Jennifer Merickel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jennifer Merickel has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Senem Velipasalar
Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY 13244, USA
3 shared publications - Yaw Adu-Gyamfi
Department of Civil and Environmental Engineering, University of Missouri-Columbia, Columbia, MO
3 shared publications Anuj Sharma
Iowa State Univ
2 shared publications- Anuj Sharma
Department of Civil, Construction and Environmental Engineering, Iowa State University, Ames, IA, USA
2 shared publications - Armstrong Aboah
North Dakota State Univ
2 shared publications Jeffrey Dawson
Department of Biostatistics University of Iowa College of Public Health Iowa City Iowa USA
2 shared publications
Latest Publications
- 17 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 24 (9) , 9368-9377
Driver Head Pose Detection From Naturalistic Driving Data
Driver behavior analysis plays an important role in driver assistance systems. A driver’s face and head pose hold the key towards understanding whether the driver’s attention and concentration are on the road while driving. Naturalistic driving studies (NDS) allow observing drivers in real-time under naturalistic traffic conditions. Yet, data collected in NDS often comprise low-resolution videos usually with more challenging camera positions compared to controlled studies. For instance, when the camera is not directly facing the driver, classifying head pose becomes more challenging, since the variation between different classes becomes much smaller. In this paper, we propose three different approaches to classify a driver’s head pose from naturalistic videos, which were captured by a camera providing a side view, instead of directly facing the driver. These approaches employ a sequence of five key points on the driver’s face. We compare these three proposed approaches with each other as well as with three different baselines by using leave-one-driver-out cross-validation on nine different drivers. Results show that our proposed method employing a Bidirectional Gated Recurrent Unit (BiGRU) outperforms the best performing baseline by 11% in terms of overall accuracy.
- 17 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 24 (9) , 9368-9377
Driver Head Pose Detection From Naturalistic Driving Data
Driver behavior analysis plays an important role in driver assistance systems. A driver’s face and head pose hold the key towards understanding whether the driver’s attention and concentration are on the road while driving. Naturalistic driving studies (NDS) allow observing drivers in real-time under naturalistic traffic conditions. Yet, data collected in NDS often comprise low-resolution videos usually with more challenging camera positions compared to controlled studies. For instance, when the camera is not directly facing the driver, classifying head pose becomes more challenging, since the variation between different classes becomes much smaller. In this paper, we propose three different approaches to classify a driver’s head pose from naturalistic videos, which were captured by a camera providing a side view, instead of directly facing the driver. These approaches employ a sequence of five key points on the driver’s face. We compare these three proposed approaches with each other as well as with three different baselines by using leave-one-driver-out cross-validation on nine different drivers. Results show that our proposed method employing a Bidirectional Gated Recurrent Unit (BiGRU) outperforms the best performing baseline by 11% in terms of overall accuracy.
- 1 March 2023
- Published by American Society of Civil Engineers (ASCE) in Journal of Transportation Engineering, Part A: Systems
- Vol. 149 (3) , 04022157
Driver Maneuver Detection and Analysis Using Time Series Segmentation and Classification
The current paper implements a methodology for automatically detecting vehicle maneuvers from vehicle telemetry data under naturalistic driving settings. Previous approaches have treated vehicle maneuver detection as a classification problem, although both time series segmentation and classification are required since input telemetry data are continuous. Our objective is to develop an end-to-end pipeline for the frame-by-frame annotation of naturalistic driving studies videos into various driving events including stop and lane-keeping events, lane changes, left-right turning movements, and horizontal curve maneuvers. To address the time series segmentation problem, the study developed an energy-maximization algorithm (EMA) capable of extracting driving events of varying durations and frequencies from continuous signal data. To reduce overfitting and false alarm rates, heuristic algorithms were used to classify events with highly variable patterns such as stops and lane-keeping. To classify segmented driving events, four machine-learning models were implemented, and their accuracy and transferability were assessed over multiple data sources. The duration of events extracted by EMA was comparable to actual events, with accuracies ranging from 59.30% (left lane change) to 85.60% (lane-keeping). Additionally, the overall accuracy of the 1D-convolutional neural network model was 98.99%, followed by the long-short-term-memory model at 97.75%, then the random forest model at 97.71%, and the support vector machine model at 97.65%. These model accuracies were consistent across different data sources. The study concludes that implementing a segmentation-classification pipeline significantly improves both the accuracy of driver maneuver detection and the transferability of shallow and deep ML models across diverse datasets.
