东北大学学报(自然科学版) ›› 2024, Vol. 45 ›› Issue (4): 600-608.DOI: 10.12068/j.issn.1005-3026.2024.04.018
• 资源与土木工程 • 上一篇
郝锐, 郑欣, 李怡霖
收稿日期:
2022-11-11
出版日期:
2024-04-15
发布日期:
2024-06-26
作者简介:
郝 锐(1999-),女,陕西渭南人,东北大学硕士研究生基金资助:
Rui HAO, Xin ZHENG, Yi-lin LI
Received:
2022-11-11
Online:
2024-04-15
Published:
2024-06-26
摘要:
为识别危险作业岗位作业人员的心理负荷,提高人机系统可靠性,以含能材料起爆作业诱导被试人员心理负荷,采集30名被试人员在静息状态和心理负荷下的心率、脑电图和眼动信号进行心理负荷识别研究.首先,采用配对t检验与秩和检验对采集的心率、脑电图和眼动信号进行统计分析,8种脑电、3种眼动及9种心率特征在静息状态和心理负荷下具有显著变化;其次,对初选获得的生理指标分别采用Pearson 相关分析、最大相关最小冗余(MRMR)算法和主成分分析(PCA)进行特征降维;最后,基于上述3种方法降维处理后得到生理指标采用Logistic Regression,KNN,SVM,XG-Boost,Decision Tree和Random Forest机器学习方法进行心理负荷识别.结果表明,基于MRMR的心理负荷特征选择结果,采用Random Forest机器学习方法具有更好的识别性能(ACC=0.917,SN=1.0,SP=0.857,F1=0.909,AUC=0.971).本研究为有效识别危险作业人员心理负荷提供了理论依据.
中图分类号:
郝锐, 郑欣, 李怡霖. 基于生理信号的危险作业人员心理负荷识别研究[J]. 东北大学学报(自然科学版), 2024, 45(4): 600-608.
Rui HAO, Xin ZHENG, Yi-lin LI. Research on Identifying the Psychological Load of Operators in Hazardous Operations Based on Physiological Signals[J]. Journal of Northeastern University(Natural Science), 2024, 45(4): 600-608.
类型 | 指标 | 单位 | 表征含义 |
---|---|---|---|
眼动指标 | 瞳孔直径 | mm | 可以反映自主神经系统的活动,特别是交感神经系统的反应.在心理负荷增加时,瞳孔直径通常会扩大 |
注视时间 | ms | 指个体在特定目标或位置保持注视的持续时间,反映信息可理解性或吸引性,信息识别越困难或用户越感兴趣,注视的时间越长,随着任务需求的增加,注视时间可能会减少 | |
眨眼频率 | 次/min | 单位时间内眨眼次数,表征任务难度或满意度,眨眼频率越高则说明疲劳或情绪消极或搜索任务越简单,在心理负荷增加的情况下,眨眼频率通常会降低 | |
心率指标 | VLF | ms2 | 极低频功率(0.003 3~0.04 Hz),反映体温的调节 |
HF | ms2 | 高频功率(0.15~0.4 Hz),主要反映副交感神经系统的活动 | |
LF | ms2 | 低频功率(0.04~0.15 Hz),与交感神经系统的活动有关,反映身体对压力的生理反应,LF的下降可以反映时间压力或情感压抑程度的增加 | |
LF/HF | — | 评估交感和副交感神经系统平衡的一个指标 | |
HFnorm | Nu | 归一化高频功率 | |
LFnorm | Nu | 归一化低频功率 | |
pNN20 | % | 相邻心跳间隔相差超过20 ms的间隔个数占总个数的百分比,是评估副交感神经系统功能的敏感指标 | |
pNN50 | % | 相邻心跳间隔相差超过50 ms的间隔个数占总个数的百分比,是评估副交感神经系统功能的敏感指标,反映了心跳间隔的不规律性 | |
SDNN | ms | 全部RR间期的标准差,评价整体HRV大小,反映心率的缓慢变化,是评估交感神经系统功能的敏感指标 | |
SDSD | ms | 相邻RR间期之间差值的标准差,用于量化相邻心跳间隔变化的一致性,反映了心率的短时变异性 | |
RMSSD | ms | 相邻RR间期之间差值的均方根值,是衡量心跳间隔短时变异性的指标 | |
Mean HR | 次/min | 平均心率 | |
Mean IBI | ms | 2次连续心跳之间的平均时间间隔,即RR间期,IBI(n)=R(n+1)-R(n) | |
脑电指标 | Delta | — | 1~3.5 Hz,20~200 μV,频率较低而振幅较大,在睡眠研究中通常与慢波睡眠相关,健康成年人深度睡眠阶段开始出现 |
Theta | — | 4~8 Hz,10~50 μV,与注意力控制机制、学习和记忆功能相关,通常随着认知活动的增加而增强 | |
Alpha | — | 8~12 Hz,成年人幅度在50 μV左右,松弛或闭眼、清醒状态时明显 | |
Beta | — | 13~30 Hz,5~20 μV,注意力集中或情绪紧张时出现较多 | |
Gamma | — | >30 Hz,频率最大的波段,与注意力相关,清醒状态不常见 |
表1 特征指标及其生理学意义
Table 1 Characteristic indicators and their physiological significance
类型 | 指标 | 单位 | 表征含义 |
