scholarly journals A Parametric Model for Accident Prediction Along Ado Ekiti – Ikole Ekiti Road, Ekiti State, Nigeria

2020 ◽  
Vol 5 (8) ◽  
pp. 980-985
Author(s):  
Olumuyiwa Samson Aderinola
Keyword(s):  
Prediction Models ◽  
Parametric Model ◽  
Road Accident ◽  
State University ◽  
Pavement Condition ◽  
Accident Prediction ◽  
The Road ◽  
Reconnaissance Survey ◽  
Proper Design ◽  
Frequency Occurrence

Road Accident Prediction Models have been used in different countries as a useful tool by road engineers and planners to predict the safety levels of roads, given their potential for determining both the crash frequency occurrence and the degree severity of crashes. The research looked into developing a parametric model for predicting accidents at specific locations along Ado-Ekiti to Ikole-Ekiti road. The reconnaissance survey of the road and the identified accident vulnerable points along the road was carried out and the factors aiding the occurrence of accidents were isolated  as Spot speed [S],  Pavement condition [P], Condition of shoulder [C], Width of the road [W], Elevation(super)/cambering [E], Gradient [G] and Accident Vulnerability [AV] which form an acronym SPCWEG-AV. The spot speed in each of the locations was gotten by measuring a 60m length and noting the time vehicles covered the distance. The pavement and shoulder conditions were evaluated to determine their conditions. The width of the road, the elevation (super)/cambering and the gradient (horizontal) were measured using tape, twine and plumb. When the analyzed data from the investigated factors from the field were imputed into SPCWEG-AV Rating system and Weights, the index (which is a multiplication of the rating and weight) of each of the parameters was got and the addition of these indices produced what is called Total SPCWEG-AV Index (T.SPCWEG-AV.I) which defines the degree of accident vulnerability of the point in question. The higher the T.SPCWEG-AV.I is, the more vulnerable the location is. The results showed ten accident prone areas. They are Federal Government College, Ikole-Ekiti (Ch 0+000), NNPC, Ikole-Ekiti (Ch 3+200), Olokonla, Ikole-Ekiti (Ch 7+000), The Nigeria Police station, Oye-Ekiti (Ch 23+2000), Federal University, Oye-Ekiti (Ch 25+600), Ifaki-Ekiti (Ch 35+400), Iworoko-Ekiti (Ch 52+100), Iworoko market (Ch 53+100), Ekiti State  University, Iworoko-Ekiti (Ch 62+750), Ilasa-Ekiti (Ch 64+800). Federal University, Oye Ekiti, Oye Ekiti (Ch 25+600) and Ilasa-Ekiti (Ch 64+800) have the highest number of accidents each having 24 and 22 and also has highest T.SPCWEG—AV.I of 71 and 70 respectively and other points show similar pattern. It is therefore, reasonable to conclude that the parametric model can replicate and predict the occurrence of accidents along Ado-Ekiti to Ikole-Ekiti road and other roads with similar features. It is recommended that the results of researches should be put to use and that agencies in charge of roads should ensure proper design, supervision and construction and to make sure the roads are properly maintained. Road Accident Prediction Models have been used in different countries as a useful tool by road engineers and planners to predict the safety levels of roads, given their potential for determining both the crash frequency occurrence and the degree severity of crashes. The research looked into developing a parametric model for predicting accidents at specific locations along Ado-Ekiti to Ikole-Ekiti road. The reconnaissance survey of the road and the identified accident vulnerable points along the road was carried out and the factors aiding the occurrence of accidents were isolated  as Spot speed [S],  Pavement condition [P], Condition of shoulder [C], Width of the road [W], Elevation(super)/cambering [E], Gradient [G] and Accident Vulnerability [AV] which form an acronym SPCWEG-AV. The spot speed in each of the locations was gotten by measuring a 60m length and noting the time vehicles covered the distance. The pavement and shoulder conditions were evaluated to determine their conditions. The width of the road, the elevation (super)/cambering and the gradient (horizontal) were measured using tape, twine and plumb. When the analyzed data from the investigated factors from the field were imputed into SPCWEG-AV Rating system and Weights, the index (which is a multiplication of the rating and weight) of each of the parameters was got and the addition of these indices produced what is called Total SPCWEG-AV Index (T.SPCWEG-AV.I) which defines the degree of accident vulnerability of the point in question. The higher the T.SPCWEG-AV.I is, the more vulnerable the location is. The results showed ten accident prone areas. They are Federal Government College, Ikole-Ekiti (Ch 0+000), NNPC, Ikole-Ekiti (Ch 3+200), Olokonla, Ikole-Ekiti (Ch 7+000), The Nigeria Police station, Oye-Ekiti (Ch 23+2000), Federal University, Oye-Ekiti (Ch 25+600), Ifaki-Ekiti (Ch 35+400), Iworoko-Ekiti (Ch 52+100), Iworoko market (Ch 53+100), Ekiti State  University, Iworoko-Ekiti (Ch 62+750), Ilasa-Ekiti (Ch 64+800). Federal University, Oye Ekiti, Oye Ekiti (Ch 25+600) and Ilasa-Ekiti (Ch 64+800) have the highest number of accidents each having 24 and 22 and also has highest T.SPCWEG—AV.I of 71 and 70 respectively and other points show similar pattern. It is therefore, reasonable to conclude that the parametric model can replicate and predict the occurrence of accidents along Ado-Ekiti to Ikole-Ekiti road and other roads with similar features. It is recommended that the results of researches should be put to use and that agencies in charge of roads should ensure proper design, supervision and construction and to make sure the roads are properly maintained.