- 1 March 2023
- Published by American Society of Civil Engineers (ASCE) in Journal of Transportation Engineering, Part A: Systems
- Vol. 149 (3) , 04022157
Driver Maneuver Detection and Analysis Using Time Series Segmentation and Classification
The current paper implements a methodology for automatically detecting vehicle maneuvers from vehicle telemetry data under naturalistic driving settings. Previous approaches have treated vehicle maneuver detection as a classification problem, although both time series segmentation and classification are required since input telemetry data are continuous. Our objective is to develop an end-to-end pipeline for the frame-by-frame annotation of naturalistic driving studies videos into various driving events including stop and lane-keeping events, lane changes, left-right turning movements, and horizontal curve maneuvers. To address the time series segmentation problem, the study developed an energy-maximization algorithm (EMA) capable of extracting driving events of varying durations and frequencies from continuous signal data. To reduce overfitting and false alarm rates, heuristic algorithms were used to classify events with highly variable patterns such as stops and lane-keeping. To classify segmented driving events, four machine-learning models were implemented, and their accuracy and transferability were assessed over multiple data sources. The duration of events extracted by EMA was comparable to actual events, with accuracies ranging from 59.30% (left lane change) to 85.60% (lane-keeping). Additionally, the overall accuracy of the 1D-convolutional neural network model was 98.99%, followed by the long-short-term-memory model at 97.75%, then the random forest model at 97.71%, and the support vector machine model at 97.65%. These model accuracies were consistent across different data sources. The study concludes that implementing a segmentation-classification pipeline significantly improves both the accuracy of driver maneuver detection and the transferability of shallow and deep ML models across diverse datasets.
- Open Access
Driver Maneuver Detection and Analysis using Time Series Segmentation and Classification
The current paper implements a methodology for automatically detecting vehicle maneuvers from vehicle telemetry data under naturalistic driving settings. Previous approaches have treated vehicle maneuver detection as a classification problem, although both time series segmentation and classification are required since input telemetry data is continuous. Our objective is to develop an end-to-end pipeline for frame-by-frame annotation of naturalistic driving studies videos into various driving events including stop and lane keeping events, lane changes, left-right turning movements, and horizontal curve maneuvers. To address the time series segmentation problem, the study developed an Energy Maximization Algorithm (EMA) capable of extracting driving events of varying durations and frequencies from continuous signal data. To reduce overfitting and false alarm rates, heuristic algorithms were used to classify events with highly variable patterns such as stops and lane-keeping. To classify segmented driving events, four machine learning models were implemented, and their accuracy and transferability were assessed over multiple data sources. The duration of events extracted by EMA were comparable to actual events, with accuracies ranging from 59.30% (left lane change) to 85.60% (lane-keeping). Additionally, the overall accuracy of the 1D-convolutional neural network model was 98.99%, followed by the Long-short-term-memory model at 97.75%, then random forest model at 97.71%, and the support vector machine model at 97.65%. These model accuracies where consistent across different data sources. The study concludes that implementing a segmentation-classification pipeline significantly improves both the accuracy for driver maneuver detection and transferability of shallow and deep ML models across diverse datasets.
Open AccessDriver Maneuver Detection and Analysis using Time Series Segmentation and Classification
The current paper implements a methodology for automatically detecting vehicle maneuvers from vehicle telemetry data under naturalistic driving settings. Previous approaches have treated vehicle maneuver detection as a classification problem, although both time series segmentation and classification are required since input telemetry data is continuous. Our objective is to develop an end-to-end pipeline for frame-by-frame annotation of naturalistic driving studies videos into various driving events including stop and lane keeping events, lane changes, left-right turning movements, and horizontal curve maneuvers. To address the time series segmentation problem, the study developed an Energy Maximization Algorithm (EMA) capable of extracting driving events of varying durations and frequencies from continuous signal data. To reduce overfitting and false alarm rates, heuristic algorithms were used to classify events with highly variable patterns such as stops and lane-keeping. To classify segmented driving events, four machine learning models were implemented, and their accuracy and transferability were assessed over multiple data sources. The duration of events extracted by EMA were comparable to actual events, with accuracies ranging from 59.30% (left lane change) to 85.60% (lane-keeping). Additionally, the overall accuracy of the 1D-convolutional neural network model was 98.99%, followed by the Long-short-term-memory model at 97.75%, then random forest model at 97.71%, and the support vector machine model at 97.65%. These model accuracies where consistent across different data sources. The study concludes that implementing a segmentation-classification pipeline significantly improves both the accuracy for driver maneuver detection and transferability of shallow and deep ML models across diverse datasets.
