營造業是高危險行業，事故發生率高於其他產業，雖然危險識別是主動預防事故的首要環節，然而仍有高達57% 的工地危害未能及時判別。如要避免意外的發生，需要藉由科技輔助工具提升施工作業隱患識別率。近年來，直覺式腦機介面(Brain- computer Interface, BCI) 是輔助人類識別危險的關鍵技術之一，期望可藉由解讀生物對環境觀察的生理反應，直接發送預警信號。爰此，本研究使用機器學習(Machine Learning)，以腦電信號結合眼動特徵，即時協助前線人員於營建工作場域預知視覺接收的作業訊息為安全、警示或危險。研究成果提出最佳的工程場域作業隱患識別模型，可整合植入穿戴式載具或現地無線感應設備，強化前線工作人員識別環境狀況的感知能力。分析成果顯示，採感官相關之精簡的腦電通道配眼動特徵所建構的營建場域作業隱患識別準確率可達99.04% (RandomForest)。另於文獻顯示跌倒前引起的大腦反應，將刺激瞳孔放大，且場景複雜性會誘使瞳孔的收縮或擴張，故依工地災害類型，迴歸探討腦電通道、眼動特徵與瞳孔直徑間的關聯性，作為日後研析作業環境危害度對視覺生理反應的量化參考依據。於腦電通道與眼動特徵的迴歸分析瞳孔直徑顯示，BAGGING:CART組合模型在面臨感電墜落、架體崩塌、物體飛落等危險類型的瞳孔直徑預測值MAPE介於4.57%~5.74%，模型績效優良。研究貢獻希冀藉由探討腦電信號與眼動特徵對營建從業人員識別安全隱患的影響，篩選關鍵因子對於預測識別安全隱患精確度的影響程度，進而權衡建構最佳模型。預期效益為縮減未來所需資料的蒐集成本，更可結合開發模型與穿戴技術整合之可能性，茲以強化施工作業的安全績效，降低營建場域的意外風險。

Construction industry is a high-risk industry with a higher accident rate than other industries. Although hazard identification is the primary link in proactive accident prevention, there are still as many as 57% of site hazards that cannot be identified in time. To avoid accidents, it is necessary to use auxiliary tools to improve the identification rate of hidden dangers in construction operations. In recent years, Brain-computer Interface is a key technology to assist humans in identifying dangers. It is expected to directly send early warning signals by interpreting biological responses to environmental observations. Therefore, this study uses machine learning to combine EEG (Electroencephalogram) signals with eye movement features to instantly assist frontline personnel in the construction work field to predict visually received operation information as safety, warning or danger. The research results put forward the best hidden danger identification model for engineering field operations, which can be integrated with implantable wearable vehicles or on-site wireless sensing equipment to enhance the perception ability of front-line workers to identify environmental conditions. The analysis results show that the identification accuracy of construction site operation hidden dangers constructed by using sensory-related EEG channels and eye movement features can reach 99.04% (RandomForest). In addition, the literature shows that the brain response evoked before a fall stimulates pupil dilation, and scene complexity induces pupil constriction or dilation. Therefore, according to the accident types at construction sites, the correlation between EEG channels, eye movement characteristics and pupil diameter should be regressed and used as a quantitative reference for future research and analysis of the hazard degree of the working environment on the visual physiological response. It is shown that the pupil diameter predicted by the BAGGING:CART ensemble model in the face of inductive fall, frame collapse, and object flying, has the MAPE between 4.57% and 5.74%, and the model performs well. The research hopes to explore the influence of EEG factors and eye movement factors in predicting workers' identification of safety hazards, and to select the best model for the subsequent prediction based on the degree of change in the accuracy of prediction and identification of safety hazards caused by different factors, which is expected to reduce data collection costs of future model predictions. In the future, the construction industry can use EEG combined with eye trackers as a possible way of wearable technology to improve the safety performance of construction sites, and ensure the health and safety of workers.

[1]林柏君, "我國營造業之發展現況與趨勢," 經濟前瞻, no. 174, pp. 43-48, 2017. 中華民國經濟研究院第三研究所.
[2]施芝吟. "營造業長期缺工 聽聽工人怎麼說." 大紀元新聞網. https://www.epochtimes.com/b5/20/11/11/n12540946.htm (accessed Mar. 10, 2021).
[3]上海財經資訊說. "美國最致命職業排行榜：建築工人死亡率最高." https://www.163.com/dy/article/E0J67C9B0519TGLN.html (accessed May. 18, 2021).
[4]勞動部職業安全衛生署, "109勞動檢查統計年報-全一冊," 2020.
