Systematic assessment of intrinsic factors influencing visual attention performances in air traffic control via clustering algorithm and statistical inference

Abstract

The intrinsic factors (IF) influencing visual attention performance (VAP) might cause potential human errors, such as "error/mistake", "forgetting" and "omission". It is a key issue to develop a systematic assessment of IF in order to distinguish the levels of VAP. Motivated by the Stimulus-Response (S-R) model, we take an interactive cancellation test-Neuron Type Test (NTT)-to explore the IF and present the corresponding systematic assessment. The main contributions of this work include three elements: a) modeling the IF on account of attention span, attention stability, distribution-shift of attention with measurable parameters by combining the psychological and statistical concepts; b) proposing quantitative analysis methods for assessing the IF via its computational representation-intrinsic qualities (IQ)-in the sense of computational model; and c) clustering the IQ of air traffic control (ATC) students in the feature space of interest. The response sequences of participants collected with the NTT system are characterized by three parameters: Hurst exponent, normalized number of decisions (NNoD) and error rate of decisions (ERD). The K-means clustering is applied to partition the feature space constructed from practical data of VAP. For the distinguishable clusters, the statistical inference is utilized to refine the assessment of IF. Our comprehensive analysis shows that the IQ can be classified into four levels, i.e., excellent, good, moderate and unqualified, which has a potential application in selecting air traffic controllers subject to reducing the risk of the inadequacy of attention performances in aviation safety management.

Fig 1. Aviation safety, visual attention theory and clustering algorithm: Logical hierarchy and technical implementation strategy.

Fig 2. Visual attention performances: From concepts to feature vectors.

Fig 3. Clusters of 2-dim features [W, H]^⊺ with boundaries generated by convex hull algorithm.

Fig 4. Clusters of 3-dim features [W, H, E]^⊺ with contours.

Fig 5. 2-dim Euclidean distances of clusters {Sk2}k=14.

Fig 6. Euclidean distance of 3-dim clusters {Sk3}k=14.

Fig 7. 2-dim clusters and TrLogDet distance per dimension.

Fig 8. 3-dim clusters and TrLogDet distance per dimension.

Fig 9. Box-plot of 2-dim clustering data.

Fig 10. Box-plot of 3-dim clustering data.