Situation awareness (SA) of air traffic controllers is defined as their ability to perceive, comprehend, and anticipate the future state of elements in the airspace. Accurate and rapid prediction of SA is considered essential for ensuring the safe and efficient operation of the aviation system. The situation awareness global assessment technique (SAGAT) was applied to objectively measure controllers’ SA based on task characteristics. A predictive model combining particle swarm optimization (PSO) and XGBoost was developed based on six control performance indicators. A visual comparison was conducted between the proposed PSO-XGBoost algorithm and three widely used algorithms. The results demonstrate that the combined optimization approach achieved a prediction accuracy of 97.17%, effectively enabling precise estimation of air traffic controllers’ situation awareness. Furthermore, based on the external datasets of the training trajectory, the effectiveness and generalization of the model were validated, proving its transferability and robustness with real data.The findings confirm the feasibility of SA prediction and suggest that the proposed algorithm and indicators provide an effective approach for enhancing prediction accuracy.
式(10)中:SAi为被试i的情景意识量化分值;Ci为被试i的正确率;ti为被试i的反应时间;t0为所有被试的平均反应时间。将所有被试的情景意识水平进行量化输出,对所得到的目标数据进行标准化处理,采用K最近邻分类算法(K-nearest neighbors,KNN),以0.1为阈值对数据进行异常值的剔除[15],并将数据点分布的核密度估计(kernel density estimation,KED)进行可视化输出,具体结果如图2所示。
结果显示无异常值存在,表明被试的情景意识数据采集较为准确,基本呈现正态分布。为检验问卷设计的合理性,对三个不同层级的情景意识量化评估结果进行重复测量方差分析(analysis of variance,ANOVA),置信度水平为95%,并输出组间的显著性水平,具体的结果如表4所示。
EndsleyM R. Measurement of situation awareness in dynamic systems[J]. Human Factors, 1995, 37(1): 65-84.
[2]
TaylorR M. Situational awareness rating technique (SART): the development of a tool for aircrew systems design[M]. Neuilly-sur-Seine: Routledge, 2017: 111-128.
LiHui, ZhuPei, ShaoQuan, et al. Controller workload detection based on decision tree model[J]. Science Technology and Engineering, 2024, 24(20): 8790-8796.
JinHuibin, LiuYawei, LiuWenhui, et al. Study of tower controllers’ situation awareness based on NNI fixation index[J]. Science Technology and Engineering, 2016, 16(31): 1671-1815.
[9]
EndsleyM R. A taxonomy of situation awareness er-rors[J]. Hu-man Factors in Aviation Operations, 1995, 3(2): 287-292.
WangYanqing, WuSiyu, YangKeyue. Study on air traffic controllers' situational awareness reliability in emergency scenarios[J]. China Safety Science Journal, 2024, 34(6): 207-215.
LiuShuang, WanyanXiaoru, ZhuangDamin, et al. Situational awareness model based on attention allocation[J]. Journal of Beijing University of Aeronautics and Astronautics, 2014, 40(8): 1066-1072.
FengChuanyan, WanyanXiaoru, LiuShuang, et al. Study on situation awareness under different mental workloads[J]. Journal of Northwestern Polytechnical University, 2020, 38(3): 610-618.
[18]
EndsleyM R. A systematic review and meta-analysis of direct objective measures of situation aware-ness: a comparison of SAGAT and SPAM[J]. Human Factors, 2021, 63(1): 124-150.
[19]
JonesR E T, ConnorsE S, EndsleyM R. A frame-work for representing agent and human situation awareness[C]// 2011 IEEE International Multi-disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support (CogSIMA). Piscataway: IEEE, 2011: 226-233.
[20]
ChenA. Augmented reality head-up displays for novice drivers[D]. New York: University Tandon School of Engineering, 2024.
[21]
WuX, FengC, WanyanX, et al. Dynamic measurement of pilot situation awareness[C]// Engineering Psychology and Cognitive Ergonomics: Cognition and Design: 14th International Conference. Cham: Springer International Publishing, 2017: 306-316.
[22]
GongL H, DingW, LiZ, et al. Quantum k-nearest neighbor classification algorithm via a divide-and-conquer strategy[J]. Advanced Quantum Technologies, 2024, 7(6): 2300221.
[23]
ChenT, GuestrinC. XGboost: a scalable tree boosting system[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 785-794.
[24]
MariniF, WalczakB. Particle swarm optimization (PSO): a tutorial[J]. Chemometrics and Intelligent Laboratory Systems, 2015, 149: 153-165.
[25]
EndsleyM R. Situation awareness misconceptions and misunderstandings[J]. Journal of Cognitive Engineering and Decision making, 2015, 9(1): 4-32.
[26]
ChiY, NieJ, ZhongL, et al. A review of situational awareness in air traffic control[J]. IEEE Access, 2023, 11: 134040-134057.
[27]
IbrahimL, MesinovicM, YangK W, et al. Explainable prediction of acute myocardial infarction using machine learning and shapley values[J]. IEEE Access, 2020, 8: 210410-210417.