Estimating Vehicle Roadside Encroachment Frequencies by Using Accident Prediction Models

1997 ◽  
Vol 1599 (1) ◽  
pp. 64-71 ◽  
Author(s):  
Shaw-Pin Miaou
Keyword(s):  
Data Collection ◽  
Prediction Models ◽  
Technical Difficulty ◽  
Road Accident ◽  
Roadside Safety ◽  
Accident Prediction ◽  
The Road ◽  
Run Off ◽  
Wide Range ◽  
Viable Approach

The existing data to support the development of roadside encroachment-based accident-prediction models are limited and largely outdated. Under FHWA and TRB sponsorship, several roadside safety projects have attempted to address this issue by proposing rather comprehensive data collection plans and conducting pilot data collection efforts. It is clear from these studies that the required cost for the proposed roadside field data-collection efforts will be very high. Furthermore, the validity of any field-collected roadside encroachment data may be questionable because of the technical difficulty of distinguishing intentional (or controlled) from unintentional (or uncontrolled) encroachments. A method to estimate some of the basic roadside encroachment parameters, including vehicle roadside encroachment frequency and the probability distribution of lateral extent of encroachments, using existing accident-based prediction models is proposed. The method is developed by utilizing the probabilistic relationships between a roadside encroachment event and a run-off-the-road accident event. With some assumptions, the method is capable of providing a wide range of basic encroachment parameters from conventional accident-based prediction models. To illustrate the concept and use of such a method, some basic encroachment parameters are estimated for rural two-lane undivided roads. In addition, the estimated encroachment parameters are compared with those estimated from the existing encroachment data. The illustration indicates that this method can be a viable approach to estimating basic encroachment parameters of interest and, thus, has the potential of reducing the roadside data collection cost.

scholarly journals Development of Road Accident Prediction Models for Akure-Owo Highway, Ondo State, Nigeria

2019 ◽  
Vol 15 (2) ◽  
pp. 53-70
Author(s):  
Olufikayo Oluwaseun Aderinlewo ◽  
◽  
Abayomi Afolayan ◽  
Keyword(s):  
Prediction Models ◽  
Road Accident ◽  
Accident Prediction ◽  
Ondo State

scholarly journals A Cognitive Contemplation of Road Accident Predicton Through Deep Learning