- 19 January 2021
- Published by Wiley in Journal of the American Geriatrics Society
- Vol. 69 (5) , 1300-1308
Visual and Cognitive Impairments Differentially Affect Speed Limit Compliance in Older Drivers
Objectives: We test the hypothesis that clinical measures of age‐related cognitive, visual, and mobility impairments negatively impact older driver speed limit compliance to advance method developments that improve older patient care and screen, identify, and advise at‐risk older drivers. Design: Real‐world driver behaviors of older adults who had a range of cognitive, visual, and mobility abilities (measured with standardized, clinical tests) were assessed in environmental context (e.g., speed limit, traffic density, roadway type). Older driver speed limit compliance was measured in constant speed limit zones and at transition zones, where speed limits changed. Setting: A naturalistic driving study of older adults living around Omaha, Nebraska. Participants: Seventy‐seven, legally licensed, active, and typically aging older drivers (65–90 years) who had a range of cognitive and visual abilities. Measurements: Drivers typical, daily driving was continuously monitored for 3 months using sensor instrumentation installed in their own vehicles. At study start, each participant completed a comprehensive, standardized, clinical assessment of cognitive, visual, and mobility abilities relevant to aging and driving. Results: Older drivers with greater cognitive impairment ( P = .10) drove slower than drivers with less cognitive impairment, linking cognitive impairment to speed control. Drivers with greater visual impairment overall complied less with speed limit changes at transition zones ( P = .01) and were more likely to comply with speed limit transitions when they occurred concurrently with changes in roadway features ( P < .01). Conclusion: Results link clinical measures of age‐related cognitive and visual impairment to impaired driver safety in real‐world contexts. Real‐world sensor data coupled with detailed, personalized older driver profiles can inform patients, caregivers, interventions, policy, and the design of supportive in‐vehicle technology for at‐risk older drivers.
- 19 January 2021
- Published by Wiley in Journal of the American Geriatrics Society
- Vol. 69 (5) , 1300-1308
Visual and Cognitive Impairments Differentially Affect Speed Limit Compliance in Older Drivers
Objectives: We test the hypothesis that clinical measures of age‐related cognitive, visual, and mobility impairments negatively impact older driver speed limit compliance to advance method developments that improve older patient care and screen, identify, and advise at‐risk older drivers. Design: Real‐world driver behaviors of older adults who had a range of cognitive, visual, and mobility abilities (measured with standardized, clinical tests) were assessed in environmental context (e.g., speed limit, traffic density, roadway type). Older driver speed limit compliance was measured in constant speed limit zones and at transition zones, where speed limits changed. Setting: A naturalistic driving study of older adults living around Omaha, Nebraska. Participants: Seventy‐seven, legally licensed, active, and typically aging older drivers (65–90 years) who had a range of cognitive and visual abilities. Measurements: Drivers typical, daily driving was continuously monitored for 3 months using sensor instrumentation installed in their own vehicles. At study start, each participant completed a comprehensive, standardized, clinical assessment of cognitive, visual, and mobility abilities relevant to aging and driving. Results: Older drivers with greater cognitive impairment ( P = .10) drove slower than drivers with less cognitive impairment, linking cognitive impairment to speed control. Drivers with greater visual impairment overall complied less with speed limit changes at transition zones ( P = .01) and were more likely to comply with speed limit transitions when they occurred concurrently with changes in roadway features ( P < .01). Conclusion: Results link clinical measures of age‐related cognitive and visual impairment to impaired driver safety in real‐world contexts. Real‐world sensor data coupled with detailed, personalized older driver profiles can inform patients, caregivers, interventions, policy, and the design of supportive in‐vehicle technology for at‐risk older drivers.
