scholarly journals Risk Prediction for Winter Road Accidents on Expressways

2021 ◽  
Vol 11 (20) ◽  
pp. 9534
Author(s):  
Daeseong Kim ◽  
Sangyun Jung ◽  
Sanghoo Yoon
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Winter Season ◽  
Weather Conditions ◽  
Road Accident ◽  
Weather Data ◽  
Road Accidents ◽  
Weather Factors ◽  
The Road ◽  
Road Geometry

Road accidents caused by weather conditions in winter lead to higher mortality rates than in other seasons. The main causes of road accidents include human carelessness, vehicle defects, road conditions, and weather factors. If the risk of road accidents with changes in road weather conditions can be quantitatively evaluated, it will contribute to reducing the road accident fatalities. The road accident data used in this study were obtained for the period 2017 to 2019. Spatial interpolation estimated the weather information; geographic information system (GIS) and Shuttle Radar Topography Mission (SRTM) data identified road geometry and accident area altitude; synthetic minority oversampling technique (SMOTE) addressed the data imbalance problem between road accidents due to weather conditions and from other causes, and finally, machine learning was performed on the data using various models such as random forest, XGBoost, neural network, and logistic regression. The training- to test data ratio was 7:3. Random forest model exhibited the best classification performance for road accident status according to weather risks. Thus, by applying weather data and road geometry to machine learning models, the risk of road accidents due to weather conditions in the winter season can be predicted and provided as a service.

scholarly journals Identification of Weather Influences on Flight Punctuality Using Machine Learning Approach

Climate ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 127
Author(s):  
Sakdirat Kaewunruen ◽  
Jessada Sresakoolchai ◽  
Yue Xiang
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Insurance Industry ◽  
Weather Conditions ◽  
Air Traffic ◽  
Civil Aviation ◽  
Support Vector ◽  
Weather Factors ◽  
Climate Conditions ◽  
Climate Resilience

One of the top long-term threats to airport resilience is extreme climate-induced conditions, which negatively affect the airport and flight operations. Recent examples, including hurricanes, storms, extreme temperatures (cold/hot), and heavy rains, have damaged airport facilities, interrupted air traffic, and caused higher operational costs. With the development of civil aviation and the pre-COVID-19 surging demand for flights, the passengers’ complaints of flight delay increased, according to FoxBusiness. This study aims to discover the weather factors affecting flight punctuality and determine a high-dimensional scale of consequences stemming from weather conditions and flight operational aspects. Machine learning has been developed in correlation with the weather and statistical data for operations at Birmingham Airport as a case study. The cross-correlated datasets have been kindly provided by Birmingham Airport and the Meteorological Office. The scope and emphasis of this study is placed on the machine learning application to practical flight punctuality prediction in relation to climate conditions. Random forest, artificial neural network, support vector machine, and linear regression are used to develop predictive models. Grid-search and cross-validation are used to select the best parameters. The model can grasp the trend of flight punctuality rates well where R2 is 0.80 and the root mean square error (RMSE) is less than 15% using the model developed by random forest technique. The insights derived from this study will help Airport Authorities and the Insurance industry in predicting the scale of consequences in order to promptly enact and enable adaptative airport climate resilience plans, including air traffic rescheduling, financial resilience to climate variances and extreme weather conditions.

scholarly journals Machine Learning Approaches to Traffic Accident Analysis and Hotspot Prediction

Computers ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 157
Author(s):  
Daniel Santos ◽  
José Saias ◽  
Paulo Quaresma ◽  
Vítor Beires Nogueira
Keyword(s):  
Machine Learning ◽  
Predictive Model ◽  
Road Accident ◽  
Influential Factors ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Economic Losses ◽  
Learning Approaches ◽  
Road Accidents ◽  
Accident Data

Traffic accidents are one of the most important concerns of the world, since they result in numerous casualties, injuries, and fatalities each year, as well as significant economic losses. There are many factors that are responsible for causing road accidents. If these factors can be better understood and predicted, it might be possible to take measures to mitigate the damages and its severity. The purpose of this work is to identify these factors using accident data from 2016 to 2019 from the district of Setúbal, Portugal. This work aims at developing models that can select a set of influential factors that may be used to classify the severity of an accident, supporting an analysis on the accident data. In addition, this study also proposes a predictive model for future road accidents based on past data. Various machine learning approaches are used to create these models. Supervised machine learning methods such as decision trees (DT), random forests (RF), logistic regression (LR), and naive Bayes (NB) are used, as well as unsupervised machine learning techniques including DBSCAN and hierarchical clustering. Results show that a rule-based model using the C5.0 algorithm is capable of accurately detecting the most relevant factors describing a road accident severity. Further, the results of the predictive model suggests the RF model could be a useful tool for forecasting accident hotspots.