[5]J. W. Garrett and J. Teizer, "Human Factors Analysis Classification System Relating to Human Error Awareness Taxonomy in Construction Safety," Journal of Construction Engineering and Management, vol. 135, no. 8, pp. 754-763, 2009, doi: doi:10.1061/(ASCE)CO.1943-7862.0000034.
[6]R. A. Haslam, S. A. Hide, A. G. F. Gibb, D. E. Gyi, T. Pavitt, S. Atkinson and A. R. Duff," Applied Ergonomics, vol. 36, no. 4, pp. 401-415, 2005/07/01/ 2005, doi: 10.1016/j.apergo.2004.12.002.
[7]P.-C. Liao, X. Sun, and D. Zhang, "A multimodal study to measure the cognitive demands of hazard recognition in construction workplaces," Safety Science, vol. 133, p. 105010, 2021.
[8]林楨中 and 鄭慶武, "營造業高處作業勞工主要不安全行為樣態及認知調查," 勞動部勞動及職業安全衛生研究所, 2017.
[9]A. Perlman, R. Sacks, and R. Barak, "Hazard recognition and risk perception in construction," Safety Science, vol. 64, pp. 22-31, 2014/04/01/ 2014, doi: 10.1016/j.ssci.2013.11.019.
[10]M. Noghabaei, K. Han, and A. Albert, "Feasibility Study to Identify Brain Activity and Eye-Tracking Features for Assessing Hazard Recognition Using Consumer-Grade Wearables in an Immersive Virtual Environment," Construction Engineering and Management, vol. 147, no. 9, p. 04021104, 2021.
[11]H. Berger, "Über das elektroenkephalogramm des menschen," Archiv für psychiatrie und nervenkrankheiten, vol. 87, no. 1, pp. 527-570, 1929.
[12]A. Behzadnia, M. Ghoshuni, and S. A. Chermahini, "EEG Activities and the Sustained Attention Performance," Neurophysiology, vol. 49, no. 3, pp. 226-233, 2017/06/01 2017, doi: 10.1007/s11062-017-9675-1.
[13]C. Berka et al., "EEG correlates of task engagement and mental workload in vigilance, learning, and memory tasks," Aviation, space, and environmental medicine, vol. 78, no. 5, pp. B231-B244, 2007.
[14]F. Babiloni et al., "Neural Basis For The Brain Responses To The Marketing Messages: an High Resolution EEG study," in 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, New York, NY, USA, 30 Aug.-3 Sept. 2006, no. 1557-170X: IEEE, pp. 3676-3679, doi: 10.1109/IEMBS.2006.260485.
[15]G. Vecchiato et al., "Spectral EEG frontal asymmetries correlate with the experienced pleasantness of TV commercial advertisements," Medical & Biological Engineering & Computing, vol. 49, no. 5, pp. 579-583, 2011/05/01 2011, doi: 10.1007/s11517-011-0747-x.
[16]J. R. Wolpaw and D. J. McFarland, "Control of a two-dimensional movement signal by a noninvasive brain-computer interface in humans," Proceedings of the National Academy of Sciences, vol. 101, no. 51, pp. 17849-17854, 2004, doi: doi:10.1073/pnas.0403504101.
[17]H. Kolayis, "Using EEG biofeedback in karate: The relationship among anxiety, motivation and brain waves," School of Physical Education and Sport, vol. 8, no. 1, pp. 13-18, 2012.
[18]J. Hu and J. Min, "Automated detection of driver fatigue based on EEG signals using gradient boosting decision tree model," Cognitive Neurodynamics, vol. 12, no. 4, pp. 431-440, 2018/08/01 2018, doi: 10.1007/s11571-018-9485-1.
[19]S. K. L. Lal, A. Craig, P. Boord, L. Kirkup, and H. Nguyen, "Development of an algorithm for an EEG-based driver fatigue countermeasure," Journal of Safety Research, vol. 34, no. 3, pp. 321-328, 2003/08/01/ 2003, doi: 10.1016/S0022-4375(03)00027-6.
[20]Y. Song, J. Liu, Q. Gao, and M. Liu, "A quadrotor helicopter control system based on Brain-computer interface," in 2015 IEEE International Conference on Mechatronics and Automation (ICMA), 2-5 Aug. 2015 2015, pp. 1478-1483, doi: 10.1109/ICMA.2015.7237703.
[21]A. Hekmatmanesh, P. H. J. Nardelli, and H. Handroos, "Review of the State-of-the-Art of Brain-Controlled Vehicles," IEEE Access, vol. 9, pp. 110173-110193, 2021, doi: 10.1109/ACCESS.2021.3100700.