---|---|---|---|
眼动指标 | 瞳孔直径 | mm | 可以反映自主神经系统的活动,特别是交感神经系统的反应.在心理负荷增加时,瞳孔直径通常会扩大 |
注视时间 | ms | 指个体在特定目标或位置保持注视的持续时间,反映信息可理解性或吸引性,信息识别越困难或用户越感兴趣,注视的时间越长,随着任务需求的增加,注视时间可能会减少 | |
眨眼频率 | 次/min | 单位时间内眨眼次数,表征任务难度或满意度,眨眼频率越高则说明疲劳或情绪消极或搜索任务越简单,在心理负荷增加的情况下,眨眼频率通常会降低 | |
心率指标 | VLF | ms2 | 极低频功率(0.003 3~0.04 Hz),反映体温的调节 |
HF | ms2 | 高频功率(0.15~0.4 Hz),主要反映副交感神经系统的活动 | |
LF | ms2 | 低频功率(0.04~0.15 Hz),与交感神经系统的活动有关,反映身体对压力的生理反应,LF的下降可以反映时间压力或情感压抑程度的增加 | |
LF/HF | — | 评估交感和副交感神经系统平衡的一个指标 | |
HFnorm | Nu | 归一化高频功率 | |
LFnorm | Nu | 归一化低频功率 | |
pNN20 | % | 相邻心跳间隔相差超过20 ms的间隔个数占总个数的百分比,是评估副交感神经系统功能的敏感指标 | |
pNN50 | % | 相邻心跳间隔相差超过50 ms的间隔个数占总个数的百分比,是评估副交感神经系统功能的敏感指标,反映了心跳间隔的不规律性 | |
SDNN | ms | 全部RR间期的标准差,评价整体HRV大小,反映心率的缓慢变化,是评估交感神经系统功能的敏感指标 | |
SDSD | ms | 相邻RR间期之间差值的标准差,用于量化相邻心跳间隔变化的一致性,反映了心率的短时变异性 | |
RMSSD | ms | 相邻RR间期之间差值的均方根值,是衡量心跳间隔短时变异性的指标 | |
Mean HR | 次/min | 平均心率 | |
Mean IBI | ms | 2次连续心跳之间的平均时间间隔,即RR间期,IBI(n)=R(n+1)-R(n) | |
脑电指标 | Delta | — | 1~3.5 Hz,20~200 μV,频率较低而振幅较大,在睡眠研究中通常与慢波睡眠相关,健康成年人深度睡眠阶段开始出现 |
Theta | — | 4~8 Hz,10~50 μV,与注意力控制机制、学习和记忆功能相关,通常随着认知活动的增加而增强 | |
Alpha | — | 8~12 Hz,成年人幅度在50 μV左右,松弛或闭眼、清醒状态时明显 | |
Beta | — | 13~30 Hz,5~20 μV,注意力集中或情绪紧张时出现较多 | |
Gamma | — | >30 Hz,频率最大的波段,与注意力相关,清醒状态不常见 |
指标 | 单位 | 配对差值 | t | Sig | |||||
---|---|---|---|---|---|---|---|---|---|
平均值 | 标准差 | 标准误差平均值 | 差值95% 置信区间 | ||||||
下限 | 上限 | ||||||||
RR(W)-RR(Y) | ms | 0.036 | 0.054 | 0.012 | 0.011 | 0.062 | 3.004 | 0.007 | |
HR(W)-HR(Y) | 次/min | -5.350 | 7.903 | 1.767 | -9.048 | -1.652 | -3.028 | 0.007 | |
LF(W)-LF(Y) | ms2 | 0.278 | 0.991 | 0.222 | -0.186 | 0.742 | 1.254 | 0.225 | |
HF(W)-HF(Y) | ms2 | 0.014 | 0.023 | 0.005 | 0.003 | 0.024 | 2.611 | 0.017 | |
VLF(W)-VLF(Y) | ms2 | 0.403 | 1.667 | 0.373 | -0.377 | 1.184 | 1.082 | 0.293 |
表2 静息状态与心理负荷下生理指标的配对t检验结果
Table 2 Paired t?test results of physiological indexes under the resting state and psychological load
指标 | 单位 | 配对差值 | t | Sig | |||||
---|---|---|---|---|---|---|---|---|---|
平均值 | 标准差 | 标准误差平均值 | 差值95% 置信区间 | ||||||
下限 | 上限 | ||||||||
RR(W)-RR(Y) | ms | 0.036 | 0.054 | 0.012 | 0.011 | 0.062 | 3.004 | 0.007 | |
HR(W)-HR(Y) | 次/min | -5.350 | 7.903 | 1.767 | -9.048 | -1.652 | -3.028 | 0.007 | |
LF(W)-LF(Y) | ms2 | 0.278 | 0.991 | 0.222 | -0.186 | 0.742 | 1.254 | 0.225 | |
HF(W)-HF(Y) | ms2 | 0.014 | 0.023 | 0.005 | 0.003 | 0.024 | 2.611 | 0.017 | |
VLF(W)-VLF(Y) | ms2 | 0.403 | 1.667 | 0.373 | -0.377 | 1.184 | 1.082 | 0.293 |
