[1]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(原第三军医大学学报),2022,44(13):1299-1306.
 XIANG Hongyi,ZHANG Qiongmin,WANG Junjie,et al.Driving fatigue recognition model based on heart rate variability and respiratory rate[J].J Amry Med Univ (J Third Mil Med Univ),2022,44(13):1299-1306.
点击复制

基于心率变异性和呼吸频率的驾驶疲劳识别模型研究(/HTML )
分享到:

陆军军医大学学报(原第三军医大学学报)[ISSN:1000-5404/CN:51-1095/R]

卷:
44卷
期数:
2022年第13期
页码:
1299-1306
栏目:
军事医学
出版日期:
2022-07-15

文章信息/Info

Title:
Driving fatigue recognition model based on heart rate variability and respiratory rate
作者:
向洪义张琼敏王俊杰王思平廖志康孙丽璐李奎赵辉
陆军特色医学中心军事交通伤防治研究室;重庆理工大学:计算机科学与工程学院,管理学院
Author(s):
XIANG Hongyi1 ZHANG Qiongmin2 WANG Junjie2 WANG Siping2 LIAO Zhikang1 SUN Lilu3 LI Kui1 ZHAO Hui1

1Department of Military Traffic Injury Prevention and Treatment, Army Medical Center of PLA, Chongqing, 400042; 2College of Computer Science and Engineering, 3College of Management, Chongqing University of Technology, Chongqing, 400054, China 

关键词:
军用车辆驾驶疲劳心率变异性呼吸频率机器学习
Keywords:
military vehicles driving fatigue heart rate variability respiratory rate machine learnin
分类号:
R331.18; R332.2; R338.63
文献标志码:
A
摘要:

目的建立结合心率变异性(heart rate variability,HRV)和呼吸频率(respiratory rate,RESP)的驾驶疲劳识别机器学习模型并明确最优特征子集。方法2021年6-12月,从陆军军医大学招募20名年龄在20~30岁之间的健康男性志愿者参加疲劳驾驶试验。记录正常睡眠和睡眠剥夺后驾驶员在驾驶任务中的心电信号,提取18维疲劳相关HRV特征值,选择清醒与疲劳状态下存在差异的HRV特征结合RESP作为特征集。比较支持向量机(support vector machines, SVM)、K最邻近(k-nearest neighbor,KNN)、朴素贝叶斯(naive Bayes,NB)、决策树(decision tree,DT)和逻辑回归(logistic regression,LR)这五种经典机器学习方法,筛选最优特征子集,并建立疲劳识别模型。结果低频功率(low frequency,LF)与高频功率(high frequency,HF)的比值LF/HF、RESP、平均RR间隔(mean RR interval,Mean RR)、样本熵(sample entropy,SampEn)、去趋势波动分析(detrended fluctuation analysis,DFA)短期斜率DFA α1五个特征是疲劳识别的有效特征子集,在SVM中分类效果最好,疲劳识别的准确性、敏感性、特异性分别为87.03%、87.07%、87.13%。其中LF/HF和RESP是最为重要的驾驶疲劳识别指标,两个维度下各个模型的准确性均能达到80%以上,SVM与LR整体表现更好,准确性、敏感性、特异性分别为84.99%、85.13%、82.65%和84.43%、86.49%、82.02%。结论LF/HF、RESP是驾驶疲劳识别的有效特征,在基于HRV特征和RESP的驾驶疲劳识别中SVM与LR的整体表现优于其他模型。

Abstract:

