysis. Specifically, an adaptive threshold method is utilized for PPG and ECG artifacts removal, peak and onset detection. Subsequently, the wavelet coefficients generated are further composed into very low frequency, low frequency and high frequency bands. Autonomous rule extraction is performed by using Kernel Fuzzy C-Means (Kernel FCM) with "if-then" rules to train the dataset for classifying driver vigilance level. By developing the hierarchical prediction model in smartphone device, it enabled the sensing data collection, fatigue level analysis, and warning sounded to driver when low arousal is detected, thus provide a safe and non-obstructive driving environment. Collected and analyzed data is uploaded to cloud server for remote monitoring. The experimental results validated prediction accuracy can be achieved at 96% to 98% on average across subjects.

KW - Adaptive threshold

KW - Cloud server

KW - ECG

KW - Fatigue prediction

KW - Kernel fuzzy cmeans

KW - PPG

KW - Wavelet spectrum

UR - https://www.scopus.com/pages/publications/84931075544

U2 - 10.1109/ICSENS.2014.6985233

DO - 10.1109/ICSENS.2014.6985233

M3 - Conference contribution

AN - SCOPUS:84931075544

T3 - Proceedings of IEEE Sensors

SP - 1236

EP - 1239

BT - IEEE SENSORS 2014, Proceedings

A2 - Arregui, Francisco J.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th IEEE SENSORS Conference, SENSORS 2014

Y2 - 2 November 2014 through 5 November 2014

ER -

Mobile-based Kernel-Fuzzy-C-Means-Wavelet for Driver Fatigue Prediction with Cloud Computing

Abstract

Publication series

Conference

UN SDGs

Free Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this