类型 | 指标 | 单位 | 静息状态median | 心理负荷median | 统计量Z | p |
---|---|---|---|---|---|---|
眼动指标 | 瞳孔直径 | mm | 3.78(3.50,4.03) | 4.74(4.45,5.29) | -3.883 | 0.000 |
注视时间 | ms | 571.50(342.75,667.00) | 393.00(286.50,438.00) | -2.688 | 0.007 | |
眨眼频率 | 次/min | 178.00(139.00,277.75) | 125.50(93.25,173.50) | -2.390 | 0.017 | |
心率指标 | SDNN | ms | 0.11(0.06,0.16) | 0.07(0.05,0.09) | -3.445 | 0.001 |
RMSDD | ms | 0.13(0.04,0.18) | 0.05(0.03,0.09) | -3.198 | 0.001 | |
SDSD | ms | 0.12(0.04,0.18) | 0.05(0.03,0.09) | -3.198 | 0.001 | |
pNN50 | % | 0.18(0.08,0.32) | 0.10(0.04,0.24) | -2.808 | 0.005 | |
pNN20 | % | 0.51(0.43,0.64) | 0.47(0.32,0.57) | -2.952 | 0.003 | |
LFnorm | Nu | 0.73(0.64,0.89) | 0.79(0.68,0.92) | -1.743 | 0.081 | |
HFnorm | Nu | 0.27(0.11,0.36) | 0.21(0.09,0.32) | -1.743 | 0.081 | |
LF/HF | — | 2.63(1.77,8.04) | 3.71(2.18,10.50) | -1.286 | 0.199 | |
CV | — | 0.16(0.09,0.23) | 0.09(0.07,0.14) | -3.178 | 0.001 | |
脑电指标 | δ波动率 | dB | 52.63(43.76,70.24) | 77.83(66.81,95.99) | -4.958 | 0.000 |
θ波动率 | dB | 41.92(36.46,54.89) | 68.51(57.09,91.75) | -5.608 | 0.000 | |
α波动率 | dB | 61.81(40.77,83.07) | 76.78(68.32,76.78) | -4.107 | 0.000 | |
β波动率 | dB | 75.38(12.21,148.63) | 120.39(82.01,206.01) | -4.608 | 0.000 | |
γ波动率 | dB | 14.99(-29.38,133.11) | -4.920 | 0.000 | ||
Peak power | dB | 21.05(16.96,32.73) | 27.73(23.75,35.06) | -3.414 | 0.001 | |
SMR | dB | 38.31(20.86,66.41) | 41.00(31.28,60.81) | -1.257 | 0.209 | |
α/β | — | 0.67(0.46,1.41) | 0.66(0.49,0.86) | -2.069 | 0.039 | |
θ/β | — | 0.48(0.31,1.23) | 0.55(0.44,0.75) | -0.581 | 0.561 | |
(α+θ)/β | — | 1.18(0.76,2.76) | 1.21(0.93,1.62) | -1.407 | 0.160 | |
(α+θ)/(α+β) | — | 0.79(0.56,1.31) | 0.72(0.62,0.86) | -2.657 | 0.008 | |
θ/(α+β) | — | 0.33(0.24,0.64) | 0.33(0.29,0.41) | -1.307 | 0.191 |
表3 静息状态与心理负荷下生理指标的秩和检验结果
Table 3 Results of rank sum test for physiological indexes under the resting state and psychological load
类型 | 指标 | 单位 | 静息状态median | 心理负荷median | 统计量Z | p |
---|---|---|---|---|---|---|
眼动指标 | 瞳孔直径 | mm | 3.78(3.50,4.03) | 4.74(4.45,5.29) | -3.883 | 0.000 |
注视时间 | ms | 571.50(342.75,667.00) | 393.00(286.50,438.00) | -2.688 | 0.007 | |
眨眼频率 | 次/min | 178.00(139.00,277.75) | 125.50(93.25,173.50) | -2.390 | 0.017 | |
心率指标 | SDNN | ms | 0.11(0.06,0.16) | 0.07(0.05,0.09) | -3.445 | 0.001 |
RMSDD | ms | 0.13(0.04,0.18) | 0.05(0.03,0.09) | -3.198 | 0.001 | |
SDSD | ms | 0.12(0.04,0.18) | 0.05(0.03,0.09) | -3.198 | 0.001 | |
