TU Darmstadt / ULB / TUprints

Multi-Level Classification of Driver Drowsiness by Simultaneous Analysis of ECG and Respiration Signals Using Deep Neural Networks

Ebrahimian, Serajeddin ; Nahvi, Ali ; Tashakori, Masoumeh ; Salmanzadeh, Hamed ; Mohseni, Omid ; Leppänen, Timo (2022)
Multi-Level Classification of Driver Drowsiness by Simultaneous Analysis of ECG and Respiration Signals Using Deep Neural Networks.
In: International Journal of Environmental Research and Public Health, 2022, 19 (17)
doi: 10.26083/tuprints-00022328
Article, Secondary publication, Publisher's Version

[img] Text
ijerph-19-10736.pdf
Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (2MB)
Item Type: Article
Type of entry: Secondary publication
Title: Multi-Level Classification of Driver Drowsiness by Simultaneous Analysis of ECG and Respiration Signals Using Deep Neural Networks
Language: English
Date: 12 September 2022
Place of Publication: Darmstadt
Year of primary publication: 2022
Publisher: MDPI
Journal or Publication Title: International Journal of Environmental Research and Public Health
Volume of the journal: 19
Issue Number: 17
Collation: 17 Seiten
DOI: 10.26083/tuprints-00022328
Corresponding Links:
Origin: Secondary publication DeepGreen
Abstract:

The high number of fatal crashes caused by driver drowsiness highlights the need for developing reliable drowsiness detection methods. An ideal driver drowsiness detection system should estimate multiple levels of drowsiness accurately without intervening in the driving task. This paper proposes a multi-level drowsiness detection system by a deep neural network-based classification system using a combination of electrocardiogram and respiration signals. The proposed method is based on a combination of convolutional neural networks (CNNs) and long short-term memory (LSTM) networks for classifying drowsiness by concurrently using heart rate variability (HRV), power spectral density of HRV, and respiration rate signal as inputs. Two models, a CNN-based model and a hybrid CNN-LSTM-based model were used for multi-level classifications. The performance of the proposed method was evaluated on experimental data collected from 30 subjects in a simulated driving environment. The performance and the results of both models are presented and compared. The best performance for both three-level and five-level drowsiness classifications was achieved by the CNN-LSTM model. The results indicate that the three-level and five-level classifications of drowsiness can be achieved with 91 and 67% accuracy, respectively.

Uncontrolled Keywords: ECG, respiration, deep learning, drowsiness detection, multi-level classification
Status: Publisher's Version
URN: urn:nbn:de:tuda-tuprints-223281
Additional Information:

This article belongs to the Special Issue Applications of Artificial Intelligence to Health

Classification DDC: 600 Technology, medicine, applied sciences > 620 Engineering and machine engineering
Divisions: 03 Department of Human Sciences > Institut für Sportwissenschaft
Zentrale Einrichtungen > Centre for Cognitive Science (CCS)
Date Deposited: 12 Sep 2022 13:23
Last Modified: 14 Nov 2023 19:05
SWORD Depositor: Deep Green
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/22328
PPN: 499564723
Export:
Actions (login required)
View Item View Item