Impact of risk factors on work zone crashes using logistic models and Random Forest

• URL: http://arxiv.org/abs/2104.06561v1
• Date: Wed, 14 Apr 2021 00:27:11 GMT
• Title: Impact of risk factors on work zone crashes using logistic models and Random Forest
• Authors: Huthaifa I Ashqar, Qadri H Shaheen, Suleiman A Ashur, and Hesham A Rakha
• Abstract summary: This study focuses on the 2016 severe crashes that occurred in the State of Michigan (USA) in work zones along highway I-94. The study identified the risk factors from a wide range of crash variables characterizing environmental, driver, crash and road-related variables.
• Score: 9.5148976460603
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Work zone safety is influenced by many risk factors. Consequently, a comprehensive knowledge of the risk factors identified from crash data analysis becomes critical in reducing risk levels and preventing severe crashes in work zones. This study focuses on the 2016 severe crashes that occurred in the State of Michigan (USA) in work zones along highway I-94. The study identified the risk factors from a wide range of crash variables characterizing environmental, driver, crash and road-related variables. The impact of these risk factors on crash severity was investigated using frequency analyses, logistic regression statistics, and a machine learning Random Forest (RF) algorithm. It is anticipated that the findings of this study will help traffic engineers and departments of transportation in developing work zone countermeasures to improve safety and reduce the crash risk. It was found that some of these factors could be overlooked when designing and devising work zone traffic control plans. Results indicate, for example, the need for appropriate traffic control mechanisms such as harmonizing the speed of vehicles before approaching work zones, the need to provide illumination at specific locations of the work zone, and the need to establish frequent public education programs, flyers, and ads targeting high-risk driver groups. Moreover, the Random Forest algorithm was found to be efficient, promising, and recommended in crash data analysis, specifically, when the data sample size is small.

Related papers

• Traffic and Safety Rule Compliance of Humans in Diverse Driving Situations [48.924085579865334]
  Analyzing human data is crucial for developing autonomous systems that replicate safe driving practices. This paper presents a comparative evaluation of human compliance with traffic and safety rules across multiple trajectory prediction datasets.
  arXiv  Detail & Related papers  (2024-11-04T09:21:00Z)
• Learning Traffic Crashes as Language: Datasets, Benchmarks, and What-if Causal Analyses [76.59021017301127]
  We propose a large-scale traffic crash language dataset, named CrashEvent, summarizing 19,340 real-world crash reports. We further formulate the crash event feature learning as a novel text reasoning problem and further fine-tune various large language models (LLMs) to predict detailed accident outcomes. Our experiments results show that our LLM-based approach not only predicts the severity of accidents but also classifies different types of accidents and predicts injury outcomes.
  arXiv  Detail & Related papers  (2024-06-16T03:10:16Z)
• RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes [57.319845580050924]
  We propose a reinforcement learning framework that combines risk-sensitive control with an adaptive action space curriculum. We show that our algorithm is capable of learning high-speed policies for a real-world off-road driving task.
  arXiv  Detail & Related papers  (2024-05-07T23:32:36Z)
• Context-Aware Quantitative Risk Assessment Machine Learning Model for Drivers Distraction [0.0]
  Multi-Class Driver Distraction Risk Assessment (MDDRA) model considers the vehicle, driver, and environmental data during a journey. MDDRA categorises the driver on a risk matrix as safe, careless, or dangerous. We apply machine learning techniques to classify and predict driver distraction according to severity levels.
  arXiv  Detail & Related papers  (2024-02-20T23:20:36Z)
• Vehicle-group-based Crash Risk Formation and Propagation Analysis for Expressways [9.337163968120915]
  This study focuses on vehicle groups as the subject of analysis and explored risk formation and propagation mechanisms. Key factors contributing to crash risks were identified, including past high-risk vehicle-group states, complex vehicle behaviors, high percentage of large vehicles, frequent lane changes within a vehicle group, and specific road geometries. The results indicated that extended periods of high-risk states, increase in vehicle-group size, and frequent lane changes are associated with adverse risk propagation patterns.
  arXiv  Detail & Related papers  (2024-02-19T07:47:23Z)
• Hotspot Prediction of Severe Traffic Accidents in the Federal District of Brazil [0.0]
  This work attempts to add to the diversity of research, by focusing mainly on concentration of accidents and how machine learning can be used to predict hotspots. Data from the Federal District of Brazil collected from forensic traffic accident analysts were used and combined with data from local weather conditions to predict hotspots of collisions. We identify that weather parameters are not as important as the accident location, demonstrating that local intervention is important to reduce the number of accidents.
  arXiv  Detail & Related papers  (2023-12-28T22:13:11Z)
• A Counterfactual Safety Margin Perspective on the Scoring of Autonomous Vehicles' Riskiness [52.27309191283943]
  This paper presents a data-driven framework for assessing the risk of different AVs' behaviors. We propose the notion of counterfactual safety margin, which represents the minimum deviation from nominal behavior that could cause a collision.
  arXiv  Detail & Related papers  (2023-08-02T09:48:08Z)
• Predicting Real-time Crash Risks during Hurricane Evacuation Using Connected Vehicle Data [1.3706331473063877]
  We present methods to determine potential crash risks during hurricane evacuation from an emerging alternative data source known as connected vehicle data. Multiple machine learning models were trained considering weather features and different traffic characteristics extracted from the connected vehicle data.
  arXiv  Detail & Related papers  (2023-06-14T18:04:07Z)
• Analyzing vehicle pedestrian interactions combining data cube structure and predictive collision risk estimation model [5.73658856166614]
  This study introduces a new concept of a pedestrian safety system that combines the field and the centralized processes. The system can warn of upcoming risks immediately in the field and improve the safety of risk frequent areas by assessing the safety levels of roads without actual collisions.
  arXiv  Detail & Related papers  (2021-07-26T23:00:56Z)
• A model for traffic incident prediction using emergency braking data [77.34726150561087]
  We address the fundamental problem of data scarcity in road traffic accident prediction by training our model on emergency braking events instead of accidents. We present a prototype implementing a traffic incident prediction model for Germany based on emergency braking data from Mercedes-Benz vehicles.
  arXiv  Detail & Related papers  (2021-02-12T18:17:12Z)
• Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings [129.80279257258098]
  Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is hazardous. We propose a "safety-critical adaptation" task setting: an agent first trains in non-safety-critical "source" environments. We propose a solution approach, CARL, that builds on the intuition that prior experience in diverse environments equips an agent to estimate risk.
  arXiv  Detail & Related papers  (2020-08-15T01:40:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.