[22]S. Saedi, A. A. F. Fini, M. Khanzadi, J. Wong, M. Sheikhkhoshkar, and M. Banaei, "Applications of electroencephalography in construction," Automation in Construction, vol. 133, p. 103985, 2022.
[23]A. Aryal, A. Ghahramani, and B. Becerik-Gerber, "Monitoring fatigue in construction workers using physiological measurements," Automation in Construction, vol. 82, pp. 154-165, 2017.
[24]M. S. Gazzaniga, "Organization of the human brain," Science, vol. 245, no. 4921, pp. 947-952, 1989.
[25]T. Bui and M. D. J, "Neuroanatomy, Cerebral Hemisphere," in StatPearls. Treasure Island (FL): StatPearls Publishing Copyright © 2022, StatPearls Publishing LLC., 2022.
[26]"The Ten Twenty Electrode System: International Federation of Societies for Electroencephalography and Clinical Neurophysiology," American Journal of EEG Technology, vol. 1, no. 1, pp. 13-19, 1961/03/01 1961, doi: 10.1080/00029238.1961.11080571.
[27]K. Holmqvist, M. Nyström, R. Andersson, R. Dewhurst, H. Jarodzka, and J. Van de Weijer, Eye tracking: A comprehensive guide to methods and measures. OUP Oxford, 2011.
[28]T. Blascheck, K. Kurzhals, M. Raschke, M. Burch, D. Weiskopf, and T. Ertl, "State-of-the-Art of Visualization for Eye Tracking Data," 2014: Eurographics Association, doi: 10.2312/eurovisstar.20141173.
[29]W. F. Asaad, G. Rainer, and E. K. Miller, "Task-specific neural activity in the primate prefrontal cortex," Journal of Neurophysiology, vol. 84, no. 1, pp. 451-459, 2000.
[30]D. H. Ballard, M. M. Hayhoe, and J. B. Pelz, "Memory representations in natural tasks," Journal of Cognitive Neuroscience, vol. 7, no. 1, pp. 66-80, 1995.
[31]J. H. Bertera and K. Rayner, "Eye movements and the span of the effective stimulus in visual search," Perception & Psychophysics, vol. 62, no. 3, pp. 576-585, 2000.
[32]M.-J. J. Wang, S.-C. Lin, and C. G. Drury, "Training for strategy in visual search," International Journal of Industrial Ergonomics, vol. 20, no. 2, pp. 101-108, 1997.
[33]M. Wedel and R. Pieters, "Eye fixations on advertisements and memory for brands: A model and findings," Marketing Science, vol. 19, no. 4, pp. 297-312, 2000.
[34]M. D. Byrne, J. R. Anderson, S. Douglass, and M. Matessa, "Eye tracking the visual search of click-down menus," presented at the Proceedings of the SIGCHI conference on Human Factors in Computing Systems, Pittsburgh, Pennsylvania, USA, 1999.
[35]B. Watson, N. Walker, L. F. Hodges, and A. Worden, "Managing level of detail through peripheral degradation: Effects on search performance with a head-mounted display," ACM Transactions on Computer-Human Interaction (TOCHI), vol. 4, no. 4, pp. 323-346, 1997.
[36]M.-J. Tsai, H.-T. Hou, M.-L. Lai, W.-Y. Liu, and F.-Y. Yang, "Visual attention for solving multiple-choice science problem: An eye-tracking analysis," Computers & Education, vol. 58, no. 1, pp. 375-385, 2012/01/01/ 2012, doi: 10.1016/j.compedu.2011.07.012.
[37]I. Jeelani, K. Han, and A. Albert, "Automating and scaling personalized safety training using eye-tracking data," Automation in Construction, vol. 93, pp. 63-77, 2018/09/01/ 2018, doi: 10.1016/j.autcon.2018.05.006.
[38]S. A. Bhoir, S. Hasanzadeh, B. Esmaeili, M. D. Dodd, and M. S. Fardhosseini, "Measuring construction workers’ attention using eye-tracking technology," in Proc., ICSC15: The Canadian Society for Civil Engineering 5th Int./11th Construction Specialty Conf, 2015: Univ. of British Columbia, Vancouver, Canada.
[39]R.-J. Dzeng, C.-T. Lin, and Y.-C. Fang, "Using eye-tracker to compare search patterns between experienced and novice workers for site hazard identification," Safety Science, vol. 82, pp. 56-67, 2016/02/01/ 2016, doi: 10.1016/j.ssci.2015.08.008.
