Visual behavior for construction site hazard identification under different cognitive loads

doi:10.16265/j.cnki.issn1003-3033.2025.01.0685

Abstract

Abstract:

In order to explore the effect of cognitive load on workers' hazard identification behavior, a cognitive experiment based on eye-tracking technology for construction site hazard identification was designed firstly. In this experiment, a N-digit task was introduced to increase the cognitive load. Secondly, the gaze and glance data were collected to analyze the static attention allocation, and the scanning path was processed to extract the dynamic transfer characteristics of attention. Finally, three parameters of variance review probability (RP), transition probability (TP) and switching probability (SP) were selected as the quantitative parameter values to classify the scanning patterns of hazard identification, which explored the influence of cognitive load on hidden hazard identification from the perspective of visual behavior performance. The results show that the level of cognitive load negatively affects hazard identification performance. The subjects with high cognitive load show longer first fixation time, fewer fixation counts and saccade counts, and there is no significant difference in fixation percentage and mean fixation duration. Additionally, based on the attention characteristics, three scanning patterns are identified: sequential inspection, repeated comparison and random discovery. With the improvement of cognitive load level, subjects will pay more attention to identifying single hazard but neglect others during sequential inspection, and reduce the attention in the hazard area but still keep the fixation point quickly and frequently switching during repeated comparison, while the number and time of inspection of hazard areas are reducing simultaneously during random discovery.

Key words: cognitive load, construction site, hazard identification, eye-tracking experiment, visual behaviors, scanning patterns

CLC Number:

X912安全生理学

DENG Hongze, KONG Yuanyuan, XU Sheng. Visual behavior for construction site hazard identification under different cognitive loads[J]. China Safety Science Journal, 2025, 35(1): 40-49.

Figures/Tables 10

Table 1

Fig.1

Table 2

Table 3

Attention transfer probability

指标	指标解释	指标计算
RP	注视点落于AOI且下一个注视点仍在该AOI的概率	$R P = ∑ i = 1 m P (X n = i) · P (X n + 1 = i X n = i)$
TP	注视点落于AOI且下一个注视点在非AOI的概率	$T P = ∑ i = 1 m P (X n = i) · P (X n + 1 = O X n = i)$
SP	注视点落于AOI且下一个注视点在另一AOI的概率	$S P = ∑ i = 1 m P (X n = i) · P (X n + 1 = j X n = i)$