2019 ◽  
Vol 9 (2) ◽  
pp. 1020-1027
Keyword(s):  
Social Activity ◽  
Road Accident ◽  
Neural Systems ◽  
Control Approach ◽  
Accident Prediction ◽  
Vehicle Accidents ◽  
The Road ◽  
Car Accidents ◽  
Traffic Security ◽  
Prevention Methods

The research based on the vehicle accidents step to collect and structure a progressive secure transportation unfortunately vehicle crashes were unavoidable. The accident prediction related with the risky environment data collection and arrangements based on the high priority of reality of accidents. The social activity and roadway structures are useful in the progression of traffic security control approach. We believe that to secure the best possible setback decline impacts with limited budgetary resources, it is basic that measures be established on coherent and objective studies of the explanations behind mishaps and seriousness of wounds. A survey based on the different algorithms able to predict the road accidents prevention methods. This paper demonstrates a couple of models to predict the reality of harm that occurred in the midst of car accidents using three artificial intelligent approaches (AI). The proposed scheme contributes a neural systems prepared utilizing choice trees and fluffy c implies bunching strategy for division.

scholarly journals Predicting and Preventing Recommender System for Telangana Road Accidents

2020 ◽  
Vol 8 (6) ◽  
pp. 1353-1358
Keyword(s):  
Road Safety ◽  
Recommendation System ◽  
Similarity Measures ◽  
Road Accident ◽  
Road Accidents ◽  
Driver Behaviour ◽  
Accident Prediction ◽  
The Road ◽  
Model Recognition

Today people are suffering with road accidents in world wide. Analyzing these Road accidents are the major challenge in identifying and predicting primary features related with catastrophes. All these features are valuable for anticipatory computes to conquer road mishaps. Integrating various analytics techniques can get better model recognition and avoid road mishaps. As road safety growing quiet apprehension, speedy analytics observes all safety techniques in dynamic to spot malfunction that may signifies road mishaps on identifying key features related with road , mishaps in Telangana state. In our propose work, a framework to analyze the road mishap with classification of accidents and clustering, which analyze mishap data of Telangana stated district wise. The proposed framework describes the recommendation system for predicting road accidents. For this, classify the road accidents into fatal, major and minor. We implemented district wise data into clustering and applying enhanced k-mean algorithm. Further, implemented similarity measures to detecting the places where the severity of accidents happened and also analysing the driver behaviour analysis while accidents occur. The implementation result reveals that the road accident prediction exhibits enhance in certain areas and those areas exists in districts should be the major concern to acquire anticipatory measure to conquer the road mishaps.

scholarly journals COMPARISON OF ROAD TRAFFIC ACCIDENT PREDICTION MODELS FOR TWO-LANE HIGHWAY INTEGRATING TRAFFIC AND PAVEMENT CONDITION PARAMETERS

2019 ◽  
Vol 16 (2) ◽  
pp. 1-10
Author(s):  
O. M. POPOOLA ◽  
O. S. ABIOLA ◽  
S. O. ODUNFA ◽  
S. O. ISMAILA
Keyword(s):  
Road Traffic Accident ◽  
Traffic Accident ◽  
Negative Binomial ◽  
Prediction Models ◽  
Road Traffic ◽  
International Roughness Index ◽  
Pavement Condition ◽  
Accident Prediction ◽  
Explanatory Variables ◽  
Roughness Index

In Nigeria, literature on the integration of traffic of pavement condition and traffic characteristics in predicting road traffic accident frequency on 2-lane highways are scanty, hence this article to fill the gap. A comparison of road traffic accident frequency prediction models on IIesha-Akure-Owo road based on the data observed between 2012 and 2014 is presented. Negative Binomial (NB), Ordered Logistic (OL) and Zero Inflated Negative Binomial (ZINB) models were used to model the frequency of road traffic accident occurrence using road traffic accident data from the Federal Road Safety Commission (FRSC) and pavement conditions parameters from pavement evaluation unit of the Federal Ministry of Works, Kaduna. The explanatory variables were: annual average daily traffic (aadt), shoulder factor (sf), rut depth (rd), pavement condition index (pci), and international roughness index (iri). The explanatory variables that were statistically significant for the three models are aadt, sf and iri with the estimated coefficients having the expected signs. The number of road traffic accident on the road increases with the traffic volume and the international roughness index while it decreases with shoulder factor. The systematic variation explained by the models amounts to 87.7, 78.1 and 74.4% for NB, ZINB and OL respectively. The research findings suggest the accident prediction models that should be integrated into pavement rehabilitation.   Keywords:  