[40]S. Hasanzadeh, B. Esmaeili, and M. D. Dodd, "Measuring the Impacts of Safety Knowledge on Construction Workers’ Attentional Allocation and Hazard Detection Using Remote Eye-Tracking Technology," Journal of Management in Engineering, vol. 33, no. 5, p. 04017024, 2017, doi: doi:10.1061/(ASCE)ME.1943-5479.0000526.
[41]D. Crundall and G. Underwood, "Chapter 11 - Visual Attention While Driving: Measures of Eye Movements Used in Driving Research," in Handbook of Traffic Psychology, B. E. Porter Ed. San Diego: Academic Press, 2011, pp. 137-148.
[42]R. J. K. Jacob and K. S. Karn, "Commentary on Section 4 - Eye Tracking in Human-Computer Interaction and Usability Research: Ready to Deliver the Promises," in The Mind's Eye, J. Hyönä, R. Radach, and H. Deubel Eds. Amsterdam: North-Holland, 2003, pp. 573-605.
[43]A. Saghafi, C. P. Tsokos, M. Goudarzi, and H. Farhidzadeh, "Random eye state change detection in real-time using EEG signals," Expert Systems with Applications, vol. 72, pp. 42-48, 2017/04/15/ 2017, doi: 10.1016/j.eswa.2016.12.010.
[44]P. Ma and Q. Gao, "EEG Signal and Feature Interaction Modeling-Based Eye Behavior Prediction Research," Computational and Mathematical Methods in Medicine, vol. 2020, p. 2801015, 2020/05/16 2020, doi: 10.1155/2020/2801015.
[45]D. H. Wolpert and W. G. Macready, "No free lunch theorems for optimization," IEEE Transactions on Evolutionary Computation, vol. 1, no. 1, pp. 67-82, 1997.
[46]J.-S. Chou, M.-Y. Cheng, Y.-W. Wu, and C.-C. Wu, "Forecasting enterprise resource planning software effort using evolutionary support vector machine inference model," International Journal of Project Management, vol. 30, no. 8, pp. 967-977, 2012.
[47]J.-S. Chou, N.-T. Ngo, and W. K. Chong, "The use of artificial intelligence combiners for modeling steel pitting risk and corrosion rate," Engineering Applications of Artificial Intelligence, vol. 65, pp. 471-483, 2017.
[48]M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. H. Witten, "The WEKA data mining software: an update," ACM SIGKDD Explorations Newsletter, vol. 11, no. 1, pp. 10-18, 2009.
[49]D. H. Moore II, "Classification and regression trees, by Leo Breiman, Jerome H. Friedman, Richard A. Olshen, and Charles J. Stone. Brooks/Cole Publishing, Monterey, 1984,358 pages, $27.95," Cytometry, vol. 8, no. 5, pp. 534-535, 1987, doi: 10.1002/cyto.990080516.
[50]J. Joyce. "Bayes' theorem." Stanford Encyclopedia of Philosophy Archive. https://stanford.library.sydney.edu.au/archives/sum2016/entries/bayes-theorem/ (accessed Jun. 22, 2022).
[51]K. H. Rosen and K. Krithivasan, Discrete mathematics and its applications: with combinatorics and graph theory. Tata McGraw-Hill Education, 2012.
[52]W. S. McCulloch and W. Pitts, "A logical calculus of the ideas immanent in nervous activity," The Bulletin of Mathematical Biophysics, vol. 5, no. 4, pp. 115-133, 1943.
[53]A. K. Jain, M. Jianchang, and K. M. Mohiuddin, "Artificial neural networks: a tutorial," Computer, vol. 29, no. 3, pp. 31-44, 1996, doi: 10.1109/2.485891.
[54]T.-T. Le, P. G. Asteris, and M. E. Lemonis, "Prediction of axial load capacity of rectangular concrete-filled steel tube columns using machine learning techniques," Engineering with Computers, 2021/07/04 2021, doi: 10.1007/s00366-021-01461-0.
[55]H.-B. Ly, T.-A. Nguyen, H.-V. Thi Mai, and V. Q. Tran, "Development of deep neural network model to predict the compressive strength of rubber concrete," Construction and Building Materials, vol. 301, p. 124081, 2021/09/27/ 2021, doi: 10.1016/j.conbuildmat.2021.124081.
[56]W. N. H. W. Mohamed, M. N. M. Salleh, and A. H. Omar, "A comparative study of Reduced Error Pruning method in decision tree algorithms," in 2012 IEEE International Conference on Control System, Computing and Engineering, 23-25 Nov. 2012 2012, pp. 392-397, doi: 10.1109/ICCSCE.2012.6487177.