ObjectiveTo establish a machine learning model for driving fatigue recognition based on heart rate variability (HRV) and respiratory rate (RESP), and identify the optimal subsets of features. MethodsFrom June 2021 to December 2021, 20 healthy male volunteers between the ages of 20 and 30 were recruited from the Army Medical University to participate in the fatigue driving experiment.  The electrocardiographic (ECG) signals under normal sleep and sleep deprivation during driving tasks were recorded, and 18-dimensional fatigue-related HRV feature values were extracted. The HRV features that differ between awake and fatigue states were selected, which were further combined with RESP as the feature set. Moreover, 5 classic machine learning methods were adopted and compared, including support vector machines (SVM), k-nearest neighbor (KNN), naive Bayes (NB), decision tree (DT) and logistic regression (LR). The optimal feature subset was screened, and then a fatigue recognition model was established. ResultsThe ratio of low frequency power to high frequency power (LF/HF), RESP, mean RR interval (Mean RR), sample entropy (SampEn), and detrended fluctuation analysis short-term slope (DFAα1) constituted the effective feature subsets of fatigue recognition, which achieved the best classification effect in SVM, with an accuracy of 87.03%, a sensitivity of 87.07% and a specificity of 87.13% in fatigue recognition. Among them, LF/HF and RESP were found as the most important indicators of driving fatigue identification, with an accuracy of each model in the above 2 dimensions reaching more than 80%. In addition, SVM and LR showed better overall performance, with an accuracy, sensitivity and specificity of 84.99%, 85.13%, 82.65% for SVM and 84.43%, 86.49%, 82.02% for LR, respectively. ConclusionLF/HF and RESP are the effective features for driving fatigue recognition. In the driving fatigue recognition model based on HRV features and RESP, the overall performance of SVM and LR models is better than the other models. 

参考文献/References:

[1]LE T D, GURNEY J M, NNAMANI N S, et al. A 12-year analysis of nonbattle injury among US service members deployed to Iraq and Afghanistan[J]. JAMA Surg, 2018, 153(9): 800-807. DOI:10.1001/jamasurg.2018.1166.
[2]SCHWEIZER M A, JANAK J C, GRAHAM B, et al. Nonfatal motor vehicle related injuries among deployed US Service members: Characteristics, trends, and risks for limb amputations[J]. J Trauma Acute Care Surg, 2019, 87(4): 907-914. DOI:10.1097/TA.0000000000002436.
[3]DE ZAMBOTTI M, TRINDER J, SILVANI A, et al. Dynamic coupling between the central and autonomic nervous systems during sleep: a review[J]. Neurosci Biobehav Rev, 2018, 90: 84-103. DOI:10.1016/j.neubiorev.2018.03.027.
[4]TANAKA M, TAJIMA S, MIZUNO K, et al. Frontier studies on fatigue, autonomic nerve dysfunction, and sleep-rhythm disorder[J]. J Physiol Sci, 2015, 65(6): 483-498. DOI:10.1007/s12576-015-0399-y.
[5]PERSSON A, JONASSON H, FREDRIKSSON I, et al. Heart rate variability for classification of alert versus sleep deprived drivers in real road driving conditions[J]. IEEE Trans Intell Transp Syst, 2020, 22(6): 3316-3325. DOI:10.1109/TITS.2020.2981941.
[6]VARON C, LAZARO J, BOLEA J, et al. Unconstrained estimation of HRV indices after removing respiratory influences from heart rate[J]. IEEE J Biomed Health Inform, 2019, 23(6): 2386-2397. DOI:10.1109/JBHI.2018.2884644.
[7]MALIK M, BIGGER J T, CAMM A J, et al. Heart rate variability: standards of measurement, physiological interpretation, and clinical use[J]. Eur Heart J, 1996, 17(3): 354-381. DOI:10.1093/oxfordjournals.eurheartj.a014868.
[8]YENTES J M, HUNT N, SCHMID K K, et al. The appropriate use of approximate entropy and sample entropy with short data sets[J]. Ann Biomed Eng, 2013, 41(2): 349-365. DOI:10.1007/s10439-012-0668-3.
[9]ESPINOSA R, TALERO J, WEINSTEIN A. Effects of tau and sampling frequency on the regularity analysis of ECG and EEG signals using ApEn and SampEn entropy estimators[J]. Entropy (Basel), 2020, 22(11): 1298. DOI:10.3390/e22111298.
[10]CICCONE A B, SIEDLIK J A, WECHT J M, et al. Reminder: RMSSD and SD1 are identical heart rate variability metrics[J]. Muscle Nerve, 2017, 56(4): 674-678. DOI:10.1002/mus.25573.
[11]National Highway Traffic Safety Administration.  Drowsy driving[EB/OL]. [2022-03-06]. https://www.nhtsa.gov/risky-driving/drowsy-driving.
[12]LIU G D, CHEN S Y, ZENG Z Q, et al. Risk factors for extremely serious road accidents: results from national Road Accident Statistical Annual Report of China[J]. PLoS One, 2018, 13(8): e0201587. DOI:10.1371/journal.pone.0201587.
[13]WANG J, YU X P, LIU Q, et al. Research on key technologies of intelligent transportation based on image recognition and anti-fatigue driving[J]. J Image Video Proc, 2019, 2019: 33. DOI:10.1186/s13640-018-0403-6.
[14]GOOD C H, BRAGER A J, CAPALDI V F, et al. Sleep in the United States military[J]. Neuropsychopharmacology, 2020, 45(1): 176-191. DOI:10.1038/s41386-019-0431-7.
[15]TEFFT B C. Acute sleep deprivation and culpable motor vehicle crash involvement[J]. Sleep, 2018, 41(10). DOI:10.1093/sleep/zsy144.
[16]CZEISLER C A, WICKWIRE E M, BARGER L K, et al. Sleep-deprived motor vehicle operators are unfit to drive: a multidisciplinary expert consensus statement on drowsy driving[J]. Sleep Health, 2016, 2(2): 94-99. DOI:10.1016/j.sleh.2016.04.003.
[17]黄晓婷. 急性部分睡眠剥夺对医务人员心血管自主神经活动的影响[D]. 福州: 福建医科大学, 2017. 
HUANG X T. The effects of acute partial sleep deprivation on cardiovascular autonomic modulation[D]. Fuzhou: Fujian Medical University, 2017. 
[18]赵小静,路海月,王梦悦,等.基于心率变异性的脑力疲劳检测[J].中国医学物理学杂志,2018,35(5):592-597. DOI:10.3969/j.issn.1005-202X.2018.05.017.
ZHAO X J, LU H Y, WANG M Y, et al. Mental fatigue detection based on heart rate variability[J].Chin J Med Physics,2018,35(5):592-597. DOI:10.3969/j. issn.1005-202X.2018.05.017.
[19]BUENDIA R, FORCOLIN F, KARLSSON J, et al. Deriving heart rate variability indices from cardiac monitoring—An indicator of driver sleepiness[J]. Traffic Inj Prev, 2019, 20(3): 249-254. DOI:10.1080/15389588.2018.1548766.
[20]LIANG W C, YUAN J, SUN D C, et al. Changes in physiological parameters induced by indoor simulated driving: effect of lower body exercise at mid-term break[J]. Sensors (Basel), 2009, 9(9): 6913-6933. DOI:10.3390/s90906913.
[21]AWAIS M, BADRUDDIN N, DRIEBERG M. A hybrid approach to detect driver drowsiness utilizing physiological signals to improve system performance and wearability[J]. Sensors (Basel), 2017, 17(9): E1991. DOI:10.3390/s17091991.
[22]BABAEIAN M, MOZUMDAR M. Driver drowsiness detection algorithms using electrocardiogram data analysis[C]//2019 IEEE 9th Annual Computing and Communication Workshop and Conference. IEEE, 2019: 1-6. DOI:10.1109/CCWC.2019.8666467.
[23]RAMZAN M, KHAN H U, AWAN S M, et al. A survey on state-of-the-art drowsiness detection techniques[J]. IEEE Access, 2019, 7: 61904-61919. DOI:10.1109/ACCESS.2019.2914373.
[24]DOUDOU M, BOUABDALLAH A, BERGE-CHERFAOUI V. Driver drowsiness measurement technologies: current research, market solutions, and challenges[J]. Int J Intell Transp Syst Res, 2020, 18(2): 297-319. DOI:10.1007/s13177-019-00199-w.
 

更新日期/Last Update: 2022-07-05