|本期目录/Table of Contents|

[1]刘成昊,罗义凯,陈邦举,等.面向短时心电信号的驾驶疲劳检测方法*[J].中国安全生产科学技术,2025,21(8):29-37.[doi:10.11731/j.issn.1673-193x.2025.08.004]
　LIU Chenghao,LUO Yikai,CHEN Bangju,et al.Driving fatigue detection method for short-term electrocardiogram signals[J].Journal of Safety Science and Technology,2025,21(8):29-37.[doi:10.11731/j.issn.1673-193x.2025.08.004]
点击复制

面向短时心电信号的驾驶疲劳检测方法*

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
21
期数:
2025年8期
页码:
29-37
栏目:
学术论著
出版日期:
2025-08-30

文章信息/Info

Title:
Driving fatigue detection method for short-term electrocardiogram signals
文章编号:
1673-193X(2025)-08-0029-09
作者:
刘成昊; 罗义凯; 陈邦举; 徐金华; 李昱燃; 李岩
（1.长安大学 运输工程学院，陕西 西安 710064；
2.北京理工大学 机械与车辆学院，北京 100081；
3.中国交通通信信息中心，北京 100011）
Author(s):
LIU Chenghao;  LUO Yikai;  CHEN Bangju;  XU Jinhua;  LI Yuran;  LI Yan
（1.College of Transportation Engineering,Chang’an University,Xi’an Shaanxi 710064,China;
2.School of Mechanical Engineering,Beijing Institute of Technology,Beijing 100081,China;
3.China Transport Telecommunications & Information Center,Beijing 100011,China）
关键词:
疲劳检测; 心电信号; 轻量梯度提升机; 核主成分分析; 粒子群优化
Keywords:
fatigue detection;  electrocardiogram signal;  light gradient boosting machine;  kernel principal component analysis;  particle swarm optimization
分类号:
X951
DOI:
10.11731/j.issn.1673-193x.2025.08.004
文献标志码:
A
摘要:
基于心电信号的驾驶疲劳检测具有准确、非侵入和低成本的优点，但传统方法需要采集较长时间数据，导致检测延迟，难以进行实时检测，提出1种面向短时心电数据的驾驶疲劳检测方法。该方法包括特征提取与疲劳识别2个模块，使用滤波方法预处理心电数据，以提取心率变异性(heart rate variability,HRV)与心电信号(electrocardiogram,ECG)指标作为识别特征；结合改进粒子群优化算法、核主成分分析与LightGBM模型进行疲劳检测，并将所提方法应用于DROZY数据集，以卡罗琳斯卡嗜睡量表评价作为标签。研究结果表明：所提方法可利用短时心电数据实现准确的疲劳检测，针对5，10，15 s的心电信号，所提方法的5折交叉验证平均检测准确率分别为95.54%，97.90%和99.05%，均优于对比方法，验证了所选特征指标的有效性。研究结果可为驾驶安全检测系统提供技术支持。
Abstract:
Driving fatigue detection based on electrocardiogram (ECG) signals offers advantages of accuracy,non-invasiveness,and low cost.However,traditional methods require prolonged data acquisition,leading to detection latency that hinders real-time monitoring.In order to address this limitation,this study proposed a driving fatigue detection method specifically designed for short-term ECG data.The proposed method consists of two modules: feature extraction and fatigue recognition.ECG data is preprocessed using filtering techniques to extract heart rate variability (HRV) and ECG signal indicators as recognition features.Fatigue detection is then performed by integrating an improved particle swarm optimization (IPSO) algorithm,kernel principal component analysis (KPCA),and the LightGBM model.The proposed method was tested using the DROZY dataset,where the Karolinska Sleepiness Scale was used as the labeling standard for evaluation.The results demonstrate that the proposed method enables accurate fatigue detection using short-term ECG data.For ECG signals of 5,10,and 15 s,the average detection accuracy rates in 5-fold cross-validation are 95.54%,97.90%,and 99.05%,respectively,outperforming the comparison methods and validating the effectiveness of the selected feature indicators.These findings provide technical support for driving safety monitoring systems.

参考文献/References:

［1］闵建亮,蔡铭.基于前额脑电多尺度小波对数能量熵的驾驶疲劳检测分析［J］.中国公路学报,2020,33(6):182-189. MIN Jianliang,CAI Ming.Driver fatigue detection based on multi-scale wavelet log energy entropy of frontal EEG［J］.China Journal of Highway and Transport,2020,33(6):182-189.
［2］熊睿,邓院昌.疲劳驾驶交通事故的严重程度影响因素分析［J］.中国安全生产科学技术,2022,18(4):20-26. XIONG Rui,DENG Yuanchang.Analysis on factors affecting severity of traffic accidents caused by fatigue driving［J］.Journal of Safety Science and Technology,2022,18(4):20-26.
［3］陈骥驰,王宏,王翘秀,等.基于脑电信号的疲劳驾驶状态研究［J］.汽车工程,2018,40(5):515-520. CHEN Jichi,WANG Hong,WANG Qiaoxiu,et al.A study on drowsy driving state based on EEG signals［J］.Automotive Engineering,2018,40(5):515-520.
［4］ORSINI F,GIUSTI G,ZARANTONELLO L,et al.Driving fatigue increases after the spring transition to daylight saving time in young male drivers:a pilot study［J］.Transportation Research Part F:Traffic Psychology and Behaviour,2023,99:83-97.
［5］施冬梅,肖锋.基于改进长短时记忆网络的驾驶行为检测方法研究［J］.汽车工程,2021,43(8):1203-1209，1262. SHI Dongmei,XIAO Feng.Study on driving behavior detection method based on improved long and short-term memory network［J］.Automotive Engineering,2021,43(8):1203-1209，1262.
［6］FREITAS A,ALMEIDA R,GONALVES H,et al.Monitoring fatigue and drowsiness in motor vehicle occupants using electrocardiogram and heart rate - A systematic review［J］.Transportation Research Part F:Traffic Psychology and Behaviour,2024,103:586-607.
［7］GAO R,YAN H,DUAN J,et al.Study on the nonfatigue and fatigue states of orchard workers based on electrocardiogram signal analysis［J］.Scientific Reports,2022,12(1):48-58.
［8］ZHAO L,LI M,HE Z,et al.Data-driven learning fatigue detection system:a multimodal fusion approach of ECG (electrocardiogram) and video signals［J］.Measurement,2022,201,111648.
［9］陶克雪,陈建武,蒋引,等.作业人员疲劳测量量表应用研究分析［J］.中国安全生产科学技术,2023,19(7):186-191. TAO Kexue,CHEN Jianwu,JIANG Yin,et al.Application research analysis of fatigue measurement scale for workers［J］.Journal of Safety Science and Technology,2023,19(7):186-191.
［10］VICENTE J,LAGUNA P,BARTRA A,et al.Drowsiness detection using heart rate variability［J］.Medical & Biological Engineering & Computing,2016,54:927-937.
［11］黄诗童,张威强,张朋柱.基于HRV分析的可穿戴心电仪精神疲劳检测［J］.计算机应用研究,2019,36(7):2093-2097，2103. HUANG Shitong,ZHANG Weiqiang,ZHANG Pengzhu.Detection of mental fatigue with wearable ECG devices based on HRV analysis［J］.Application Research of Computers,2019,36(7):2093-2097，2103.
［12］KUNDINGER T,SOFRA N,RIENER A.Assessment of the potential of wrist-worn wearable sensors for driver drowsiness detection［J］.Sensors,2020,20(4):1029.
［13］LU K,DAHLMAN A S,KARLSSON J,et al.Detecting driver fatigue using heart rate variability:a systematic review［J］.Accident Analysis & Prevention,2022,178:106830.
［14］向洪义,张琼敏,王俊杰,等.基于心率变异性和呼吸频率的驾驶疲劳识别模型研究 ［J］.陆军军医大学学报,2022,44(13):1299-306. XIANG Hongyi,ZHANG Qiongin,Wang Junjie,et al.Driving fatigue recognition model based on heart rate variability and respiratory rate［J］.Journal of Third Military Medical University,2022,44(13):1299-306.
［15］陈桂珍,程慧婷,朱才华,等.考虑驾驶员生理信息的城市交叉口风险评估方法［J］.吉林大学学报(工学版),2024,54(5):1277-1284. CHEN Guizhen,CHENG Huiting,ZHU Caihua,et al.A risk evaluation method for urban intersections considering drivers’ physiological information［J］.Journal of Jilin University(Engineering and Technology Edition) 2024,54(5):1277-1284.
［16］MASSOZ Q,LANGOHR T,FRANOIS C,et al.The ULg multi-modality drowsiness database (called DROZY) and examples of use［C］//2016 IEEE Winter Conference on Applications of Computer Vision (WACV).IEEE,2016:1-7.
［17］XU J,LU W,LI Y,et al.A multi-directional recurrent graph convolutional network model for reconstructing traffic spatiotemporal diagram［J］.Transportation Letters,2023,16(5),405-415.

相似文献/References:

[1]陈盈,卢继坤,卢才武,等.fNIRS在智慧矿山辅运司机作业疲劳检测中的应用*[J].中国安全生产科学技术,2026,22(1):183.[doi:10.11731/j.issn.1673-193x.2026.01.023]
　CHEN Ying,LU Jikun,LU Caiwu,et al.The application of fNIRS in the detection of fatigue among deep mine auxiliary transport drivers in smart mines[J].Journal of Safety Science and Technology,2026,22(8):183.[doi:10.11731/j.issn.1673-193x.2026.01.023]

备注/Memo

备注/Memo:
收稿日期： 2024-11-18
* 基金项目： 国家自然科学基金项目(72371035)；陕西省自然科学基础研究计划项目(2025JC-YBMS-367,2025JC-YBQN-524)
作者简介： 刘成昊，硕士研究生，主要研究方向为交通安全、疲劳识别。
通信作者： 李岩，博士，教授，主要研究方向为交通安全、智能交通。
更新日期/Last Update: 2025-09-01