- 25 November 2019
- Published by Taylor & Francis in Traffic Injury Prevention
- Vol. 20 (sup2) , S110-S115
Real-world risk exposure in older drivers with cognitive and visual dysfunction
Objective: This study addresses the need to measure and monitor objective, real-world driver safety behavior in at-risk drivers with age-related dysfunction. Older drivers are at risk for age-related cognitive and visual dysfunction, which may reduce mobility and increase errors that lead to crashes. Understanding patterns of real-world behavior, exposure, and cognitive–perceptual processes underlying risk in environmental context and in older drivers requires new approaches. Methods: We assessed patterns of objective, real-world driver risk exposure and vehicle control related to steering, braking, and accelerating in older adults with a range of cognitive and visual functional abilities. Real-world driver behavior was collected from passive-monitoring systems installed in 77 drivers’ vehicles and analyzed across 242,153 km (150,467 miles) driven. Driver behavior was assessed cross-sectionally in relationship to driver functional abilities and safety-critical environmental contexts (roadway type and visibility condition). Results: Results suggest that cognitive dysfunction impairs vehicle control across wide-ranging environments. Drivers with greater cognitive dysfunction showed more erratic braking and accelerating during daytime commercial and interstate driving. Drivers with less cognitive dysfunction showed more erratic braking and accelerating on residential roadways regardless of visibility condition. Greater cognitive dysfunction predicted more erratic steering on commercial and interstate roadways and less erratic steering on residential roadways. Greater visual dysfunction impaired braking and accelerating during nighttime and interstate driving, but not on residential or commercial roadways. Steering behavior was unaffected by visual abilities. Drivers with greater cognitive dysfunction did not appear to reduce driving frequency in higher-risk environments. Visually impaired drivers drove more on residential roadways and less on commercial roadways, but did not reduce driving on interstates, where they showed the greatest risk per mile driven. Conclusions: Results successfully mapped driver cognitive and visual profiles onto contemporaneous, real-world behavior and risk loci. Results link age-related dysfunction to real-world vehicle control and show that drivers may not sufficiently reduce exposure to higher-risk driving environments. Employing naturalistic observation to monitor and measure patterns of driver behavior can inform methods for early detection of age-related risk, fitness-to-drive assessments, and interventions to preserve safety, mobility, and quality of life in aging or other at-risk populations.
- 25 November 2019
- Published by Taylor & Francis in Traffic Injury Prevention
- Vol. 20 (sup2) , S110-S115
Real-world risk exposure in older drivers with cognitive and visual dysfunction
Objective: This study addresses the need to measure and monitor objective, real-world driver safety behavior in at-risk drivers with age-related dysfunction. Older drivers are at risk for age-related cognitive and visual dysfunction, which may reduce mobility and increase errors that lead to crashes. Understanding patterns of real-world behavior, exposure, and cognitive–perceptual processes underlying risk in environmental context and in older drivers requires new approaches. Methods: We assessed patterns of objective, real-world driver risk exposure and vehicle control related to steering, braking, and accelerating in older adults with a range of cognitive and visual functional abilities. Real-world driver behavior was collected from passive-monitoring systems installed in 77 drivers’ vehicles and analyzed across 242,153 km (150,467 miles) driven. Driver behavior was assessed cross-sectionally in relationship to driver functional abilities and safety-critical environmental contexts (roadway type and visibility condition). Results: Results suggest that cognitive dysfunction impairs vehicle control across wide-ranging environments. Drivers with greater cognitive dysfunction showed more erratic braking and accelerating during daytime commercial and interstate driving. Drivers with less cognitive dysfunction showed more erratic braking and accelerating on residential roadways regardless of visibility condition. Greater cognitive dysfunction predicted more erratic steering on commercial and interstate roadways and less erratic steering on residential roadways. Greater visual dysfunction impaired braking and accelerating during nighttime and interstate driving, but not on residential or commercial roadways. Steering behavior was unaffected by visual abilities. Drivers with greater cognitive dysfunction did not appear to reduce driving frequency in higher-risk environments. Visually impaired drivers drove more on residential roadways and less on commercial roadways, but did not reduce driving on interstates, where they showed the greatest risk per mile driven. Conclusions: Results successfully mapped driver cognitive and visual profiles onto contemporaneous, real-world behavior and risk loci. Results link age-related dysfunction to real-world vehicle control and show that drivers may not sufficiently reduce exposure to higher-risk driving environments. Employing naturalistic observation to monitor and measure patterns of driver behavior can inform methods for early detection of age-related risk, fitness-to-drive assessments, and interventions to preserve safety, mobility, and quality of life in aging or other at-risk populations.
