scholarly journals Evaluation of Contributing Factors Affecting Number of Vehicles Involved in Crashes Using Machine Learning Techniques in Rural Roads of Cosenza, Italy

Author(s):  
Giuseppe Guido ◽  
Sina Shaffiee Haghshenas ◽  
Sami Shaffiee Haghshenas ◽  
Alessandro Vitale ◽  
Vittorio Astarita ◽  
...  

Evaluation of road safety is a critical issue having to be conducted for successful safety management in road transport systems, whereas safety management is considered in road transportation systems as a challenging task according to the dynamic of this issue and the presence of a large number of effective parameters on road safety. Therefore, evaluation and analysis of important contributing factors affecting the number of crashes play a key role in increasing the efficiency of road safety. For this purpose, in this research work, two machine learning algorithms including the group method of data handling (GMDH)-type neural network and a combination of support vector machine (SVM) and the grasshopper optimization algorithm (GOA) are employed for evaluating the number of vehicles involved in the accident based on the seven factors affecting transport safety including the Daylight (DL), Weekday (W), Type of accident (TA), Location (L), Speed limit (SL), Average speed (AS) and Annual average daily traffic (AADT) of rural roads of Cosenza in southern Italy. In this study, 564 data sets of rural areas were investigated and relevant effective parameters were measured. In the next stage, several models were developed to investigate the parameters affecting the safety management of road transportation for rural areas. The results obtained demonstrated that "Average speed" has the highest level and "Weekday" has the lowest level of importance in the investigated rural area. Finally, although the results of both algorithms were the same, the GOA-SVM model showed a better degree of accuracy and robustness than the GMDH model.

2020 ◽  
Vol 10 (5) ◽  
pp. 1675 ◽  
Author(s):  
Ciyun Lin ◽  
Dayong Wu ◽  
Hongchao Liu ◽  
Xueting Xia ◽  
Nischal Bhattarai

Crashes among young and inexperienced drives are a major safety problem in the United States, especially in an area with large rural road networks, such as West Texas. Rural roads present many unique safety concerns that are not fully explored. This study presents a complete machine leaning pipeline to find the patterns of crashes involved with teen drivers no older than 20 on rural roads in West Texas, identify factors that affect injury levels, and build four machine learning predictive models on crash severity. The analysis indicates that the major causes of teen driver crashes in West Texas are teen drivers who failed to control speed or travel at an unsafe speed when they merged from rural roads to highways or approached intersections. They also failed to yield on the undivided roads with four or more lanes, leading to serious injuries. Road class, speed limit, and the first harmful event are the top three factors affecting crash severity. The predictive machine learning model, based on Label Encoder and XGBoost, seems the best option when considering both accuracy and computational cost. The results of this work should be useful to improve rural teen driver traffic safety in West Texas and other rural areas with similar issues.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Akhilesh Nautiyal ◽  
Sunil Sharma

PurposeA large number of roads have been constructed in the rural areas of India to connect habitations with the nearest major roads. With time, the pavements of these roads have deteriorated and they need some kind of maintenance, although they all do not need maintenance at the same time, as they have all not deteriorated to the same level. Hence, they have to be prioritized for maintenance.Design/methodology/approachIn order to present a scientific methodology for prioritizing pavement maintenance, the factors affecting prioritization and the relative importance of each were identified through an expert survey. Analytic Hierarchy Process (AHP) was used to scientifically establish weight (importance) of each factor based on its relative importance over other factors. The proposed methodology was validated through a case study of 203 low volume rural roads in the state of Himachal Pradesh in India. Ranking of these roads in order of their priority for maintenance was presented as the final result.FindingsThe results show that pavement distresses, traffic volume, type of connectivity and the socioeconomic facilities located along a road are the four major factors to be considered in determining the priority of a road for maintenance.Research limitations/implicationsThe methodology provides a comprehensive, scientific and socially responsible pavement maintenance prioritization method which will automatically select roads for maintenance without any bias.Practical implicationsTimely maintenance of roads will also save budgetary expenditure of restoration/reconstruction, leading to enhancement of road service life. The government will not only save money but also provide timely benefit to the needy population.Social implicationsRoad transportation is the primary mode of inland transportation in rural areas. Timely maintenance of the pavements will be of great help to the socioeconomic development of rural areas.Originality/valueThe proposed methodology lays special emphasis on rural roads which are small in length, but large in number. Instead of random, a scientific method for selection of roads for maintenance will be of great help to the public works department for better management of rural road network.


