A Fuzzy Artificial Alarm by using S/N Ratio for Improving Sustained Attention in Automation Monitoring

摘要

Previous researches have shown that the attention determines the reliability of human performance, especially in low levels of arousal during sustained attention. Usually, operator perceives the good or poor signals from display in automation, and he/she must make a judgement and act. However, sometimes operator would loss the ability to maintain attention to stimuli over prolonged periods. The purpose of this research was to study how the fuzzy technique can improve performance on tasks requiring sustained attention. Firstly, a quantitative detection performance-measuring model (QDPMM) with signal to noise ratio (S/N ratio or η value) for dynamic characteristics of human decision-making was proposed. Secondly, using the value of the QDPMM, a fuzzy artificial alarm system was constructed to produce artificial signals to keep adaptive attention over prolonged periods. The results of this study indicated that the QDPMM used to measure the human detection performance was easy and objective, and the fuzzy artificial alarm can improve the monitoring performance significantly.