- 24 April 2019
- Published by Springer Nature
- Vol. 943, 192-204
Road Weather Condition Estimation Using Fixed and Mobile Based Cameras
Automated interpretation and understanding of the driving environment using image processing is a challenging task, as most current vision-based systems are not designed to work in dynamically-changing and naturalistic real-world settings. For instance, road weather condition classification using a camera is a challenge due to high variance in weather, road layout, and illumination conditions. Most transportation agencies, within the U.S., have deployed some cameras for operational awareness. Given that weather related crashes constitute 22% of all vehicle crashes and 16% of crash fatalities, this study proposes using these same cameras as a source for estimating roadway surface condition. The developed model is focused on three road surface conditions resulting from weather including: Clear (clear/dry), Rainy-Wet (rainy/slushy/wet), and Snow (snow-covered/partially snow-covered). The camera sources evaluated are both fixed Closed-circuit Television (CCTV) and mobile (snow plow dash-cam). The results are promising; with an achieved 98.57% and 77.32% road weather classification accuracy for CCTV and mobile cameras, respectively. Proposed classification method is suitable for autonomous selection of snow plow routes and verification of extreme road conditions on roadways. Keywords Road weather classification Scene classification VGG16 Neural networks CCTV Mobile camera
- 24 April 2019
- Published by Springer Nature
- Vol. 943, 192-204
Road Weather Condition Estimation Using Fixed and Mobile Based Cameras
Automated interpretation and understanding of the driving environment using image processing is a challenging task, as most current vision-based systems are not designed to work in dynamically-changing and naturalistic real-world settings. For instance, road weather condition classification using a camera is a challenge due to high variance in weather, road layout, and illumination conditions. Most transportation agencies, within the U.S., have deployed some cameras for operational awareness. Given that weather related crashes constitute 22% of all vehicle crashes and 16% of crash fatalities, this study proposes using these same cameras as a source for estimating roadway surface condition. The developed model is focused on three road surface conditions resulting from weather including: Clear (clear/dry), Rainy-Wet (rainy/slushy/wet), and Snow (snow-covered/partially snow-covered). The camera sources evaluated are both fixed Closed-circuit Television (CCTV) and mobile (snow plow dash-cam). The results are promising; with an achieved 98.57% and 77.32% road weather classification accuracy for CCTV and mobile cameras, respectively. Proposed classification method is suitable for autonomous selection of snow plow routes and verification of extreme road conditions on roadways. Keywords Road weather classification Scene classification VGG16 Neural networks CCTV Mobile camera
- Open Access
- 1 January 2019
- Published by Society of Automotive Engineers of Japan, Inc. in International Journal of Automotive Engineering
- Vol. 10 (1) , 34-40
Driving Safety and Real-Time Glucose Monitoring in Insulin-Dependent Diabetes
Our goal is to address the need for driver-state detection using wearable and in-vehicle sensor measurements of driver physiology and health. To address this goal, we deployed in-vehicle systems, wearable sensors, and procedures capable of quantifying real-world driving behavior and performance in at-risk drivers with insulin-dependent type 1 diabetes mellitus (DM). We applied these methodologies over 4 weeks of continuous observation to quantify differences in realworld driver behavior profiles associated with physiologic changes in drivers with DM (N=19) and without DM (N=14). Results showed that DM driver behavior changed as a function of glycemic state, particularly hypoglycemia. DM drivers often drive during at-risk physiologic states, possibly due to unawareness of impairment, which in turn may relate to blunted physiologic responses (measurable heart rate) to hypoglycemia after repeated episodes of hypoglycemia. We found that this DM driver cohort has an elevated risk of crashes and citations, which our results suggest is linked to the DM driver’s own momentary physiology. Overall, our findings demonstrate a clear link between at-risk driver physiology and real-world driving. By discovering key relationships between naturalistic driving and parameters of contemporaneous physiologic changes, like glucose control, this study directly advances the goal of driver-state detection through wearable physiologic sensors as well as efforts to develop “gold standard” metrics of driver safety and an individualized approach to driver health and wellness.
- 1 January 2019
- Published by Society of Automotive Engineers of Japan, Inc. in International Journal of Automotive Engineering
- Vol. 10 (1) , 34-40
Open AccessDriving Safety and Real-Time Glucose Monitoring in Insulin-Dependent Diabetes
Our goal is to address the need for driver-state detection using wearable and in-vehicle sensor measurements of driver physiology and health. To address this goal, we deployed in-vehicle systems, wearable sensors, and procedures capable of quantifying real-world driving behavior and performance in at-risk drivers with insulin-dependent type 1 diabetes mellitus (DM). We applied these methodologies over 4 weeks of continuous observation to quantify differences in realworld driver behavior profiles associated with physiologic changes in drivers with DM (N=19) and without DM (N=14). Results showed that DM driver behavior changed as a function of glycemic state, particularly hypoglycemia. DM drivers often drive during at-risk physiologic states, possibly due to unawareness of impairment, which in turn may relate to blunted physiologic responses (measurable heart rate) to hypoglycemia after repeated episodes of hypoglycemia. We found that this DM driver cohort has an elevated risk of crashes and citations, which our results suggest is linked to the DM driver’s own momentary physiology. Overall, our findings demonstrate a clear link between at-risk driver physiology and real-world driving. By discovering key relationships between naturalistic driving and parameters of contemporaneous physiologic changes, like glucose control, this study directly advances the goal of driver-state detection through wearable physiologic sensors as well as efforts to develop “gold standard” metrics of driver safety and an individualized approach to driver health and wellness.