scholarly journals Case Study for Road Safety Audit of Aurangabad City

2020 ◽  
Vol 170 ◽  
pp. 06008
Author(s):  
Prashant Awsarmal ◽  
S. L. Hake ◽  
Shubham Vaidya ◽  
P. K. Bhandari ◽  
M. P. Wagh
Keyword(s):  
Road Safety ◽  
Human Life ◽  
Research Work ◽  
Police Department ◽  
Road Accident ◽  
Audit Process ◽  
Severe Injuries ◽  
The Road ◽  
Road Geometry ◽  
Road Safety Audit

Efficient road network is a part-n-parcel of rapid industralization, urbanization and development of nation. While designing roads and highways, main emphasis is given on speed which will help to reduce time of journey and save fuel. But safety of drivers and passengers travelling along road is also important. In past, it was observed that while travelling, due to excess speed passengers safety was compromised. It will lead to accidents. It may cause severe injuries and loss of human life. Therefore it is important to check every aspect of vehicles as well as road during its design, construction and throughout the life of the road. Road safety audit is conducted to check performance of new road projects on grounds of offering maximum safety. Also checks are applied to study performance of existing roads to suggest repairs, rehabiliatation and maintenance work in order to improve condition of roads. During audit process, accident prone locations are identified. Past accident record from traffic department, Police department, hospitals etc are referred to understand damage that had occured. Even road geometry is investigated on technical basis. In present investigation, particular stretch of Beed Bypass Road passing through Aurangabad city in Maharashtra state, India was selected. On this road, accident sites where major accidents occurred in past were identified and investigated for different parameters. Based upon study, different causes of accidents and thereafter preventive methods were recommended during research work.

Machine learning in road accident research: decision trees describing road accidents during cross-flow turns

Ergonomics ◽  
1998 ◽  
Vol 41 (7) ◽  
pp. 1060-1079 ◽  
Author(s):  
DAVID D. CLARKE ◽  
RICHARD FORSYTH ◽  
RICHARD WRIGHT
Keyword(s):  
Machine Learning ◽  
Decision Trees ◽  
Cross Flow ◽  
Road Accident ◽  
Road Accidents ◽  
Accident Research ◽  
Research Decision

scholarly journals Agrocompanion: A Smart Farming Approach Based on Iot and Machine Learning

2020 ◽  
Vol 9 (12) ◽  
pp. 254-262
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Random Forest ◽  
Weather Conditions ◽  
The Internet ◽  
Machine Learning Model ◽  
Smart Farming ◽  
Water Tanks ◽  
And Control ◽  
The Internet Of Things

Agriculture is one of the cardinal sectors of the Indian Economy. The proposed system offers a methodology to efficiently monitor and control various attributes that affect crop growth and production. The system also uses machine learning along with the Internet of Things (IoT) to predict the crop yield. Various weather conditions such as temperature, humidity, and soil moisture are monitored in real-time using IoT sensors. IoT is also used to regulate the water level in the water tanks, which helps in reducing the wastage of water resources. A machine learning model is developed to predict the yield of the crop based on parameters taken from these sensors. The model uses Random Forest Regressor and gives an accuracy of 87.5%. Such a system provides a simple and efficient way to maintain and monitor the health of the crop.

scholarly journals The Effects of Roadside Hazards on Road Accident Severity

2019 ◽  
Vol 49 (2) ◽  
pp. 319-339 ◽  
Author(s):  
Marcin Budzyński ◽  
Kazimierz Jamroz ◽  
Łukasz Jeliński ◽  
Anna Gobis
Keyword(s):  
Road Safety ◽  
Road Accident ◽  
Road User ◽  
Road Accidents ◽  
Safety Equipment ◽  
Design Rules ◽  
The Road ◽  
Run Off ◽  
Safety Strategies ◽  
Accident Severity

Abstract The risk of becoming involved in an accident emerges when elements of the transport system do not operate properly (man – vehicle – road – roadside). The road, its traffic layout and safety equipment have a critical impact on road user safety. This gives infrastructural work a priority in road safety strategies and programmes. Run-off-road accidents continue to be one of the biggest problems of road safety with consequences including vehicle roll-over or hitting a roadside object. This type of incident represents more than 20% of rural accidents and about 18% of all road deaths in Poland. Mathematical models must be developed to determine how selected roadside factors affect road safety and provide a basis for new roadside design rules and guidelines.

