Identifying Incident Causal Factors to Improve Aviation Transportation Safety: Proposing a Deep Learning Approach

Table 7

An example of how the “HF threshold” affects the identification result.

	Probability of each factor
HF threshold	HF	AC	CP	PR	WE	AP	Identification
Threshold = 0	0.42	0.37	0.09	0.03	0.03	0.06	HF
Threshold = 0.55	0.42	0.37	0.09	0.03	0.03	0.06	AC

If an HF threshold is specified, HF will only be identified when its probability exceeds the specified value; otherwise, the factor with the second-highest confidence is chosen. In this way, the bias toward the dominant factors is well compensated by tuning the threshold. Threshold = 0 (no threshold). Threshold = 0.55.