EFFECTS OF HIGHWAY GEOMETRIC ELEMENTS ON ACCIDENT MODELING

2015 ◽  
Vol 2 (1) ◽  
Author(s):  
Ujjal Chattaraj ◽  
Mohita Mohan Garnaik
Keyword(s):  
Road Safety ◽  
Prediction Models ◽  
Transportation Systems ◽  
Road Accident ◽  
Geometric Parameters ◽  
Incident Management ◽  
Accident Rate ◽  
Inference System ◽  
K Value ◽  
The Road

Road accident prediction plays an important role in accessing and improving the road safety. Fuzzy logic is one of the popular techniques in the broad field of artificial intelligence and ability to improve performance similar to human reasoning and describe complex systems in linguistic terms instead of numerical values. In this study, a system was established based on Fuzzy Inference System (FIS) in which output data such as traffic Accident Rate (AR) and input data such as various highway geometric parameters. The study was conducted on two road segment from plain and rolling terrain highway and two road segments from hilly and mountainous terrain highway within the rural area of the Indian Territory. Two Highway Accident Rate Prediction Models (HARPMPRT and HARPMHMT) were developed due to the complexity of geometric parameters of rural highway on different terrain conditions which takes horizontal radius, superelevation, K-value, vertical grade and visibility as input variables and Accident Rate (AR) as output variables. The findings show that the proposed model can be effectively applied as a useful Road Safety tool capable of identifying risk factors related to the characteristics of the road and great support to the decision making of incident management in Intelligent Transportation Systems.

scholarly journals Driving license regranting in DUI subjects: Road accident variables and predictive factors of substance use disorder

2021 ◽  
Vol 104 (3) ◽  
pp. 003685042110337
Author(s):  
Elena Beccegato ◽  
Angelo Ruggeri ◽  
Massimo Montisci ◽  
Claudio Terranova
Keyword(s):  
Substance Use ◽  
Comparison Group ◽  
Blood Alcohol Concentration ◽  
Road Accident ◽  
Ethyl Glucuronide ◽  
Binary Logistic Regression Analysis ◽  
Psychoactive Substance ◽  
Psychoactive Substances ◽  
Driving License ◽  
The Road

A comparative case study (2017–2020) was conducted to identify demographic, social, medico-legal, and toxicological variables associated with non-fatal accidents in driving under the influence (DUI) subjects. A second aim was to identify the factors predictive of substance use disorders among subjects. Drivers charged with alcohol DUI (blood alcohol concentration (BAC) > 0.5) and/or psychoactive substance DUI were included; cases included those involved in an accident while intoxicated, and the comparison group included DUI offenders negative for road accident involvement. Significance was determined by chi-square and Mann–Whitney tests. To prevent confounding effects, a multivariate binary logistic regression analysis was performed. Our sample encompassed 882 subjects (381 in the case group and 501 in the comparison group). Parameters such as psychoactive substances and BAC at the time of the road crash/DUI and the day of the week, when subjects were involved in the road accident or found DUI, resulted in significant differences ( p < 0.01) between groups. The model’s independent variables of BAC > 1.5 g/L ( p = 0.013), BAC > 2.5 g/L ( p < 0.001), and concurrent alcohol and psychoactive substance use ( p < 0.001) were independent risk factors for an accident. Smoking >20 cigarettes/day was an independent risk factor for unfitness to drive ( p < 0.01). Unfitness to drive was based primarily on ethyl glucuronide levels >30 pg/mg. Our results suggest a detailed assessment of DUI subjects with variables associated with accidents (BAC > 1.5 g/L and concurrent intake of psychoactive substances). Hair analysis, including ethylglucuronide (EtG) concentration, should be always performed. Based on our results, nicotine use should be investigated in cases of driving license regranting.

