Driver fatigue detection using PPG signal, facial features, head postures with an LSTM model

Background and objective: Background and objective: Human fatigue is a major cause of road traffic accidents. Currently widely used fatigue driving detection methods are based on eyelid closure, vehicle information or physiological parameter detection. However, the detection of each single feature h...

Full description

Saved in:
Bibliographic Details
Main Authors: Lu Yu, Xinyi Yang, Hengjian Wei, Jianguo Liu, Bo Li
Format: Article
Language:English
Published: Elsevier 2024-11-01
Series:Heliyon
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405844024155107
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846167022281424896
author Lu Yu
Xinyi Yang
Hengjian Wei
Jianguo Liu
Bo Li
author_facet Lu Yu
Xinyi Yang
Hengjian Wei
Jianguo Liu
Bo Li
author_sort Lu Yu
collection DOAJ
description Background and objective: Background and objective: Human fatigue is a major cause of road traffic accidents. Currently widely used fatigue driving detection methods are based on eyelid closure, vehicle information or physiological parameter detection. However, the detection of each single feature has certain limitations. Which in turn affects the accuracy of detection and the possibility and efficiency of prediction. Methods: This paper introduces a novel driver fatigue detection framework that leverages facial features, head pose, and PPG signals to establish a fatigue detection model. To validate this approach, a real-road driving experiment was conducted, resulting in the acquisition of multi-source feature signal data from 30 drivers. Utilizing a method for locating 68 facial landmarks, we extracted 2D facial and 3D head feature parameters. Additionally, five-dimensional heart rate variability (HRV) features were extracted from PPG signals. These ten-dimensional features were fused to construct a fatigue driving dataset. Subsequently, a Long Short-Term Memory (LSTM) network model for fatigue detection was established and optimized using four optimization algorithms: Momentum, Rmsprop, Adam, and SGD. For comparison, Decision Tree (DT), Random Forest (RF), and Bidirectional LSTM (BiLSTM) models were also evaluated. Within the dataset, 2880 samples were designated as the training set, while 720 samples served as the test set. Results: Adam's optimized LSTM fatigue detection model is the most effective, with a model accuracy of 97.36 %, precision of 97.4 %, recall of 97.4 %, and F1 of 0.97. It shows that the model can provide a more timely and accurate prediction and warning for drivers who are already fatigued.
format Article
id doaj-art-1aae97e26d3a42dc89830a302b396c66
institution Kabale University
issn 2405-8440
language English
publishDate 2024-11-01
publisher Elsevier
record_format Article
series Heliyon
spelling doaj-art-1aae97e26d3a42dc89830a302b396c662024-11-15T06:12:50ZengElsevierHeliyon2405-84402024-11-011021e39479Driver fatigue detection using PPG signal, facial features, head postures with an LSTM modelLu Yu0Xinyi Yang1Hengjian Wei2Jianguo Liu3Bo Li4School of Traffic and Transportation Engineering, Dalian Jiaotong University, Liaoning, Dalian, 116028, China; Corresponding author.School of Traffic and Transportation Engineering, Dalian Jiaotong University, Liaoning, Dalian, 116028, ChinaSchool of Traffic and Transportation Engineering, Dalian Jiaotong University, Liaoning, Dalian, 116028, ChinaSchool of Civil and Resource Engineering from University of Science and Technology Beijing, Beijing, 100083, ChinaSchool of Traffic and Transportation Engineering, Dalian Jiaotong University, Liaoning, Dalian, 116028, ChinaBackground and objective: Background and objective: Human fatigue is a major cause of road traffic accidents. Currently widely used fatigue driving detection methods are based on eyelid closure, vehicle information or physiological parameter detection. However, the detection of each single feature has certain limitations. Which in turn affects the accuracy of detection and the possibility and efficiency of prediction. Methods: This paper introduces a novel driver fatigue detection framework that leverages facial features, head pose, and PPG signals to establish a fatigue detection model. To validate this approach, a real-road driving experiment was conducted, resulting in the acquisition of multi-source feature signal data from 30 drivers. Utilizing a method for locating 68 facial landmarks, we extracted 2D facial and 3D head feature parameters. Additionally, five-dimensional heart rate variability (HRV) features were extracted from PPG signals. These ten-dimensional features were fused to construct a fatigue driving dataset. Subsequently, a Long Short-Term Memory (LSTM) network model for fatigue detection was established and optimized using four optimization algorithms: Momentum, Rmsprop, Adam, and SGD. For comparison, Decision Tree (DT), Random Forest (RF), and Bidirectional LSTM (BiLSTM) models were also evaluated. Within the dataset, 2880 samples were designated as the training set, while 720 samples served as the test set. Results: Adam's optimized LSTM fatigue detection model is the most effective, with a model accuracy of 97.36 %, precision of 97.4 %, recall of 97.4 %, and F1 of 0.97. It shows that the model can provide a more timely and accurate prediction and warning for drivers who are already fatigued.http://www.sciencedirect.com/science/article/pii/S2405844024155107Driver fatiguePPG signalsLSTM modelFacial featureHead posture
spellingShingle Lu Yu
Xinyi Yang
Hengjian Wei
Jianguo Liu
Bo Li
Driver fatigue detection using PPG signal, facial features, head postures with an LSTM model
Heliyon
Driver fatigue
PPG signals
LSTM model
Facial feature
Head posture
title Driver fatigue detection using PPG signal, facial features, head postures with an LSTM model
title_full Driver fatigue detection using PPG signal, facial features, head postures with an LSTM model
title_fullStr Driver fatigue detection using PPG signal, facial features, head postures with an LSTM model
title_full_unstemmed Driver fatigue detection using PPG signal, facial features, head postures with an LSTM model
title_short Driver fatigue detection using PPG signal, facial features, head postures with an LSTM model
title_sort driver fatigue detection using ppg signal facial features head postures with an lstm model
topic Driver fatigue
PPG signals
LSTM model
Facial feature
Head posture
url http://www.sciencedirect.com/science/article/pii/S2405844024155107
work_keys_str_mv AT luyu driverfatiguedetectionusingppgsignalfacialfeaturesheadpostureswithanlstmmodel
AT xinyiyang driverfatiguedetectionusingppgsignalfacialfeaturesheadpostureswithanlstmmodel
AT hengjianwei driverfatiguedetectionusingppgsignalfacialfeaturesheadpostureswithanlstmmodel
AT jianguoliu driverfatiguedetectionusingppgsignalfacialfeaturesheadpostureswithanlstmmodel
AT boli driverfatiguedetectionusingppgsignalfacialfeaturesheadpostureswithanlstmmodel