Table 3

Table 4

Table 5

Fig.2

Table 6

Fig.3

Fig.4

References 30

[1]	崔淼, 栗继祖. 煤矿团队韧性的驱动机制:基于智能化矿山矿工心理韧性的上行传递模型分析[J]. 中国安全生产科学技术, 2024, 20(2):132-137.
	CUI Miao, LI Jizu. Driving mechanism of team resilience in coal mine: analysis of ascending transmission model based on psychological resilience of miners in intelligent mine[J]. Journal of Safety Science and Technology, 2024, 20(2): 132-137.
[2]	宋晓蕾, 田珍珍, 董梅梅. 智能交互系统中人机组队协同工效提升的模型构建[J]. 包装工程, 2023, 44(20):8-17.
	SONG Xiaolei, TIAN Zhenzhen, DONG Meimei. Construction of collaborative efficiency improvement model for human-autonomy teaming in intelligent interactive system[J]. Packaging Engineering, 2023, 44(20): 8-17.
[3]	郑霞忠, 石博元, 陈云, 等. 融合VR-眼动的施工现场隐患识别视觉注意与搜索特征研究[J]. 安全与环境学报, 2024, 24(3):1087-1095.
	ZHENG Xiazhong, SHI Boyuan, CHEN Yun, et al. A study of visual attention and search features for construction site hazard identification incorporating VR-eye movement[J]. Journal of Safety and Environment, 2024, 24(3): 1087-1095.
[4]	SHIFFRIN R M, SCHNEIDER W. Controlled and automatic human information processing: II perceptual learning, automatic attending and a general theory[J]. Psychological Review, 1977, 84(2): 127-190.
[5]	LIU Yizhi, HABIBNEZHAD M, JEBELLI H. Brainwave-driven human-robot collaboration in construction[J]. Automation in Construction, 2021, 124: DOI: 10.1016/j.autcon.2021.103556.
[6]	SHAYESTEH S, OJHA A, LIU Yizhi, et al. Human-robot teaming in construction: evaluative safety training through the integration of immersive technologies and wearable physiological sensing[J]. Safety Science, 2023, 159: DOI:10.1016/j.ssci.2022.106019.
[7]	廖彬超, 刘梅, 徐晴雯, 等. 眼动试验在建筑业安全隐患识别研究中的应用与展望[J]. 中国安全科学学报, 2016, 26(11):31-36.
	LIAO Binchao, LIU Mei, XU Qingwen, et al. Application prospect of eye-tracking experiments in studies of construction safety hazard identification[J]. China Safety Science Journal, 2016, 26(11): 31-36.
[8]	OUYANG Yewei, LUO Xiaowei. Differences between inexperienced and experienced safety supervisors in identifying construction hazards: seeking insights for training the inexperienced[J]. Advanced Engineering Informatics, 2022, 52: DOI:10.1016/j.aei.2022.101602.
[9]	胡飞翔, 周建亮, 林欣燕, 等. 情绪对建筑工人不安全行为影响的认知试验[J]. 中国安全科学学报, 2023, 33(4):75-83. doi: 10.16265/j.cnki.issn1003-3033.2023.04.0864
	HU Feixiang, ZHOU Jianliang, LIN Xinyan, et al. A cognitive experiment of effect of emotion on construction workers' unsafe behavior[J]. China Safety Science Journal, 2023, 33(4): 75-83. doi: 10.16265/j.cnki.issn1003-3033.2023.04.0864
[10]	HAN Yu, YIN Zhenzhen, ZHANG Jingjie, et al. Eye-tracking experimental study investigating the influence factors of construction safety hazard recognition[J]. Journal of Construction Engineering and Management, 2020, 146(8): DOI:10.1061/(ASCE)CO.1943-7862.0001884.
[11]	XU Qingwen, CHONG H Y, LIAO Pinchao. Exploring eye-tracking searching strategies for construction hazard recognition in a laboratory scene[J]. Safety Science, 2019, 120: 824-832. doi: 10.1016/j.ssci.2019.08.012
[12]	张帅, 韩豫, 裴中玉, 等. 基于数据挖掘的施工危险识别注意投入与分配研究[J]. 中国安全生产科学技术, 2023, 19(1):115-121.
	ZHANG Shuai, HAN Yu, PEI Zhongyu, et al. Attention input and allocation of construction hazard identification based on data mining[J]. Journal of Safety Science and Technology, 2023, 19(1):115-121.
[13]	韩豫, 张帅, 张泾杰. 施工危险目标识别的注意转移过程特性分析[J]. 安全与环境学报, 2023, 23(3):838-845.
	HAN Yu, ZHANG Shuai, ZHANG Jingjie. Characteristic analysis of attention transfer process in recognition of construction hazard targets[J]. Journal of Safety and Environment, 2023, 23(3): 838-845.
[14]	LIU Ping, FORTE J, SEWELL D, et al. Cognitive load effects on early visual perceptual processing[J]. Attention, Perception & Psychophysics, 2018, 80(4): 929-950.
[15]	陈龙, 王崴, 瞿珏, 等. EEG功率信息显示特征对认知负荷的影响[J]. 中国安全科学学报, 2020, 30(2):183-189. doi: 10.16265/j.cnki.issn1003-3033.2020.02.029
	CHEN Long, WANG Wei, QU Jue, et al. Influence of display characteristics of EEG power on cognitive load[J]. China Safety Science Journal, 2020, 30(2): 183-189. doi: 10.16265/j.cnki.issn1003-3033.2020.02.029
[16]	车敬上, 孙海龙, 肖晨洁, 等. 为什么信息超载损害决策?基于有限认知资源的解释[J]. 心理科学进展, 2019, 27(10):1758-1768. doi: 10.3724/SP.J.1042.2019.01758
	CHE Jingshang, SUN Hailong, XIAO Chenjie, et al. Why information overload damages decision? an explanation based on limited cognitive resources[J]. Advances in Psychological Science, 2019, 27(10): 1758-1768. doi: 10.3724/SP.J.1042.2019.01758
[17]	SUZUKI Y, WILD F, SCANLON E. Measuring cognitive load in augmented reality with physiological methods: a systematic review[J]. Journal of Computer Assisted Learning, 2023, 40(2): 375-393.
[18]	AYRES P, LEE J Y, PAAS F, et al. The validity of physiological measures to identify differences in intrinsic cognitive load[J]. Frontiers in Psychology, 2021, 12:DOI:10.3389/fpsyg.2021.702538.
[19]	张会明, 袁伟, 陈其源, 等. 听觉-言语认知负荷下工作记忆容量对换道决策的影响[J]. 安全与环境学报, 2024, 24(1):195-205.
	ZHANG Huiming, YUAN Wei, CHEN Qiyuan, et al. Effect of working memory capacity on lane-changing decisions under auditory-verbal cognitive load[J]. Journal of Safety and Environment, 2024, 24(1): 195-205.
[20]	ALLEN R J, BADDELEY A D, HITCH G J. Is the binding of visual features in working memory resource-demanding?[J]. Journal of Experimental Psychology: General, 2006, 135(2): 298-313.
[21]	ALLRED S R, GRAWFORD L E, DUFFY S, et al. Working memory and spatial judgments: cognitive load increases the central tendency bias[J]. Psychonomic Bulletin Review, 2016, 23(6): 1825-1831.
[22]	LIANG Qi, ZHOU Zhiyuan, YE Gui, et al. Unveiling the mechanism of construction workers' unsafe behaviors from an occupational stress perspective: a qualitative and quantitative examination of a stress-cognition-safety model[J]. Safety Science, 2022, 145: DOI:10.1016/j.ssci.2021.105486.
[23]	CHENG Baoquan, LUO Xiaowei, MEI Xiang, et al. A systematic review of eye-tracking studies of construction safety[J]. Frontiers in Neuroscience, 2022, 16: DOI:10.3389/fnins.2022.891725.
[24]	倪国栋, 方亚琦, 张琦, 等. 风险倾向对新生代建筑工人危险感知的影响机制[J]. 中国安全科学学报, 2023, 33(5):221-229. doi: 10.16265/j.cnki.issn1003-3033.2023.05.2044
	NI Guodong, FANG Yaqi, ZHANG Qi, et al. Influencing mechanism of risk propensity on hazard perception of new generation of construction workers[J]. China Safety Science Journal, 2023, 33(5): 221-229. doi: 10.16265/j.cnki.issn1003-3033.2023.05.2044
[25]	LIU Yizhi, OJHA A, SHAYESTEH S, et al. Human-centric robotic manipulation in construction: generative adversarial networks based physiological computing mechanism to enable robots to perceive workers' cognitive load[J]. Canadian Journal of Civil Engineering, 2023, 50(3): 224-238.
[26]	黄月胜, 张豹, 范兴华, 等. 无关工作记忆表征的负性情绪信息能否捕获视觉注意?一项眼动研究[J]. 心理学报, 2021, 53(1): 26-37. doi: 10.3724/SP.J.1041.2021.00026
	HUANG Yuesheng, ZHANG Bao, FAN Xinghua, et al. Can negative emotion of task-irrelevant working memory representation affect its attentional capture? a study of eye movements[J]. Acta Psychologica Sinica, 2021, 53(1): 26-37. doi: 10.3724/SP.J.1041.2021.00026
[27]	郑霞忠, 王毓, 陈云, 等. 建筑施工安全培训信息呈现方式学习效果评价[J]. 中国安全科学学报, 2023, 33(5):96-102. doi: 10.16265/j.cnki.issn1003-3033.2023.05.0933
	ZHENG Xiazhong, WANG Yu, CHEN Yun, et al. Construction safety training information presentation learning effect evaluation[J]. China Safety Science Journal, 2023, 33(5): 96-102. doi: 10.16265/j.cnki.issn1003-3033.2023.05.0933
[28]	JEELANI I, ALBERT A, HAN K, et al. Are visual search patterns predictive of hazard recognition performance? empirical investigation using eye-tracking technology[J]. Journal of Construction Engineering and Management, 2019, 145(1): DOI: 10.1061/(ASCE)CO.1943-7862.0001589.
[29]	JEELANI I, HAN K, ALBERT A. Automating and scaling personalized safety training using eye-tracking data[J]. Automation in Construction, 2018, 93: 63-77.
[30]	钟奇, 支锦亦, 郭钢. 车载信息系统交互方式对驾驶行为的影响研究[J]. 安全与环境学报, 2022, 22(3):1406-1411.
	ZHONG Qi, ZHI Jinyi, GUO Gang. Influence of in-vehicle information system interaction modes on driving behavior[J]. Journal of Safety and Environment, 2022, 22(3): 1406-1411.