SIMULATION ◽  
2021 ◽  
pp. 003754972097512
Author(s):  
Hung Khanh Nguyen ◽  
Raymond Chiong ◽  
Manuel Chica ◽  
Richard H Middleton

Recent large-scale migration flows from rural areas of the Mekong Delta (MKD) to larger cities in the South-East (SE) region of Vietnam have created the largest migration corridor in the country. This migration trend has further contributed to greater rural–urban disparities and widened the development gap between regions. In this study, our aim is to understand the migration dynamics and determine the most critical factors affecting the behavior of migrants in the MKD region. We present an agent-based model and incorporate the Theory of Planned Behavior to effectively break down migration intention into related components and contributing factors. A genetic algorithm is used for automated calibration and sensitivity analysis of model parameters, in order to validate our agent-based model. We further explore the migration behavior of people in certain demographic groups and delineate migration flows across cities and provinces from the MKD to the SE region.


In the fast pacing world, we commune from one place to another or one city to another with the means of vehicles. In recent years, data shows the worse conditions of the roads in Delhi with rapidly increasing of accidents. Roads in Delhi are more accident prone which creates more jeopardy to survive in Delhi for everyone. This problem persist from last few years due to various factors like open sewage, speed breakers, damaged roads which leads to loss of life of manhood and ecosystem. Since India is a developing nation there is a constant demand for good quality infrastructure, transportation and services. But since India is a vast country with quite a sizeable population this problem still has not yet addressed in totality. By using proposed methodology, for reducing the risk in the life of manhood as well as ecosystem by detecting all the factors for accidents and then improvement can be assured at the level of road safety management effectively and efficiently. Through this methodology, we can resolve these major issues by using Computer Vision, vision detector and Machine Learning so that drivers can easily aware of what ahead of them and act alertly before accident actually happens. Models are preinstalled on vehicles for safety purposes of the people, by using vision detector driver can acknowledge the obstruction ahead the car. Using the divergent and advanced technologies, live screening of the objects or obstacles ahead the vehicle will be visible to the driver for better ease and safe drive. Driver will get the notification from articulate assistant in any language by detecting the data ahead the car whilst specific range. Simple commands would comprise of “Speed Breaker ahead, slow down”.


2020 ◽  
Vol 9 (11) ◽  
pp. 638
Author(s):  
Sina Keller ◽  
Raoul Gabriel ◽  
Johanna Guth

Average speed information, which is essential for routing applications, is often missing in the freely available OpenStreetMap (OSM) road network. In this contribution, we propose an estimation framework, including different machine learning (ML) models that estimate rural roads’ average speed based on current road information in OSM. We rely on three datasets covering two regions in Chile and Australia. Google Directions API data serves as reference data. An appropriate estimation framework is presented, which involves supervised ML models, unsupervised clustering, and dimensionality reduction to generate new input features. The regression performance of each model with different input feature modes is evaluated on each dataset. The best performing model results in a coefficient of determination R2=80.43%, which is significantly better than previous approaches relying on domain-knowledge. Overall, the potential of the ML-based estimation framework to estimate the average speed with OSM road network data is demonstrated. This ML-based approach is data-driven and does not require any domain knowledge. In the future, we intend to focus on the generalization ability of the estimation framework concerning its application in different regions worldwide. The implementation of our estimation framework for an exemplary dataset is provided on GitHub.


2019 ◽  
Vol 2 (2) ◽  
pp. 76
Author(s):  
Erika Buchari ◽  
Dinar Dwi Anugrah Putranto ◽  
Dwi Asmoro ◽  
Lisbeth Dolok Saribu