scholarly journals Intelligent Accident Prevention in VANETs

2019 ◽  
Vol 8 (2) ◽  
pp. 2401-2405
Keyword(s):  
Road Safety ◽  
Ad Hoc Network ◽  
Ad Hoc ◽  
Weather Conditions ◽  
Accident Prevention ◽  
Road Accidents ◽  
Human Errors ◽  
The Road ◽  
On The Road ◽  
Nearest Neighbour Classifier

Accident prevention has always been an important issue for governments and car manufacturers across the world. Roughly 1.5 million people are killed in road accidents annually in India. The primary causes of accidents are broken and weathered roads, hazardous weather conditions, as well as human errors such as over speeding, distracted driving, and not following road safety rules. The traffic police work hard to enforce strict rules and maintain accident-free roads, but this hasn’t proven to be efficient. A vehicular ad hoc network (VANET), as the name says, is a network consisting of nodes. These nodes depict vehicles on the road. This project aims to use this technology with K-Nearest Neighbour Classifier (KNN) to create a prototype of a system which can notify drivers of an impending accident caused by forward collisions, rear collision etc., thus enabling them to take immediate action and prevent it.

scholarly journals Willingness-To-Pay for Estimation the Risk Pedestrian Group Accident Cost

2020 ◽  
Vol 6 (6) ◽  
pp. 1064-1073 ◽  
Author(s):  
Chompoonut Puttawong ◽  
Preeda Chaturabong
Keyword(s):  
Willingness To Pay ◽  
Injury Risk ◽  
Road Accident ◽  
Road Accidents ◽  
The Road ◽  
Statistical Life ◽  
Perception Of Safety ◽  
Road Users ◽  
Pedestrian Injury ◽  
The Cost

The proven willingness-to-pay with contingent valuation (WTP-CV) method is an effective tool for evaluating the cost of road accidents in many countries. In Thailand, the most fatalities on Thailand’s roads involve the vulnerable road users (VRUs) including motorcycle users, bicyclists, and pedestrians. With the effectiveness of using WTP-CV in analyzing the accident cost of motorcycle users and lack of specific accident cost for pedestrians, this research focuses on evaluating the accident cost on the pedestrians which is the second most VRU fatality. In this research, the road accident cost of pedestrians aged 15-39 years in Bangkok by WTP-CV method was determined. The WTP-CV questionnaire was employed as a tool to measure the payment of which each pedestrian is willing to pay to reduce the fatality and injury risk from road accidents. One thousand and two hundred pedestrians in Bangkok were interviewed. With the results, the value of statistical life (VOSL) for pedestrians in Bangkok is valued at US$ 0.43 million, while the value of statistical injury (VOSI) is estimated at about US$ 0.014 million, respectively. In addition, it is found from the regression analysis that for the fatality risk reduction, higher educational levels and private business pedestrians are likely to pay more to save their lives. In order to reduce the risk of injury, respondents, who are single in marriage status, are likely to pay more to reduce the risk of pedestrian injury. However, a high perception of safety is less likely to pay for the reduction of injury risk.

scholarly journals Modeling the Complexity of Road Accidents Prevention

2020 ◽  
Vol 9 (2) ◽  
pp. 24-41
Author(s):  
Alex Kizito ◽  
Agnes Rwashana Semwanga
Keyword(s):  
Traffic Safety ◽  
Police Officers ◽  
Road Transport ◽  
Road Accident ◽  
Road Accidents ◽  
Dynamic Interactions ◽  
The Road ◽  
Dynamic Synthesis ◽  
Road Users ◽  
Synthesis Methodology

Simplistic representations of traffic safety disregard the dynamic interactions between the components of the road transport system (RTS). The resultant road accident (RA) preventive measures are consequently focused almost solely on individual/team failures at the sharp end of the RTS (mainly the road users). The RTS is complex and therefore cannot be easily understood by studying the system parts in isolation. The study modeled the occurrence of road accidents in Uganda using the dynamic synthesis methodology (DSM). This article presents the work done in the first three stages of the DSM. Data was collected from various stakeholders including road users, traffic police officers, road users, and road constructors. The study focused on RA prevention by considering the linear and non-linear interactions of the variables during the pre-crash phase. Qualitative models were developed and from these, key leverage points that could possibly lower the road accident incidences demonstrating the need for a shared system wide responsibility for road safety at all levels are suggested.

Sign in / Sign up

Export Citation Format

Share Document