pNN50 | % | 0.18(0.08,0.32) | 0.10(0.04,0.24) | -2.808 | 0.005 | |
pNN20 | % | 0.51(0.43,0.64) | 0.47(0.32,0.57) | -2.952 | 0.003 | |
LFnorm | Nu | 0.73(0.64,0.89) | 0.79(0.68,0.92) | -1.743 | 0.081 | |
HFnorm | Nu | 0.27(0.11,0.36) | 0.21(0.09,0.32) | -1.743 | 0.081 | |
LF/HF | — | 2.63(1.77,8.04) | 3.71(2.18,10.50) | -1.286 | 0.199 | |
CV | — | 0.16(0.09,0.23) | 0.09(0.07,0.14) | -3.178 | 0.001 | |
脑电指标 | δ波动率 | dB | 52.63(43.76,70.24) | 77.83(66.81,95.99) | -4.958 | 0.000 |
θ波动率 | dB | 41.92(36.46,54.89) | 68.51(57.09,91.75) | -5.608 | 0.000 | |
α波动率 | dB | 61.81(40.77,83.07) | 76.78(68.32,76.78) | -4.107 | 0.000 | |
β波动率 | dB | 75.38(12.21,148.63) | 120.39(82.01,206.01) | -4.608 | 0.000 | |
γ波动率 | dB | 14.99(-29.38,133.11) | -4.920 | 0.000 | ||
Peak power | dB | 21.05(16.96,32.73) | 27.73(23.75,35.06) | -3.414 | 0.001 | |
SMR | dB | 38.31(20.86,66.41) | 41.00(31.28,60.81) | -1.257 | 0.209 | |
α/β | — | 0.67(0.46,1.41) | 0.66(0.49,0.86) | -2.069 | 0.039 | |
θ/β | — | 0.48(0.31,1.23) | 0.55(0.44,0.75) | -0.581 | 0.561 | |
(α+θ)/β | — | 1.18(0.76,2.76) | 1.21(0.93,1.62) | -1.407 | 0.160 | |
(α+θ)/(α+β) | — | 0.79(0.56,1.31) | 0.72(0.62,0.86) | -2.657 | 0.008 | |
θ/(α+β) | — | 0.33(0.24,0.64) | 0.33(0.29,0.41) | -1.307 | 0.191 |
方法 | 类型 | 指标 |
---|---|---|
Pearson 相关分析 | 眼动指标 | 瞳孔直径、注视时间、眨眼频率 |
心率指标 | RR,HR,SDNN,HF,pNN50 | |
脑电指标 | δ,θ,γ,Peak power,(α+θ)/(α+β) | |
MRMR | 眼动指标 | 瞳孔直径、注视时间、眨眼频率 |
心率指标 | RR,HF,RMSDD | |
脑电指标 | δ,θ,γ,(α+θ)/(α+β) | |
PCA | 眼动指标 | 瞳孔直径、眨眼频率 |
心率指标 | RR,HR,SDNN,HF,pNN50 | |
脑电指标 | θ,α,β,γ,Peak power |
表4 特征提取结果
Table 4 Feature extraction results
方法 | 类型 | 指标 |
---|---|---|
Pearson 相关分析 | 眼动指标 | 瞳孔直径、注视时间、眨眼频率 |
心率指标 | RR,HR,SDNN,HF,pNN50 | |
脑电指标 | δ,θ,γ,Peak power,(α+θ)/(α+β) | |
MRMR | 眼动指标 | 瞳孔直径、注视时间、眨眼频率 |
心率指标 | RR,HF,RMSDD | |
脑电指标 | δ,θ,γ,(α+θ)/(α+β) | |
PCA | 眼动指标 | 瞳孔直径、眨眼频率 |
心率指标 | RR,HR,SDNN,HF,pNN50 | |
脑电指标 | θ,α,β,γ,Peak power |
方法 | 模型 | ACC | SN | SP | F1 | AUC |
---|---|---|---|---|---|---|
Pearson 相关分析 | Logit | 0.833 | 0.8 | 0.857 | 0.857 | 0.829 |
KNN | 0.75 | 0.6 | 0.857 | 0.800 | 0.686 | |
SVM | 0.75 | 0.8 | 0.714 | 0.769 | 0.714 | |
XGB | 0.917 | 0.8 | 1.0 | 0.933 | 0.900 | |
DT | 0.75 | 0.8 | 0.714 | 0.769 | 0.757 | |
RF | 0.917 | 0.8 | 1.0 | 0.933 | 0.943 | |
MRMR | Logit | 0.750 | 0.8 | 0.743 | 0.727 | 0.771 |
KNN | 0.750 | 0.6 | 0.857 | 0.667 | 0.743 | |
SVM | 0.833 | 0.6 | 1.0 | 0.750 | 0.771 | |
XGB | 0.917 | 0.8 | 1.0 | 0.889 | 0.957 | |