1组图片 (编号1—3)
隐患解析 (编号1—3)	①未按要求设置临边护栏;②未戴安全帽;③挖掘机作业范围内有人;④坐在危险临边	①未按要求搭设脚手板;②未系安全带;③易受坠落物体打击	①站在危险临边;②防护围栏缺失;③临时电源线搭接混乱
2组图片 (编号4—6)
隐患解析 (编号4—6)	①临边堆物;②建筑废料随意丢弃;③站在危险临边;④吊装范围内有人	①未戴安全帽;②未与运行中车辆保持足够安全距离;③挖掘机作业范围内有人	①吊件未按要求固定;②木材堆放超高;③材料未按规定堆放整齐

指标	指标解释
首次注视时间/ms	图片呈现后,被试的注视点首次落到AOIs所需的时间
注视占比/%	注视点在AOIs停留时间与整个隐患识别任务时间的比值
注视次数	落在AOIs内的注视点数量
平均注视时长/ms	构成一个注视点的首个采样点与最后一个采样点之间的平均持续时间
扫视次数	在单个刺激材料中的总扫视次数

分组	个案数	平均值/%	标准差/%	显著性
低负荷	22	84.38	6.75	0.004^***
高负荷	22	77.57	8.45	0.004^***

指标	平均值±标准差		显著性 p(双尾)
指标	低认知负荷	高认知负荷	显著性 p(双尾)
首次注视时间/ms	790.88±274.38	1184.15±433.57	0.001^***
注视占比/%	46.79±13.53	45.94±13.26	0.833
注视次数	8.98±2.19	7.69±1.75	0.029^**
平均注视时长/ms	579.02±238.54	622.70±225.60	0.544
扫视次数	15.77±4.12	13.50±3.75	0.003^***

指标	聚类中心(低认知负荷)			聚类中心(高认知负荷)
指标	1(N=23)	2(N=47)	3(N=77)	1(N=17)	2(N=35)	3(N=83)
RP	50.83	18.92	16.66	65.58	16.90	11.38
TP	10.17	14.88	21.84	9.07	13.30	22.29
SP	20.59	39.01	13.27	5.11	37.38	7.96