[57]D. W. Hosmer Jr, S. Lemeshow, and R. X. Sturdivant, Applied logistic regression. Stowe, Vermont Columbus, Ohio West Point, New York: John Wiley & Sons, 2013.
[58]A. Smola and V. Vapnik, "Support Vector Regression Machines," in Advances in Neural Information Processing Systems 9: Proceedings of the 1996 Conference, 1997, vol. 9: MIT Press, p. 155.
[59]H. A. Kazem, J. H. Yousif, and M. T. Chaichan, "Modeling of daily solar energy system prediction using support vector machine for Oman," International Journal of Applied Engineering Research, vol. 11, no. 20, pp. 10166-10172, 2016.
[60]G. A. Seber and A. J. Lee, Linear regression analysis. John Wiley & Sons, 2012.
[61]L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone, Classification and regression trees, 1st Edition ed. New York: Routledge, 2017.
[62]A. M. Prasad, L. R. Iverson, and A. Liaw, "Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction," Ecosystems, vol. 9, no. 2, pp. 181-199, 2006/03/01 2006, doi: 10.1007/s10021-005-0054-1.
[63]L. Breiman, "Random forests," Machine learning, vol. 45, no. 1, pp. 5-32, 2001.
[64] H. Tin Kam, "Random decision forests," in Proceedings of 3rd International Conference on Document Analysis and Recognition, USA, 14-16 Aug. 1995 1995, vol. 1: IEEE Computer Society, pp. 278-282 vol.1, doi: 10.1109/ICDAR.1995.598994.
[65]J.-S. Chou, C.-F. Tsai, A.-D. Pham, and Y.-H. Lu, "Machine learning in concrete strength simulations: Multi-nation data analytics," Construction and Building Materials, vol. 73, pp. 771-780, 2014/12/30/ 2014, doi: 10.1016/j.conbuildmat.2014.09.054.
[66]E. M. de Oliveira and F. L. Cyrino Oliveira, "Forecasting mid-long term electric energy consumption through bagging ARIMA and exponential smoothing methods," Energy, vol. 144, pp. 776-788, 2018/02/01/ 2018, doi: 10.1016/j.energy.2017.12.049.
[67]K. Szafranek, "Bagged neural networks for forecasting Polish (low) inflation," International Journal of Forecasting, vol. 35, no. 3, pp. 1042-1059, 2019/07/01/ 2019, doi: 10.1016/j.ijforecast.2019.04.007.
[68]J.-S. Chou and A.-D. Pham, "Enhanced artificial intelligence for ensemble approach to predicting high performance concrete compressive strength," Construction and Building Materials, vol. 49, pp. 554-563, 2013/12/01/ 2013, doi: 10.1016/j.conbuildmat.2013.08.078.
[69]R. V. Andreao, B. Dorizzi, and J. Boudy, "ECG signal analysis through hidden Markov models," IEEE Transactions on Biomedical engineering, vol. 53, no. 8, pp. 1541-1549, 2006.
[70]A. Lemmens, C. Croux, and S. Stremersch, "Dynamics in the international market segmentation of new product growth," International Journal of Research in Marketing, vol. 29, no. 1, pp. 81-92, 2012.
[71]S. Agarwal and C. R. Chowdary, "A-Stacking and A-Bagging: Adaptive versions of ensemble learning algorithms for spoof fingerprint detection," Expert Systems with Applications, vol. 146, p. 113160, 2020/05/15/ 2020, doi: 10.1016/j.eswa.2019.113160.
[72]C. Qi and X. Tang, "Slope stability prediction using integrated metaheuristic and machine learning approaches: a comparative study," Computers & Industrial Engineering, vol. 118, pp. 112-122, 2018.
[73]I. H. Witten, E. Frank, and M. Hall. "Weka 3–Machine Learning Software in Java." University of Waikato, Hamilton City and Tauranga Region, New Zealand. https://www.cs.waikato.ac.nz/ml/weka/index.html (accessed Dec. 10, 2021).
[74]MathWorks. "MATLAB." https://ww2.mathworks.cn/products/matlab.html (accessed Sep. 20, 2021).
[75]G. Holmes, A. Donkin, and I. H. Witten, "Weka: A machine learning workbench," in Proceedings of ANZIIS'94-Australian New Zealnd Intelligent Information Systems Conference, 1994: IEEE, pp. 357-361.
[76]J.-S. Chou, D.-N. Truong, and C.-F. Tsai, "Solving Regression Problems with Intelligent Machine Learner for Engineering Informatics," Mathematics, vol. 9, no. 6, p. 686, 2021, doi: 10.3390/math9060686.