DT | 0.833 | 0.8 | 0.857 | 0.800 | 0.829 | |
RF | 0.917 | 1.0 | 0.857 | 0.909 | 0.971 | |
PCA | Logit | 0.917 | 0.8 | 1.0 | 0.889 | 0.857 |
KNN | 0.750 | 0.8 | 0.714 | 0.727 | 0.829 | |
SVM | 0.833 | 1.0 | 0.714 | 0.8 | 0.857 | |
XGB | 0.750 | 1.0 | 0.571 | 0.769 | 0.843 | |
DT | 0.750 | 0.8 | 0.714 | 0.727 | 0.757 | |
RF | 0.833 | 1.0 | 0.714 | 0.800 | 0.914 |
表5 机器学习分类结果
Table 5 Machine learning classification results
方法 | 模型 | ACC | SN | SP | F1 | AUC |
---|---|---|---|---|---|---|
Pearson 相关分析 | Logit | 0.833 | 0.8 | 0.857 | 0.857 | 0.829 |
KNN | 0.75 | 0.6 | 0.857 | 0.800 | 0.686 | |
SVM | 0.75 | 0.8 | 0.714 | 0.769 | 0.714 | |
XGB | 0.917 | 0.8 | 1.0 | 0.933 | 0.900 | |
DT | 0.75 | 0.8 | 0.714 | 0.769 | 0.757 | |
RF | 0.917 | 0.8 | 1.0 | 0.933 | 0.943 | |
MRMR | Logit | 0.750 | 0.8 | 0.743 | 0.727 | 0.771 |
KNN | 0.750 | 0.6 | 0.857 | 0.667 | 0.743 | |
SVM | 0.833 | 0.6 | 1.0 | 0.750 | 0.771 | |
XGB | 0.917 | 0.8 | 1.0 | 0.889 | 0.957 | |
DT | 0.833 | 0.8 | 0.857 | 0.800 | 0.829 | |
RF | 0.917 | 1.0 | 0.857 | 0.909 | 0.971 | |
PCA | Logit | 0.917 | 0.8 | 1.0 | 0.889 | 0.857 |
KNN | 0.750 | 0.8 | 0.714 | 0.727 | 0.829 | |
SVM | 0.833 | 1.0 | 0.714 | 0.8 | 0.857 | |
XGB | 0.750 | 1.0 | 0.571 | 0.769 | 0.843 | |
DT | 0.750 | 0.8 | 0.714 | 0.727 | 0.757 | |
RF | 0.833 | 1.0 | 0.714 | 0.800 | 0.914 |
1 | 汪伟忠,卢明银,靖培星.煤矿特种作业人员安全胜任指数模型构建[J].安全与环境学报,2016,16(1):20-23. |
Wang Wei‐zhong, Lu Ming‐yin, Jing Pei‐xing.Research on the establishment of a safety competency index model for the special operators in the coal mines[J].Journal of Safety and Environment,2016,16(1):20-23. | |
2 | 徐明伟.有限空间人因参数对疲劳影响及防护研究[D].北京:北京科技大学,2021. |
Xu Ming‐wei.Study on influence of human factors parameters on fatigue in confined space and protection[D].Beijing:University of Science and Technology Beijing,2021. | |
3 | 晋良海,李宬.高处作业人员心理负荷的SWAT量表主观评定方法研究[J].安全与环境工程,2015,22(3):70-74,82. |
Jin Liang‐hai, Li Cheng.Study on the mental workload of high‐place operating personnel with the subjective assessment method of SWAT scale[J].Safety and Environmental Engineering,2015,22(3):70-74,82. | |
4 | 孙崇勇.心理负荷测量方法的现状与发展趋势[J].人类工效学,2012,18(2):88-92. |
Sun Chong‐yong.Present situation and development trend of psychological load measurement methods[J].Chinese Journal of Ergonomics,2012,18(2):88-92. | |
5 | Young M S, Brookhuis K A, Wickens C D,et al.State of science:mental workload in ergonomics[J].Ergonomics,2015,58(1):1-17. |
