Developing a grouped random parameter beta model to analyze drivers’ speeding behavior on urban and suburban arterials with probe speed data

Cai, Qing; Abdel-Aty, Mohamed; Mahmoud, Nada; Ugan, Jorge; Al-Omari, Ma’en Mohammad Ali

doi:10.1016/j.aap.2021.106386

Cited by 15 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both speed variability and vibration are unpredictable forces to control for in accelerometry data alone, as these factors would vary considerably based on road conditions and vehicle type [74]. Speed variability is particularly prevalent on urban roads due to rapidly changing traffic conditions, such as changes in traffic density, which requires constant and rapid changes in vehicle speed [75]. However, secondary signals, such as a global navigation satellite system, have been used in conjunction with accelerometers to account for speed variability in studies focusing on road surface classification [76,77].…”

Section: Discussionmentioning

confidence: 99%

A Deep Learning Approach to Classify Sitting and Sleep History from Raw Accelerometry Data during Simulated Driving

Tuckwell

Keal

Gupta

et al. 2022

Sensors

View full text Add to dashboard Cite

Prolonged sitting and inadequate sleep can impact driving performance. Therefore, objective knowledge of a driver’s recent sitting and sleep history could help reduce safety risks. This study aimed to apply deep learning to raw accelerometry data collected during a simulated driving task to classify recent sitting and sleep history. Participants (n = 84, Mean ± SD age = 23.5 ± 4.8, 49% Female) completed a seven-day laboratory study. Raw accelerometry data were collected from a thigh-worn accelerometer during a 20-min simulated drive (8:10 h and 17:30 h each day). Two convolutional neural networks (CNNs; ResNet-18 and DixonNet) were trained to classify accelerometry data into four classes (sitting or breaking up sitting and 9-h or 5-h sleep). Accuracy was determined using five-fold cross-validation. ResNet-18 produced higher accuracy scores: 88.6 ± 1.3% for activity (compared to 77.2 ± 2.6% from DixonNet) and 88.6 ± 1.1% for sleep history (compared to 75.2 ± 2.6% from DixonNet). Class activation mapping revealed distinct patterns of movement and postural changes between classes. Findings demonstrate the suitability of CNNs in classifying sitting and sleep history using thigh-worn accelerometer data collected during a simulated drive. This approach has implications for the identification of drivers at risk of fatigue-related impairment.

show abstract

Section: Discussionmentioning

confidence: 99%

A Deep Learning Approach to Classify Sitting and Sleep History from Raw Accelerometry Data during Simulated Driving

Tuckwell

Keal

Gupta

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Bassani et al analyzed the 85% percentile speed on urban arterials and identified the effects of road attributes such as the presence of shoulder, bus and taxi lane, and sidewalks on drivers' speed choice [7]. Bhowmik [8,9]. The models analyzed the effects of roadway attributes, traffic data, land use, socio-demographic characteristics, and environmental factors on the speed proportions by different arterials.…”

Section: Literature Reviewmentioning

confidence: 99%

Using Connected Vehicle Trajectory Data to Evaluate the Effects of Speeding

Ugan,

Abdel-Aty,

Islam

2024

IEEE Open J. Intell. Transp. Syst.

Self Cite

View full text Add to dashboard Cite

Speeding remains a key factor in traffic fatalities, prompting transportation agencies to propose speed management solutions. While studies have examined speeding percentages above limits, few address its impact on individual journeys. Most studies rely on detector speed data, lacking route insights. This research employs connected vehicle trajectory data to analyze driver paths and variables, predicting speeding levels with various learning models. Extreme Gradient Boosting performed best, achieving 75.6% accuracy. This model elucidates how journey factors influence speeding and forecasts high-speed zones. Results reveal a driver's total travel time significantly affects speeding, along with environmental features like residential area proportions. These findings aid transportation agencies in understanding trip-specific speeding factors, potentially informing better road safety measures.

show abstract

“… Kurte et al (2019) used vehicle probe data from the city of Chicago to examine how weather events cause variations in traffic speed across the roadway network, showing how drivers slow down in response to poor weather conditions. Cai et al (2021) used Inrix probe data to evaluate speed reduction strategies. In Connecticut, Doucette et al (2020) used Streetlight's LBS based probe data to estimate VMT in the state before and during the COVID-19 stay-at-home order.…”

Section: Introductionmentioning

confidence: 99%

Leveraging probe data to model speeding on urban limited access highway segments: Examining the impact of operational performance, roadway characteristics, and COVID-19 pandemic

Marshall¹,

Shirazi²,

Shahlaee³

et al. 2023

Accident Analysis & Prevention

View full text Add to dashboard Cite

Developing a grouped random parameter beta model to analyze drivers’ speeding behavior on urban and suburban arterials with probe speed data

Cited by 15 publications

References 26 publications

A Deep Learning Approach to Classify Sitting and Sleep History from Raw Accelerometry Data during Simulated Driving

A Deep Learning Approach to Classify Sitting and Sleep History from Raw Accelerometry Data during Simulated Driving

Using Connected Vehicle Trajectory Data to Evaluate the Effects of Speeding

Leveraging probe data to model speeding on urban limited access highway segments: Examining the impact of operational performance, roadway characteristics, and COVID-19 pandemic

Contact Info

Product

Resources

About