A Mechanism Study of Cognitive VDT Monitoring Performance Based on Process Recognition

doi:10.3969/j.issn.1007-7375.2023.04.004

Abstract

Abstract: To improving the performance of cognitive visual display terminal (VDT) monitoring, the hidden Markov model (HMM) is used to analyze the operation process and the mechanism of performance formation. An HMM conceptual model of cognitive VDT monitoring task is established and the experiments are designed by E-Prime. Then, the performance and eye movement data are collected by ErgoLAB platform to train and test the HMM parameters. The observation sequences are decoded into cognitive therbligs chains by Viterbi algorithm. Finally, the relationship between the characteristics of cognitive therbligs chains and operation performance to explore the mechanism of performance formation. Results show that the process of cognitive VDT monitoring can be represented by cognitive therbligs chains, and the differences in operators and operations may lead to different chains; under the same structure, the operation performance decreases as the cognitive therbligs chain becomes longer; differences in structures and types of cognitive therbligs chains affect the operation performance when the lengths of chains are equal.

Key words: cognitive VDT monitoring, cognitive therbligs chain, hidden Markov model (HMM), cluster analysis, performance mechanism

CLC Number:

X913.4
TP399

HUANG Kun, LIAO Bin. A Mechanism Study of Cognitive VDT Monitoring Performance Based on Process Recognition[J]. Industrial Engineering Journal, 2023, 26(4): 27-34,43.

References

[1] 冯亮, 冯明放. 科技进步条件下劳动形式的划分[J]. 财经科学, 2015, 59(1): 58-68
FENG Liang, FENG Mingfang. Classification of labor forms on the condition of scientific and technological advancement[J]. Finance & Economics, 2015, 59(1): 58-68
[2] 廖斌, 吕思思, 冯海芹. 基于结构方程模型的认知性VDT作业过程解析[J]. 中国安全生产科学术, 2021, 17(6): 154-160
LIAO Bin, LVU Sisi, FENG Haiqin. Process analysis of cognitive VDT operation based on structural equation modeling[J]. Journal of Safety Science and Technology, 2021, 17(6): 154-160
[3] 廖斌, 冯海芹, 滕卉敏, 等. 认知性VDT持续监控作业人因可靠性预测模型研究[J]. 中国安全科学学报, 2016, 26(5): 53-58
LIAO Bin, FENG Haiqin, TENG Huimin, et al. Model for predicting human reliability in cognitive VDT continuous monitoring operation[J]. China Safety Science Journal, 2016, 26(5): 53-58
[4] 何旭宏, 黄祥瑞. 工业系统中人的可靠性分析: 原理、方法与应用[M]. 北京: 清华大学出版社, 2007: 11-13.
[5] 泰勒. 科学管理原理[M]. 蔡上国译. 上海: 上海科学技术出版社, 1982: 18-53.
[6] 罗园园, 许百华. 认知性警戒作业绩效与刺激率、记忆负荷的关系[J]. 人类工效学, 2006, 12(1): 49-52
[7] 冯海芹, 廖斌, 罗俊浩, 等. 认知性VDT持续监控作业人因可靠性动态预测方法[J]. 数学的实践与认识, 2019, 49(4): 99-105
FENG Haiqin, LIAO Bin, LUO Junhao, et al. Human reliability dynamic prediction method of cognitive monitoring in VDT continuous operation[J]. Mathamatics in Practice and Theory, 2019, 49(4): 99-105
[8] 张德乾, 张智君, 仰和芝. 计算机模拟视觉监视警戒作业的颜色警示语声音警示效应[J]. 心理科学, 2010, 33 (4): 831-834.
ZHANG Deqian, ZHANG Zhijun, YANG Hezhi. Vigilance performance: effects of sound and color cues on the simulated clock task[J]. Psychology Science, 2010, 33 (4); 831-834.
[9] 吴雪琴, 廖斌. 基于疲劳模式识别的VDT作业工间休息机制[J]. 中国安全生产科学技术, 2021, 17(3): 169-174
WU Xueqin, LIAO Bin. Break mechanism of VDT continuous operation based on fatigue pattern recognition[J]. Journal of Safety Science and Technology, 2021, 17(3): 169-174
[10] MICHAEL T, GERHARD P. Impact of background noise on reaction time and brain DC potential changes of VDT-based spatial attention[J]. Ergonomics, 2006, 49(2): 202-208
[11] 罗俊浩, 廖斌, 滕卉敏, 等. VDT作业中光照强度与背景颜色对人因可靠性的综合影响[J]. 人类工效学, 2017, 23(2): 50-54
LUO Junhao, LIAO Bin, TENG Huimin, et al. The synthetic effect of illumination intensity and background color on human reliability in VDT operation[J]. Chinese Journal of Ergonomics, 2017, 23(2): 50-54
[12] 刘河生, 高小榕, 杨福生. 隐马尔可夫模型的原理与实现[J]. 国外医学生物医学工程分册, 2002, 25(6): 253-259
LIU Hesheng, GAO Xiaorong, YANG Fusheng. Theory of hidden Markov modeling and its implementation[J]. Foreign Medical Sciences (Biomedical Engineering Fascicle), 2002, 25(6): 253-259
[13] WICKENS C D. Introduction to human factors engineering[M]. New Jersey: Prentice Hall, 2003: 142-144.
[14] RAYNER K. Eye movements and attention in reading, scene perception, and visual search[J]. Quarterly Journal of Experimental Psychology, 2009, 62(8): 1457-1506
[15] 陆润豪, 张兴利, 施建农. 眼动技术在个体认知能力差异研究中的应用[J]. 心理科学, 2021, 44(3): 552-558
LU Runhao, ZHANG Xingli, SHI Jiannong. The application of eye-movement technique in the study of individual cognitive differences[J]. Journal of Psychological Science, 2021, 44(3): 552-558
[16] LUKE S G, DAROWSKI E S, GALE S D. Predicting eye-movement characteristics across multiple tasks from working memory and executive control[J]. Memory and Cognition, 2018, 46(5): 826-839
[17] HENDERSON J M, CHOI W, LUKE S G, et al. Neural correlates of individual differences in fixation duration during natural reading[J]. Quarterly Journal of Experimental Psychology, 2018, 71(1): 314-323
[18] JOSHI S, LI Y, KALWANI R, et al. Relationships between pupil diameter and neuronal activity in the locus coeruleus, colliculi, and cingulate cortex[J]. Neuron, 2016, 89(1): 221-234
[19] HAYES T R, PETROV A A. Pupil diameter tracks the explorationexploitation trade-off during analogical reasoning and explains individual differences in fluid intelligence[J]. Journal of Cognitive Neuroscience, 2016, 28(2): 308-318
[20] 余翔, 白友良, 李成. 多维有序聚类法在地质数据分类中的应用[J]. 计算机应用, 2015, 35(S1): 152-155
YU Xiang, BAI Youliang, LI Cheng. Application of multi-dimension sequential clustering method in geological data classification[J]. Journal of Computer Applications, 2015, 35(S1): 152-155
[21] 赵娜. 基于多观察序列的HMM训练算法[J]. 湖北工程学院学报, 2013, 33(3): 41-43
ZHAO Na. An HMM training algorithm based on multiple observations[J]. Journal of Hubei Engineering University, 2013, 33(3): 41-43