6 | 冯源,李彦蕾,李一凡,等.基于注意力机制的多分支LSTM心理负荷评估模型[J].计算机应用研究,2021,38(11):3371-3375. |
Feng Yuan, Li Yan‐lei, Li Yi‐fan,et al.Novel multiclass classification framework with multi‐branch LSTM and attention mechanism for mental workload evaluation[J].Application Research of Computers,2021,38(11):3371-3375. | |
7 | 陆勇.民用无人机操作心理负荷测评与预测研究[D].徐州:中国矿业大学(江苏),2021. |
Lu Yong.Research on evaluation and prediction of operational psychological load of civil UAV[D].Xuzhou:China University of Mining and Technology(Jiangsu),2021. | |
8 | 侯文真.考虑时间压力和任务复杂度的轻装作业者心理负荷与管理策略[D].镇江:江苏科技大学,2020. |
Hou Wen‐zhen.Mental load and management strategy of light assembly operators considering time pressure and task complexity[D].Zhenjiang:Jiangsu University of Science and Technology,2020. | |
9 | 吕晓薇.基于脑电及行为特征的塔吊司机心理负荷状态识别模型研究[D].北京:北方工业大学,2022. |
Xiao‐wei Lyu.Research on the recognition model of psychological load state of tower crane driver based on EEG and behavioral characteristics[D].Beijing:North China University of Technology,2022. | |
10 | Charles R L, Nixon J.Measuring mental workload using physiological measures:a systematic review[J].Applied Ergonomics,2019,74:221-232. |
11 | Di Stasi L L, McCamy M B, Macknik S L,et al.Saccadic eye movement metrics reflect surgical residents' fatigue[J].Annals of Surgery,2014,259(4):824-829. |
12 | Fairclough S H, Houston K.A metabolic measure of mental effort[J].Biological Psychology,2004,66(2):177-190. |
13 | Tao D, Tan H B, Wang H L,et al.A systematic review of physiological measures of mental workload[J].International Journal of Environmental Research and Public Health,2019,16(15):2716. |
14 | De Rivecourt M, Kuperus M N, Post W J,et al.Cardiovascular and eye activity measures as indices for momentary changes in mental effort during simulated flight[J].Ergonomics,2008,51(9):1295-1319. |
15 | Brookings J B, Wilson G F, Swain C R.Psychophysiological responses to changes in workload during simulated air traffic control[J].Biological Psychology,1996,42(3):361-377. |
16 | Hjortskov N, Rissén D, Blangsted A K,et al.The effect of mental stress on heart rate variability and blood pressure during computer work[J].European Journal of Applied Physiology,2004,92(1):84-89. |
17 | Finsen L, Søgaard K, Jensen C,et al.Muscle activity and cardiovascular response during computer‐mouse work with and without memory demands[J].Ergonomics,2001,44(14):1312-1329. |
