Classifying Cognitive Decline in Older Drivers from Behavior on Adverse Roads Detected Using Computer Vision  

作　　者：Md Zahid Hasan Guillermo Basulto-Elias Shauna Hallmark Jun Ha Chang Anuj Sharma Jeffrey D. Dawson Soumik Sarkar Matthew Rizzo Md Zahid Hasan;Guillermo Basulto-Elias;Shauna Hallmark;Jun Ha Chang;Anuj Sharma;Jeffrey D. Dawson;Soumik Sarkar;Matthew Rizzo(Institute for Transportation, Iowa State University, Ames, Iowa, USA;Department of Neurological Sciences, University of Nebraska Medical Center, Omaha, Nebraska, USA)

机构地区：[1]Institute for Transportation, Iowa State University, Ames, Iowa, USA [2]Department of Neurological Sciences, University of Nebraska Medical Center, Omaha, Nebraska, USA

出　　处：《Journal of Transportation Technologies》2025年第1期135-154,共20页交通科技期刊(英文)

摘　　要：As drivers age, roadway conditions may become more challenging, particularly when normal aging is coupled with cognitive decline. Driving during lower visibility conditions, such as inclement weather, is especially challenging for older drivers due to their sensitivity to glare and reduced visibility. As a result, older drivers may adjust their behavior during adverse weather. This paper explores the differential impacts of weather on older drivers with cognitive decline compared to older drivers with normal cognitive function. Data were from a naturalistic driving study of older drivers in Omaha, Nebraska. Driver speed and weather data were extracted and the correlation between speed compliance, road weather conditions, and the cognitive/neurological status of the drivers was examined. Speed compliance was used as the surrogate safety measure since driving at lower speeds can indicate that the driver is challenged by roadway or environmental conditions and can therefore indicate a risk. The percentage of time during a trip when drivers were 16.1 kph under the speed limit was modeled as the dependent variable using beta regression. The variables that resulted in the best fit model were mild cognitive impairment (MCI), age group, traffic density, and weather. Results indicated that the youngest group of older drivers (young-old) spent less time driving at impeding speeds and had the least variability compared to the other two age groups. The middle group of older drivers (middle-old) had the highest amount of time driving at impeding speeds and had more variability than young-old drivers. The oldest group of older drivers (old-old) were the most likely to drive at impeding speeds and had the most variability. In general, older drivers were more likely to drive at impeding speeds during peak hours than during non-peak hours. Additionally, in most cases, older drivers spent less time below the speed limit when the weather was clear than in adverse conditions. Results indicate that older drivers are impacted by weathAs drivers age, roadway conditions may become more challenging, particularly when normal aging is coupled with cognitive decline. Driving during lower visibility conditions, such as inclement weather, is especially challenging for older drivers due to their sensitivity to glare and reduced visibility. As a result, older drivers may adjust their behavior during adverse weather. This paper explores the differential impacts of weather on older drivers with cognitive decline compared to older drivers with normal cognitive function. Data were from a naturalistic driving study of older drivers in Omaha, Nebraska. Driver speed and weather data were extracted and the correlation between speed compliance, road weather conditions, and the cognitive/neurological status of the drivers was examined. Speed compliance was used as the surrogate safety measure since driving at lower speeds can indicate that the driver is challenged by roadway or environmental conditions and can therefore indicate a risk. The percentage of time during a trip when drivers were 16.1 kph under the speed limit was modeled as the dependent variable using beta regression. The variables that resulted in the best fit model were mild cognitive impairment (MCI), age group, traffic density, and weather. Results indicated that the youngest group of older drivers (young-old) spent less time driving at impeding speeds and had the least variability compared to the other two age groups. The middle group of older drivers (middle-old) had the highest amount of time driving at impeding speeds and had more variability than young-old drivers. The oldest group of older drivers (old-old) were the most likely to drive at impeding speeds and had the most variability. In general, older drivers were more likely to drive at impeding speeds during peak hours than during non-peak hours. Additionally, in most cases, older drivers spent less time below the speed limit when the weather was clear than in adverse conditions. Results indicate that older drivers are impacted by weath

关 键 词：Traffic Safety Older Driver Cognitive Impairment Machine Learning SPEED 

分 类 号：U49[交通运输工程—交通运输规划与管理]