According to IRSMS or Integrated Road Safety Management System, mostly 37.78% of road accidents happened in road class II. In terms of road function, the most frequent accidents happened in Arterial road, which is 33.22%. Majority accidents 31.60% happened in the straight road. This study aims to analyze the motorcycle’s speed, motorcyclist behavior in speeding, the effect of geometric road condition toward the speed. Some surveys having been done are road damage survey, traffic count survey, speed survey, and interview survey on motorist behavior. The results of the study are (1) The average speed of motorcyclists in  Jalan Noerdin Pandji on the direction of Bandara –Kenten is about 63.3 kph and the average speed on the direction of Kenten- Bandara 44.4 kph. (2) Motorist behavior in changing speed seems an anomaly attitude that they tend to increase the speed when approaching the intersection. Speeding behavior has many reasons for each motorist, such as faster reason, sleepy reason, and the increase of self-confidence (3). The effect of road geometric toward the speed of motorists is that the flat road condition can cause carelessness, and speeding up when approaching the intersection. Menurut data Integrated Road Safety Management System (IRSMS), kecelakaan menurut jenis kelas jalan yang terbanyak terjadi di jalan Kelas II,  yaitu 37.78% dan korban  kecelakaan menurut fungsi jalan yang terbanyak terjadi di jalan Arteri, yaiu 33.22%. Mayoritas kecelakaan 31,60% terjadi di jalan lurus. Tujuan penelitian adalah untuk,  menganalisis  kecepatan pengendara motor pada daerah kajian, perilaku pengendara dalam melakukan perubahan kecepatannya, menganalisis  pengaruh kondisi geometris jalan terhadap kecepatan pengendara. Survey yang dilakukan adalah survey kerusakan jalan, surveh perhitungan lalu lintas, survey kecepatan dan survey perilaku. Kesimpulan yang diperoleh adalah (1) Kecepatan pengendara motor pada daerah kajian menunjukkan bahwa kecepatan rata rata Jalan Nordin Pandji arah Bandara –Kenten 63.3 kph dan kecepatan rata rata arah Kenten- Bandara 44.4 kph. (2) Perilaku pengendara dalam melakukan perubahan kecepatannya terjadi anomali sikap pengendara motor, yaitu cenderung mempercepat kendaraan atau ngebut ketika memasuki simpang. Perilaku ngebut juga ternyata mempunyai banyak alasan bagi setiap pengendara motor antara lain, ingin cepat, supaya tidak ngantuk, supaya percaya diri (3) Pengaruh kondisi geometris jalan terhadap kecepatan pengendara, yaitu bahwa kondisi datar membuat pengendara tidak hati hati, ngebut pada saat melintasi simpang.


2015 ◽  
Vol 10 (2) ◽  
pp. 132-140 ◽  
Author(s):  
Luis Amador-Jimenez ◽  
Amir Pooyan Afghari

The implementation of pavement management seems to ignore road safety, with its focus being mainly on infrastructure condition. Safety management as part of pavement management should consider various means of reducing the frequency of vehicle crashes by allocating corrective measures to mitigate accident exposure, as well as reduce accident severity and likelihood. However, it is common that lack of accident records and crash contributing factors impedes incorporating safety into pavement management. This paper presents a case study for the initial development of pavement management systems considering data limitations for 3000 km of Tanzania’s national roads. A performance based optimization utilizes indices for safety and surface condition to allocate corrective measures. A modified Pareto analysis capable of accounting for annual performance and of balancing resources to achieve good surface condition and low levels of safety was applied. Tradeoff analysis for the case study found the need to assign 30% relevance to condition and 70% to road safety. Safety and condition deficiencies were corrected within 5 years with the majority of improvements dedicated to surface treatments and some geometric corrections. Large investments for correcting geo-metric issues were observed in years two and three if more money was made available.


2021 ◽  
Vol 11 (23) ◽  
pp. 11198
Author(s):  
Mohammadali Tofighi ◽  
Ali Asgary ◽  
Ghassem Tofighi ◽  
Brady Podloski ◽  
Felippe Cronemberger ◽  
...  

First responders including firefighters, paramedics, and police officers are among the first to respond to vehicle collisions on roads and highways. Police officers conduct regular roadside Please check if the country name is correct traffic controls and checks on urban and rural roads, and highways. Once first responders begin such operations, they are vulnerable to motor vehicle collisions by oncoming traffic, a circumstance that calls for a better understanding of contributing factors and the extent to which they affect tragic outcomes. In light of factors identified in the literature, this paper applies machine learning methods including decision tree and random forest to a subset of the National Collision Database (NCDB) of Canada that includes information on collisions between two vehicles (one in parked position) and the severity of these collisions as measured by having or not having injuries. Findings reveal that key measurable, predictable, and sensible factors such as time, location, and weather conditions, as well as the interconnections among them, can explain the severity of collisions that may happen between motor vehicles and first responders who are working alongside the roads. Analysis from longitudinal data is rich and the use of automated methods can be used to predict and assess the risk and vulnerability of first responders while responding to or operating on different roads and conditions.


Sign in / Sign up

Export Citation Format

Share Document