18 | Heine T, Lenis G, Reichensperger P,et al.Electrocardiographic features for the measurement of drivers’ mental workload[J].Applied Ergonomics,2017,61:31-43. |
19 | Delaney J P, Brodie D A.Effects of short‐term psychological stress on the time and frequency domains of heart‐rate variability[J].Perceptual and Motor Skills,2000,91(2):515-524. |
20 | Matthews G, Reinerman‐Jones L E, Barber D J,et al.The psychometrics of mental workload:multiple measures are sensitive but divergent[J].Human Factors,2015,57(1):125-143. |
21 | Mun S, Whang M, Park S,et al.Effects of mental workload on involuntary attention:a somatosensory ERP study[J].Neuropsychologia,2017,106:7-20. |
22 | Di Stasi L L, Antolí A, Cañas J J.Evaluating mental workload while interacting with computer‐generated artificial environments[J].Entertainment Computing,2013,4(1):63-69. |
23 | Foy H J, Chapman P.Mental workload is reflected in driver behaviour,physiology,eye movements and prefrontal cortex activation[J].Applied Ergonomics,2018,73:90-99. |
24 | Hwang S L, Yau Y J, Lin Y T,et al.Predicting work performance in nuclear power plants[J].Safety Science,2008,46(7):1115-1124. |
25 | Wilson G F, Fullenkamp P, Davis I.Evoked potential,cardiac,blink,and respiration measures of pilot workload in air‐to‐ground missions[J].Aviation,Space,and Environmental Medicine,1994,65(2):100-105. |
26 | Jaquess K J, LoL C, Oh H,et al.Changes in mental workload and motor performance throughout multiple practice sessions under various levels of task difficulty[J].Neuroscience,2018,393:305-318. |
27 | Kosti M V, Georgiadis K, Adamos D A,et al.Towards an affordable brain computer interface for the assessment of programmers’ mental workload[J].International Journal of Human‐Computer Studies,2018,115:52-66. |
28 | Choi M K, Lee S M, Ha J S,et al.Development of an EEG‐based workload measurement method in nuclear power plants[J].Annals of Nuclear Energy,2018,111:595-607. |
29 | Sharma L D, Chhabra H, Chauhan U,et al.Mental arithmetic task load recognition using EEG signal and Bayesian optimized K‐nearest neighbor[J].International Journal of Information Technology,2021,13(6):2363-2369. |
30 | Zhang P B, Wang X, Chen J F,et al.Spectral and temporal feature learning with two‐stream neural networks for mental workload assessment[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2019,27(6):1149-1159. |
31 | Das Chakladar D, Dey S, Roy P P,et al.EEG‑based mental workload estimation using deep BLSTM‑LSTM network and evolutionary algorithm[J].Biomedical Signal Processing and Control,2020,60:101989. |
