Detecting driver distraction

摘要: The increasing use of in-vehicle information systems (IVISs), such as navigation devices and MP3 players, can jeopardize safety by introducing distraction into driving. One way to address this problem is develop mitigation systems, which adapt IVIS functions according driver state. In a system, correctly identifying critical, the focus dissertation. Visual cognitive distractions are two major types that interfere with driving most compared other types. occur individually or in combination. research gaps detecting interactions visual have not been well studied no accurate algorithm/strategy has developed detect visual, cognitive, combined distraction. To bridge these gaps, dissertation fulfilled three specific aims. first aim demonstrated layered algorithm based on data mining methods could improve detection from my previous studies. second estimation algorithms for strong relationship estimated increased risk real crashes using naturalistic data. third objective examined interaction an effective strategy identify Together aims suggest be detected performance indicators appropriate quantitative methods. Data techniques represent promising category construct algorithms. When sequential way, dominates effects while reduces overall impairments performance. Therefore, it necessary if present.