Beyond Deep Learning: An Econometric Example

2020 ◽  
Vol 28 (Supp01) ◽  
pp. 31-38 ◽  
Author(s):  
Ruofan Liao ◽  
Paravee Maneejuk ◽  
Songsak Sriboonchitta
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Prediction Models ◽  
Original Data ◽  
Parametric Model ◽  
Parametric Models ◽  
The Past ◽  
Currency Exchange ◽  
Currency Exchange Rate ◽  
Linear And Nonlinear

In the past, in many areas, the best prediction models were linear and nonlinear parametric models. In the last decade, in many application areas, deep learning has shown to lead to more accurate predictions than the parametric models. Deep learning-based predictions are reasonably accurate, but not perfect. How can we achieve better accuracy? To achieve this objective, we propose to combine neural networks with parametric model: namely, to train neural networks not on the original data, but on the differences between the actual data and the predictions of the parametric model. On the example of predicting currency exchange rate, we show that this idea indeed leads to more accurate predictions.

Accident prediction models with random corridor parameters

2009 ◽  
Vol 41 (5) ◽  
pp. 1118-1123 ◽  
Author(s):  
Karim El-Basyouny ◽  
Tarek Sayed
Keyword(s):  
Prediction Models ◽  
Accident Prediction

scholarly journals Nine Recommendations for the Safety on Road both of the People and the Traffic Police

2018 ◽  
Vol 1 (01) ◽  
pp. 79-85
Author(s):  
Madhur Dev Bhattarai
Keyword(s):  
Cost Effective ◽  
Road Accident ◽  
Public Hospitals ◽  
Occupational Hazards ◽  
Traffic Police ◽  
The Road ◽  
The People ◽  
On The Road ◽  
The Cost ◽  
Injured Patients

Safety of people and traffic police on road and the provision of prompt and appropriate treatment of injured persons in road accident are urgent concerns. The nine recommendations accordingly made are 1) Considering anyone who informs about or brings to the hospitals the accident victims as innocent until proved otherwise, 2) Annual payment by all vehicle owners (as per the cost of vehicles) to generate treatment fund for any road accident injured patients in the free general (not paying or private or extended health service) outdoor or emergency clinics or ward of the public hospitals irrespective of anyone’ fault in the accident (insurance or other agencies may be assigned to handle the amount deposited and reimbursement of the payments to the hospitals), 3) Implementation of helmet wearing by motorcycle riders and pillion riders in motorcycles, 4) Stricter fine for hazardous traffic offenses, 5) Drivers of the larger vehicles should not automatically be held responsible for any accidents involving other smaller vehicles (to prevent smaller vehicles and motorcycles to drive recklessly), 6) Drivers should not be just held responsible to bear health expenses of injured patients (which is much more than the compensation required in the event of death of injured persons); this is to encourage drivers to take injured persons immediately to hospitals and prevent inclination to allow their deaths indirectly or directly; the drivers should be proportionately fined or punished as per the traffic regulations if they are found to be negligent, 7) Safe and visible platform for the traffic police to stay on the road, 8) Provision of cost-effective respirators for traffic police and traffic supervisors, and 9) Compensation for occupational hazards to the traffic police and field traffic supervisors by distributing to them adequate proportion (e.g. one-third to one-half) of the fund collected by stricter fine paid for the hazardous traffic offences. Provision of various allowances, including for hazards, and benefits is a common practice in the country. Compensation for the occupational hazards of the traffic police provides incentives to and motivates them to remain vigilant about hazardous traffic offenses day and night everywhere and, thus, is essential for the safety of the people.   

Sign in / Sign up

Export Citation Format

Share Document