32 | Qu H Q, Gao X Y, Pang L P.Classification of mental workload based on multiple features of ECG signals[J].Informatics in Medicine Unlocked,2021,24:100575. |
33 | Zhang H N.A mental workload evaluation model based on improved multibranch LSTM network with attention mechanism[J].Advances in Multimedia,2022,2022:9601946. |
34 | 张旭.时序信号的异常检测与预测研究[D].成都:电子科技大学,2021. |
Zhang Xu.Research on anomaly detection and prediction of time series signals[D].Chengdu:University of Electronic Science and Technology,2021. | |
35 | 王竞一,曹欢,刘晓冬,等.基于长短时记忆模型网络的水处理系统参数预测与评价[J].智能制造,2022(5):96-99. |
Wang Jing‐yi, Cao Huan, Liu Xiao‐dong,et al.Parameter prediction and evaluation of water treatment system based on long‐term and short‐term memory model network[J].Intelligent Manufacturing,2022(5):96-99. | |
36 | 祁胜锋.基于Boosting算法的人体动作数据识别研究[D].武汉:武汉纺织大学,2019. |
Qi Sheng‐feng.The study of the human motion data recognition based on Boosting algorithm[D].Wuhan:Wuhan Textile University,2019. |
[1] | 赵彬, 吴成东, 姜杨, 孙若怀. 空间参数聚类辨识的机器人零位标定方法与精度评估[J]. 东北大学学报(自然科学版), 2023, 44(6): 761-769. |
[2] | 金长宇, 于佳强, 王强, 陈立军. 基于集成学习CatBoost优化模型的爆堆大块率预测[J]. 东北大学学报(自然科学版), 2023, 44(12): 1743-1750. |
[3] | 刘克奇, 杜佃春, 赵文, 丁万涛. 基于机器学习的泥水盾构关键掘进参数预测与优化[J]. 东北大学学报(自然科学版), 2023, 44(11): 1621-1630. |
[4] | 赵海, 陈佳伟, 施瀚, 王相. 一种应用于人体活动识别的迁移学习算法[J]. 东北大学学报(自然科学版), 2022, 43(6): 776-782. |
[5] | 徐礼胜, 崔慧颖, 吴俊鼎, 王仲怡. 级联自适应局部投影降噪方法[J]. 东北大学学报(自然科学版), 2022, 43(3): 368-375. |
[6] | 马海涛, 路家蕊, 于文鑫, 于长永. 线性区域数量与PLNN表达能力的相关性[J]. 东北大学学报(自然科学版), 2021, 42(2): 201-207. |
[7] | 李壮年, 储满生, 柳政根, 李宝峰. 基于机器学习和遗传算法的高炉参数预测与优化[J]. 东北大学学报:自然科学版, 2020, 41(9): 1262-1267. |
[8] | 杨望, 江咏涵, 张三峰. 基于网页结构与语言特征的垃圾网页链接检测方法[J]. 东北大学学报:自然科学版, 2020, 41(8): 1091-1096. |
[9] | 郭甲腾, 刘寅贺, 韩英夫, 王徐磊. 基于机器学习的钻孔数据隐式三维地质建模方法[J]. 东北大学学报:自然科学版, 2019, 40(9): 1337-1342. |
[10] | 王蒙湘, 李芳芳, 于戈. 交互式数据探索框架的特征自适应技术[J]. 东北大学学报:自然科学版, 2018, 39(12): 1685-1690. |
[11] | 朱继召, 乔建忠, 林树宽. 表示学习知识图谱的实体对齐算法[J]. 东北大学学报:自然科学版, 2018, 39(11): 1535-1539. |
[12] | 王彦华, 乔建忠, 林树宽, 赵廷磊. 基于SVM的CPU-GPU异构系统任务分配模型[J]. 东北大学学报:自然科学版, 2016, 37(8): 1089-1094. |
[13] | 黄璐, 王宏. 基于盲反卷积的脑电信号盲分离研究[J]. 东北大学学报:自然科学版, 2016, 37(8): 1100-1103. |
[14] | 朱靖波;陈文亮. 基于领域知识的文本分类[J]. 东北大学学报(自然科学版), 2005, 26(8): 733-735. |
[15] | 孙杰;李晶皎;张俐;姚天顺. 机器翻译系统中词类搭配规则的自动获取方法[J]. 东北大学学报(自然科学版), 1999, 20(2): 4--. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||